JP6665356B2 - Information processing apparatus, information processing method, and information processing program - Google Patents

Description

  The present invention relates to an information processing device, an information processing method, and an information processing program.

  2. Description of the Related Art Conventionally, a technology relating to a system for managing electronic mail has been known. For example, if the address (TO or CC) of the e-mail requested to be transmitted from the user terminal to the e-mail server frequently matches, a mailing list is automatically generated together with the sender name. There has been proposed a technology for automatic deletion.

JP 2008-97116 A

  However, in the above-described conventional technology, it is not always possible to provide an e-mail with high appeal. Specifically, in the above-described conventional technology, a mailing list is only automatically generated in accordance with the frequency of use of an e-mail address, and it is not always possible to provide an e-mail with a high appealing power. .

  The present application has been made in view of the above, and an object of the present invention is to provide an information processing apparatus, an information processing method, and an information processing program capable of providing an e-mail with high appeal.

  An information processing apparatus according to the present application includes an acquiring unit that acquires mail information regarding an electronic mail to be transmitted, and display information displayed as a sender name of the electronic mail based on the mail information acquired by the acquiring unit. A generating unit that generates display information for displaying information other than the identification information for identifying the sender of the electronic mail.

  According to an aspect of the embodiment, there is an effect that an e-mail with high appealing power can be provided.

FIG. 1 is a diagram illustrating an example of an e-mail according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the information processing system according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the information processing apparatus according to the embodiment. FIG. 4 is a diagram illustrating an example of a plan information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of a user information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of a mail information storage unit according to the embodiment. FIG. 7 is a diagram illustrating an example of the model information storage unit according to the embodiment. FIG. 8 is a diagram illustrating an example of an electronic mail according to a modification. FIG. 9 is a diagram illustrating an example of an electronic mail according to a modification. FIG. 10 is a diagram illustrating an example of an electronic mail according to a modification. FIG. 11 is a diagram illustrating an example of an electronic mail according to a modification. FIG. 12 is a flowchart illustrating an information processing procedure according to the embodiment. FIG. 13 is a flowchart illustrating a calculation processing procedure according to the embodiment. FIG. 14 is a flowchart illustrating a learning processing procedure according to the embodiment. FIG. 15 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device.

  Hereinafter, an information processing apparatus, an information processing method, and an embodiment (hereinafter, referred to as “embodiment”) for implementing an information processing program according to the present application will be described in detail with reference to the drawings. The information processing apparatus, the information processing method, and the information processing program according to the present application are not limited by the embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and overlapping description will be omitted.

[1. Example of information processing)
First, an example of an e-mail according to the embodiment will be described with reference to FIG. FIG. 1 illustrates an example in which the information processing apparatus 100 generates display information that is displayed as a sender name of an email based on planning information on a sales promotion project planned by S-shopping that is the sender of the email. . FIG. 1 is a diagram illustrating an example of an e-mail according to the embodiment. FIG. 1 shows a case where the user terminal 10 that receives an e-mail is a smartphone.

  The diagram shown on the left side of FIG. 1 is a diagram corresponding to a list screen of e-mails received by the user terminal 10. As shown on the left side of FIG. 1, on the smartphone, the sender's name is displayed above the subject on the mail list screen of many models. In addition, in the case of smartphones, on the mail list screens of many models, the sender's name is displayed in characters larger than the subject's character size. In addition, the thickness of the character of the sender name is displayed in a bold font than the thickness of the character of the subject. Therefore, the display information displayed as the sender of the e-mail is information that is visually appealing to the user who has received the e-mail.

  In general, the display information displayed as the sender name of the mail is considered to be information having a higher priority in determining the importance of the electronic mail received by the receiver of the mail. For example, in the case of work, if the sender of the e-mail is a business partner, failure to confirm the content directly leads to loss of business opportunities and loss of trust from the business partner, so the mail is highly important to the recipient Is likely to be determined. On the other hand, an e-mail sent from a colleague of a company is less important than an e-mail sent from a business partner because it is unlikely that not responding immediately will directly lead to disadvantages of the company. It is thought that it is easy to be judged. Also, in everyday life, if the sender of the e-mail is your child, e-mail is judged to be highly important to the recipient because failure to check the contents may affect the safety of the child It is thought that it is easy to be done. On the other hand, an e-mail whose sender is unknown at all may be mis-sent and have a low relationship with the recipient, so it is less important than an e-mail sent from your child It is thought that it is easy to be judged that it is an email. As described above, it is considered that the importance of the received e-mail largely depends on the sender of the e-mail for the e-mail recipient. In other words, the display information displayed as the sender name of the e-mail is information with a high priority for the recipient of the e-mail when confirming the contents of the e-mail. That is, the display information displayed as the sender name of the e-mail is information with a high appeal to the recipient of the e-mail.

  Here, the information processing apparatus 100 displays display information displayed as the sender name of the electronic mail based on the mail information about the electronic mail to be transmitted, and information other than the identification information for identifying the sender of the electronic mail. The server device generates display information to be displayed. The information processing apparatus 100 generates display information that is displayed as a sender name of an e-mail distributed by a company that provides a service related to an online shopping mall. In the present specification, the name of a company that provides services related to the online shopping mall is described as “S shopping”. In the example illustrated in FIG. 1, a case will be described in which S shopping transmits an electronic mail M <b> 1 regarding the first notification of a sales promotion project for promoting sales of pet supplies. The information processing apparatus 100 generates, as information other than the identification information for identifying the sender of the e-mail, display information in which a plan name related to a sales promotion plan planned by S shopping, which is the sender of the e-mail, is displayed.

  Specifically, the information processing apparatus 100 refers to the plan information storage unit 121 illustrated in FIG. 4 to acquire plan information on a sales promotion plan planned by S shopping. Subsequently, the information processing apparatus 100 generates display information on which information other than the identification information for identifying the sender of the e-mail is displayed based on the acquired plan information. In the example illustrated in FIG. 1, the information processing apparatus 100 acquires, as the plan information, “pet special (first)” which is a phrase indicating a plan name planned by S shopping. Subsequently, the information processing apparatus 100 decomposes words included in the acquired plan information into words by morphological analysis. For example, the information processing apparatus 100 decomposes “pet special (first)”, which is a phrase indicating a plan name acquired as plan information, into “pet special” and “(first)”. Here, the sender's name has a limitation that the number of characters that can be displayed is smaller because the size of the character at the time of browsing is larger than the subject. For example, in a smartphone, the number of display characters of a subject when an electronic mail is received is about 21 characters, whereas the number of display characters of a sender name is up to about 14 characters. Therefore, the information processing apparatus 100 generates the display information so that the display information is limited to about 14 characters, which is the number of characters that can be displayed as the sender name. For example, the information processing apparatus 100 extracts a word of “pet special” excluding “(first)” from “pet special (first)” which is a phrase indicating a plan name acquired as plan information. Subsequently, the information processing apparatus 100 generates display information in which the extracted word “pet special” is displayed as information other than the identification information for identifying the sender of the electronic mail.

  In addition, the information processing apparatus 100 generates display information in which “S shopping”, which is character information indicating a business name, is displayed as identification information for identifying the sender of the e-mail. In the example illustrated in FIG. 1, the information processing apparatus 100 displays, as display information displayed as the sender name of the e-mail, a concatenation of “pet special feature” as the project name and “S shopping” as the business name. Generate display information to be displayed.

  Further, the information processing apparatus 100 generates display information to which additional information for enhancing a visual effect is added. For example, the information processing apparatus 100 generates display information to which special symbols, such as an angle bracket, a corner bracket, double angle brackets, and pictograms, such as emoticons, are added as additional information for enhancing a visual effect. In the example illustrated in FIG. 1, the information processing apparatus 100 adds a parenthesis as additional information for enhancing a visual effect, and displays “pet special” which is character information indicating a project name between the parenthesis. "[Pet special feature] S shopping" which is display information to be generated is generated. Note that corner brackets and double angle brackets may be used instead of the square brackets.

  Further, the information processing apparatus 100 generates subject information to be displayed as the subject of the e-mail based on the display information. Specifically, the information processing apparatus 100 determines to generate subject information based on plan information other than the plan name because the display information includes the plan name. For example, the information processing apparatus 100 refers to the plan information storage unit 121 shown in FIG. 4 and describes, as the plan contents, character information “dog article special feature (dog food, kennel / cage...), Cat article special feature (cat food). , Cat litter, toilets ...), bird supplies special issue (birdcages ...). Subsequently, the information processing apparatus 100 decomposes words included in the acquired plan information into words by morphological analysis. Subsequently, the information processing apparatus 100 extracts a main keyword according to the weight of each word using a weight value such as tf-idf (Term Frequency, Inverse Document Frequency), and based on the extracted keyword. Generate a plan summary. For example, the information processing apparatus 100 extracts words such as “dog supplies” and “cat supplies” as main keywords. Subsequently, the information processing apparatus 100 reads “dog, cat, bird, small animal, tropical fish, aquarium,” which is a character string in which the main keywords are separated by spaces based on the words extracted as the main keywords. Generate as information.

  The user terminal 10 displays, on a screen of the user terminal 10, a content C11 corresponding to the list screen of the e-mail received by the user terminal 10 by a mailer mounted on the user terminal 10. In the diagram shown on the left side of FIG. 1, the user terminal 10 displays a partial content P11 as a part of the content C11. The partial content P11 is information including display information “Ichiro Suzuki” displayed as the sender name of the e-mail received by the user terminal 10 and subject information “Influenza vaccination” displayed as the subject.

  Further, the user terminal 10 displays the partial content P12 as a part of the content C11. The partial content P12 is information including display information “Hanako Tanaka” displayed as the sender name of the e-mail received by the user terminal 10 and subject information “Matter of tomorrow's lunch” displayed as the subject.

  Further, the user terminal 10 displays the partial content P13 as a part of the content C11. The partial content P13 includes display information "[pet special feature] S shopping" displayed as the sender name of the e-mail received by the user terminal 10 and subject information "dog supplies cat supplies bird supplies ..." displayed as the subject. It is information including.

  Further, the user terminal 10 displays the partial content P14 as a part of the content C11. The partial content P14 is information including display information “Jiro Sato” displayed as the sender name of the e-mail received by the user terminal 10 and subject information “Meeting for meeting” displayed as the subject.

  Although not shown in FIG. 1, the user terminal 10 may display another partial content as a part of the content C11. The other partial content is information including display information displayed as a sender name of another e-mail received by the user terminal 10 and subject information displayed as a subject. In the diagram shown on the left side of FIG. 1, an e-mail corresponding to the partial content P13 is selected from the e-mail list screen in accordance with a user operation.

  The diagram shown on the right side of FIG. 1 is a diagram corresponding to the detailed screen of the e-mail corresponding to the partial content P13 selected by the user. The user terminal 10 displays, on a screen of the user terminal 10, a content C12 corresponding to a detailed screen of the e-mail selected by the user by a mailer mounted on the user terminal 10.

  In the diagram shown on the right side of FIG. 1, the user terminal 10 displays the partial content P21 as a part of the content C12. The partial content P21 is information including "[Pet special feature] S shopping" which is display information displayed as the sender name of the e-mail and "User U1" which is destination information displayed as the destination of the e-mail. .

  Further, the user terminal 10 displays the partial content P22 as a part of the content C12. The partial content P22 is information indicating the date and time of receiving the e-mail and “Dog supplies Cat supplies Bird supplies Small animal supplies Tropical fish / aquarium supplies” which is the subject information displayed as the subject of the e-mail. 0:00 ”.

