JP7779800B2 - Information processing device, 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.

Traditionally, various metrics have been used in delivering advertisements via the Internet. For example, technology is known that measures the effectiveness of advertisement delivery using various metrics such as CVR (Conversion Rate) (see, for example, Patent Document 1).

Japanese Patent Application Laid-Open No. 2018-116345

However, in recent years, there has been a demand to anonymize user information in order to protect personal information, and using conventional technology, it has been difficult to measure conversions from delivered advertisements under such regulations.

The present invention has been made in consideration of the above, and aims to provide an information processing device, information processing method, and information processing program that can measure conversions of delivered advertisements while anonymizing user information.

In order to solve the above-mentioned problems and achieve the objectives, the information processing device according to the present invention includes a generation unit that generates a cohort for classifying users based on user information about the users, and a measurement unit that measures conversions related to advertisements delivered to the users using a cohort identifier related to the cohort generated by the generation unit.

According to the present invention, it is possible to measure conversions from delivered advertisements while anonymizing user information.

FIG. 1 is a diagram illustrating an example of an information processing system according to an embodiment. FIG. 2 is a diagram illustrating an example of information processing according to the embodiment. FIG. 3 is a block diagram illustrating an example of an information processing apparatus according to the embodiment. FIG. 4 is a diagram illustrating an example of a cohort information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of a conversion information storage unit according to the embodiment. FIG. 6 is a flowchart illustrating an example of a cohort generation process according to the embodiment. FIG. 7 is a flowchart illustrating an example of a conversion measurement process according to the embodiment. FIG. 8 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing apparatus according to the embodiment.

Below, modes for implementing the information processing device, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, information processing method, and information processing program according to the present application are not limited to these embodiments.

[Embodiment]
1.1 Information Processing System
First, an overview of an information processing system and information processing according to an embodiment will be described with reference to Figures 1 and 2. Figure 1 is a diagram illustrating an example of an information processing system according to an embodiment. Figure 2 is a diagram illustrating an example of information processing according to an embodiment.

As shown in FIG. 1, the information processing system 1 according to the embodiment includes a user terminal 50, an information processing device 100, and an advertiser server 200, all connected via a network N. Note that FIG. 1 illustrates a case in which the information processing system 1 includes one user terminal 50, one information processing device 100, and one advertiser server 200, but the information processing system 1 may include multiple user terminals 50, multiple information processing devices 100, and one advertiser server 200.

The information processing device 100 shown in FIG. 1 is an information processing device that provides content related to various web services to a user terminal 50. For example, the information processing device 100 distributes advertisements submitted by advertisers to the user terminal 50 along with the content.

The information processing device 100 also measures the conversion (hereinafter also referred to as CV) of the delivered advertisements provided to the user terminal 50. Then, the information processing device 100 optimizes the CVR (Conversion Rate) of each delivered advertisement according to the measured CV.

The user terminal 50 is a terminal owned by a user. For example, the user terminal 50 displays content delivered from the information processing device 100 along with delivered advertisements. The user terminal 50 may be any of a variety of client terminals, such as a smartphone, tablet terminal, personal computer, or wearable device.

Furthermore, when a user clicks on a delivered advertisement displayed together with content related to a web service, the user terminal 50 moves to an advertiser site operated by the advertiser. When a predetermined CV is made on the advertiser site, the user terminal 50 transmits CV information to the information processing device 100. This allows the information processing device 100 to measure the CV of the delivered advertisement.

The advertiser server 200 is a server device that operates the advertiser's advertiser site. For example, the advertiser server 200 provides the advertiser site to the user terminal 50 in response to access by the user terminal 50.

[1.2. An example of information processing]
In recent years, in order to respect user privacy, anonymization of personal information is required in ad delivery. However, under such regulations, it becomes difficult to measure the conversion rate of delivered ads.

Therefore, the information processing device 100 according to the embodiment generates a cohort for each user with similar user information and measures CV on a cohort-by-cohort basis. Specifically, as shown in FIG. 1, the information processing device 100 generates cohorts from user vectors based on user information such that users with similar user vectors belong to the same cohort.

Next, the information processing device 100 delivers advertisements and measures conversions using the generated cohort. In other words, the information processing device 100 can anonymize user information by using a cohort ID (an example of a cohort identifier) that further abstracts the granularity of user information related to the user. Then, by delivering advertisements and measuring conversions using the cohort ID, the information processing device 100 can measure conversions for the delivered advertisements while anonymizing user information.

