JP7699068B2 - Information providing device, information providing method, and information providing program - Google Patents

Description

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

In recent years, with the rapid spread of the Internet, techniques for analysis using various information on the Internet have been provided. For example, techniques are known that use purchase history data and other data to analyze customers (or "users" as appropriate) taking into account trends over time.

JP 2015-146145 A

However, the above-mentioned conventional technologies leave room for improvement in providing useful information to users.

The present application has been made in consideration of the above, and aims to provide an information providing device, an information providing method, and an information providing program that can provide useful information to users.

In order to solve the above-mentioned problems and achieve the objective, the information providing device according to the present invention is characterized by comprising: a collection unit that collects user information relating to a user; a calculation unit that calculates, for each transaction object based on the user information, an ownership score indicating the possibility that the user owns the object and a purchase tendency score indicating the possibility that the user will purchase the object; and a generation unit that generates information to be provided to the user based on the ownership score and the purchase tendency score.

The information provision method according to the present invention is an information provision method executed by an information provision device, and is characterized by including a collection step of collecting user information about a user, a calculation step of calculating, for each transaction object based on the user information, an ownership score indicating the possibility that the user owns the object and a purchase propensity score indicating the possibility that the user will purchase the object, and a generation step of generating provision information to be provided to the user based on the ownership score and the purchase propensity score.

The information provision program of the present invention is characterized in that it causes a computer to execute a collection step of collecting user information about a user, a calculation step of calculating, for each transaction object, an ownership score indicating the possibility that the user owns the object and a purchase propensity score indicating the possibility that the user will purchase the object based on the user information, and a generation step of generating provision information to be provided to the user based on the ownership score and the purchase propensity score.

The present invention can provide useful information to users.

FIG. 1 is a diagram illustrating an example of a process of an information providing system according to an embodiment. FIG. 2 is a block diagram illustrating an example of a configuration of an information providing device according to the embodiment. FIG. 3 is a diagram illustrating an example of a user information storage unit according to the embodiment. FIG. 4 is a diagram illustrating an example of a trading object information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of a score information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of a provided information storage unit according to the embodiment. FIG. 7 is a diagram illustrating a specific example 1 of the score calculation process according to the embodiment. FIG. 8 is a diagram showing a second specific example of the score calculation process according to the embodiment. FIG. 9 is a diagram illustrating a specific example 3 of the score calculation process according to the embodiment. FIG. 10 is a flowchart showing an example of the flow of the information providing process according to the embodiment. FIG. 11 is a diagram illustrating an example of a hardware configuration.

Below, the information providing device, information providing method, and information providing program according to the present application (hereinafter, "embodiments") will be described in detail with reference to the drawings. Note that the information providing device, information providing method, and information providing program according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments will be given the same reference numerals, and duplicated descriptions will be omitted.

[Embodiment]
The process of the information providing system 100 according to the embodiment, the configuration of the information providing device 10, a specific example of the score calculation process, and the flow of the information providing process will be described below in this order, and finally, the effects of this embodiment will be described.

1. Processing of the Information Providing System 100
The processing of an information providing system (hereinafter, referred to as the present system) 100 according to the present embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the processing of the information providing system according to the embodiment. Below, the configuration example of the present system 100, the processing of the present system 100, and the effects of the present system 100 will be described in that order.

(1-1. Configuration example of system 100)
1 includes an information providing device 10, a user terminal 20, and a transaction target information database 30. Here, the information providing device 10, the user terminal 20, and the transaction target information database 30 are connected to each other so as to be able to communicate with each other by wire or wirelessly via a predetermined communication network (not shown). Note that the system 100 may include a plurality of information providing devices 10, a plurality of user terminals 20, and a plurality of transaction target information databases 30.

(1-1-1. Information providing device 10)
The information providing device 10 is a device that transmits and receives data between the user terminal 20 and the transaction target information database 30, and is realized, for example, by a server device, a cloud system, etc. The example of Fig. 1 shows a case where the information providing device 10 is realized by a server device.

(1-1-2. User terminal 20)
The user terminal 20 is a device (computer) used by a user U to browse web pages and perform internet shopping on the web. The user terminal 20 accepts operations by the user U. The user terminal 20 is realized, for example, by a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), etc. The example of FIG. 1 shows a case where the user terminal 20 is realized by a smartphone.

(1-2. Processing of System 100)
(1-2-1. Processing of step S1)
In the present system 100, first, the information providing device 10 collects user information of the user U from the user terminal 20 (step S1). Here, the user information is information about the user U of the present system 100, and includes the behavioral history of the user U, such as the search history and purchase history on the website of the user U, as well as the user attributes, such as the gender, age, generation, occupation, annual income, place of residence, marital status, and the presence or absence of children of the user U. Furthermore, the user information may be information including screen information of the user terminal 20, location information and biometric information of the user U, and is not particularly limited. In the example of FIG. 1, the information providing device 10 acquires the user information of the user U from the user terminal 20, but may also acquire the user information from the terminal of the user U, other terminals, databases, etc., not shown.

(1-2-2. Processing of step S2)
In the present system 100, secondly, the information providing device 10 refers to the transaction object information database 30 and acquires transaction object information (step S2). Here, the transaction object information is information on the transaction object such as a product or service, and includes transaction object attributes such as product name or service name, product or service classification or type, business name, offered price, warranty period, and validity period, but is not limited thereto. In addition, the transaction object includes objects that are purchased or used for a fee, as well as objects that are provided free of charge at the request of a customer. In the example of FIG. 1, the information providing device 10 acquires the transaction object information from the transaction object information database 30, but may acquire the information from the user terminal 20 or other terminals or databases not shown.

(1-2-3. Processing of step S3)
Thirdly, in the present system 100, the information providing device 10 calculates an ownership score for each transaction object of the user U from the collected user information and transaction object information (step S3). For example, the information providing device 10 calculates an ownership score for each transaction object by using a machine learning model based on the user U's user attributes, search history, purchase history, etc., so that the ownership score is a numerical value between 0 and 1 according to the possibility that the user U owns each transaction object. For example, the information providing device 10 calculates the ownership score by using a machine learning model such as a deep neural network (DNN) that has been trained to output an ownership score for each transaction object of the user U when the user information and transaction object information of the user U are input. The information providing device 10 may also calculate the ownership score on a rule basis.

(1-2-4. Processing of step S4)
Fourthly, in the present system 100, the information providing device 10 calculates a purchase propensity score for each transaction object of the user U from the collected user information and transaction object information (step S3). For example, the information providing device 10 calculates a purchase propensity score for each transaction object, which takes a value between 0 and 1 according to the possibility that the user U will purchase each transaction object, using a machine learning model based on the user attributes, search history, purchase history, etc. of the user U. For example, the information providing device 10 calculates the purchase propensity score using a machine learning model such as DNN that has been trained to output a purchase propensity score for each transaction object of the user U when the user information and transaction object information of the user U are input. The information providing device 10 may also calculate the purchase propensity score on a rule-based basis.

The above-mentioned steps S3 to S4 will be described below using a specific example. For example, if there is a purchase history of product X from user U, or if there is a search history of user U owning product X (e.g., "how to use product X"), the information providing device 10 calculates a high ownership score for product X.

The information providing device 10 calculates a purchasing tendency score using common parameters such as the purchase history of product Y related to product X, the transaction target attribute, the user attribute, and the purchase history of the attribute (purchase history of other users with the same user attribute). For example, the information providing device 10 calculates a high purchasing tendency score for product X as the transaction target attribute of product X when product X is a one-of-a-kind product. Also, the information providing device 10 calculates a low purchasing tendency score for product X when product X is a consumer good as the transaction target attribute of product X. Also, for example, the information providing device 10 calculates a high purchasing tendency score for product X as the user attribute of user U when user U has a collecting habit. Also, the information providing device 10 calculates a high purchasing tendency score for products Y and Z, which are related products of product X that have already been purchased and superior compatible products, as the user attribute of user U when user U has a long period of interest in a specific category (e.g., 10 years of camping experience).

When user U has no purchase history of product X and has a search history of considering product X (e.g., "product X reviews"), the information providing device 10 calculates a low ownership score and a high purchase tendency score for product X. On the other hand, when user U has no purchase history of product X or a search history of considering product X, the information providing device 10 calculates a low ownership score and a low purchase tendency score for product X.

(1-2-5. Processing of step S5)
Fifthly, in the present system 100, the information providing device 10 generates information to be provided to the user U based on the calculated ownership score and purchase tendency score of the user U (step S5). Here, the information to be provided is information for inducing a purchase behavior of a transaction object, and is, but is not limited to, an advertisement recommending a transaction object not owned by the user U, an advertisement recommending a transaction object related to a transaction object owned by the user U, content such as a video for increasing the purchasing tendency of the user U, an advertisement recommending the transaction object when it is time to replace the transaction object owned by the user U, and the like.

For example, when user U has a low ownership score and a high purchasing tendency score for product X (first category), user U is likely to purchase product X, and so the information providing device 10 generates an advertisement recommending product X. When user U has a high ownership score and a high purchasing tendency score for product X (second category), user U is likely to purchase a related product of product X, and so the information providing device 10 generates an advertisement recommending product Y related to product X. When user U has a low ownership score and a low purchasing tendency score for product X (third category), user U is unlikely to purchase product X, and so the information providing device 10 does not generate an advertisement recommending product X, and generates video content to increase user U's purchasing tendency. Furthermore, when user U has a high ownership score and a low purchasing tendency score for product X (fourth category), the information providing device 10 generates an advertisement that recommends product X when user U is due to replace product X, since user U is likely to repurchase product X in the future.

(1-2-6. Processing of step S6)
Sixth, in the present system 100, the information providing device 10 transmits the generated information to be provided to the user terminal 20 of the user U (step S6). To explain using the example of step S5 above, the information providing device 10 transmits an advertisement recommending product X to users U in the first category. The information providing device 10 transmits an advertisement recommending related product Y to users U in the second category. The information providing device 10 does not transmit an advertisement recommending product X to users U in the third category, but transmits video content to increase the purchasing tendency of users U. The information providing device 10 transmits an advertisement recommending product X to users U in the fourth category when it is time to replace product X.

(1-2-7. Processing of step S7)
Seventhly, in the present system 100, the information providing device 10 learns the calculated score (step S7). For example, when information that the user U actually owns the product X is input to the machine learning model, the information providing device 10 learns using backpropagation or the like so as to output the ownership score of the user U's product X as "1". In addition, when information that the user U does not own the product X is input to the machine learning model, the information providing device 10 learns using backpropagation or the like so as to output the ownership score of the user U's product X as "0". Similarly, when information of the user U who actually purchased the product X and information immediately before the purchase is input to the machine learning model, the information providing device 10 learns using backpropagation or the like so as to output the purchasing tendency score of the user U's product X as "1". In addition, when information of the user U who has not purchased the product X is input to the machine learning model, the information providing device 10 learns using backpropagation or the like so as to output the purchasing tendency score of the user U's product X as "0".

(1-3. Effects of System 100)
In the present system 100, the information providing device 10 collects user information on the user U via the user terminal 20, and calculates an ownership score indicating the possibility that the user U owns the item and a purchase tendency score indicating the possibility that the user U will purchase the item based on the collected user information of the user U, and generates information to be provided to the user U based on the calculated ownership score and purchase tendency score. That is, the present system 100 estimates the products owned and the purchase tendency for products based on the search behavior and purchase behavior of the user U and the user attributes of the user U, and can grasp a more detailed image of the user. For example, the present system 100 can estimate that the user U who owns the product X also owns the product Y and has a high purchase tendency. Therefore, the present system 100 can provide the user U with useful information such as advertisements for products that the user U is more likely to want to purchase. In addition, the present system 100 calculates not only the ownership score of the user U but also the purchase tendency score, thereby enabling more accurate estimation than the ownership estimation using the conventional technology.

In addition, the system 100 classifies the user U using the ownership score and the purchasing tendency score, and provides information based on the classification to the user U. As a result, the system 100 is expected to improve the targeting accuracy, and contribute to increasing advertising sales to businesses that provide trading objects such as goods and services.

Furthermore, by classifying users U using the ownership score and purchasing tendency score, the system 100 can also grasp information regarding areas with high and low purchasing tendencies for each product. For example, the system 100 can contribute to optimizing inventory management by, for example, replenishing inventory at mass retailers in areas where many customers who do not own product X but are interested in product X live.

2. Configuration of Information Providing Device 10
A configuration of the information providing device 10 according to the embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing an example of the configuration of the information providing device 10 according to the embodiment. As shown in Fig. 2, the information providing device 10 has a communication unit 11, a storage unit 12, and a control unit 13. Note that the information providing device 10 may have an input unit (e.g., a keyboard, a mouse, etc.) that accepts various operations from an administrator of the information providing device 10, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

(2-1. Communication Unit 11)
The communication unit 11 is realized by, for example, a network interface card (NIC), etc. The communication unit 11 is connected to a predetermined communication network by wire or wirelessly, and transmits and receives information to and from various devices.

(2-2. Storage unit 12)
The storage unit 12 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. 2, the storage unit 12 according to the embodiment has a user information storage unit 12a, a transaction target information storage unit 12b, a score information storage unit 12c, and a provided information storage unit 12d. The storage unit 12 stores various information referenced when the control unit 13 operates and various information acquired when the control unit 13 operates.

(2-2-1. User information storage unit 12a)
The user information storage unit 12a stores various types of information (user information) related to the user U. An example of information stored in the user information storage unit 12a will now be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the user information storage unit 12a according to an embodiment. In the example of Fig. 3, the user information storage unit 12a has items such as "user ID", "user attributes", "search history", and "purchase history".

"User ID" indicates identification information for identifying user U. "User attributes" indicates information that contributes to classifying user U, such as user U's gender, age, generation, occupation, annual income, place of residence, marital status, and whether or not the user has children. "User attributes" may also be information indicating categories of interest inferred from products and services owned by user U. "Search history" indicates information such as search terms used by user U to search for websites using user terminal 20, as well as website browsing history. "Purchase history" indicates information related to products and services purchased by user U on websites using user terminal 20.

In other words, Figure 3 shows an example in which, for user U identified by user ID "UID#1", the user attribute is "user attribute #1", the search history is "search history #1", and the purchase history is "purchase history #1".

(2-2-2. Transaction object information storage unit 12b)
The transaction object information storage unit 12b stores various information (transaction object information) related to transaction objects such as products and services. An example of information stored in the transaction object information storage unit 12b will be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the transaction object information storage unit 12b according to the embodiment. In the example of Fig. 4, the transaction object information storage unit 12b has items such as "transaction object ID" and "transaction object attribute".

"Transaction object ID" indicates identification information for identifying the transaction object. "Transaction object attributes" indicates information that contributes to the classification of the transaction object, such as product or service name, product or service category or type, business name, offered price, warranty period, validity period, etc.

That is, Figure 4 shows an example in which the transaction object attribute for the transaction object identified by the transaction object ID "GID#1" is "transaction object attribute #1."

(2-2-3. Score information storage unit 12c)
The score information storage unit 12c stores the ownership score and purchasing tendency score (score information) for each transaction object calculated by the calculation unit 13b of the control unit 13. Here, an example of information stored in the score information storage unit 12c will be described with reference to FIG. 5. FIG. 5 is a diagram showing an example of the score information storage unit 12c according to the embodiment. In the example of FIG. 5, the score information storage unit 12c has items such as "user ID", "transaction object ID", "ownership score", and "purchase tendency score".

"User ID" indicates identification information for identifying user U. "Transaction target ID" indicates identification information for identifying the transaction target. "Ownership score" is a numerical value indicating the likelihood of user U owning or having the authority to use each product or service. "Purchase tendency score" is a numerical value indicating the likelihood of user U's future purchasing behavior for each product or service.

In other words, FIG. 5 shows an example in which, for user U identified by user ID "UID#1", the ownership score of the transaction object identified by transaction object ID "GID#1" is "ownership score #1" and the purchasing propensity score is "purchase propensity score #1", and the ownership score of the transaction object identified by transaction object ID "GID#2" is "ownership score #2" and the purchasing propensity score is "purchase propensity score #2".

(2-2-4. Provided information storage unit 12d)
The provided information storage unit 12d stores the provided information generated by the generation unit 13c of the control unit 13. An example of information stored in the provided information storage unit 12d will now be described with reference to Fig. 6. Fig. 6 is a diagram showing an example of the provided information storage unit 12d according to the embodiment. In the example of Fig. 6, the provided information storage unit 12d has items such as "user ID", "transaction target ID", and "provided information".

"User ID" indicates identification information for identifying user U. "Transaction target ID" indicates identification information for identifying the transaction target. "Provided information" is information including advertisements, content, etc. selected for each product or service of user U.

In other words, FIG. 6 shows an example in which, for user U identified by user ID "UID#1," the provided information of the transaction object identified by transaction object ID "GID#1" is "provided information #1," and the provided information of the transaction object identified by transaction object ID "GID#2" is "provided information #2."

(2-3. Control Unit 13)
The control unit 13 is realized, for example, by a central processing unit (CPU) or a micro processing unit (MPU) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information providing device 10 using a RAM as a working area. The control unit 13 is also realized, for example, by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

As shown in FIG. 2, the control unit 13 has a collection unit 13a, a calculation unit 13b, a generation unit 13c, a transmission unit 13d, and a learning unit 13e, and realizes or executes the functions and actions of the information processing described below. Note that the internal configuration of the control unit 13 is not limited to the configuration shown in FIG. 2, and may be other configurations as long as they perform the information processing described below. Also, the connection relationships between the processing units in the control unit 13 are not limited to the connection relationships shown in FIG. 2, and may be other connection relationships.

(2-3-1. Collection unit 13a)
The collection unit 13a collects user information about the user U. For example, the collection unit 13a collects user U's user attributes, search history, purchase history, etc. from the user terminal 20 of the user U as user information. The collection unit 13a also collects transaction target information including transaction target attributes. For example, the collection unit 13a collects the transaction target attributes, etc. from the transaction target information database 30. The collection unit 13a stores the collected user information in the user information storage unit 12a. The collection unit 13a also stores the collected transaction target information in the transaction target information storage unit 12b.

(2-3-2. Calculation unit 13b)
The calculation unit 13b calculates, for each transaction object, an ownership score indicating the possibility that the user U owns the item and a purchase tendency score indicating the possibility that the user U will purchase the item, based on the user information. For example, the calculation unit 13b calculates the ownership score and the purchase tendency score for each transaction object using the attributes, search history, or purchase history of the user U as the user information. The calculation unit 13b also calculates the ownership score and the purchase tendency score for each transaction object using the user information and the transaction object information. To explain using a specific example, when calculating the ownership score and purchase tendency score of the user U for the product X, the calculation unit 13b calculates each score using common parameters (the purchase history of the related product Y of the product X, the transaction object attributes, the user attributes, the purchase history of the attributes, etc.), the search history of the product X, and the purchase history of the product X.

To explain the calculation method, the calculation unit 13b calculates the ownership score and the purchase propensity score using a machine learning model such as DNN that is trained to output the ownership score and the purchase propensity score for each transaction object of the user U when the user information and the transaction object information of the user U are input. In addition, the information providing device 10 may calculate the ownership score and the purchase propensity score on a rule basis.

Regarding the calculated scores, the calculation unit 13b calculates the ownership score and the purchase propensity score so that they take a numerical value between 0 and 1 depending on the possibility for each transaction object. The calculation unit 13b may also calculate the ownership score and the purchase propensity score so that they take a numerical value between 0 and 100% depending on the possibility for each transaction object, and the range and unit of the calculated scores are not particularly limited.

The calculation unit 13b acquires user information from the user information storage unit 12a. The calculation unit 13b acquires transaction target information from the transaction target information storage unit 12b. Meanwhile, the calculation unit 13b stores the calculated ownership score and purchasing tendency score in the score information storage unit 12c.

(2-3-3. Generation unit 13c)
The generating unit 13c generates information to be provided to the user U based on the ownership score and the purchase tendency score. For example, when the ownership score of the transaction object is less than a predetermined threshold and the purchase tendency score is equal to or greater than a predetermined threshold (first category), the generating unit 13c generates information to be provided that recommends the purchase of the transaction object. To explain using a specific example, for product X, when the ownership score of user U is lower than a set value (e.g., 0.8), the purchase tendency score is higher than a set value (e.g., 0.5), and user U is in the first category (highly likely to purchase product X), an advertisement recommending product X is generated as information to be provided to user U.

When the ownership score of the transaction object is equal to or greater than a predetermined threshold and the purchase tendency score is equal to or greater than a predetermined threshold (second category), the generation unit 13c generates information to be provided that recommends the purchase of a transaction object related to the transaction object. To explain using a specific example, when the ownership score of user U for product X is higher than a set value (e.g., 0.8), the purchase tendency score is higher than a set value (e.g., 0.5), and user U is in the second category (highly likely to purchase related product Y), an advertisement recommending related product Y is generated as information to be provided to user U.

When the ownership score of the transaction target is less than a predetermined threshold and the purchase propensity score is less than a predetermined threshold (third category), the generation unit 13c generates information to be provided for the purpose of increasing the purchase propensity score of the transaction target. To explain using a specific example, when the ownership score of user U for product X is lower than a set value (e.g., 0.8), the purchase propensity score is lower than a set value (e.g., 0.5), and user U is in the third category (low likelihood of purchasing product X), an advertisement recommending product X is not generated, and video content to increase user U's purchase propensity is generated as information to be provided to user U.

When the ownership score of the transaction object is equal to or greater than a predetermined threshold and the purchase tendency score is less than a predetermined threshold (fourth category), the generation unit 13c generates information to be provided to the user U recommending the purchase of the transaction object when it is time to replace the transaction object. To explain using a specific example, when the ownership score of user U for product X is higher than a set value (e.g., 0.8), the purchase tendency score is lower than a set value (e.g., 0.5), and user U is in the fourth category (highly likely to repurchase product X in the future), an advertisement recommending product X when it is time to replace the product is generated as information to be provided to user U.

The generation unit 13c acquires the ownership score and the purchasing tendency score from the score information storage unit 12c. The generation unit 13c also stores the generated provision information in the provision information storage unit 12d.

(2-3-4. Transmission unit 13d)
The transmission unit 13d transmits the provision information generated by the generation unit 13c to the user U. To explain using a specific example, the transmission unit 13d transmits an advertisement recommending product X to users U in the first category (highly likely to purchase product X). The transmission unit 13d also transmits an advertisement recommending related product Y to users U in the second category (highly likely to purchase related product Y). The transmission unit 13d does not transmit an advertisement recommending product X to users U in the third category (lowly likely to purchase product X), but transmits video content to increase the purchasing tendency of the user U. The transmission unit 13d also transmits an advertisement recommending product X to users U in the fourth category (highly likely to repurchase product X in the future) at the time of replacing product X.

The transmission unit 13d acquires the provided information from the provided information storage unit 12d. The transmission unit 13d may also acquire the ownership score and the purchasing tendency score from the score information storage unit 12c and transmit them to a business operator terminal or a database (not shown).

(2-3-5. Learning unit 13e)
The learning unit 13e learns the machine learning model so as to output the ownership score and purchase tendency score for each transaction object of the user U when the user information and transaction object information of the user U are input. To explain using a specific example, the learning unit 13e learns the machine learning model so as to output the ownership score of the user U's product X as "1" when information that the user U actually owns the product X is input to the machine learning model, and to output the ownership score of the user U's product X as "0" when information that the user U does not own the product X is input to the machine learning model. In addition, the learning unit 13e learns the machine learning model so as to output the purchase tendency score of the user U's product X as "1" when information of the user U who actually purchased the product X and information immediately before the purchase is input to the machine learning model, and to output the purchase tendency score of the user U's product X as "0" when information of the user U who has not purchased the product X is input to the machine learning model. At this time, the learning unit 13e may learn the machine learning model by backpropagation or the like.

3. Specific example of score calculation process
A specific example of the score calculation process according to the embodiment will be described in detail with reference to Fig. 7 to Fig. 9. Fig. 7 to Fig. 9 are diagrams showing a specific example of the process control system according to the embodiment.

(3-1. Specific Example 1)
A specific example 1 of the score calculation process will be described with reference to Fig. 7. In the following, a user U1 (30s, male, single, technical occupation, annual income XXX) who has a purchase history of a smartphone G11 will be described.

As shown in FIG. 7, the information providing device 10 calculates the ownership score and purchasing tendency score of user U1 as follows: smartphone G11 [ownership score: 1, purchasing tendency score: 0.45], earphones G12 [ownership score: 0.62, purchasing tendency score: 0.32], electronic pen G13 [ownership score: 0.34, purchasing tendency score: 0.32], smart watch G14 [ownership score: 0.75, purchasing tendency score: 0.35], cosmetics G15 [ownership score: 0.02, purchasing tendency score: 0.12], bag G16 [ownership score: 0.31, purchasing tendency score: 0.81], shirt G17 [ownership score: 0.33, purchasing tendency score: 0.62], ..., glasses G18 [ownership score: 0.21, purchasing tendency score: 0.71].

As shown in the above specific example 1, the information providing device 10 uses the purchase history of user U1 to estimate that user U1 owns smartphone G11 (ownership score of smartphone G11 is "1"). Furthermore, the information providing device 10 uses the purchase history and user attributes to estimate that the probability that user U1 who owns smartphone G11 also owns earphones G12 and the like is high (ownership score of earphones G12 is "0.62"). Furthermore, by using the search history, the information providing device 10 can also estimate that the probability of user U1 owning earphones G12 is low if user U1 performs a search behavior such as "recommended earphones."

(3-2. Specific Example 2)
A specific example 2 of the score calculation process will be described with reference to Fig. 8. In the following, a user U2 (in her 20s, female, married, annual income △△△) who has a purchase history of a smartphone G21 from company A and has purchased earphones G22 from company A and a power cable G23 from company A will be described.

As shown in FIG. 8, the information providing device 10 calculates the ownership score and purchasing propensity score of user U2 as follows: Company A smartphone G21 [ownership score: 1, purchasing propensity score: 0.45], Company A earphones G22 [ownership score: 1, purchasing propensity score: 0.32], Company A power cable G23 [ownership score: 1, purchasing propensity score: 0.32], Company A smartwatch G24 [ownership score: 0.75, purchasing propensity score: 0.95], Company B smartwatch G25 [ownership score: 0.75, purchasing propensity score: 0.22], and Company C smartwatch G26 [ownership score: 0.75, purchasing propensity score: 0.31].

As shown in the above specific example 2, the information providing device 10 can estimate that the user U2 owns a smartphone G21 from company A, earphones G22 from company A, and a power cable G23 from company A by using the purchase history of the user U2 (ownership score of smartphone G21 from company A, earphones G22 from company A, and power cable G23 from company A is "1"). The information providing device 10 also collects information on "like products from company A" as a category of interest from the purchase history of smartphone G21, which is a product of company A. Furthermore, by using the purchase history, the information providing device 10 can infer that the user U2 also has a tendency to purchase genuine products from company A for smartwatches, based on the tendency of the user U2 to purchase genuine products from company A as smartphone peripherals (earphones, power cable) (purchase tendency score of smartwatch G24 from company A is "0.95").

(3-3. Specific Example 3)
A specific example 3 of the score calculation process will be described with reference to Fig. 9. The following describes a user U3 (40s, male, married, annual income XXX) who has a purchase history of a camping item, a fire pit G31, and who has previously purchased and owns multiple mountain climbing items, such as mountain climbing boots G33 and mountain climbing wear G34.

As shown in FIG. 9, the information providing device 10 calculates the ownership score and purchasing tendency score of user U3 as follows: fire pit G31 [ownership score: 1, purchasing tendency score: 0.45], tent G32 [ownership score: 0.34, purchasing tendency score: 0.99], hiking boots G33 [ownership score: 1, purchasing tendency score: 0.95], hiking wear G34 [ownership score: 1, purchasing tendency score: 0.22], ...

As shown in the above specific example 3, the information providing device 10 can estimate that the user U3 owns the fire pit G31, hiking boots G33, hiking wear G34, etc. by using the purchase history of the user U3, etc. (Ownership score of the fire pit G31, hiking boots G33, and hiking wear G34 is "1"). Furthermore, by using the transaction target information, etc., the information providing device 10 can estimate that the user U3 has a high tendency to purchase the tent G32 because mountain climbing and camping are highly compatible and the user U3 owns multiple mountain climbing goods (purchase tendency score of the tent G32 is "0.99").

[4. Information provision process flow]
The procedure of information processing of the information providing device 10 according to the embodiment will be described with reference to Fig. 10. Fig. 10 is a flowchart showing an example of the flow of the information providing process according to the embodiment. Note that the following steps S101 to S107 may be executed in a different order. Also, some of the following steps S101 to S107 may be omitted.

(4-1. User information collection process)
First, the collection unit 13a of the information providing device 10 executes a user information collection process (step S101). For example, the collection unit 13a collects user information of the user U from the user terminal 20.

(4-2. Transaction target information collection process)
Secondly, the collection unit 13a of the information providing device 10 executes a transaction target information collection process (step S102). For example, the collection unit 13a refers to the transaction target information database 30 and acquires transaction target information.

(4-3. Possession score calculation process)
Third, the calculation unit 13b of the information providing device 10 executes an ownership score calculation process (step S103). For example, the calculation unit 13b calculates an ownership score for each transaction object of the user U from the collected user information and transaction object information.

(4-4. Purchase propensity score calculation process)
Fourth, the calculation unit 13b of the information providing device 10 executes a purchase propensity score calculation process (step S104). For example, the calculation unit 13b calculates a purchase propensity score for each transaction object of the user U from the collected user information and transaction object information.

(4-5. Provision Information Generation Processing)
Fifth, the generating unit 13c of the information providing device 10 executes a provision information generating process (step S105). For example, the generating unit 13c generates provision information to be provided to the user U based on the calculated ownership score and purchase tendency score of the user U.

(4-6. Provision information transmission process)
Sixth, the transmitting unit 13d of the information providing device 10 executes a process of transmitting the provided information (step S106). For example, the transmitting unit 13d transmits the generated provided information to the user terminal 20 of the user U.

(4-7. Score Calculation Learning Process)
Seventh, the learning unit 13e of the information providing device 10 executes a score calculation learning process (step S107). For example, the learning unit 13e performs learning of the calculated possession score and purchase tendency score.

5. Effects of the embodiment
(5-1. Effect 1)
In the process according to the embodiment described above, user information about user U is collected, and for each transaction object, an ownership score indicating the possibility that user U owns it and a purchase propensity score indicating the possibility that user U will purchase it are calculated based on the collected user information, and information to be provided to user U is generated based on the calculated ownership score and purchase propensity score. Therefore, in this process, useful information can be provided to user U.

(5-2. Effect 2)
In the process according to the embodiment described above, the ownership score and purchase tendency score are calculated for each transaction object using the attributes, search history, or purchase history of the user U as user information. Therefore, in this process, it is possible to provide the user U with more accurate and useful information.

(5-3. Effect 3)
In the process according to the embodiment described above, transaction object information including attributes of the transaction object is further collected, and the ownership score and purchase tendency score are calculated for each transaction object using the collected user information and transaction object information. Therefore, in this process, more accurate and useful information can be provided to the user U more effectively.

(5-4. Effect 4)
In the process according to the embodiment described above, when the ownership score of the transaction object is less than a predetermined threshold and the purchase tendency score is equal to or greater than a predetermined threshold, information to be provided that recommends the purchase of the transaction object is generated. Therefore, in this process, more accurate and useful information can be provided more effectively to a user U who is likely to purchase the transaction object.

(5-5. Effect 5)
In the process according to the embodiment described above, when the ownership score of the transaction object is equal to or greater than a predetermined threshold and the purchase tendency score is equal to or greater than a predetermined threshold, information to be provided is generated that recommends the purchase of a transaction object related to the transaction object. Therefore, in this process, more accurate and useful information can be provided more effectively to a user U who is likely to purchase a transaction object related to the transaction object.

(5-6. Effect 6)
In the process according to the embodiment described above, when the ownership score of the transaction object is less than a predetermined threshold and the purchase propensity score is less than a predetermined threshold, information to be provided is generated for the purpose of increasing the purchase propensity score of the transaction object. Therefore, in this process, more accurate and useful information can be provided more effectively to a user U who is unlikely to purchase the transaction object.