  Further, the user terminal 10 displays the partial content P23 as a part of the content C12. The partial content P23 is content information displayed as the content of the body of the e-mail. In the diagram shown on the right side of FIG. 1, the e-mail selected by the user is an e-mail in HTML (Hyper Text Markup Language) format. In addition, an image or the like relating to the pet special feature is displayed as the content of the body of the email. The content of the body of the electronic mail may be a text mail.

  As described above, the information processing apparatus 100 acquires the mail information regarding the electronic mail to be transmitted. Further, the information processing apparatus 100 displays, based on the acquired mail information, display information that is displayed as the sender name of the electronic mail and that displays information other than identification information for identifying the sender of the electronic mail. Generate. Thereby, the information processing apparatus 100 can display information other than the identification information for identifying the sender as a sender name which is information having a higher priority for the receiver. In other words, the information processing apparatus 100 can display information other than the identification information for identifying the sender as information with high appeal to the recipient. Therefore, the information processing apparatus 100 can provide an e-mail with high appeal.

  The information processing apparatus 100 may use the display information generated in FIG. 1 as teacher data to learn a model that predicts a response index that is an index indicating a degree of a user's response to an e-mail. Specifically, the information processing apparatus 100 calculates a response index that is an index indicating a degree of a user's response to the electronic mail M1. Then, the information processing apparatus 100 learns a model that predicts a response index based on the display information, using the generated display information and the calculated response index as teacher data. Then, the information processing device 100 generates display information based on the response index predicted by the learned model.

  More specifically, information processing apparatus 100 acquires the user's access information for transmitted e-mail M1. Then, the information processing apparatus 100 calculates a response index, which is an index indicating the degree of the user's response to the electronic mail M1, based on the acquired access information. For example, the information processing apparatus 100 calculates, as a response index, an e-mail opening rate indicating whether or not the e-mail M1 is opened. For example, the information processing apparatus 100 calculates the ratio of the number of users who have opened the mail M1 to the number of destination users of the mail M1 as the opening rate of the mail M1. Further, the information processing apparatus 100 calculates, as a response index, a click rate indicating whether or not the content included in the email M1 is selected. For example, the information processing apparatus 100 calculates, as the click rate of the mail M1, a ratio of the number of users who have selected the content in the electronic mail M1 to the number of destination users of the mail M1. In addition, the information processing apparatus 100 calculates, as a response index, a conversion rate indicating whether or not an action that will benefit the advertiser of the advertising content included in the email occurs. For example, the information processing apparatus 100 calculates the ratio of the number of conversions to the number of clicks of the mail M1 as the conversion rate of the mail M1. Further, the information processing apparatus 100 calculates, as a response index, opening period information regarding a period until the electronic mail is opened. For example, the information processing apparatus 100 calculates the number of days of the difference between the transmission date of the mail M1 and the opening date of the mail M1 as the opening period.

  Subsequently, the information processing apparatus 100 learns a model that predicts a response index based on the display information, using the generated display information and the calculated response index as teacher data. For example, the information processing device 100 learns a model MD1 for estimating the opening rate of mail. Further, the information processing apparatus 100 learns a model MD2 that predicts a click rate of an email as a response index. Further, the information processing apparatus 100 learns a model MD3 that predicts a mail conversion rate as a response index. Further, the information processing device 100 learns a model MD4 that predicts opening period information regarding a period until the electronic mail is opened.

  Subsequently, the information processing device 100 generates display information based on the response index predicted by the learned model. For example, the information processing apparatus 100 generates a plurality of pieces of display information for the same mail. Subsequently, the information processing apparatus 100 predicts a response index for each of the plurality of pieces of display information as input data of a model that has learned each of the plurality of pieces of display information. Subsequently, the information processing apparatus 100 selects, from among the plurality of pieces of display information, the display information having the highest e-mail opening rate, as the display information of the transmission target e-mail, among the predicted response indices. Note that the information processing apparatus 100 may use the entirety of the generated display information as input data of the model, or may use a part of the generated display information as input data of the model. Specifically, the information processing apparatus 100 learns a model for predicting a response index based on a portion of the generated display information other than the identification information for identifying the sender of the e-mail. For example, the information processing apparatus 100 learns a model that predicts a response index based on a keyword included in a part that is information other than identification information for identifying a sender of an electronic mail.

  Further, the information processing apparatus 100 may learn a model that predicts a response index for each user attribute. Then, the information processing apparatus 100 may generate display information of a mail to be transmitted to a new user having an attribute similar to the attribute corresponding to the model, based on the response index predicted by the learned model. For example, the information processing apparatus 100 learns a model MD11 that predicts an e-mail opening rate of a user who is a woman in her twenties as a user attribute. For example, the information processing apparatus 100 learns a model MD11 that predicts the opening rate of a user who is a woman in her twenties based on a keyword included in a portion that is information other than identification information for identifying a sender of an e-mail. The information processing apparatus 100 extracts, from the mail M11 transmitted to the new user who is a woman in her twenties, a keyword included in a part that is information other than the identification information for identifying the sender of the electronic mail. Subsequently, the information processing apparatus 100 selects a keyword having the highest predicted opening rate based on the opening rate predicted by the learned model MD11. Subsequently, the generation unit 132 generates display information including a keyword having the highest predicted opening rate as the display information of the mail M11 transmitted to the new user who is a woman in her twenties.

  In addition, the information processing apparatus 100 learns, as an attribute of the user, a model MD31 that predicts a mail conversion rate of a user who is a university student living in Tokyo. For example, the information processing apparatus 100 learns a model MD31 that predicts the conversion rate of a user who is a university student living in Tokyo, based on a keyword included in a part that is information other than identification information for identifying a sender of an e-mail. . The information processing apparatus 100 extracts a keyword included in a part of the mail M51 transmitted to a new user who is a university student living in Tokyo, other than the identification information for identifying the sender of the electronic mail. Subsequently, the information processing apparatus 100 selects a keyword having the highest predicted conversion rate based on the conversion rate predicted by the model MD31 learned by the information processing apparatus 100. Subsequently, the information processing apparatus 100 generates display information including a keyword having the highest predicted conversion rate as display information of the mail M51 transmitted to a new user who is a university student living in Tokyo.

[2. Configuration of information processing system]
Next, the configuration of the information processing system 1 including the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of the information processing system 1 according to the embodiment. As illustrated in FIG. 2, the information processing system 1 according to the embodiment includes a user terminal 10, an e-commerce server 50, and an information processing device 100. These various devices are communicably connected by wire or wireless via a network N (for example, the Internet). Note that the information processing system 1 illustrated in FIG. 2 may include an arbitrary number of user terminals 10, an arbitrary number of e-commerce servers 50, and an arbitrary number of information processing apparatuses 100.

  The user terminal 10 is an information processing device used by a user. The user terminal 10 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a mobile phone, a PDA (Personal Digital Assistant), or the like. FIG. 1 shows a case where the user terminal 10 is a smartphone. In the following, the user terminal 10 may be identified with the user in some cases. That is, the user can be replaced with the user terminal 10 below.

  Hereinafter, the user specified by the user ID “U1” may be referred to as “user U1”. Thus, hereinafter, when "user U * (* is an arbitrary numerical value)" is described, it indicates that the user is a user specified by the user ID "U *". For example, when "user U2" is described, the user is a user specified by the user ID "U2".

  Hereinafter, the user terminal 10 will be described as the user terminals 10-1 and 10-2 according to the user who uses the user terminal 10. For example, the user terminal 10-1 is the user terminal 10 used by the user U1. Further, for example, the user terminal 10-2 is the user terminal 10 used by the user U2. In the following, the user terminals 10-1 and 10-2 are referred to as the user terminals 10 in the case where they are described without particular distinction.

  In addition, the user terminal 10 transmits, to the mail server, a content distribution request including a list of e-mails received by the user terminal 10 in response to a user operation. Upon receiving the distribution request, the mail server transmits to the user terminal 10 a content C11 corresponding to the list screen of the e-mail received by the user terminal 10. Upon receiving the content C11, the user terminal 10 displays the received content C11 on the screen of the user terminal 10.

  In addition, when the user selects an e-mail corresponding to the partial content P13 from the received e-mail list screen according to the operation of the user, the user terminal 10 issues a distribution request of the content corresponding to the selected e-mail. Send to mail server. Upon receiving the distribution request, the mail server transmits the content C12 corresponding to the selected e-mail to the user terminal 10. Upon receiving the content C12, the user terminal 10 displays the received content C12 on the screen of the user terminal 10.

  The electronic commerce server 50 is a server device that provides a service called a so-called online shopping mall (or electronic mall). More specifically, the e-commerce server 50 provides a service for selling various products by combining product sales pages of a plurality of stores that sell products via the Internet into one service. The e-commerce server 50 provides a user with a service of an e-commerce street. In addition, the e-commerce server 50 provides various operating tools for operating a store to a store opening in an online shopping mall.

  The e-commerce server 50 is managed by a company that provides services related to the online shopping mall. In the example illustrated in FIG. 1, a business name that is a name of a business providing a service related to the online shopping mall is referred to as “S shopping”. In the following, “S shopping” may be used as the name of a service related to the online shopping mall provided by “S shopping” as a business operator.

  “S shopping”, which is a business operator, issues various notifications to the user to encourage the user to use the online shopping mall. For example, “S shopping”, which is a business operator, notifies the user of a sales promotion plan for promoting sales in the online shopping mall. For example, “S shopping”, which is a business operator, sends a notification to the user using an email or a push notification. In the example shown in FIG. 1, the business “S shopping” notifies the user by email about “pet specials”, which is a sales promotion plan for promoting sales of pet-related products.

  The information processing device 100 is a server device that performs the information processing described in FIG. The information processing apparatus 100 acquires plan information on “pet special” which is a sales promotion plan planned by “S shopping”, which is the sender of the e-mail. Subsequently, the information processing apparatus 100 displays, based on the acquired plan information, display information that is displayed as the sender name of the e-mail and that is information other than identification information for identifying the sender of the e-mail. Is generated as “[Pet special feature] S shopping”. Subsequently, the information processing apparatus 100 transmits to the user terminal 10 an electronic mail in which the generated display information is displayed as the sender name of the electronic mail. More specifically, the information processing apparatus 100 transfers the electronic mail in which the generated display information “[pet specialty] S shopping” is displayed as the sender name of the electronic mail to the mail server of the user terminal 10. The user terminal 10 transmits a distribution request of the e-mail received by the mail server to the mail server. The mail server transmits the electronic mail transferred from the information processing device 100 to the user terminal 10 in response to the distribution request received from the user terminal 10.

  In the example illustrated in FIG. 2, the case where the electronic commerce server 50 and the information processing device 100 are separate devices has been described, but the electronic commerce server 50 and the information processing device 100 may be integrated. For example, the information processing apparatus 100 may have a function of the electronic commerce server 50, and may provide a service of an online shopping mall, and generate both display information and send an electronic mail.

[3. Configuration of information processing device]
Next, the configuration of the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the information processing apparatus 100 according to the embodiment. As shown in FIG. 3, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The information processing apparatus 100 includes an input unit (for example, a keyboard and a mouse) for receiving various operations from an administrator or the like of the information processing apparatus 100, and a display unit (for example, a liquid crystal display) for displaying various information. May have.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network by wire or wirelessly, and transmits and receives information between the user terminal 10 and the e-commerce server 50, for example.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 3, the storage unit 120 includes a plan information storage unit 121, a user information storage unit 122, a mail information storage unit 123, and a model information storage unit 124.