More specifically, as shown in FIG. 2, the information processing device 100 delivers content and distribution advertisements to the user terminal 50, and the content P and distribution advertisements AD are displayed via a web browser or app on the user terminal 50.

When a user clicks on the delivered advertisement AD, click information is notified from the user terminal 50 to the information processing device 100. Upon receiving the click information, the information processing device 100 passes the cohort ID corresponding to the user of the user terminal 50 and the URL related to the landing page of the delivered advertisement to the user terminal 50.

The user terminal 50 stores the cohort ID received from the information processing device 100 in web browser storage or a cookie, and displays advertiser site A by accessing the URL received from the information processing device 100.

Then, for example, when an operation that satisfies a CV tag embedded in advertiser site A is performed by user terminal 50 (for example, purchasing a product on the advertiser site), the cohort ID and CV information are notified from advertiser server 200 to information processing device 100. Note that information processing device 100 may also acquire the cohort ID and CV information notified from a third-party server (for example, a platform provider).

The information processing device 100 can then compare the click information notified from the user terminal 50 with the cohort ID and CV information notified from advertiser site A, thereby estimating (measuring) the CV corresponding to the click information.

This enables the information processing device 100 to perform CV measurement using the cohort ID. In this way, by using the cohort ID, the information processing device 100 can perform CV measurement while anonymizing user information.

2. Configuration example of information processing device
Next, a configuration example of the information processing device 100 will be described with reference to Fig. 3. Fig. 3 is a block diagram showing a configuration example of the information processing device 100 according to the embodiment. As shown in Fig. 3, the information processing device 100 includes a communication unit 110, a control unit 120, and a storage unit 130.

The communication unit 110 is realized, for example, by a NIC (Network Interface Card). The communication unit 110 transmits and receives information to and from external devices via a network N, which may be any of various wireless communication networks such as 4G (Generation), 5G, LTE (Long Term Evolution), Wi-Fi (registered trademark), or a wireless LAN (Local Area Network), or any of various wired communication networks.

The storage unit 130 is realized, for example, by a semiconductor memory element such as RAM or flash memory, or a storage device such as a hard disk or optical disk. The storage unit 130 also has a user information storage unit 131, a user vector model storage unit 132, a cohort information storage unit 133, a distribution advertising information storage unit 134, a distribution plan information storage unit 135, and a conversion information storage unit 136.

The user information storage unit 131 stores user information. User information is various information related to the user. For example, user information includes information registered in a web service provided by the information processing device 100 and behavioral information on the web service.

The user vector model storage unit 132 stores user vector models. A user vector model is a model that has been trained to output similar user vectors when similar user information is input. Note that similar vectors indicate high cosine similarity.

The cohort information storage unit 133 stores cohort information. Cohort information includes definitions of each cohort and information about the users included in each cohort. Figure 4 is a diagram showing an example of the cohort information storage unit 133 according to an embodiment.

As shown in Figure 4, the cohort information storage unit 133 stores cohort information organized in a hierarchical structure. In the example shown in Figure 4, "Cohort.1" in the first layer has "Cohort.11" and "Cohort.12" in the second layer under it, and "Cohort.11" in the second layer has "Cohort.111" in the third layer under it.

For example, each cohort stores corresponding cohort information (cohort definition and user information).

Returning to the explanation of Figure 3, the distribution advertisement information storage unit 134 will now be described. The distribution advertisement information storage unit 134 stores distribution advertisement information. The distribution advertisement information is information related to distribution advertisements submitted by each advertiser, and includes, for example, information related to the image (or video and audio) to be displayed as the distribution advertisement, distribution conditions (distribution target), target number of deliveries, target cost per conversion (tCPA), and landing page URL.

The distribution plan information storage unit 135 stores distribution plan information. The distribution plan information is, for example, information about a distribution plan for optimizing the CVR of each distribution advertisement and distributing it.

The conversion information storage unit 136 stores conversion information. The conversion information is information regarding conversions for each cohort ID for each distributed advertisement. Figure 5 is a diagram showing an example of the conversion information storage unit 136 according to an embodiment.

As shown in FIG. 5, the conversion information storage unit 136 stores information such as "Camp. ID," "Cohort ID," and "Delivery performance" in association with each other. "Camp. ID" is an identifier for identifying the campaign of each delivered advertisement.