(5-7. Effect 7)
In the process according to the present embodiment described above, when the ownership score of the transaction object is equal to or greater than a predetermined threshold and the purchase tendency score is less than a predetermined threshold, provision information is generated that recommends the purchase of the transaction object to be provided when it is time to replace the transaction object. Therefore, in this process, more accurate and useful information can be provided more effectively to a user U who is likely to purchase the transaction object again in the future.

[Hardware configuration]
The information providing device 10 according to the embodiment described above is realized, for example, by a computer 1000 having a configuration as shown in Fig. 11. The information providing device 10 will be described below as an example. Fig. 11 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information providing device 10. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a 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 component. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, and programs that depend on the hardware of the computer 1000, etc.

HDD 1400 stores programs executed by CPU 1100 and data used by such programs. Communication interface 1500 receives data from other devices via a specified communication network N and sends it to CPU 1100, and transmits data generated by CPU 1100 to other devices via the specified communication network N.

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 acquires data from the input devices via the input/output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input/output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it 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) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

For example, when the computer 1000 functions as the information providing device 10 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 13. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a specified communication network.

〔others〕
Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. The above-described components include those that can be easily imagined by a person skilled in the art, those that are substantially the same, and those that are within the so-called equivalent range. Furthermore, the above-described components can be appropriately combined. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the gist of the above-described embodiments.

Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

For example, the information providing device 10 described above may be realized by multiple server computers, and depending on the functions, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

The above-described embodiments and variations can be combined as appropriate to the extent that they do not cause inconsistencies in the processing content.

The above-mentioned "section, module, unit" can be read as "means" or "circuit." For example, a control unit can be read as a control means or a control circuit.

REFERENCE SIGNS LIST 10 Information providing device 11 Communication unit 12 Storage unit 12a User information storage unit 12b Transaction object information storage unit 12c Score information storage unit 12d Provided information storage unit 13 Control unit 13a Collection unit 13b Calculation unit 13c Generation unit 13d Transmission unit 13e Learning unit 20 User terminal 30 Transaction object information database 100 Information providing system

Claims (8)

A collection unit that collects user information including at least one of a user's search history and a purchase history and transaction target information including attributes of transaction targets ;
a calculation unit that calculates the ownership score and the purchase propensity score for each of the transaction objects using a machine learning model that has been trained to output, when the user information and the transaction object information are input, an ownership score indicating the possibility that the user owns the item and a purchase propensity score indicating the possibility that the user will purchase the item ; and
a generation unit that generates information to be provided to the user in accordance with a combination of high and low of the ownership score and the purchase tendency score;
An information providing device comprising: the calculation unit further uses, as the user information, a user attribute indicating an interest of the user, to calculate the ownership score and the purchase tendency score for each of the transaction objects.
2. The information providing device according to claim 1 . the generation unit generates the provision information recommending the purchase of the transaction object when the ownership score of the transaction object is less than a predetermined threshold and the purchase tendency score is equal to or greater than a predetermined threshold.
3. The information providing device according to claim 1 or 2 . the generation unit generates the provision information recommending the purchase of a transaction object related to the transaction object when the ownership score of the transaction object is equal to or greater than a predetermined threshold and the purchase tendency score is equal to or greater than a predetermined threshold.
3. The information providing device according to claim 1 or 2 . when the ownership score of the transaction object is less than a predetermined threshold and the purchase propensity score is less than a predetermined threshold, the generation unit generates the provided information for the purpose of increasing the purchase propensity score of the transaction object.
3. The information providing device according to claim 1 or 2 . the generation unit generates the provision information recommending the purchase of the transaction object to be provided at a time when the transaction object is to be replaced, when the ownership score of the transaction object is equal to or greater than a predetermined threshold and the purchase tendency score is less than a predetermined threshold.
3. The information providing device according to claim 1 or 2 . An information providing method executed by an information providing device, comprising:
A collection step of collecting user information including at least one of a user's search history and a purchase history and transaction object information including attributes of the transaction object ;
a calculation step of calculating, for each of the transaction objects, the ownership score and the purchase propensity score by using a machine learning model trained to output, when the user information and the transaction object information are input, an ownership score indicating the possibility that the user owns the item and a purchase propensity score indicating the possibility that the user will purchase the item ;
generating information to be provided to the user in accordance with a combination of the ownership score and the purchase tendency score;
13. An information providing method comprising: A collection step of collecting user information including at least one of a user's search history and a purchase history and transaction target information including attributes of the transaction target ;
a calculation step of calculating the ownership score and the purchase propensity score for each of the transaction objects using a machine learning model trained to output, when the user information and the transaction object information are input, an ownership score indicating the possibility that the user owns the item and a purchase propensity score indicating the possibility that the user will purchase the item ;
a generation step of generating information to be provided to the user in accordance with a combination of the ownership score and the purchase tendency score;
An information providing program that causes a computer to execute the above steps.

Images