(Planning information storage unit 121)
The plan information storage unit 121 stores various types of information related to a sales promotion plan planned by “S shopping” as a business. FIG. 4 illustrates an example of the plan information storage unit according to the embodiment. In the example shown in FIG. 4, the plan information storage unit 121 has items such as "plan ID", "plan date", "plan name", and "plan contents".

  The “plan ID” indicates an ID for identifying a sales promotion plan planned by the business operator “S shopping”. In the example shown in the first record of FIG. 4, the plan ID “E1” indicates “pet special” which is a plan corresponding to the electronic mail shown in FIG.

  The “plan date and time” indicates information on the plan date and time of the sales promotion plan. In the example shown in the first record of FIG. 4, the plan date and time “July 1, 2018 to July 31, 2018” indicates that the plan (plan E1) identified by the plan ID “E1” is July 1, 2018. It is shown that the event will be held from the date to the period of July 31, 2018.

  The “plan name” indicates information on the plan name of the sales promotion plan. In the example shown in the first record in FIG. 4, the plan name “pet special (first)” indicates the plan name of the plan (plan E1) identified by the plan ID “E1”.

  The “plan content” indicates information on the plan content of the sales promotion plan. In the example shown in the first record in FIG. 4, the contents of the plan are “dog specialty (dog food, kennel / cage ...), cat specialty (cat food, cat litter / toilet ...), bird specialty (bird cage / ..) ”indicates information on the plan contents of the plan (plan E1) identified by the plan ID“ E1 ”. As described with reference to FIG. 1, the "pet special feature" is a project aimed at promoting the sale of pet supplies in the online shopping mall, and the content of the plan is a collection of special features set for each pet accessory according to the type of pet. Things.

(User information storage unit 122)
The user information storage unit 122 stores various types of information regarding users who use the online shopping mall provided by “S shopping” as a business operator. FIG. 5 illustrates an example of the user information storage unit according to the embodiment. In the example shown in FIG. 5, the user information storage unit 122 has items such as “user ID”, “member information”, and “service use history”.

  “User ID” indicates an ID for identifying a user who uses the online shopping mall. In the example shown in the first record in FIG. 5, the user (user U1) identified by the user ID “U1” indicates the user who is the destination of the e-mail shown in FIG.

  “Member information” stores various types of information on users who use the online shopping mall. The “member information” further includes small items such as “member type”, “attribute information”, “point (pt)”, and “expiration date”.

  “Member type” is information indicating whether the user who uses the online shopping mall is a “paid member” or a “free member”. The “paid member” is a type of member who obtains better services and benefits than a free member by paying an additional fee such as an annual membership fee or a monthly fee to “S shopping” as a business. The “free member” is a member type that can use a normal service without paying an annual membership fee or a monthly membership fee for “S shopping”, which is a business entity. In the example shown in the first record of FIG. 5, the member type “paid member” indicates that the member type of the user U1 is “paid member”.

  “Attribute information” indicates attribute information of a user who uses the online shopping mall. In the example shown in the first record of FIG. 5, the attribute information “attribute information # 1” indicates the attribute information of the user U1. Specifically, the attribute information “attribute information # 1” indicates demographic information such as the sex, age, date of birth, address, occupation, marriage status, and child status of the user U1.

  “Point (pt)” indicates the number of points held by the user using the online shopping mall. In the example shown in the first record of FIG. 5, the point (pt) “100” indicates that the number of points held by the user U1 is 100 points.

  The “expiration date” indicates the expiration date of the points held by the user using the online shopping mall. In the example shown in the first record in FIG. 5, the expiration date “2018/9/1 PM 24:00” indicates that the expiration date of the points held by the user U1 is until 24:00 PM on September 1, 2018. Indicates that Note that the points expire after the expiration date of the points. In other words, points cannot be used.

  The “service usage history” stores various types of information regarding the service usage history of the user who uses the online shopping mall. The “service use history” further has small items such as “purchase history”, “shopping cart”, and “favorite field”.

  “Purchase history” indicates various types of information relating to the history of the user shopping at the online shopping mall. In the example shown in the first record of FIG. 5, the purchase history “cat food” indicates that the product purchased most recently by the user U1 is “cat food”. Although not shown in FIG. 5 for simplicity, the “purchase history” includes a history of all products purchased by the user in the online shopping mall, information on purchase date and time of purchase of each product, and a purchase price. Information may be stored.

  “Shopping cart” indicates information on a product put into a shopping cart by a user to purchase in the online shopping mall. In the example shown in the first record of FIG. 5, the shopping cart "cat sand" indicates a product that the user U1 has put into the shopping cart to purchase. Although not shown in FIG. 5 for simplicity, information on a product put in “favorite” by the user U1 may be stored as “service usage history”.

  The “favorite field” is information on a field presumed to be preferred by the user. For example, “favorite field” is information on a product category in which a user frequently purchases a product. In the example shown in the first record of FIG. 5, the favorite field “cat” indicates that the field estimated to be preferred by the user U1 is the “cat” category.

(Email information storage unit 123)
The mail information storage unit 123 stores various types of information regarding electronic mail. FIG. 6 illustrates an example of a mail information storage unit according to the embodiment. In the example illustrated in FIG. 6, the mail information storage unit 123 stores “mail ID”, “contents of text”, “transmission date and time”, “transmission destination information”, “sender display”, “subject display”, and “opened date and time”. , “Conversion date and time”.

  “Mail ID” indicates an ID for identifying an electronic mail. In the example shown in the first record in FIG. 6, the mail (mail M1) identified by the mail ID “M1” indicates the electronic mail related to the pet special feature shown in FIG.

  “Contents of the body” indicates the contents of the body of the e-mail. The “contents of the text” is, for example, character information described in the text when the electronic mail is a text mail. The “contents of the text” may include information on an image or a moving image, for example, when the electronic mail is an HTML-formatted mail. In the example shown in the first record in FIG. 6, the content "MC1" of the text indicates the content of the text of the mail M1.

  “Send date and time” indicates information on the date and time when the e-mail was sent. The “sending date and time” is the same information as the receiving date and time for the user terminal that has received the e-mail. In the example shown in the first record in FIG. 6, the transmission date and time “17:00 on July 1, 2018” indicates that the date and time when the mail M1 was transmitted is 17:00 on July 1, 2018.

  “Destination information” indicates information about the user who is the destination of the e-mail. The “destination information” further has small items such as “user ID”, “address”, and “browsing environment”. “User ID” indicates an ID for identifying a user to which an electronic mail is transmitted. In the example shown in the first record of FIG. 6, the user (user U1) identified by the user ID “U1” indicates the user who is the destination of the e-mail shown in FIG. “Address” indicates the mail address of the user to whom the e-mail is sent. In the example shown in the first record of FIG. 6, the address “AD # 1” indicates the mail address of the user U1. “Browsing environment” indicates the type of mailer and the type of user terminal installed in the user terminal. The type of the user terminal indicates a smartphone model, a tablet terminal, a notebook PC, a mobile phone, a PDA, or the like. In the example shown in the first record of FIG. 6, the browsing environment “EN # 1” indicates that the type of mailer and the type of user terminal mounted on the user terminal 10-1 of the user U1 are smartphones.

  “Sender display” indicates display information displayed as the sender name of the e-mail. “Sender display” further has small items such as “other than identification information” and “identification information”. “Other than identification information” indicates information displayed as information other than the identification information for identifying the sender of the electronic mail among the display information displayed as the sender name of the electronic mail. “Identification information” indicates information displayed as identification information for identifying the sender of the e-mail among display information displayed as the sender name of the e-mail. In the example shown in the first record of FIG. 6, “[pet special feature]” other than the identification information is displayed as information other than the identification information for identifying the sender of the electronic mail among the display information displayed as the sender name of the mail M1. Indicates that the information to be displayed is “[Pet specials]”. In the example shown in the first record of FIG. 6, the identification information “S shopping” is the information displayed as the identification information for identifying the sender of the electronic mail among the display information displayed as the sender name of the mail M1. Indicates "S shopping".

  "Subject display" indicates subject information displayed as the subject of the e-mail. In the example shown in the first record in FIG. 6, the subject information displayed as the subject of the mail M1 is “Dog supplies, cat supplies, bird supplies,. Indicates that

  “Open date and time” indicates information on the date and time when the e-mail was opened by the user who is the destination of the e-mail. In the example shown in the first record in FIG. 6, the opening date and time “18:00 on July 1, 2018” indicates that the date and time when the mail M1 was opened by the user U1 to which the mail M1 was sent is July 1, 2018. 18:00.

  The “conversion date and time” indicates information on the date and time when the user who is the destination of the e-mail has performed an action that is profitable for the advertiser of the advertising content included in the e-mail. Specifically, the advertiser of the advertising content refers to a store that has opened a store in an online shopping mall operated by “S shopping” as a business operator. In the example shown in FIG. 6, the information indicating the date and time when the user who is the transmission destination of the e-mail purchased the product corresponding to the advertising content included in the e-mail is shown. The conversion may be any action other than product purchase, as long as it is an action that is profitable for the advertiser of the advertising content. For example, the conversion may be an inquiry or a document request for a product corresponding to the advertising content, a reservation for purchase of the product, or an access to a Web site of a store.

(Model information storage unit 124)
The model information storage unit 124 stores, based on the display information, various types of information related to a model that predicts a response index, which is an index indicating a degree of a user's response to an electronic mail to be transmitted. FIG. 7 illustrates an example of the model information storage unit according to the embodiment. In the example shown in FIG. 7, the model information storage unit 124 has items such as “model ID”, “prediction target”, and “model data”.

  “Model ID” indicates an ID for identifying a model that predicts a response index based on display information. The “prediction target” indicates a response index that is a prediction target of the model. The prediction target “opening rate” shown in the first record of FIG. 7 indicates a probability that the electronic mail to be transmitted is opened. The prediction target “click rate” shown in the second record in FIG. 7 indicates a probability that the content included in the electronic mail to be transmitted is selected. The prediction target “conversion rate” shown in the third record in FIG. 7 indicates a probability that an action that will be profitable for the advertiser of the advertising content included in the email to be transmitted occurs. The prediction target “opening period” shown in the fourth record in FIG. 7 indicates a probability that an action that will benefit the advertiser of the advertising content included in the electronic mail to be transmitted will occur. “Model data” indicates specific model data of a model that predicts a response index based on display information. For example, the model data indicates a character string or a numerical value indicating a model structure or a connection coefficient. In the example shown in the first record of FIG. 7, the model identified by the model ID “MD1” (model MD1) is a model that predicts the opening rate of the e-mail to be transmitted based on the display information. Show. In the example shown in the first record of FIG. 7, the model data “MDT1” indicates specific model data of the model MD1.

(Control unit 130)
Returning to the description of FIG. 3, the control unit 130 is a controller, and is stored in a storage device inside the information processing apparatus 100 by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). Are implemented by executing various programs (corresponding to an example of a generation program) using a RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

  Further, the control unit 130 performs, based on information processing according to a model to be described later, for the predetermined display information input to the input layer, each element belonging to each layer other than the output layer as a first element, and By performing the calculation based on the weight of one element, whether or not the e-mail displaying the predetermined display information is opened by the user, and whether the product or the like follows the action of the e-mail being opened by the user. The computer is made to output a score regarding whether or not the purchase is made from the output layer. The model such as the model MD1 may be assumed to be used as a program module that is a part of the artificial intelligence software. Further, the model such as the model MD1 may be a program.

  As illustrated in FIG. 3, the control unit 130 includes an acquisition unit 131, a generation unit 132, a transmission unit 133, a calculation unit 134, and a learning unit 135, and realizes an information processing operation described below. Or execute. Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 3, and may be another configuration as long as it performs information processing to be described later.

(Acquisition unit 131)
The obtaining unit 131 obtains mail information regarding an electronic mail to be transmitted. The acquiring unit 131 acquires, as mail information, meta information related to the content of the body of the e-mail. Specifically, the acquiring unit 131 acquires, as the mail information, the plan information on the plan planned by the sender of the e-mail. For example, the obtaining unit 131 obtains, from the e-commerce server 50, information on a plan date and time, a plan name, and plan contents as plan information on the plan planned by the sender of the e-mail. Subsequently, when acquiring the plan information, the acquiring unit 131 stores the acquired plan information in the plan information storage unit 121. Note that the acquisition unit 131 may decompose the words included in the acquired plan information into words by morphological analysis, and store the decomposed words in the plan information storage unit 121.

(Generation unit 132)
The generating unit 132 is a display that displays, based on the mail information acquired by the acquiring unit 131, information other than the identification information for identifying the sender of the e-mail, the display information being displayed as the sender name of the e-mail. Generate information. The generation unit 132 generates display information based on the meta information acquired by the acquisition unit 131. Specifically, the generation unit 132 generates display information based on the plan information acquired by the acquisition unit 131. For example, the generation unit 132 refers to the plan information storage unit 121 and acquires, as the plan information, “pet special (first)”, which is a word indicating the plan name stored in the item of the plan name. Subsequently, the generation unit 132 decomposes the words included in the acquired plan information into words by morphological analysis. For example, the generation unit 132 decomposes “pet special (first)”, which is a phrase indicating a plan name acquired as plan information, into “pet special” and “(first)”. Subsequently, the generation unit 132 generates the display information so that the display information is limited to about 14 characters, which is the number of characters that can be displayed as the sender name. For example, the generation unit 132 extracts a word of “pet special feature” excluding “(first feature)” from “pet special feature (first feature)” which is a phrase indicating a project name acquired as plan information. Subsequently, the generating unit 132 generates display information in which the extracted word “pet special” is displayed as information other than the identification information for identifying the sender of the electronic mail.

  Further, the generation unit 132 generates display information in which identification information for identifying the sender of the e-mail is displayed as the display information. For example, the generation unit 132 determines to display “S shopping”, which is character information indicating a business name, as identification information for identifying the sender of the e-mail. Subsequently, the generation unit 132 combines the project name “pet special feature”, which is information other than the identification information for identifying the sender of the e-mail, and the business name “S shopping”, which is the identification information for identifying the sender of the e-mail. Generate display information to be linked and displayed.

  The generation unit 132 generates display information to which additional information for enhancing a visual effect is added. More specifically, the generation unit 132 generates display information to which special symbols such as square brackets, corner brackets and double angle brackets, and pictograms such as emoticons are added as additional information for enhancing the visual effect. For example, the generation unit 132 is display information that adds a parenthesis as additional information for enhancing a visual effect, and displays “pet special feature” which is character information indicating a project name between the parenthesis. [Pet specials: S shopping] is generated.

  Further, the generating unit 132 generates subject information to be displayed as the subject of the e-mail based on the display information. Specifically, the generation unit 132 generates display information based on the plan information acquired by the acquisition unit 131. For example, the generation unit 132 determines to display a summary of the plan contents as the subject information. Subsequently, the generation unit 132 refers to the plan information storage unit 121 and extracts the character information stored in the item of the plan content. Subsequently, the generation unit 132 decomposes the words included in the extracted character information into words by morphological analysis. Subsequently, the generating unit 132 extracts a main keyword from the extracted words and phrases according to the weight of each word using a weight value such as tf-idf. Subsequently, the generation unit 132 generates, as subject information, a character string in which main keywords are displayed separated by spaces. Note that the generation unit 132 is not limited to a character string in which main keywords are displayed separated by spaces, and may generate subject information displayed in various modes. For example, the generation unit 132 may generate a character string that displays main keywords separated by a slash as subject information.

(Transmission unit 133)
The transmission unit 133 transmits an e-mail to the user terminal 10. Specifically, the transmitting unit 133 transmits an e-mail in which the display information generated by the generating unit 132 is displayed as the sender name to the user terminal 10. For example, the transmission unit 133 acquires the e-mail address of the user registered in S shopping from the e-commerce server 50. Next, the transmission unit 133 transmits the e-mail with the acquired mail address specified as the destination. Subsequently, when transmitting the e-mail, the transmission unit 133 stores mail information regarding the transmitted e-mail in the mail information storage unit 123.

  In addition, the transmission unit 133 acquires the user's access information to the transmitted e-mail. Specifically, the transmission unit 133 incorporates a web beacon (Web Beacon), which is a program for access analysis, into e-mail content in HTML format and transmits the content. For example, the transmitting unit 133 incorporates a web beacon into the e-mail content by mounting a JavaScript (registered trademark) tag in an HTML file forming the e-mail content. When the e-mail is opened according to the operation of the user, the user terminal 10 displays the e-mail content incorporating the web beacon on the screen. Subsequently, when the e-mail content is displayed on the screen of the user terminal 10, a Java Script (registered trademark) code embedded in the e-mail content is activated, and the user terminal 10 transmits the user access data to the user terminal. 10 to the information processing apparatus 100. The transmitting unit 133 acquires information on the date and time when the user's access data was received as the user's access date and time to the e-mail.

  Specifically, the transmission unit 133 acquires information on the opening date and time of the e-mail as user access information for the transmitted e-mail. For example, the transmission unit 133 acquires the date and time when the user's access data is first received as the opening date and time. Upon acquiring the information on the opening date and time, the transmitting unit 133 stores the acquired information on the opening date and time in the mail information storage unit 123.

  In addition, the transmission unit 133 acquires information regarding the selected date and time when the content included in the transmitted e-mail is selected, as the user's access information to the transmitted e-mail. For example, the transmission unit 133 acquires information on the content selected by the user and the date and time when the content was selected by incorporating a web beacon for each content included in the email. When acquiring the information on the selected date and time, the transmitting unit 133 may store the acquired information on the selected date and time in the mail information storage unit 123.

  In addition, the transmission unit 133 acquires, as the user's access information to the transmitted e-mail, information on the date and time when an action that would benefit the advertiser of the advertising content included in the e-mail occurred. Specifically, the transmission unit 133 acquires information on the purchase date and time when the product corresponding to the advertisement content was purchased, as the date and time when an action that would be profitable for the advertiser of the advertisement content included in the email occurred. For example, the transmission unit 133 refers to the mail information storage unit 123 and acquires a user ID for identifying the user who opened the transmitted e-mail. In addition, the transmission unit 133 acquires information on the advertisement content selected by the user and the date and time when the advertisement content was selected by incorporating a web beacon for each advertisement content included in the email. It is assumed that the electronic commerce server 50 stores the product ID of the product corresponding to the advertisement content and the advertisement content ID in the storage unit in association with each other. In addition, the transmission unit 133 acquires information about the purchase history of S shopping from the electronic commerce server 50. Then, the transmission unit 133 determines whether or not the user corresponding to the acquired user ID has purchased a product corresponding to the selected advertisement content based on the acquired information regarding the purchase history. If the transmission unit 133 determines that the user corresponding to the acquired user ID has purchased a product corresponding to the selected advertisement content, the transmission unit 133 relates to the date and time at which an action that would benefit the advertiser of the advertisement content included in the email occurred. The date and time of purchase of a product is acquired as information. When acquiring the purchase date and time of the product, the transmission unit 133 stores the acquired purchase date and time in the item of the conversion date and time in the mail information storage unit 123.

(Calculation unit 134)
The calculation unit 134 calculates a response index that is an index indicating the degree of the user's response to the e-mail. Specifically, the calculation unit 134 calculates a response index that is an index indicating a degree of a user's response to the email based on the user's access information to the email acquired by the transmission unit 133. For example, the calculation unit 134 calculates, as a response index, an index value indicating whether an email is opened. For example, the calculation unit 134 calculates the mail opening rate as an index value indicating whether the electronic mail is opened. For example, the calculation unit 134 calculates the number of users to which the mail M1 is transmitted as 100 with reference to the mail information storage unit 123. Subsequently, the calculation unit 134 calculates the number of users who have opened the mail M1 as 50 with reference to the mail information storage unit 123. For example, the calculation unit 134 calculates the number of users whose opening date and time information is stored in the item of opening date and time as 50 with reference to the mail information storage unit 123. Subsequently, the calculation unit 134 calculates 50%, which is a ratio of 50, which is the number of users who have opened the mail M1, to 100, which is the number of users to whom the mail M1 is transmitted, as the opening rate of the mail M1.

  Further, the calculation unit 134 calculates an index value indicating whether or not the content included in the email is selected as the response index. For example, the calculation unit 134 calculates the click rate of the content included in the email as an index value indicating whether or not the content included in the email is selected. For example, the calculation unit 134 calculates the number of users to which the mail M1 is transmitted as 100 with reference to the mail information storage unit 123. Subsequently, the calculating unit 134 calculates that the number of users who have selected the content included in the mail M1 is 30. For example, the calculation unit 134 calculates that the number of users who selected the content included in the mail M1 and in which the web beacon is incorporated is 30. Subsequently, the calculating unit 134 calculates the click rate of the mail M1 as 30%, which is a ratio of 30 as the number of users who selected the content to 100 as the number of users to which the mail M1 is transmitted.

  In addition, the calculation unit 134 calculates, as a response index, an index value that indicates whether an action that will benefit the advertiser of the advertising content included in the email occurs. For example, the calculation unit 134 calculates the conversion rate as an index value indicating whether an action that is profitable for the advertiser of the advertising content included in the email occurs. For example, the calculation unit 134 calculates the number of users who have selected the advertisement content included in the mail M1 and in which the web beacon is incorporated, as 30. Subsequently, the calculation unit 134 calculates the number of users who have purchased the product corresponding to the advertising content included in the mail M1 as 3 with reference to the mail information storage unit 123. For example, the calculating unit 134 calculates the number of users whose conversion date and time information is stored in the conversion date and time item as 3 with reference to the mail information storage unit 123. Subsequently, the calculation unit 134 calculates 10%, which is the ratio of 3 being the number of conversions to 30 being the number of clicks of the mail M1, as the conversion rate of the mail M1.

  Further, the calculation unit 134 calculates, as a response index, opening period information on a period until the electronic mail is opened. For example, the calculation unit 134 refers to the mail information storage unit 123 and calculates the number of days between the transmission date and the opening date of the electronic mail as the opening period. In the example shown in the second record of FIG. 6, the transmission date and time when the mail M1 was transmitted to the user U2 is "17:00 on July 1, 2018". The opening date and time when the mail M1 was opened by the user U2 is "19:00 on July 5, 2018". In this case, the calculation unit 134 determines that the difference between the “July 1, 2018” that is the transmission date of the mail M1 and the “July 5, 2018” that is the opening date of the mail M1 is 5 days. The opening period is calculated as 5 days.

(Learning unit 135)
The learning unit 135 learns a model for predicting a response index based on the display information generated by the generation unit 132. Specifically, the learning unit 135 learns a model that outputs the response index calculated by the calculation unit 134 using the display information generated by the generation unit 132 as input data. For example, the learning unit 135 learns a model that predicts a response index for each user attribute.