"Cohort ID" is an identifier used to identify each cohort. "Delivery performance" is broadly divided into "click count" and "CV count." For example, "click count" indicates the number of times users with the corresponding "cohort ID" clicked on an ad delivered by the corresponding campaign, while "CV count" indicates the number of conversions by users.

The example in Figure 5 shows that the number of clicks by the user identified by "Cohort.1" for the advertisement delivered in the campaign identified by "Camp.1" was "2" and the number of conversions was "1".

Returning to the explanation of Figure 3, the control unit 120 will now be described. The control unit 120 is, for example, a controller, and is implemented by a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs stored in a storage device within the information processing device 100 using RAM as a working area. The control unit 120 is also a controller, and is implemented by an integrated circuit, for example, an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

As shown in FIG. 2, the control unit 120 has an acquisition unit 121, a generation unit 122, an allocation unit 123, a distribution unit 124, an assignment unit 125, a measurement unit 126, and an output unit 127.

The acquisition unit 121 acquires various information from the user terminal 50. The information acquired by the acquisition unit 121 includes, for example, various user information and requests for distributed advertisements. The acquisition unit 121 may acquire user information using a cookie (for example, a 1st Party cookie). The acquisition unit 121 may also acquire, as user information, the user's behavioral history in web services provided by the information processing device 100.

The acquisition unit 121 stores the acquired user information in the user information storage unit 131, and when a request for a distributed advertisement is acquired, it passes information about the request to the distribution unit 124.

The generation unit 122 generates a cohort that classifies users based on user information about the users. For example, when generating a cohort, the generation unit 122 first extracts an arbitrary number of pieces of user information from the user information stored in the user information storage unit 131.

Next, the generation unit 122 generates a user vector from the extracted user information using the user vector model stored in the user vector model storage unit 132. The generation unit 122 then generates a cohort, for example, by hierarchical clustering of the user vector.

The generation unit 122 may generate a cohort using various clustering processes, such as Euclidean distance or Ward's method. Furthermore, the generation unit 122 is not limited to hierarchical clustering, and may generate a cohort using a non-hierarchical clustering process. After generating a cohort, the generation unit 122 stores information about the generated cohort in the cohort information storage unit 133.

The allocation unit 123 allocates users (hereinafter referred to as allocation targets) who were not used to generate the cohort to the cohort generated by the generation unit 122. The allocation unit 123 extracts user information related to the allocation targets from the user information storage unit 131 and converts the user information into a user vector using a user vector model.

The allocating unit 123 then classifies the individuals to be allocated into each cohort based on the Mahalanobis distance between the converted user vector of the individual and the cluster center of each cohort. In this way, in the information processing device 100, the generating unit 122 generates cohorts using user information about some users, and the allocating unit 123 allocates the individuals to each cohort.

This reduces the processing load of the clustering process related to generating the cohort compared to when the generation unit 122 generates the cohort using the user information of all users.

The distribution unit 124 distributes a distribution advertisement in response to a request for a distribution advertisement (hereinafter simply referred to as a request) from the user terminal 50. For example, if the cohort of the user who is the request source is known, the distribution unit 124 selects a distribution advertisement to be distributed in accordance with distribution plan information stored in the distribution plan information storage unit 135, including information about the cohort and information about the display medium of the distribution advertisement.

Then, the distribution unit 124 selects an advertisement to be distributed in response to the request in accordance with the distribution plan, and distributes it to the user terminal 50 that made the request. The distribution unit 124 also passes, for example, the cohort ID of the user that made the request to the assignment unit 125.

In addition, if the cohort of the user requesting the request has not been determined, the distribution unit 124 requests the allocation unit 123 to allocate a cohort to the user, and selects an advertisement to be distributed using the cohort allocated by the allocation unit 123.

In this case, for example, the allocation unit 123 may allocate cohorts using the user's behavioral history within the same session as user information, or may allocate cohorts using various user information linked to the user ID.

The assigning unit 125 assigns a cohort ID corresponding to the user to information (URL) indicating the link destination of the delivered advertisement. For example, when a user terminal 50 clicks on a delivered advertisement delivered by the delivery unit 124, the assigning unit 125 acquires click information from the user terminal 50.

When the assignment unit 125 acquires the click information, it assigns a cohort ID corresponding to the user to the URL related to the landing page of the distributed advertisement and provides it to the user terminal 50. For example, the cohort ID assigned by the assignment unit 125 is stored in the web browser of the user terminal 50. The above click information is also notified to the measurement unit 126.

The measurement unit 126 uses the cohort identifier for the cohort generated by the generation unit 122 to measure conversions related to the advertisements delivered to the user. For example, the cohort ID assigned to the URL by the assignment unit 125 is stored for a predetermined period on the web browser of the user terminal 50.

During this time, if the user takes an action on the advertiser's site that satisfies the conditions of the CV tag, the cohort ID and CV information are notified to the information processing device 100 from the advertiser's site or a third-party server (for example, a platform provider). The measurement unit 126 measures the CV of each delivered advertisement according to the notified cohort ID and CV information.

The measurement unit 126 then updates the "number of conversions" in the conversion information stored in the conversion information storage unit 136 each time a conversion is measured, and updates the "number of clicks" in the conversion information based on the click information. The measurement unit 126 may also update the distribution plan information stored in the distribution plan information storage unit 135 in accordance with the measured conversions.

The output unit 127 outputs various information. For example, the output unit 127 generates an advertiser report regarding CV or CVR for each advertisement (campaign) delivered and outputs it to each advertiser.

3. Processing Flow
Next, an example of a processing procedure executed by the information processing device 100 according to the embodiment will be described with reference to Fig. 6 and Fig. 7. Fig. 6 is a flowchart showing an example of a cohort generation process according to the embodiment. Fig. 7 is a flowchart showing an example of a conversion measurement process according to the embodiment.

As shown in FIG. 6, first, the information processing device 100 extracts user information for generating a cohort (step S101). Next, the information processing device 10 acquires user vectors corresponding to each piece of extracted user information (step S102).

Next, the information processing device 100 generates cohorts through various clustering processes (step S103). Then, the information processing device 100 assigns the remaining users to each cohort based on, for example, the distance from the cluster center of the cohort (step S104), and ends the process.

Next, the processing steps of the conversion measurement process will be described using Figure 7. As shown in Figure 7, the information processing device 100 delivers a distribution advertisement to the user terminal 50 based on the request (step S111).

Next, the information processing device 100 determines whether click information for the delivered advertisement has been acquired (step S112). If click information has been acquired (step S112; Yes), the information processing device 100 assigns a cohort ID to the URL of the landing page (step S113).

Next, the information processing device 100 determines whether CV information has been acquired within a predetermined period (step S114), and if CV information has been acquired (step S114; Yes), determines whether a cohort ID has been acquired along with the CV information (step S115).

If the information processing device 100 determines in step S115 that a cohort ID has been acquired (step S115; Yes), it measures the CV (step S116) and terminates the processing.

Furthermore, if the information processing device 100 has not acquired click information in step S112 (step S112; No), has not acquired CV information in step S114 (step S114; No), or has not acquired a cohort ID in step S115 (step S115; No), it terminates processing.

4. Modifications
In the above-described embodiment, the information processing device 100 generates a cohort, but the present invention is not limited to this. For example, cohorts and cohort IDs may be shared between companies that have business partnerships.

5. Effects
The information processing device 100 according to the embodiment described above includes a generation unit 122 that generates a cohort for classifying users based on user information about the users, and a measurement unit 126 that measures conversions related to delivered advertisements delivered to users by using cohort identifiers related to the cohorts generated by the generation unit 122. Therefore, the information processing device 100 according to the embodiment can measure conversions related to delivered advertisements while anonymizing user information.

Furthermore, the generation unit 122 according to the above-described embodiment generates a cohort based on user information relating to some users. Therefore, according to the information processing device 100 according to the embodiment, the load of generating a cohort can be reduced compared to when a cohort is generated from all users.

Furthermore, the generation unit 122 according to the above-described embodiment generates cohorts by clustering according to the similarity of user information. Therefore, the information processing device 100 according to the embodiment can appropriately generate cohorts.

The information processing device 100 according to the embodiment described above includes an assignment unit 125 that assigns the cohort identifier according to the user to information indicating the link destination of a distributed advertisement, and a measurement unit 126 that measures conversions based on the cohort identifier and conversion information notified after a conversion occurs in response to a distributed advertisement.