  More specifically, the learning unit 135 sets a higher score for display information that has a higher probability of being opened by the user and that has a higher probability that the user has an action of purchasing a product or the like subsequent to the action of opening the e-mail. Generate a model that has been learned to be calculated. For example, the learning unit 135 generates the model MD1 that has been learned so as to calculate a higher score for display information having a higher opening rate, which is the probability that the electronic mail is opened by the user. Further, the learning unit 135 generates a model MD2 that is learned so that display information having a higher click rate, which is a probability that a content included in an e-mail is selected by the user, is calculated as the display information is higher. In addition, the learning unit 135 generates the model MD3 that is learned so as to calculate a higher score for display information having a higher conversion rate, which is a probability that the user performs an action of purchasing a product or the like following an action of opening an email. . Further, the learning unit 135 generates the model MD4 that is learned so as to calculate a higher score as the display information whose opening period during which the electronic mail is opened by the user is shorter.

  The learning unit 135 may learn the model using the entirety of the generated display information as the input data of the model, or may learn the model using a part of the generated display information as the input data of the model. Is also good. Specifically, the learning unit 135 may use a portion of the generated display information other than the identification information for identifying the sender of the e-mail as input data of the model. For example, the learning unit 135 may use a keyword included in a part that is information other than the identification information for identifying the sender of the e-mail as input data of the model. Then, the learning unit 135 may learn a model for predicting a response index based on a keyword included in a part that is information other than the identification information for identifying the sender of the electronic mail.

  Note that the learning unit 135 may generate the model using any learning algorithm. For example, the learning unit 135 generates a model using a learning algorithm such as a neural network, a support vector machine, clustering, and reinforcement learning. As an example, when the learning unit 135 generates a model using a neural network, the model includes an input layer including one or more neurons, an intermediate layer including one or more neurons, and an output layer including one or more neurons. Having.

  In addition, the generation unit 132 generates display information based on a response index that is an index indicating a degree of a user's response to the electronic mail. Specifically, the learning unit 135 learns a model that predicts a response index for each attribute of the user. Then, the generation unit 132 generates display information of an e-mail to be transmitted to a new user having an attribute similar to the attribute corresponding to the model, based on the response index predicted by the model learned for each user attribute by the learning unit 135. I do. For example, the learning unit 135 learns, for each attribute of the user, a model that predicts a response index of a portion that is information other than the identification information for identifying the sender of the email. For example, the learning unit 135 learns, for each attribute of the user, a model for predicting a response index based on a keyword included in a part that is information other than identification information for identifying a sender of an electronic mail. Then, the generation unit 132 generates display information of an e-mail to be transmitted to a new user having an attribute similar to the attribute corresponding to the model, based on the response index predicted by the learned model.

  Specifically, the generating unit 132 generates display information based on an index value indicating whether or not the email is opened as a response index. For example, the learning unit 135 learns, as an attribute of the user, a model MD11 that predicts an e-mail opening rate of a user who is a woman in her twenties. For example, the learning unit 135 learns a model MD11 that predicts the opening rate of a user who is a woman in her twenties based on a keyword included in a portion that is information other than identification information for identifying a sender of an electronic mail. The generation unit 132 extracts keywords F11 to F15 as keywords included in a part of the mail M11 transmitted to the new user who is a woman in her twenties other than the identification information for identifying the sender of the e-mail. Subsequently, the generation unit 132 selects the keyword F11 with the highest predicted opening rate from the five keywords F11 to F15 based on the opening rate predicted by the model MD11 learned by the learning unit 135. . Subsequently, the generation unit 132 generates display information including the keyword F11 having the highest predicted opening rate as the display information of the mail M11 transmitted to the new user who is a woman in her twenties.

  In addition, the generation unit 132 generates display information based on an index value indicating whether or not the content included in the email is selected as the response index. The content included in the e-mail is, for example, advertisement content related to a product. Alternatively, the content included in the e-mail may be a homepage of a store that handles products. For example, the learning unit 135 learns, as an attribute of the user, a model MD21 that predicts a click rate of a mail of a user who is a male in his thirties. For example, the learning unit 135 learns a model MD21 that predicts a click rate of a user who is a male in his thirties, based on a keyword included in a part that is information other than identification information for identifying a sender of an electronic mail. The generation unit 132 extracts keywords F41 to F45 as keywords included in a part of information other than the identification information for identifying the sender of the electronic mail, for the mail M41 transmitted to the new user who is a male in his thirties. Subsequently, the generation unit 132 selects the keyword F41 having the highest predicted click rate from the five keywords F41 to F45 based on the click rate predicted by the model MD21 learned by the learning unit 135. . Subsequently, the generation unit 132 generates display information including the keyword F41 having the highest predicted click rate as the display information of the mail M41 transmitted to the new user who is a male in his thirties.

  In addition, the generation unit 132 generates the display information as a response index based on an index value indicating whether an action that is profitable for the advertiser of the advertising content included in the email occurs. For example, the learning unit 135 learns, as an attribute of the user, a model MD31 that predicts a mail conversion rate of a user who is a university student living in Tokyo. For example, the learning unit 135 learns a model MD31 that predicts the conversion rate of a user who is a college student living in Tokyo, based on a keyword included in a part that is information other than identification information for identifying a sender of an electronic mail. The generation unit 132 extracts keywords F51 to F55 as keywords included in a part of information other than the identification information for identifying the sender of the electronic mail, for the mail M51 transmitted to a new user who is a university student living in Tokyo. Subsequently, the generation unit 132 selects the keyword F51 with the highest predicted conversion rate from the five keywords F51 to F55 based on the conversion rate predicted by the model MD31 learned by the learning unit 135. . Subsequently, the generating unit 132 generates display information including the keyword F51 having the highest predicted conversion rate as the display information of the mail M51 transmitted to the new user who is a university student living in Tokyo.

  In addition, the generation unit 132 generates display information based on opening period information regarding a period until the electronic mail is opened as a response index. For example, the learning unit 135 learns, as an attribute of the user, a model MD41 that predicts an opening period of a mail of a user who is a paying member. For example, the learning unit 135 learns a model MD41 that predicts the opening period of a paying member user based on a keyword included in a part that is information other than identification information for identifying a sender of an electronic mail. The generation unit 132 extracts keywords F61 to F65 as keywords included in a part of information other than the identification information for identifying the sender of the electronic mail, for the mail M61 transmitted to the new user who is a paying member. Subsequently, based on the opening period predicted by the model MD41 learned by the learning unit 135, the generating unit 132 selects a keyword F61 having the shortest predicted opening period from the five keywords F61 to F65. . Subsequently, the generation unit 132 generates display information including the keyword F61 whose predicted opening period is the shortest as display information of the mail M61 transmitted to the new user who is a paying member.

  Note that the generating unit 132 may generate display information based on a plurality of response indices. For example, the generation unit 132 generates five different display information items F71 to F75 for the mail M71. Subsequently, the generation unit 132 generates five pieces of display information F71 based on four response indices of the opening rate, the click rate, the conversion rate, and the opening period predicted by the models MD1 to MD4 learned by the learning unit 135. From F75 to F75, a total score of the four predicted response indices may be calculated, and the display information F71 having the highest total score may be selected. Note that the generation unit 132 may calculate the total score of the response index by weighting the index among the four response indexes of the opening rate, the click rate, the conversion rate, and the opening period. For example, among the four response indexes of the opening rate, the click rate, the conversion rate, and the opening period, the generation unit 132 sets the weight of the opening rate to 3, the weight of the click rate to 4, the weight of the conversion rate to 5, and the weight of the opening period. Assuming that the weight is 2, the total score of the response index may be calculated.

  Further, the generation unit 132 may generate the display information based on the log of the relationship between the subject and the sender's name. For example, the generation unit 132 generates display information based on whether or not the relationship between the subject and the sender's name is mutually complementary. For example, the transmission unit 133 performs an AB test for checking the correlation between the subject and the sender's name, and collects logs. For example, the generation unit 132 generates display information in which the main keyword is displayed only in the sender name and display information in which the main keyword is displayed in both the subject and the sender name for the mail M8 having the same content. . Subsequently, the transmission unit 133 simultaneously and randomly transmits the mail M81 in which the main keyword is displayed only in the sender's name and the mail M82 in which the main keyword is displayed in both the subject and the sender's name. Subsequently, the calculating unit 134 calculates a response index, which is an index indicating a degree of a user's response to each of the mails M81 and M82, based on the user's access information to the mails M81 and M82 obtained by the transmitting unit 133. calculate. Similarly, the transmission unit 133 performs a plurality of AB tests and collects a log of the relationship between the subject and the sender's name. The calculating unit 134 calculates a response index for each of the plurality of AB tests. The results showed that email open rates and conversion rates were almost the same between emails where key keywords appeared only in the subject and emails where key keywords appeared in both the subject and the sender's name. Suppose. In this case, the generation unit 132 may generate an email in which the main keyword is displayed only in the sender name. The learning unit 135 may learn the relationship between the subject and the sender's name based on the response index calculated by the calculation unit 134.

[4. Information processing flow)
Next, a procedure of information processing according to the embodiment will be described with reference to FIG. FIG. 12 is a flowchart illustrating an information processing procedure according to the embodiment. In the example illustrated in FIG. 12, the information processing apparatus 100 determines whether or not the plan information on the plan planned by the sender of the e-mail has been acquired as the mail information on the e-mail to be transmitted (step S101). If the information processing apparatus 100 determines that the plan information has not been acquired as the mail information (step S101; No), the processing ends.

  When the information processing apparatus 100 determines that the plan information has been acquired as the mail information (step S101; Yes), the information processing apparatus 100 displays the information as the sender name of the mail, other than the identification information for identifying the sender. Display information for displaying the plan name is generated (step S102).

  Subsequently, the information processing apparatus 100 transmits an e-mail in which the plan name is displayed as the sender name (Step S103).

[5. Calculation process flow)
Next, the procedure of the calculation process according to the embodiment will be described with reference to FIG. FIG. 13 is a flowchart illustrating a calculation processing procedure according to the embodiment. In the example illustrated in FIG. 13, the information processing apparatus 100 determines whether or not response information indicating a user's response to the transmitted mail has been acquired (step S201). When the information processing apparatus 100 determines that the user's reaction information has not been acquired (step S201; No), the processing ends.

  When determining that the user's response information has been acquired (Step S201; Yes), the information processing apparatus 100 calculates a response index indicating the degree of the user's response to the mail based on the response information (Step S202).

[6. Learning process flow)
Next, the procedure of the learning process according to the embodiment will be described with reference to FIG. FIG. 14 is a flowchart illustrating a learning processing procedure according to the embodiment. In the example illustrated in FIG. 14, the information processing apparatus 100 acquires display information displayed as the sender name of the e-mail (step S301). Subsequently, the information processing apparatus 100 acquires a response index of the mail corresponding to the display information (Step S302).

  Subsequently, the information processing apparatus 100 learns a model for predicting the response index based on the display information, using the acquired set data of the display information and the response index as learning data (step S303).

[7. Modification)
The information processing system 1 according to the above-described embodiment may be implemented in various different forms other than the above-described embodiment. Therefore, another embodiment of the information processing system 1 will be described below. The same parts as those of the embodiment are denoted by the same reference numerals, and description thereof will be omitted.

[7-1. Sender display based on user information)
FIG. 8 illustrates an example in which the information processing apparatus 100 generates display information displayed as a sender name of an electronic mail based on user information regarding a user who is a destination of the electronic mail. FIG. 8 is a diagram illustrating an example of an electronic mail according to a modification. In FIG. 8, S shopping transmits an e-mail M2 related to the notification of the “pet special feature (second)” to the user who opened the e-mail M1 related to the notification of the “pet special feature (first)”. Will be described.

  In the example illustrated in the upper part of FIG. 8, the user terminal 10-1 receives the mail M1 related to “pet special feature (first)” illustrated in FIG. 1 from the information processing device 100 (step S1-1). The user U1 who has received the mail M1 browses the mail M1 and purchases cat food at S shopping (step S2-1).

  In the example illustrated in the upper part of FIG. 8, the acquisition unit 131 acquires the user information on the user U1 as the destination of the electronic mail as the mail information on the electronic mail M2 to be transmitted. Specifically, the obtaining unit 131 obtains, from the electronic commerce server 50, the mail information as the member information of the user U1 registered in the S shopping and the information regarding the use history of the service. The generation unit 132 generates display information based on the user information acquired by the acquisition unit 131. Specifically, the generation unit 132 refers to the user information storage unit 122 illustrated in FIG. 5 and determines whether the user U1 has a cat based on “cat food” which is a noun indicating a product name included in the purchase history of the user U1. It is estimated that you have a. Subsequently, the acquiring unit 131 acquires a plan name and plan contents as plan information with reference to the plan information storage unit 121 illustrated in FIG. Subsequently, the generation unit 132 decomposes the words included in the acquired plan information into words by morphological analysis. Subsequently, since the generation unit 132 estimates that the user U1 has a cat, the generation unit 132 extracts a “cat special feature” that is a phrase including a word related to a cat from the decomposed words. Subsequently, the generation unit 132 generates the display information so that the display information is limited to about 14 characters, which is the number of characters that can be displayed as the sender name. For example, the generation unit 132 extracts the word of “cat special feature” by removing the word of “product” from the extracted phrase of “cat special feature”. Subsequently, the generation unit 132 converts the kanji “cat” into the hiragana “cat” in consideration of the visibility of the user. In this way, the generation unit 132 generates the word “cat special”. Subsequently, the generation unit 132 generates display information in which the generated “cat special feature” is displayed as information other than the identification information for identifying the sender of the electronic mail.

  Further, the generation unit 132 generates display information in which identification information for identifying the sender of the e-mail is displayed as the display information. For example, the generation unit 132 determines to display “S shopping”, which is character information indicating a business name, as identification information for identifying the sender of the e-mail. Subsequently, the generation unit 132 displays “cat special”, which is information other than the identification information for identifying the sender of the e-mail, and “S shopping”, which is the identification information for identifying the sender of the e-mail, in a linked manner. Generate display information.

  The generation unit 132 generates display information to which additional information for enhancing a visual effect is added. For example, the generation unit 132 adds display brackets as additional information to enhance the visual effect, and displays information “[cat special]” that is character information between the parentheses. S shopping "is generated.

  Further, the generating unit 132 generates subject information to be displayed as the subject of the e-mail based on the display information. Specifically, since the display information includes the “cat special feature” in the display information, the generating unit 132 determines to generate the subject information based on the plan information other than the “cat special feature”. Subsequently, since the generation unit 132 has estimated that the user U1 has a cat, the generation unit 132 refers to the plan information storage unit 121 shown in FIG. Toilet ... "is extracted. Subsequently, the generation unit 132 decomposes the words included in the extracted character information into words by morphological analysis. Subsequently, the generating unit 132 extracts a main keyword from the extracted words and phrases according to the weight of each word using a weight value such as tf-idf. Subsequently, the generation unit 132 generates, as subject information, a character string in which main keywords are displayed separated by spaces. For example, the generation unit 132 extracts words such as “cat food” and “cat litter / toilet” as main keywords. Subsequently, based on the word extracted as the main keyword, the generation unit 132 generates “cat food, cat sand, toilet...”, Which is a character string in which the main keywords are arranged by separating them with spaces, as subject information. The transmission unit 133 transmits the electronic mail M2 in which the display information generated by the generation unit 132 is displayed as the sender name and the subject information generated by the generation unit 132 is displayed as the subject to the user terminal 10-1. (Step S3-1).

  On the other hand, in the example shown in the lower part of FIG. 8, the user terminal 10-2 receives the mail M1 related to “Pet special (first)” shown in FIG. 1 from the information processing device 100 (step S1-2). The user U2 that has received the mail M1 browses the mail M1 and purchases dog food at S shopping (step S2-2).

  In the example illustrated in the lower part of FIG. 8, the acquisition unit 131 acquires, as the mail information regarding the electronic mail M2 to be transmitted, the user information regarding the user U2 as the destination of the electronic mail. Specifically, the obtaining unit 131 obtains, from the e-commerce server 50, mail information such as member information of the user U2 registered in S-shopping and information on service usage history. The generation unit 132 generates display information based on the user information acquired by the acquisition unit 131. Specifically, the generation unit 132 refers to the user information storage unit 122 illustrated in FIG. 5 and determines that the user U2 has a dog based on the product name “dog food” included in the purchase history of the user U2. presume. Subsequently, the acquiring unit 131 acquires a plan name and plan contents as plan information with reference to the plan information storage unit 121 illustrated in FIG. Subsequently, the generation unit 132 decomposes the words included in the acquired plan information into words by morphological analysis. Subsequently, since the generation unit 132 estimates that the user U2 has a dog, the generation unit 132 extracts a "dog special feature" which is a phrase including a word relating to a dog from the decomposed words. Subsequently, the generation unit 132 generates the display information so that the display information is limited to about 14 characters, which is the number of characters that can be displayed as the sender name. For example, the generation unit 132 extracts the word of “dog special feature” by removing the word of “product” from the extracted phrase of “dog special feature”. Subsequently, the generation unit 132 converts the kanji “dog” into the hiragana “inu” in consideration of the visibility of the user. In this way, the generation unit 132 generates the word “inu special feature”. Subsequently, the generating unit 132 generates display information in which the generated “Inu Special” is displayed as information other than the identification information for identifying the sender of the electronic mail.

  Further, the generation unit 132 generates display information in which identification information for identifying the sender of the e-mail is displayed as the display information. For example, the generation unit 132 determines to display “S shopping”, which is character information indicating a business name, as identification information for identifying the sender of the e-mail. Subsequently, the generation unit 132 displays the “Inu Special”, which is information other than the identification information for identifying the sender of the e-mail, and “S shopping”, which is the identification information for identifying the sender of the e-mail. Generate display information.

  The generation unit 132 generates display information to which additional information for enhancing a visual effect is added. For example, the generation unit 132 adds display brackets as additional information for enhancing the visual effect, and displays the character information “Inu Special” between the brackets “[Inu Special]”. S shopping "is generated.

  Further, the generating unit 132 generates subject information to be displayed as the subject of the e-mail based on the display information. Specifically, since the display information includes the “inu special feature” in the display information, the generating unit 132 determines to generate the subject information based on the plan information other than the “inu special feature”. Subsequently, since the generation unit 132 has estimated that the user U2 has a dog, the generation unit 132 refers to the plan information storage unit 121 shown in FIG. Cage ... "is extracted. Subsequently, the generation unit 132 decomposes the words included in the extracted character information into words by morphological analysis. Subsequently, the generating unit 132 extracts a main keyword from the extracted words and phrases according to the weight of each word using a weight value such as tf-idf. Subsequently, the generation unit 132 generates, as subject information, a character string in which main keywords are displayed separated by spaces. For example, the generation unit 132 extracts words such as “dog food” and “dog house / cage” as main keywords. Subsequently, the generation unit 132 generates “dog food kennel / cage...”, Which is a character string in which the main keywords are separated by spaces, based on the words extracted as the main keywords, as subject information. The transmitting unit 133 transmits the electronic mail M2 in which the display information generated by the generating unit 132 is displayed as the sender name and the subject information generated by the generating unit 132 is displayed as the subject to the user terminal 10-2. (Step S3-2).

  The generation unit 132 registers, as information other than the identification information for identifying the sender of the e-mail, a “shopping cart” for registering a product to be purchased by the user and a “favorite list” for registering a product that the user likes. Display information for displaying the product name of the product being displayed may be generated. Specifically, for a product for which a predetermined period has elapsed since the user registered in the “shopping cart”, the user is notified of the shopping forgotten with a content such as “Is there a product you forgot to buy?” You may send an e-mail. For example, the generation unit 132 refers to the user information storage unit 122 illustrated in FIG. 5 and identifies that the user U3 has registered a product such as a men's shirt in the “shopping cart”, and thus identifies the sender of the e-mail. As display information other than the information, display information for displaying a “men's shirt” which is a product name registered in the “shopping cart” is generated.

  In addition, when a product registered in the “favorite list” is discounted, an e-mail is sent to the user recommending purchase with a message such as “My favorite product is now on sale”. May be. For example, the generation unit 132 refers to the user information storage unit 122 illustrated in FIG. 5, and the “tie”, which is a product registered by the user U3 in the “favorite list”, is a target to be discounted by 30% of the price. In this case, display information is generated in which "tie", which is a product name registered in the "favorite list", and "30% OFF" are displayed as information other than the identification information for identifying the sender of the e-mail. I do.

[7-2. Sender display based on user profit information)
In FIG. 9, an example in which the information processing apparatus 100 generates display information that displays profit information on profits that can be enjoyed by the user who is the destination of the e-mail by using a service provided by the sender of the e-mail Will be described. FIG. 9 is a diagram illustrating an example of an electronic mail according to a modification. FIG. 9 illustrates a case where S shopping transmits an e-mail M3 relating to notification of a ten-fold point day, which is a sales promotion plan, to the user U1.

  In the example illustrated in FIG. 9, the acquisition unit 131 can use the service provided by the sender of the e-mail as the mail information regarding the e-mail M3 to be transmitted, so that the user who is the destination of the e-mail can enjoy it. Get profit information about profit. Specifically, the acquiring unit 131 acquires a plan name and plan contents as plan information with reference to the plan information storage unit 121 illustrated in FIG. Subsequently, the generation unit 132 decomposes the words included in the acquired plan information into words by morphological analysis. Subsequently, the generating unit 132 outputs, as the profit information, “10 days only” which is a word indicating a period during which the user can enjoy the profit, and “point 10 times” which is a word indicating the content of the profit that the user can enjoy. Is extracted. Subsequently, the generation unit 132 generates the display information so that the display information is limited to about 14 characters, which is the number of characters that can be displayed as the sender name. For example, the generation unit 132 decomposes the extracted word of “point 10 times” into “point” and “10 times” using morphological analysis. Subsequently, the generating unit 132 generates “Po”, which is an abbreviation of the decomposed “Point”. Subsequently, the generating unit 132 is decomposed into “Po”, which is generated as an abbreviation of “limited to 10 days”, which is character information extracted as profit information, as information other than the identification information for identifying the sender of the e-mail. "10 times" is generated in conjunction with the display information.

  In addition, the generation unit 132 generates display information in which “S!”, Which is an abbreviation of a business name, is displayed as identification information for identifying the sender of the e-mail. In the example illustrated in FIG. 9, the generation unit 132 displays “10 days only! 10 times” as profit information and “S!” As an abbreviation of the business name as display information displayed as the sender name of the e-mail. And [[10 days limited! 10 times] S!], Which is display information displayed in conjunction with.

  Further, the generating unit 132 generates subject information to be displayed as the subject of the e-mail based on the display information. Specifically, since the display information includes “10 days only” and “10 times” extracted as the profit information in the display information, the generation unit 132 selects a plan other than “10 days only” and “10 times”. It decides to generate subject information based on the information. For example, the generation unit 132 refers to the plan information storage unit 121 illustrated in FIG. 4 and extracts character information that “paid members have double points” from plan information. Subsequently, the generation unit 132 acquires member information indicating that the member type of the user U1 is a paying member with reference to the user information storage unit 122 illustrated in FIG. Subsequently, based on the acquired user information and plan information, the generation unit 132 determines that the user U1 is a target user with double points because the user U1 is a paying member. Since the generation unit 132 has determined that the user U1 is a target user with double points, the generation unit 132 generates “You are a paid member” as character information indicating that the user U1 is a target user with double points. Subsequently, based on the acquired plan information “paid member is double the points” and the generated “paid member you”, the generating unit 132 sets “paid member you further points 2” as the subject information. The character information "double!" Is generated. The transmission unit 133 transmits an electronic mail M3 in which the display information generated by the generation unit 132 is displayed as the sender name and the subject information generated by the generation unit 132 is displayed as the subject to the user terminal 10-1. .

  Note that the generation unit 132 may generate different subject information according to the user information. For example, the generation unit 132 acquires member information indicating that the member type of the user U2 is a free member with reference to the user information storage unit 122 illustrated in FIG. Since the user U2 is not a paying member, the generating unit 132 does not generate “You are a paid member”, which is character information indicating that the user U2 is a target of double points. Based on the acquired user information and plan information, the generation unit 132 generates subject information in which the character information “paid member is further doubled points” extracted from the plan information and the symbol “!” Are linked. The transmission unit 133 transmits an electronic mail M3 in which the display information generated by the generation unit 132 is displayed as the sender name and the subject information generated by the generation unit 132 is displayed as the subject to the user terminal 10-2. .

  Further, the generation unit 132 may generate different display information according to the user information. For example, the generation unit 132 acquires the user's membership type with reference to the user information storage unit 122 illustrated in FIG. Subsequently, the generation unit 132 generates display information based on the user's membership type. For example, when the generation unit 132 determines that the user U1 is a paying member, the generating unit 132 generates display information in which “to you as a paying member” or “paid member only” which is character information is displayed.

  In the above description, an example has been described in which the information processing apparatus 100 generates display information in which profit information is displayed based on plan information as profit information. Display information in which profit information is displayed may be generated based on the information. Specifically, the obtaining unit 131 obtains character information described in an HTML file as content information regarding the content of the body of the electronic mail M3. Subsequently, the generation unit 132 decomposes the words included in the obtained character information into words by morphological analysis. Subsequently, the acquisition unit 131 uses the word “8/10 only”, which is a word indicating the period in which the user can enjoy the profit, and the phrase “point 10 times”, which indicates the content of the profit that the user can enjoy, as the profit information. And extract Subsequently, the generation unit 132 generates the display information so that the display information is limited to about 14 characters, which is the number of characters that can be displayed as the sender name. For example, the generation unit 132 decomposes the extracted word of “point 10 times” into “point” and “10 times” using morphological analysis. Subsequently, the generating unit 132 generates “Po”, which is an abbreviation of the decomposed “Point”. Subsequently, the generating unit 132 is decomposed into “Po” generated as abbreviation “8/10 limited”, which is character information extracted as profit information, as information other than the identification information for identifying the sender of the e-mail. The display information which is displayed in connection with "10 times" is generated.

[7-3. Sender display based on the content of the email body)
FIG. 10 illustrates an example in which the information processing apparatus 100 generates display information based on content information regarding the content of the body of an e-mail. FIG. 10 is a diagram illustrating an example of an electronic mail according to a modification. FIG. 10 illustrates a case where the S shopping transmits an e-mail M4 related to a product shipping notification to the user U1. The electronic mail M4 is a text mail.

  In the example illustrated in FIG. 10, the acquiring unit 131 acquires, as mail information, content information regarding the content of the body of the electronic mail. More specifically, the acquiring unit 131 provides information on the contents of the body of the e-mail M4 as “S-shopping. The ordered product has been sent. Product code: 111111111, Product name: Cat food, Shipment Number: 1, shipping date: September 1, 2018 ... ". Subsequently, the generation unit 132 generates display information based on the content information acquired by the acquisition unit 131. Specifically, the generation unit 132 decomposes words included in the extracted character information into words by morphological analysis. Subsequently, the generating unit 132 extracts “cat food” as a product name and “dispatch” as a verb from the content information. Subsequently, the generating unit 132 generates, as display information, display information in which content information on the content of the body of the e-mail is displayed. In the example illustrated in FIG. 10, the generation unit 132 outputs “cat food”, which is character information extracted as a product name, and character information, which is extracted as a verb, as information other than the identification information for identifying the sender of the electronic mail. Generate display information that is displayed in conjunction with “ship”. Note that the generation unit 132 extracts a main keyword from the extracted words and phrases according to the weight of each word using a weight value such as tf-idf, and displays display information based on the extracted keywords. May be generated.

  In addition, the generation unit 132 generates display information in which “S!”, Which is an abbreviation of a business name, is displayed as identification information for identifying the sender of the e-mail. In the example illustrated in FIG. 10, the generation unit 132 determines that the display information displayed as the sender name of the e-mail is “cat food dispatch”, which is display information in which the extracted product name and verb are displayed in connection with each other. It generates display information in which “S!”, Which is the abbreviation of the person's name, is displayed in combination.

[7-4. Sender display based on user disadvantage information)
In FIG. 11, display information in which the information processing apparatus 100 does not use a service provided by the sender of the e-mail, thereby displaying disadvantage information regarding a disadvantage that the user who is the destination of the e-mail may suffer An example of generating is described. FIG. 11 is a diagram illustrating an example of an electronic mail according to a modification. FIG. 11 illustrates a case where S shopping transmits an e-mail M5 related to a notification that notifies the user U1 of the expiration date of points.

  In the example illustrated in FIG. 11, the acquisition unit 131 does not use the service provided by the sender of the e-mail as the mail information regarding the e-mail M5 to be transmitted, so that the user who is the destination of the e-mail may suffer. Obtain disadvantage information about disadvantages with certainty. Specifically, the acquiring unit 131 acquires, as disadvantage information, content information on the content of the body of the e-mail. Subsequently, the generation unit 132 generates display information based on the content information acquired by the acquisition unit 131. Specifically, the acquisition unit 131 provides the content information regarding the content of the body of the e-mail M4, "◆ Notice of point expiration date ◆ I have contacted today because the point of user U1 has expired ...." Get text such as. Subsequently, the generation unit 132 decomposes the words included in the acquired text into words by morphological analysis. The generation unit 132 includes, as the disadvantage information, “today” which is a noun indicating a period in which the user suffers a disadvantage, “point” which is a noun indicating an object of the disadvantage suffered by the user, and details of the disadvantage suffered by the user Is extracted, which is a verb indicating "revocation". Subsequently, the generation unit 132 generates the display information so that the display information is limited to about 14 characters, which is the number of characters that can be displayed as the sender name. For example, the generating unit 132 generates “Po” which is an abbreviation of the extracted “Point”. Subsequently, the generation unit 132 generates the word “today” extracted as disadvantageous information as an abbreviation “Po” as information other than the identification information for identifying the sender of the e-mail, and disassembled “Revoked” Generates display information that is displayed in conjunction with.

  In addition, the generation unit 132 generates display information in which “S!”, Which is an abbreviation of a business name, is displayed as identification information for identifying the sender of the e-mail. In the example illustrated in FIG. 11, the generating unit 132 connects the disadvantage information “point expiration” and the abbreviated name “S!” Of the business name as display information displayed as the sender name of the electronic mail. Generate display information to be displayed.

  In the above description, an example has been described in which the information processing apparatus 100 generates display information in which disadvantage information is displayed based on disadvantage information which is content information relating to the content of the body of the e-mail. Display information on which the disadvantage information is displayed may be generated based on the information. Specifically, the acquisition unit 131 acquires information on the points of the user whose expiration date is today as the disadvantage information every day with reference to the user information storage unit 122 illustrated in FIG. For example, it is assumed that today is September 1, 2018. The acquisition unit 131 extracts the user U1 whose expiration date to which the user suffers is “September 1, 2018” today. Subsequently, the generation unit 132 outputs, as information other than the identification information for identifying the sender of the e-mail, as the disadvantage information, “today” which is a word indicating the time limit when the user is disadvantaged, and the content of the disadvantage suffered by the user. Is generated in combination with the phrase “expired”, which is a phrase indicating

[7-5. Sender display based on user terminal information)
FIG. 1 illustrates an example in which the information processing apparatus 100 generates display information that is displayed as a sender name of an e-mail on the user terminal 10 that is a smartphone, but is displayed as the sender name on the user terminal 10 other than the smartphone. Display information may be generated. Specifically, the acquiring unit 131 acquires, as the mail information, terminal information regarding the terminal device of the user who is the destination of the electronic mail. Subsequently, the generation unit 132 generates display information based on the terminal information acquired by the acquisition unit 131.

  More specifically, the acquisition unit 131 acquires, as terminal information, information on the type of mailer installed in the user's terminal device. For example, the acquisition unit 131 acquires information on the type of mailer of the user based on the history of sending and receiving e-mail with the user, such as inquiries and orders for S shopping. For example, the acquisition unit 131 determines the mailer used by the user from the item “X-Mailer” in which the mail software used by the sender is described as an item included in the header information of the mail received from the user. Specify the type. Note that the acquisition unit 131 may acquire information on the type of mailer used by the user from another service. Further, the acquisition unit 131 acquires, as the terminal information, information on the type of the terminal device of the user. For example, the acquisition unit 131 acquires, as the information regarding the type of the user terminal, information regarding a smartphone model, a tablet terminal, a notebook PC, a mobile phone, a PDA, or the like. Subsequently, based on the type of the mailer and the type of the terminal device acquired by the acquiring unit 131, the generation unit 132 displays the optimal number of characters as the sender name according to the type of the mailer and the type of the user terminal. Generate display information. For example, the generation unit 132 generates display information in which the sender name is displayed in the number of characters displayed in one line according to the type of the mailer and the type of the user terminal.

[7-6. Sender display by stores opening in the online shopping mall)
FIG. 1 illustrates an example in which the information processing apparatus 100 generates display information of an e-mail distributed by S shopping, which is a provider of a service related to an online shopping mall. The display information of the e-mail distributed by the store may be generated. Specifically, S-shopping provides, via a network, an operation tool for operating a store to a store terminal that is a terminal managed by a manager of a store opening in an online shopping mall. . S-shopping provides an e-mail distribution function for distributing information about stores as one function of an operation tool. The acquisition unit 131 acquires mail information on the electronic mail to be transmitted from the store terminal via the operation tool. For example, the acquisition unit 131 acquires, as mail information, content information about the content of the body of the e-mail from the store terminal. Further, the acquisition unit 131 acquires the name of the store from the store terminal as identification information for identifying the sender of the e-mail. Subsequently, the generation unit 132 displays, based on the content information acquired by the acquisition unit 131, information other than the identification information for identifying the sender of the email, which is display information displayed as the sender name of the email. Generate display information to be displayed. For example, the generation unit 132 generates display information in which the name of the store is displayed as identification information for identifying the sender of the e-mail.

[8. effect〕
As described above, the information processing apparatus 100 according to the embodiment includes the acquisition unit 131 and the generation unit 132. The obtaining unit 131 obtains mail information regarding an electronic mail to be transmitted. The generating unit 132 is a display that displays, based on the mail information acquired by the acquiring unit 131, information other than the identification information for identifying the sender of the e-mail, the display information being displayed as the sender name of the e-mail. Generate information.

  Here, the information processing apparatus 100 displays information other than the identification information for identifying the sender of the electronic mail as display information displayed as the sender name of the electronic mail based on the mail information regarding the electronic mail to be transmitted. Generate display information. Thereby, the information processing apparatus 100 can display information other than the identification information for identifying the sender as a sender name which is information having a higher priority for the receiver. In other words, the information processing apparatus 100 can display information other than the identification information for identifying the sender as information with high appeal to the recipient. Therefore, the information processing apparatus 100 can provide an e-mail with high appeal.

  Further, the obtaining unit 131 obtains, as mail information, content information on the content of the body of the electronic mail. The generation unit 132 generates display information based on the content information acquired by the acquisition unit 131.

  Thereby, the information processing apparatus 100 can provide an e-mail with high appeal based on the content information on the content of the text of the e-mail.

  Further, the acquiring unit 131 acquires, as the mail information, meta information related to the content of the body of the e-mail. The generation unit 132 generates display information based on the meta information acquired by the acquisition unit 131.

  Thereby, the information processing apparatus 100 can provide an e-mail with a high appealing power based on the meta information related to the content of the body of the e-mail.

  Further, the acquisition unit 131 acquires, as the mail information, the plan information on the plan planned by the sender of the e-mail. The generation unit 132 generates display information based on the plan information acquired by the acquisition unit 131.

  Thereby, the information processing apparatus 100 can provide an e-mail with a high appealing power based on the plan information on the plan planned by the sender of the e-mail.

  Further, the obtaining unit 131 obtains, as mail information, user information regarding the user who is the destination of the electronic mail. The generation unit 132 generates display information based on the user information acquired by the acquisition unit 131.

  Thereby, the information processing apparatus 100 can provide an e-mail with a high appealing power based on the user information on the user who is the destination of the e-mail.

  In addition, the acquisition unit 131 acquires, as the mail information, terminal information on the terminal device of the user who is the destination of the e-mail. The generation unit 132 generates display information based on the terminal information acquired by the acquisition unit 131.

  As a result, the information processing apparatus 100 can display the appealing power based on the type of mailer and the type of the terminal device (whether it is a PC or a smartphone) mounted on the terminal device of the user who is the destination of the e-mail. High e-mail can be provided.

  In addition, the generation unit 132 generates, as display information, display information in which profit information relating to profits that can be enjoyed by the user who is the destination of the e-mail is displayed by using a service provided by the sender of the e-mail. .

  In general, people are more likely to be informed about information about their profits and losses (losses and profits). Therefore, the information processing apparatus 100 can provide an e-mail with a higher appeal by displaying profit information relating to the user's profit as the display information.

  In addition, the generation unit 132 displays, as the display information, the disadvantage information regarding the disadvantage that the user who is the destination of the e-mail may suffer by not using the service provided by the sender of the e-mail. Generate information.

  In general, people are more likely to be informed about information about their profits and losses (losses and profits). Therefore, the information processing apparatus 100 can provide an e-mail with a higher appeal by displaying the disadvantage information relating to the loss of the user as the display information.

  Further, the generation unit 132 generates display information in which identification information for identifying the sender of the e-mail is displayed as the display information.

  Thereby, the information processing apparatus 100 can generate display information in which the identification information for identifying the sender of the email is displayed in addition to the information other than the identification information for identifying the sender of the email.

  Further, the generating unit 132 generates subject information to be displayed as the subject of the e-mail based on the display information.

  Thereby, the information processing apparatus 100 can provide an e-mail with higher appealing power according to the relationship between the sender name of the e-mail and the subject of the e-mail.

  In addition, the generation unit 132 generates display information based on a response index that is an index indicating a degree of a user's response to the electronic mail.

  Thereby, the information processing apparatus 100 can generate display information based on the degree of reaction of the user to the email as an index for measuring the appealing power to the email.

  In addition, the generation unit 132 generates display information as a response index based on an index value indicating whether or not the email is opened.

  Thereby, the information processing apparatus 100 can generate display information based on the opening rate of the email as an index for measuring the appealing power to the email.

  In addition, the generation unit 132 generates display information based on an index value indicating whether or not the content included in the email is selected as the response index.

  Thereby, the information processing apparatus 100 can generate display information based on the selection rate of the content included in the email as an index for measuring the appealing power to the email.

  In addition, the generation unit 132 generates the display information as a response index based on an index value indicating whether an action that is profitable for the advertiser of the advertising content included in the email occurs.

  Thereby, the information processing apparatus 100 can generate display information based on the conversion rate as an index for measuring the appealing power to the e-mail.

  In addition, the generation unit 132 generates display information based on opening period information regarding a period until the electronic mail is opened as a response index.

  Thereby, the information processing apparatus 100 can generate display information as an index for measuring the appealing power to the electronic mail based on the opening period until the mail is opened.

  Further, the information processing apparatus 100 according to the embodiment further includes a learning unit 135. The learning unit 135 learns a model for predicting a response index based on the display information generated by the generation unit 132.

  Thereby, the information processing apparatus 100 can predict the response index corresponding to each display information by inputting the generated display information to the learned model before transmitting the e-mail. That is, the information processing apparatus 100 can determine the generated display information based on the response index.

[9. Hardware configuration)
The information processing apparatus 100 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as illustrated in FIG. FIG. 15 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing apparatus 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, a program that depends on hardware of the computer 1000, and the like.

  The HDD 1400 stores a program executed by the CPU 1100, data used by the program, and the like. Communication interface 1500 receives data from another device via a predetermined communication network, sends the data to CPU 1100, and transmits the data generated by CPU 1100 to the other device via the predetermined communication network.

  The CPU 1100 controls output devices such as a display and a printer and input devices such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 obtains data from an input device via the input / output interface 1600. Further, CPU 1100 outputs the generated data to an output device via input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc), a PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

  For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing a program or data loaded on the RAM 1200. Although the CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, as another example, these programs may be obtained from another device via a predetermined communication network.

  As described above, some of the embodiments of the present application have been described in detail with reference to the drawings. However, these are merely examples, and various modifications, It is possible to implement the invention in other forms with improvements.

[10. Others)
Further, among the processes described in the above embodiments and modifications, all or a part of the processes described as being performed automatically can be manually performed, or described as being performed manually. All or a part of the processing can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown.

  Each component of each device illustrated is a functional concept, and does not necessarily need to be physically configured as illustrated. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or a part thereof may be functionally or physically distributed / arbitrarily divided into arbitrary units according to various loads and usage conditions. Can be integrated and configured.

  Further, the above-described embodiments and modified examples can be appropriately combined within a range that does not contradict processing contents.

  Further, the “section (section, module, unit)” described above can be read as “means”, “circuit”, or the like. For example, the generation unit can be replaced with a generation unit or a generation circuit.

Reference Signs List 1 information processing system 10 user terminal 50 e-commerce server 100 information processing device 121 plan information storage unit 122 user information storage unit 123 mail information storage unit 124 model information storage unit 131 acquisition unit 132 generation unit 133 transmission unit 134 calculation unit 135 learning unit

Claims (18)

An obtaining unit that obtains, as mail information regarding an electronic mail related to an electronic commerce service to be transmitted, usage information regarding a use history of the electronic commerce service of a user who is a destination of the electronic mail and attribute information regarding an attribute of the user ;
Based on the mail information obtained by the obtaining unit, the display information is displayed as the sender name of the electronic mail, and as information other than identification information for identifying the sender of the electronic mail, the destination of the electronic mail For each attribute of a user, display information in which information generated according to a certain user is displayed is generated, and a response index that is an index indicating a degree of response to the email is predicted based on the generated display information. The display information displayed in an e-mail transmitted to a new user having an attribute corresponding to the attribute of the user based on a response index predicted by a model corresponding to the attribute of the user among the models learned in An information processing apparatus, comprising: a generation unit configured to generate. The acquisition unit,
As the mail information, obtain content information on the content of the body of the email,
The generation unit includes:
The information processing apparatus according to claim 1, wherein the display information is generated based on the content information acquired by the acquisition unit. The acquisition unit,
As the mail information, obtain meta information related to the content of the body of the email,
The generation unit includes:
The information processing apparatus according to claim 1, wherein the display information is generated based on meta information acquired by the acquisition unit. The acquisition unit,
As the mail information, obtain plan information on a plan planned by the sender of the e-mail,
The generation unit includes:
The information processing device according to claim 1, wherein the display information is generated based on the plan information acquired by the acquisition unit. The acquisition unit,
As the mail information, obtain user information on a user who is a destination of the electronic mail,
The generation unit includes:
The information processing device according to any one of claims 1 to 4, wherein the display information is generated based on the user information acquired by the acquisition unit. The acquisition unit,
As the mail information, obtain terminal information on a terminal device of a user who is a destination of the electronic mail,
The generation unit includes:
The information processing apparatus according to any one of claims 1 to 5, wherein the display information is generated based on the terminal information acquired by the acquisition unit. The generation unit includes:
By using a service provided by the sender of the e-mail as the display information, display information that displays profit information on profits that can be enjoyed by a user who is the destination of the e-mail is generated. The information processing apparatus according to claim 1. The generation unit includes:
By not using a service provided by the sender of the electronic mail as the display information, generating display information in which disadvantage information regarding a disadvantage that may be incurred by a user who is a destination of the electronic mail is displayed. The information processing apparatus according to claim 1, wherein: The generation unit includes:
The information processing device according to any one of claims 1 to 8, wherein display information that displays identification information for identifying a sender of the e-mail is displayed as the display information. The generation unit includes:
The information processing apparatus according to claim 1, wherein subject information to be displayed as a subject of the electronic mail is generated based on the display information. The generation unit includes:
The information processing apparatus according to any one of claims 1 to 10, wherein the display information is generated based on a response index that is an index indicating a degree of a user's response to the electronic mail. The generation unit includes:
The information processing apparatus according to claim 11, wherein the display information is generated based on an index value indicating whether or not the electronic mail is opened as the response index. The generation unit includes:
The information processing apparatus according to claim 11, wherein the display information is generated based on an index value indicating whether a content included in the email is selected as the response index. The generation unit includes:
The display information is generated as the response index based on an index value indicating whether or not an action that is profitable for an advertiser of the advertising content included in the email occurs. The information processing device according to any one of the above. The generation unit includes:
The information processing apparatus according to any one of claims 11 to 14, wherein the display information is generated based on opening period information regarding a period until the electronic mail is opened as the response index. . The information processing apparatus according to any one of claims 11 to 15, further comprising: a learning unit configured to learn a model for predicting the response index based on the display information generated by the generation unit. An information processing method executed by a computer,
Acquisition step of acquiring, as mail information relating to an e-mail relating to an e-commerce service to be transmitted, utilization information relating to a use history of the e-commerce service of a user who is a destination of the e-mail and attribute information relating to an attribute of the user ,
Based on the mail information obtained in the obtaining step, the display information displayed as the sender name of the electronic mail, as information other than identification information for identifying the sender of the electronic mail, the destination of the electronic mail For each attribute of a user, display information in which information generated according to a certain user is displayed is generated, and a response index that is an index indicating a degree of response to the email is predicted based on the generated display information. The display information displayed in an e-mail transmitted to a new user having an attribute corresponding to the attribute of the user based on a response index predicted by a model corresponding to the attribute of the user among the models learned in And a generating step of generating. An acquisition step of acquiring, as mail information relating to an e-mail relating to an e-commerce service to be transmitted, utilization information relating to a use history of the e-commerce service of a user who is a destination of the e-mail and attribute information relating to an attribute of the user ;
Based on the mail information obtained by the obtaining procedure, based on the mail information, the display information is displayed as the sender name of the electronic mail, as information other than identification information for identifying the sender of the electronic mail, the destination of the electronic mail For each attribute of a user, display information in which information generated according to a certain user is displayed is generated, and a response index that is an index indicating a degree of response to the email is predicted based on the generated display information. The display information displayed in an e-mail transmitted to a new user having an attribute corresponding to the attribute of the user based on a response index predicted by a model corresponding to the attribute of the user among the models learned in An information processing program characterized by causing a computer to execute:

Images