Furthermore, the generation unit 122 according to the above-described embodiment generates a cohort from user information using a user vector model that has been trained to output similar user vectors when similar user information is input. Therefore, the information processing device 100 according to the embodiment can generate appropriate cohorts such that similar user information is grouped into the same cohort.

The information processing method according to the above-described embodiment is an information processing method executed by a computer, and includes a generation step of generating a cohort for classifying users based on user information about the users, and a measurement step of measuring conversions related to delivered advertisements delivered to the users using a cohort identifier related to the cohort generated by the generation step. Therefore, the information processing method according to the embodiment makes it possible to measure conversions related to delivered advertisements while anonymizing user information.

The information processing program according to the above-described embodiment causes a computer to execute a generation step of generating a cohort for classifying users based on user information about the users, and a measurement step of measuring conversions related to delivered advertisements delivered to the users using a cohort identifier related to the cohort generated by the generation step. Therefore, the information processing program according to the embodiment makes it possible to measure conversions related to delivered advertisements while anonymizing user information.

6. Hardware Configuration
The information processing apparatus 100 according to the embodiment described above is realized by, for example, a computer 1000 configured as shown in Fig. 8. Fig. 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing apparatus 100 according to the embodiment. 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 programs stored in the ROM 1300 or HDD 1400, and controls each component. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

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

The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice (in Figure 8, the output devices and input devices are collectively referred to as "input/output devices") 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.

Media interface 1700 reads programs or data stored on recording medium 1800 and provides them to CPU 1100 via RAM 1200. CPU 1100 loads the programs from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded programs. 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 processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200, thereby realizing the functions of the control unit 120. 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 also obtain these programs from another device via the network N.

The above describes in detail some of the embodiments of the present application based on the drawings, but these are merely examples, and the present invention can be implemented in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the Disclosure of the Invention section.

[7. Other]
Furthermore, among the processes described in the above embodiments and modifications, 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.

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

Furthermore, the above-described embodiments and variations can be combined as appropriate to the extent that the processing content is not contradictory.

Furthermore, the above-mentioned "section, module, unit" can be interpreted as "means" or "circuit." For example, the acquisition unit 121 can be interpreted as acquisition means or acquisition circuit.

1 Information processing system 50 User terminal 100 Information processing device 120 Control unit 121 Acquisition unit 122 Generation unit 123 Allocation unit 124 Distribution unit 125 Assignment unit 126 Measurement unit 127 Output unit 131 User information storage unit 132 User vector model storage unit 133 Cohort information storage unit 134 Distribution advertisement information storage unit 135 Distribution plan information storage unit 136 Conversion information storage unit 200 Advertiser server

Claims (6)

A generation unit that generates a cohort that classifies users based on user information about the users;
a measurement unit that measures conversions related to the advertisement delivered to the user by using the cohort identifier related to the cohort generated by the generation unit,
The generation unit
A user vector model that has been trained to output similar user vectors when similar user information is input is used to generate a user vector from the user information, and a cohort is generated by clustering the user vector.
1. An information processing device comprising: The generation unit
The information processing device according to claim 1 , wherein the cohort is generated based on the user information relating to a portion of the users. The generation unit
The information processing device according to claim 1 , wherein the cohort is generated by clustering according to a similarity of the user information. an assigning unit that assigns the cohort identifier corresponding to the user to information indicating a link destination of the delivered advertisement;
The measurement unit
The information processing device according to claim 1 , wherein the conversion is measured based on conversion information notified after a conversion occurs in response to a distributed advertisement and the cohort identifier. 1. A computer-implemented information processing method, comprising:
A generation step of generating a cohort that classifies users based on user information about the users;
a measuring step of measuring conversions related to the advertisement delivered to the user by using the cohort identifier related to the cohort generated by the generating step,
The generating step includes:
A user vector model that has been trained to output similar user vectors when similar user information is input is used to generate a user vector from the user information, and a cohort is generated by clustering the user vector.
An information processing method comprising: A generation step of generating a cohort for classifying users based on user information about the users;
a measurement step of measuring conversions related to the advertisement delivered to the user by using the cohort identifier related to the cohort generated by the generation step;
The generating procedure includes:
A user vector model that has been trained to output similar user vectors when similar user information is input is used to generate a user vector from the user information, and a cohort is generated by clustering the user vector.
An information processing program characterized by: