Information processing apparatus, information processing method, and information processing program

Abstract

To support efficient approaches to a target consumer group for an advertisement.SOLUTION: An information processing apparatus includes a receiving unit, an acquisition unit, a selection unit, a generation unit, and a providing unit. The receiving unit receives, from an operator, an input of commodity information regarding a commodity. The acquisition unit acquires information indicating an attribute of a first user group registered in a region in which an access to registered data is restricted. The selection unit selects, as a target user group, a second user group having an attribute similar to the attribute of the first user group, from among a plurality of second user groups classified based on the same condition as a predetermined condition which is used for classifying first users. The generation unit generates persona information, which is information indicating a typical user profile of second users belonging to the target user group, using the commodity information and second user information of the second users belonging to the target user group. The providing unit provides the persona information generated by the generation unit to the operator.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present application relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] In recent years, various techniques have been proposed for measuring the effectiveness of content such as advertisements distributed over the Internet. For example, a technique for estimating the degree of viewer attention to content is known (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-040432 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional techniques leave room for improvement in supporting efficient advertising approaches to targeted consumer demographics.

[0005] The present application has been made in view of the above, and aims to support an efficient approach to consumer groups that are the target of advertising. [Means for solving the problem]

[0006] The information processing device according to the present application includes a receiving unit, an acquiring unit, a selecting unit, a generating unit, and a providing unit. The receiving unit accepts input of product information about a product from an operator. The acquiring unit acquires cluster information indicating attributes of a first cluster into which customers are classified based on customer information about customers of a business that advertises the product, the cluster information being information registered in an area where access to registered data is restricted. The cluster information indicates attributes of a first cluster into which customers are classified based on customer information about customers of a business that advertises the product. The selecting unit selects, as a target cluster to be processed, a second cluster having attributes similar to the attributes of the first cluster indicated in the cluster information from among a plurality of different second clusters into which service users are classified based on the same predetermined conditions used to classify customers using user information about a plurality of service users who use an online service. The generating unit generates persona information, which is information indicating typical user profiles corresponding to a plurality of service users belonging to the target cluster, using the product information and user information about service users belonging to the target cluster. The providing unit provides the persona information generated by the generating unit to an operator. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to assist in an efficient approach to a consumer group that is a target of advertising. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of display of persona information according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of display of persona information according to the embodiment. [Figure 4] FIG. 4 is a diagram for explaining an example of another information process according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of the system configuration of the information processing system according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of the configuration of an information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of user information stored in a user information DB according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of cluster information stored in the cluster information DB according to the embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of model information stored in a model DB according to the embodiment. [Figure 10] FIG. 10 is a flowchart showing an example of a procedure (part 1) of information processing executed by the information processing device according to the embodiment. [Figure 11] FIG. 11 is a flowchart showing an example of a procedure (part 2) of information processing executed by the information processing device according to the embodiment. [Figure 12] FIG. 12 is a flowchart showing an example of a procedure (part 3) of information processing executed by the information processing device according to the embodiment. [Figure 13] FIG. 13 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, modes for implementing an information processing device, an information processing method, and an 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, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the respective embodiments can be appropriately combined within the scope of not causing any contradiction in the processing content. Furthermore, the same components in the following embodiments will be assigned the same reference numerals, and redundant explanations will be omitted.

[0010] [Embodiment] [1-1. An example of information processing] An example of information processing according to the embodiment will be described below with reference to the drawings: Fig. 1 is a diagram for explaining an example of information processing according to the embodiment.

[0011] As shown in FIG. 1, the information processing according to the embodiment is realized by an information processing system SYS-1 including a terminal device 10, an operator device 20, a service providing device 30, and an information processing device 100.

[0012] 1 executes information processing according to the embodiment. For example, the information processing device 100 executes information processing to support an efficient approach to a consumer demographic that is a target of advertisements that provide online services to a service user U who is a user of the online service. The information processing device 100 is realized, for example, by one or more servers or cloud systems.

[0013] 1, the information processing device 100 acquires user information about a service user U from the service providing device 30. The information processing device 100 also classifies the service users U based on the user information acquired from the service providing device 30, thereby determining multiple clusters (examples of "user groups") that are different from one another. The information processing device 100 then registers cluster information about the multiple clusters in a cluster information DB (for example, the cluster information DB 122 shown in FIG. 6).

[0014] The information processing device 100 can acquire, as the user information, information that is not directly related to the product to be advertised. For example, the user information includes attribute information indicating the attributes of the service user U and behavior information regarding the behavior of the service user U.

[0015] The attribute information includes demographic attributes (also referred to as "demographic attributes") such as the service user U's personal information, such as name, age, gender, occupation, annual household income, and type of residence, as well as psychological attributes (also referred to as "psychographic attributes") such as the service user U's interests and lifestyle.

[0016] The behavioral information corresponds to information indicating the content of the behavior of the service user U in the online service. The information indicating the content of the behavior includes the history of the behavior in the online service, such as search history, browsing history, and purchase history.

[0017] When the information processing device 100 acquires, as user information, for example, attribute information indicating the attributes of service users U, it can determine multiple clusters by classifying service users U with similar attributes into the same group. Classification of service users U can be performed using well-known techniques that use existing algorithms, such as "hierarchical clustering," "K-means algorithm," and "DB Scan." The determination of whether attributes are similar or not may be performed based on the commonality of specific attributes among the attributes of service users U. For example, if at least one of specific attributes such as age, gender, family structure, annual income, interests, and lifestyle is common, it can be determined that the attributes are similar.

[0018] When the information processing device 100 acquires, for example, behavioral information of a service user U as user information, it generates multiple clusters by classifying service users U whose behavioral content is similar into the same group. The determination of whether the behavioral content is similar may be set based on the judgment of an administrator of the information processing device 100, or may be performed using existing well-known technology. For example, the information processing device 100 converts text information corresponding to the behavioral content into a vector representation indicating features corresponding to the behavioral content using Word2Vec or the like. Then, the information processing device 100 compares the vector representations corresponding to the behavioral content with each other and calculates the similarity of the vector representations to determine whether the behavioral content is similar.

[0019] The information processing device 100 can acquire, as the user information, for example, information on the results of a personality assessment questionnaire administered to the service user U in order to determine the personality characteristics of the service user U. In this case, the personality assessment questionnaire is administered by the service providing device 30 in response to a request from the information processing device 100, but may also be administered by the information processing device 100. The personality assessment questionnaire can be administered by using, for example, a test based on an existing personality analysis method such as the "Big Five."

[0020] When the information processing device 100 acquires information on the results of a personality assessment questionnaire for a service user U as user information, the information processing device 100 classifies service users U with similar personality traits into the same group, thereby determining multiple clusters. The information processing device 100 can determine the similarity of personality traits based on whether the results of a personality analysis based on the questionnaire results are similar. For example, if a personality assessment questionnaire is conducted using a test based on the "Big Five" personality analysis method, the information processing device 100 classifies the personality traits of the service user U based on the five "Big Five" factors, and determines whether the personality traits of the service users U are similar based on whether the classification results are similar.

[0021] In this way, the information processing device 100 can pre-classify service users U of online services into multiple general-purpose clusters using an objective measure unrelated to the product being advertised. Note that the advertisement target is not limited to goods provided by advertisers and traded in the market, and may include various services.

[0022] 1, the information processing device 100 receives input of product information about a product to be advertised from an operator OP using the operator device 20 (step S1). For example, the product-related information may include the product category, price, name of the company that provides the product, and information for identifying the target consumers of the product.

[0023] Next, the information processing device 100 selects a target cluster to be processed from among the plurality of cluster information (step S2). For example, the information processing device 100 may select a cluster designated by the operator OP as the target cluster. Specifically, the information processing device 100 transmits a request to the operator device 20 requesting selection of a target cluster. Upon receiving input of identification information for identifying a cluster from the operator OP, the information processing device 100 selects, as the target cluster, a cluster corresponding to the identification number designated by the operator OP from among the plurality of clusters stored in the cluster information DB 122.

[0024] Furthermore, the information processing device 100 may automatically select, from among a plurality of clusters, a cluster to which a service user U who is estimated to have a high probability of purchasing the advertised product belongs as a target cluster. For example, the information processing device 100 uses the purchase history of the service user U to train a model, for each product, on feature information indicating the personality traits of the service user U who has a history of purchasing the product. For example, when product information is input, the information processing device 100 generates a first trained model through machine learning that is trained to output the personality traits of the service user U who is estimated to have a high probability of purchasing the product. For example, when a personality assessment questionnaire is conducted using a test based on the "Big Five" personality analysis method, the feature information may be composed of scores corresponding to five factors.

[0025] Furthermore, the information processing device 100 learns a model that estimates the degree of similarity between feature information indicating the personality traits of a service user U who is likely to purchase a product to be processed and the personality traits of the service user U to be processed. For example, when the information processing device 100 receives, by machine learning, feature information indicating the personality traits of a service user U who is likely to purchase a product to be processed and feature information indicating the personality traits of the service user U to be processed, it generates a second trained model that is trained to output a higher score the more similar the input feature information is to each other.

[0026] The information processing device 100 inputs product information to be processed into the first trained model described above, thereby acquiring feature information corresponding to the target product to be processed (i.e., feature information indicating the personality traits of a service user U who is estimated to be highly likely to purchase the target product). The information processing device 100 also selects one cluster from among multiple clusters, and individually inputs each piece of feature information indicating the personality traits of multiple service users U belonging to the selected cluster and the feature information corresponding to the target product into the second trained model described above, thereby acquiring a score indicating the similarity of the feature information corresponding to the target product for each service user U belonging to the cluster. The information processing device 100 also calculates the sum (or average) of the acquired scores, and identifies the cluster with the largest sum (or average) as the cluster most similar to the feature information corresponding to the target product. The information processing device 100 then selects the identified cluster as the target cluster. The model for estimating the cluster may be a trained model generated using existing well-known technology, such as a trained model that determines whether to deliver an advertised product or a trained model that determines whether to suggest an advertised product.

[0027] Furthermore, the information processing device 100 may select, from among a plurality of clusters, a cluster to which a service user U who is estimated to have a low possibility of purchasing the advertised product belongs as a target cluster. This can assist in understanding the personality traits of the service user U who is unlikely to purchase the product. For example, the information processing device 100 uses the purchase history of the service user U to train a model for each product with feature information that indicates the personality traits of non-purchasers of the product. For example, the information processing device 100 generates a third trained model through machine learning that is trained to output feature information that indicates the personality traits of the service user U who is estimated to have a low possibility of purchasing the product when product information is input.

[0028] The information processing device 100 inputs product information to be processed into the third trained model described above, thereby acquiring feature information corresponding to the target product to be processed (i.e., feature information indicating the personality traits of the service user U who is estimated to have a low possibility of purchasing the target product). The information processing device 100 also selects one cluster from among multiple clusters, and individually inputs each piece of feature information indicating the personality traits of multiple service users U belonging to the selected cluster and the feature information corresponding to the target product into the second trained model described above, thereby acquiring a score indicating the similarity of the feature information corresponding to the target product for each service user U belonging to the cluster. The information processing device 100 also calculates the sum (or average) of the acquired scores, and identifies the cluster with the largest sum (or average) as the cluster most similar to the feature information corresponding to the target product. The information processing device 100 then selects the identified cluster as the target cluster.

[0029] Returning to FIG. 1, after selecting a target cluster, the information processing device 100 acquires user information of service users U belonging to the target cluster from the user information DB 121. Then, the information processing device 100 generates persona information, which is information indicating typical user profiles corresponding to multiple service users U belonging to the target cluster, using the product information and the user information of the service users U belonging to the target cluster (step S3). For example, the information processing device 100 can generate persona information by inputting instruction information (also referred to as a "prompt") that instructs a generation AI that has been trained to generate answers to input questions to generate information describing typical user profiles corresponding to multiple service users U belonging to the target cluster based on the product information, the user information of the target cluster, and user characteristics including behavior and degree of interest in products.

[0030] Generative AI is a language model trained to predict and output the next token from an input token sequence, and includes, for example, transfer-based models and RNN (Recurrent Neural Network)-based models.

[0031] Examples of transfer-based models include, but are not limited to, "GPT (Generative Pre-trained Transformer)" and "BARD (Bidirectional Auto Regressive Dialogues)." Examples of RNN-based models include, but are not limited to, "RWKV (Receptance Weighted Key Value)." When training a model, it is desirable for the generative AI to conceal input information, such as personal information, by training the model so that the input information is not used as a new answer.

[0032] The generative AI may also be a multimodal AI that generates images from text or generates text from images. Examples of multimodal AI include, but are not limited to, "GPT-4-Trubo," "GPT-4V," "CM3Leon (Chameleon Multimodal Model)," and "Stable Diffusion."

[0033] For example, the information processing device 100 inputs to the generation AI an instruction sentence instructing the generation of text information for describing a representative user image of multiple users belonging to the target cluster, using product information about the product to be advertised and user information about users belonging to the target cluster, as well as the results of a personality assessment questionnaire, a user profile, and affinity with the product. The information processing device 100 also inputs an instruction sentence instructing the generation of image information showing a representative user image of multiple users belonging to the target cluster, using the user information about the users belonging to the target cluster. The information processing device 100 then generates persona information by arranging the text information and image information output from the generation AI according to a predetermined template.

[0034] Furthermore, the information processing device 100 may input to the generation AI product information on the product to be advertised and user information on users belonging to the target cluster, as well as an instruction sentence instructing the generation AI to estimate the affinity between the product and the target cluster.The information processing device 100 may then include the affinity information output from the generation AI in the persona information.Note that the information processing device 100 may use the score output from the second trained model described above as the affinity between the product and the target cluster.

[0035] Persona information according to the embodiment will be described with reference to Figures 2 and 3. Figures 2 and 3 are diagrams showing examples of display of persona information according to the embodiment. The persona information shown in Figures 2 and 3 is created using information output from a generation AI by inputting a plurality of clusters into which a plurality of service users U have been pre-classified using the results of a personality assessment questionnaire, and products designated by an operator OP.

[0036] FIG. 2 shows an example of persona information when the product specified by the operator OP is a reverse mortgage. Using information output by the generation AI, the information processing device 100 can generate persona information including appearance information indicating the persona's appearance, questionnaire information indicating the results of a personality assessment questionnaire, profile information indicating the persona's profile, and affinity information indicating the persona's affinity with the product. The questionnaire information shown in FIG. 2 is composed of the appearance rate of service user U having the profile shown in FIG. 2 in the personality assessment questionnaire. The profile shown in FIG. 2 is composed of multiple items, such as "Name," "Age / Gender," "Interests / Concerns," "Annual Household Income," "Type of Residence," "Lifestyle," "Purchasing Behavior," and "Future Plans," along with information for each item. The reverse mortgage affinity shown in FIG. 2 is composed of four scales: "1. Real Estate Assets," "2. Intention to Be Independent," "3. Income Concerns," and "4. Longevity Risk," along with information for each scale.

[0037] FIG. 3 shows an example of persona information when the product specified by the operator OP is a sports lottery. Using information output by the generation AI, the information processing device 100 can generate persona information including appearance information indicating the persona's appearance, questionnaire information indicating the results of a personality assessment questionnaire, profile information indicating the persona's profile, and affinity information indicating the persona's affinity with the product. FIG. 3 shows an example of information generated that differs in content and structure from the persona information shown in FIG. 2. The appearance information shown in FIG. 3 displays information indicating the persona's appearance that differs from the appearance information shown in FIG. 2. The questionnaire information shown in FIG. 3 includes, for example, the appearance rate of service user U having the profile shown in FIG. 3 in the personality assessment questionnaire. The profile shown in FIG. 3 includes multiple items, such as "Name," "Age / Gender," "Occupation," "Interests / Concerns," "Annual Household Income," "Values," "Lifestyle," and "Purchasing Behavior," along with information for each item. The sports lottery affinity shown in FIG. 3 includes three scales: "1. Probability Judgment," "2. Escapism," and "3. Sports Liking," along with information for each scale.

[0038] Returning to FIG. 1, the information processing device 100 transmits the generated persona information to the operator device 20, thereby providing the persona information to the operator OP (step S4).

[0039] In this way, the information processing device 100 shown in Fig. 1 can provide the operator OP with, for example, persona information that indicates a profile of users who are likely to purchase a product, and persona information that indicates a profile of users who are unlikely to purchase a product. The operator OP can use the persona information provided by the information processing device 100 to carry out sales activities for advertisers regarding advertising strategies for their products. In this way, the information processing device 100 shown in Fig. 1 can support an efficient approach to the consumer demographic that is the target of advertising.

[0040] [1-2. Examples of other information processing] Furthermore, the information processing device 100 may execute another information process in which the persona information is generated by expanding a first cluster in which customers are classified using customer information about customers of the advertiser business Ad to a second cluster in which the service user U is classified using user information about the service user U, and the persona information is provided to the operator OP. Hereinafter, an example of another information process according to the embodiment will be described with reference to Fig. 4. Fig. 4 is a diagram for describing an example of another information process according to the embodiment.

[0041] As shown in FIG. 4, another information processing according to the embodiment is realized by an information processing system SYS-2 including a terminal device 10, an operator device 20, a service providing device 30, an advertiser device 40, a cooperating device 50, and an information processing device 100.

[0042] In the information processing system SYS-2 shown in FIG. 4, the information processing device 100 receives an input of product information on a product to be advertised from an operator OP using the operator device 20 (step S11).

[0043] Next, the information processing device 100 acquires first cluster information from the coordinating device 50 by transmitting a request for providing information to the coordinating device 50 (step S12). The first cluster information is information indicating attributes of first clusters into which a plurality of first users are classified, based on customer information about customers of the business Ad that is the advertiser. The customers of the business Ad that is the advertiser are an example of "first users." The customer information is an example of "first user information." The first cluster is an example of "first user group."

[0044] The advertiser device 40 determines a plurality of first clusters by classifying a plurality of customers based on customer information about the customers input by the advertiser business Ad. The advertiser device 40 may, for example, introduce a determination result of whether or not customer attributes are similar as a predetermined condition for classifying customers. In this case, the advertiser device 40 can determine a plurality of first clusters by classifying customers with similar attributes into the same group. The determination of whether or not attributes are similar may be performed based on the commonality of a specific attribute among the customer attributes included in the customer information. The classification of the first clusters may be performed using an existing classification algorithm such as "hierarchical clustering," "K-means," or "DB Scan."

[0045] The customer information is information that is not directly related to the product. For example, the customer information includes attribute information indicating the attributes of the customer and behavioral information regarding the customer's behavior, similar to the user information of the service user U in the embodiment described above. The customer information may also include information on the results of a personality assessment questionnaire administered to the customer to determine the customer's personality traits.

[0046] After determining the multiple first clusters, the advertiser device 40 registers first cluster information, which is information indicating the attributes of the first cluster designated by the advertiser business entity Ad from among information indicating the attributes of the multiple first clusters, in an access-restricted area in which access to registered data is restricted, stored in the linked device 50. The first cluster information may be information configured by normalizing attribute values ​​corresponding to each attribute characterizing the first cluster.

[0047] In response to a request from the information processing device 100, the cooperating device 50 transmits the first cluster information registered in the access restricted area to the information processing device 100.

[0048] Next, the information processing device 100 selects, from among the plurality of second clusters, a second cluster having an attribute similar to the attribute of the first cluster as a target cluster to be processed (step S13).

[0049] The multiple second clusters are multiple different clusters in which multiple service users U who are users of online services are classified based on user information about the multiple service users U, based on the same conditions as the predetermined conditions used to classify customer information (for example, whether the attributes are similar or not).

[0050] Furthermore, the user information is information that has no direct relation to the product. For example, the user information includes attribute information indicating the attributes of the service user U and behavioral information regarding customer behavior, similar to the user information of the service user U according to the embodiment described above. The user information may also include information on the results of a personality assessment questionnaire administered to the service user U to determine the personality traits of the service user U.

[0051] In the information processing device 100, the determination of whether the attributes of the first cluster and the attributes of the second cluster are similar may be performed based on the commonality of specific attributes. For example, when at least one of specific attributes such as age, sex, family structure, annual income, interests, and lifestyle corresponding to the second cluster is common to the attributes of the first cluster, the information processing device 100 can derive a determination result that the second cluster has attributes similar to the attributes of the first cluster.

[0052] Furthermore, in the information processing device 100, determining whether the attributes of the first cluster and the second cluster are similar may be performed by determining whether the content of the activity corresponding to the first cluster is similar to the content of the activity corresponding to the second cluster. For example, the information processing device 100 converts text information corresponding to the content of the activity corresponding to the first cluster and text information corresponding to the content of the activity corresponding to the second cluster into vector representations indicating features corresponding to the content of the activity using Word2Vec or the like. Then, the information processing device 100 compares the vector representation corresponding to the content of the activity corresponding to the first cluster with the vector representation corresponding to the content of the activity corresponding to the second cluster and determines the similarity of the vector representations to determine whether the content of the activities is similar. If the information processing device 100 determines that the content of the activities is similar, it can derive a determination result that the second cluster has attributes similar to the attributes of the first cluster.

[0053] Furthermore, in the information processing device 100, the determination of whether the attributes of the first cluster and the attributes of the second cluster are similar may be performed by determining whether the personality traits of the customers belonging to the first cluster are similar to the personality traits of the service user U belonging to the second cluster. For example, if a personality diagnostic questionnaire is administered to the customers and the service user U using a test based on the "Big Five" personality analysis method, the information processing device 100 classifies the personality traits of the customers belonging to the first cluster and the personality traits of the service user U belonging to the second cluster based on the five factors of the "Big Five," and determines whether the personality traits of the customers belonging to the first cluster and the personality traits of the service user U belonging to the second cluster are similar based on whether the classification results are similar. If the information processing device 100 determines that the personality traits of the customers belonging to the first cluster and the personality traits of the service user U belonging to the second cluster are similar, it can derive a determination result that the second cluster has attributes similar to the attributes of the first cluster.

[0054] Returning to Figure 4, after selecting the target cluster, the information processing device 100 uses product information and user information of service users U belonging to the target cluster to generate persona information, which is information that indicates typical user profiles corresponding to multiple service users U belonging to the target cluster (step S14).

[0055] For example, the information processing device 100 shown in Fig. 4 can generate persona information by inputting product information, user information of the target cluster, and instruction information (also referred to as "prompt") that instructs the generation of information describing typical user images corresponding to multiple service users U belonging to the target cluster based on user characteristics including behavior and degree of interest in products to a generation AI that has been trained to generate answers to input questions. The generation AI is the same as the generation AI described in the above embodiment.

[0056] The information processing device 100 shown in FIG. 4 transmits the generated persona information to the operator device 20, thereby providing the persona information to the operator OP (step S15).

[0057] Furthermore, in step S13 described above, the information processing device 100 may generate persona information by inputting product information about the product specified by the operator in step S11 described above, customer information about the customers belonging to the first cluster, and an instruction sentence that instructs the generation AI to generate information showing a typical user profile of the customers belonging to the first cluster using the product information and customer information, without selecting a second cluster similar to the attributes of the first cluster as the target cluster.

[0058] [2. System Configuration] The configuration of the information processing system SYS according to the embodiment will be described in detail below with reference to Fig. 5. Fig. 5 is a diagram showing an example of the system configuration of the information processing system SYS according to the embodiment. The information processing system SYS shown in Fig. 5 realizes the information processing system SYS-1 shown in Fig. 1, the information processing system SYS-2 shown in Fig. 4, etc.

[0059] As shown in FIG. 5, the information processing system SYS according to the embodiment includes a plurality of terminal devices 10, an operator device 20, a service providing device 30, an advertiser device 40, a cooperating device 50, and an information processing device 100.

[0060] The terminal device 10, the operator device 20, the service providing device 30, the advertiser device 40, the cooperating device 50, and the information processing device 100 are connected to a network N by wire or wirelessly. Each of the terminal device 10, the operator device 20, the service providing device 30, the advertiser device 40, the cooperating device 50, and the information processing device 100 can communicate with other devices via the network N.

[0061] The network N includes, for example, a WAN (Wide Area Network) such as the Internet, and mobile communication networks such as LTE (Long Term Evolution), 4G (4th Generation), and 5G (5th Generation: 5th generation mobile communication system).

[0062] The terminal device 10, the operator device 20, and the advertiser device 40 are connected to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or wireless LAN (Local Area Network), and can communicate with other devices such as the service providing device 30, the cooperating device 50, and the information processing device 100 through the network N.

[0063] The terminal device 10 is used by a service user U of various online services provided by the service providing device 30. Each of the multiple terminal devices 10 is used by a different service user U.

[0064] The operator device 20 is used by an operator OP who receives persona information from the information processing device 100.

[0065] The service providing device 30 provides various online services to the service user U. For example, the online services provided to the service user U may include a search service, a travel information providing service, a social networking service (SNS), an e-commerce service, an electronic payment service, an online game, an online banking service, an online trading service, a hotel reservation service, a ticket reservation service, a video distribution service, a music distribution service, a news distribution service, a map information service, a route search service, a route guidance service, a line information service, an operation information service, a weather information service, and a question service. The various online services may also include an API (Application Programming Interface) service corresponding to various applications.

[0066] The advertiser device 40 is used by a business entity Ad (see, for example, FIG. 4) that provides products and services to consumers and advertises its own products and services.

[0067] The coordinating device 50 coordinates first cluster information, which is information indicating attributes of a first cluster registered by an advertiser (Ad), with the information processing device 100. The coordinating device 50 includes a storage unit that is an area (also referred to as a "clean room") where access to registered data is restricted. The coordinating device 50 stores and manages the first cluster information in the storage unit.

[0068] The terminal device 10, the operator device 20, and the advertiser device 40 are, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, a tablet PC, or a wearable device. Examples of wearable devices include, but are not limited to, smart glasses and smart watches.

[0069] The service providing device 30, the cooperating device 50, and the information processing device 100 are typically server devices, but may be realized by a mainframe, a workstation, etc. Furthermore, when the service providing device 30, the cooperating device 50, and the information processing device 100 are realized by a server device, they may be realized by a single server device, or may be realized by a cloud system in which a plurality of server devices and a plurality of storage devices operate in cooperation with each other.

[0070] A service user U using a terminal device 10 can use various online services by operating the terminal device 10 to access the service providing device 30. For example, the terminal device 10 can display web content provided by the service providing device 30 using a web browser or an application. When the terminal device 10 receives control information for realizing information display processing from the service providing device 30 or the like, the terminal device 10 realizes the display processing in accordance with the control information.

[0071] An operator OP using the operator device 20 operates the operator device 20 to access the information processing device 100, and thereby uses persona information provided by the information processing device 100.

[0072] The business entity Ad that uses the advertiser device 40 operates the advertiser device 40 to access the coordinating device 50, thereby uploading the first cluster information to the coordinating device 50.

[0073] The information processing device 100 executes information processing according to the embodiment. Processing function units that the information processing device 100 has for realizing the information processing according to the embodiment will be described later.

[0074] [3. Equipment configuration] An example of the functional configuration of the information processing device 100 included in the information processing system SYS according to the embodiment will be described below with reference to Fig. 6. Fig. 6 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 6, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0075] (Communication unit 110) The communication unit 110 is realized by, for example, a communication module or a network interface card (NIC). The communication unit 110 is connected to a network N by wire or wirelessly. The information processing device 100 transmits and receives information to and from other devices such as the operator device 20, the service providing device 30, and the cooperating device 50 via the network N.

[0076] (Storage unit 120) The storage unit 120 stores, for example, programs and data used for control and calculation by the control unit 130. For example, the storage unit 120 is realized by 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. For example, the storage unit 120 has a user information DB 121, a cluster information DB 122, and a model DB 123. Note that the storage unit 120 is not particularly limited to the example shown in FIG. 6 and can store data necessary for executing the information processing according to the embodiment as appropriate.

[0077] (User information DB121) The user information DB 121 stores user information related to service users U of various online services. The user information stored in the user information DB 121 is acquired by the information processing device 100 from the service providing device 30. Fig. 7 is a diagram showing an example of user information stored in the user information DB 121 according to the embodiment.

[0078] 7, the user information stored in the user information DB 121 has multiple items such as a "user ID" item, a "personal information" item, a "search history" item, a "browsing history" item, a "purchase history" item, etc. These items in the user information are associated with each other.

[0079] The "User ID" field stores identification information for uniquely identifying the service user U. The "Personal Information" field stores the personal information of the service user U. The personal information includes information on demographic attributes (also referred to as "demographic attributes") such as name, age, gender, occupation, annual household income, place of residence, and type of housing, as well as information on psychological attributes (also referred to as "psychographic attributes") such as the service user U's interests and concerns, such as travel, clothing, cars, and religion, as well as lifestyle, thoughts, and ideological tendencies.

[0080] The "search history" item stores information on search queries used by the service user U in the past in online services with search functions, such as search services and travel information services.

[0081] The "browsing history" item stores information about content that the service user U has previously viewed in video distribution services, news distribution services, and the like.

[0082] The "purchase history" item stores information about transaction targets with which the service user U has previously conducted transactions in electronic commerce services, electronic payment services, and the like.

[0083] (Cluster information DB122) The cluster information DB 122 stores cluster information relating to clusters into which the service users U are classified. Fig. 8 is a diagram showing an example of cluster information stored in the cluster information DB 122 according to the embodiment.

[0084] 8, the cluster information stored in the cluster information DB 122 has multiple items such as an "identification information" item, multiple "classification element" items, and an "affiliated user" item. These items in the cluster information are associated with each other.

[0085] The "identification information" field stores unique identification information for each cluster. The "classification element" field stores values ​​corresponding to elements used to classify the service user U. When the service user U is classified based on the attributes of the service user U, the classification element field stores values ​​corresponding to the attributes. For example, a pattern such as classification item 1 = "age," classification item 2 = "gender," and classification item 3 = "annual household income" is conceivable. When the corresponding value is not a number, such as gender, it may be quantified by any method or vectorized using well-known existing technology (e.g., Word2Vec). When the service user U is classified using the results of a personality assessment questionnaire conducted using a test based on the "Big Five" personality analysis method, the classification element field stores values ​​corresponding to the five "Big Five" factors ("openness," "conscientiousness," "conscientiousness," "extraversion," and "neuroticism").

[0086] The "belonging user" field stores the user ID of a service user U who belongs to the corresponding cluster.

[0087] (Model DB123) The model DB 123 stores the trained models described above and model information corresponding to the generation AI. Fig. 9 is a diagram illustrating an example of model information stored in the model DB 123 according to the embodiment.

[0088] 9, the model information stored in the model DB 123 has a plurality of items such as a "model ID" item and a "model information" item. These items in the model information are associated with each other.

[0089] The "Model ID" field stores unique identification information for each model. The "Model Information" field stores information about the trained model. For example, if machine learning is performed using a neural network, the trained model information may include various information such as connection information about how nodes included in each of the multiple layers that make up the neural network are connected to each other, and connection coefficients that are multiplied by numerical values ​​input and output between connected nodes.

[0090] The trained models stored in model DB123 include a first trained model that has been trained through machine learning to output characteristic information indicating the personality traits of a service user U who is estimated to be likely to purchase a product when product information is input.

[0091] In addition, the trained models stored in model DB123 include a second trained model that has been trained through machine learning to output a higher score when characteristic information of a service user U who is likely to purchase the product to be processed is input, and the more similar the input characteristic information is to each other, the higher the score will be.

[0092] In addition, the trained models stored in model DB123 include a third trained model that has been trained through machine learning to output characteristic information indicating the personality traits of service user U who is estimated to be unlikely to purchase the product when product information is input.

[0093] In addition, the trained model stored in model DB123 includes a generation AI that has been trained to generate answers to input questions using product information, user information for the target cluster, and instruction information that instructs the generation of information that describes typical user profiles corresponding to multiple service users U belonging to the target cluster based on user characteristics including behavior and degree of interest in products.

[0094] (control unit 130) The control unit 130 is a controller, and is realized by a CPU (Central Processing Unit), MPU (Micro Processing Unit), etc., executing various programs (examples of "information processing programs") stored in a storage device inside the information processing device 100 using RAM as a working area.

[0095] Furthermore, the control unit 130 may be realized by an integrated circuit such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a general purpose graphic processing unit (GPGPU).

[0096] As shown in FIG. 6, the control unit 130 has an acquisition unit 131, a determination unit 132, a reception unit 133, a selection unit 134, a generation unit 135, and a provision unit 136, and each of these units realizes or executes the information processing functions and actions described below.

[0097] Note that control unit 130 may have an internal configuration divided into multiple processing units that realize or execute the information processing functions and actions described below. Furthermore, control unit 130 is not limited to the configuration shown in Fig. 6, and may have other configurations as long as they perform the information processing described below, and may have other functional units other than those shown in Fig. 6.

[0098] (Acquisition part 131) The acquisition unit 131 acquires user information about a plurality of service users U who use online services. The acquisition unit 131 can acquire the user information from the service providing device 30 via the communication unit 110. The acquisition unit 131 registers the acquired user information in the user information DB 121.

[0099] The acquiring unit 131 can acquire, as the user information, information that is not directly related to the product to be advertised. For example, the user information includes attribute information indicating the attributes of the service user U and behavior information regarding the behavior of the service user U.

[0100] The attribute information includes demographic attributes (also referred to as "demographic attributes") such as the service user U's personal information, such as name, age, gender, occupation, annual household income, and type of residence, as well as psychological attributes (also referred to as "psychographic attributes") such as the service user U's interests and lifestyle.

[0101] The behavioral information corresponds to information indicating the content of the behavior of the service user U in the online service. The information indicating the content of the behavior includes the history of the behavior in the online service, such as search history, browsing history, and purchase history.

[0102] Furthermore, the acquisition unit 131 can acquire, as the user information, information on the results of a personality assessment questionnaire administered to the service user U in order to determine the personality characteristics of the service user U. In this case, the personality assessment questionnaire is administered by the service providing device 30 in response to a request from the information processing device 100, but may also be administered by the information processing device 100. The personality assessment questionnaire can be administered by using a test based on an existing personality analysis method such as the "Big Five," for example.

[0103] The acquisition unit 131 also acquires first cluster information, which is information registered in an area where access to registered data is restricted and indicates attributes of a first cluster into which multiple customers are classified based on customer information about customers of the advertiser business Ad. The acquisition unit 131 can acquire the first cluster information from the linked device 50 via the communication unit 110. A customer of the advertiser business Ad is an example of a "first user." The customer information is an example of "first user information." The first cluster is an example of a "first user group."

[0104] The customer information is information that is not directly related to the product. For example, the customer information includes attribute information indicating the attributes of the customer and behavioral information regarding the customer's behavior, similar to the user information of the service user U in the embodiment described above. The customer information may also include information on the results of a personality assessment questionnaire administered to the customer to determine the customer's personality traits.

[0105] (Decision unit 132) The determination unit 132 determines multiple clusters that are different from each other by classifying multiple service users U based on the user information acquired by the acquisition unit 131. A cluster is an example of a "user group." The determination unit 132 registers cluster information about the multiple clusters in the cluster information DB 122.

[0106] Furthermore, when the determination unit 132 acquires attribute information indicating the attributes of the service users U as user information, for example, it can determine multiple clusters by classifying service users U with similar attributes into the same group. Note that the classification of the service users U can be performed using well-known techniques using existing algorithms such as "hierarchical clustering," "K-means algorithm," and "DB Scan." The determination of whether the attributes are similar or not may be performed based on the commonality of a specific attribute among the attributes of the service users U. For example, if at least one of specific attributes such as age, gender, family structure, annual income, interests, and lifestyle is common, it can be determined that the attributes are similar.

[0107] Furthermore, when the determination unit 132 acquires, for example, behavioral information of a service user U as user information, it generates multiple clusters by classifying service users U whose behavioral content is similar into the same group. The determination of whether the behavioral content is similar may be determined based on the judgment of an administrator of the information processing device 100, or may be performed using existing well-known technology. For example, the determination unit 132 converts text information corresponding to the behavioral content into a vector representation indicating features corresponding to the behavioral content using Word2Vec or the like. Then, the determination unit 132 compares the vector representations corresponding to the behavioral content with each other and calculates the similarity of the vector representations to determine whether the behavioral content is similar.

[0108] Furthermore, when the determination unit 132 acquires, for example, information on the results of a personality assessment questionnaire on the service user U as user information, the determination unit 132 classifies service users U with similar personality traits into the same group, thereby determining multiple clusters. The determination unit 132 can determine the similarity of personality traits based on whether the results of a personality analysis based on the questionnaire results are similar. For example, when a personality assessment questionnaire is conducted using a test based on the "Big Five" personality analysis method, the determination unit 132 classifies the personality traits of the service user U based on the five factors of the "Big Five," and determines whether the personality traits of the service user U are similar based on whether the classification results are similar.

[0109] (Reception Department 133) The reception unit 133 receives, from the operator OP, input of product information relating to the product to be provided to the service user U. The reception unit 133 can acquire the product information transmitted from the operator device 20 via the communication unit 110.

[0110] (Selection unit 134) When the receiving unit 133 receives input of product information, the selecting unit 134 selects a target cluster to be processed from among a plurality of clusters.

[0111] For example, the selection unit 134 may select a cluster designated by the operator OP as the target cluster. Specifically, the selection unit 134 transmits a request for selecting a target cluster to the operator device 20 via the communication unit 110. Then, upon receiving input of identification information for identifying a cluster from the operator OP via the communication unit 110, the selection unit 134 selects, as the target cluster, a cluster corresponding to the identification number designated by the operator OP from among the plurality of clusters stored in the cluster information DB 122.

[0112] Furthermore, the selection unit 134 may automatically select, from among a plurality of clusters, a cluster to which a service user U who is estimated to be highly likely to purchase the advertised product belongs as a target cluster.

[0113] For example, the selection unit 134 acquires a first trained model and a second trained model from the model DB 123. The selection unit 134 inputs the product information received by the reception unit 133 into the first trained model to acquire feature information corresponding to the target product (i.e., feature information corresponding to a service user U who is estimated to be highly likely to purchase the target product). The selection unit 134 selects one cluster from among multiple clusters and individually inputs the feature information of the multiple service users U belonging to the selected cluster and the feature information corresponding to the target product into the second trained model to acquire a score indicating the similarity of the feature information corresponding to the target product for each service user U belonging to the cluster. The selection unit 134 calculates the sum (or average) of the acquired scores, and identifies the cluster with the largest sum (or average) as the cluster most similar to the feature information corresponding to the target product. The selection unit 134 then selects the identified cluster as the target cluster.

[0114] Furthermore, the selection unit 134 may select, from among a plurality of clusters, a cluster to which a service user U who is estimated to have a low possibility of purchasing the advertised product belongs as a target cluster.

[0115] For example, the selection unit 134 acquires a second trained model and a third trained model from the model DB 123. The selection unit 134 inputs the product information received by the reception unit 133 into the third trained model to acquire feature information corresponding to the target product (i.e., feature information corresponding to a service user U who is estimated to have a low possibility of purchasing the target product). The selection unit 134 selects one cluster from among multiple clusters and individually inputs the feature information of the multiple service users U belonging to the selected cluster and the feature information corresponding to the target product into the second trained model to acquire a score indicating the similarity of the feature information corresponding to the target product for each service user U belonging to the cluster. The selection unit 134 calculates the sum (or average) of the acquired scores, and identifies the cluster with the largest sum (or average) as the cluster most similar to the feature information corresponding to the target product. The selection unit 134 then selects the identified cluster as the target cluster. This makes it possible to assist in understanding the personality traits of service users U who are unlikely to purchase a product.

[0116] Furthermore, the selection unit 134 selects, from among the plurality of second clusters, a second cluster having an attribute similar to the attribute of the first cluster as a target cluster to be processed.

[0117] The second cluster is a plurality of different clusters in which a plurality of service users U who are users of online services are classified based on user information about the plurality of service users U, based on the same predetermined conditions (for example, whether the attributes are similar) as those used to classify customer information.

[0118] Furthermore, the user information is information that has no direct relation to the product. For example, the user information includes attribute information indicating the attributes of the service user U and behavioral information regarding customer behavior, similar to the user information of the service user U according to the embodiment described above. The user information may also include information on the results of a personality assessment questionnaire administered to the service user U to determine the personality traits of the service user U.

[0119] Furthermore, the selection unit 134 may determine whether the attributes of the first cluster and the attributes of the second cluster are similar based on the commonality of a specific attribute. For example, when at least one of specific attributes such as age, sex, family structure, annual income, interests, and lifestyle corresponding to the second cluster is common to the attributes of the first cluster, the selection unit 134 can derive a determination result that the second cluster has attributes similar to the attributes of the first cluster.

[0120] In addition, the selection unit 134 may determine whether the attributes of the first cluster and the attributes of the second cluster are similar by determining whether the content of the behavior corresponding to the first cluster and the content of the behavior corresponding to the second cluster are similar.

[0121] Specifically, the selection unit 134 converts text information corresponding to the content of the action corresponding to the first cluster and text information corresponding to the content of the action corresponding to the second cluster into vector expressions indicating features corresponding to the content of the action, for example, using Word2Vec. Then, the selection unit 134 compares the vector expressions corresponding to the content of the action corresponding to the first cluster with the vector expressions corresponding to the content of the action corresponding to the second cluster, and determines whether the content of the actions is similar by calculating the similarity of the vector expressions. If the selection unit 134 determines that the content of the actions is similar, it can derive a determination result that the second cluster has attributes similar to the attributes of the first cluster.

[0122] In addition, the selection unit 134 may determine whether the attributes of the first cluster and the attributes of the second cluster are similar by determining whether the personality characteristics of the customers belonging to the first cluster are similar to the personality characteristics of the service users U belonging to the second cluster.

[0123] Specifically, for example, when a personality diagnostic questionnaire is administered to customers and service users U using a test based on the "Big Five" personality analysis method, the selection unit 134 classifies the personality traits of customers belonging to the first cluster and the personality traits of service users U belonging to the second cluster based on the five factors of the "Big Five." Furthermore, the selection unit 134 determines whether the personality traits of customers belonging to the first cluster are similar to the personality traits of service users U belonging to the second cluster based on whether the classification results are similar. Then, when the selection unit 134 determines that the personality traits of customers belonging to the first cluster are similar to the personality traits of service users U belonging to the second cluster, it can derive a determination result that the second cluster has attributes similar to the attributes of the first cluster.

[0124] (Generation unit 135) After selecting the target cluster, the generation unit 135 uses product information and user information of service users U belonging to the target cluster to generate persona information, which is information that indicates a typical user profile corresponding to multiple service users U belonging to the target cluster.

[0125] The generation unit 135 can generate persona information, for example, by inputting product information received by the reception unit 133, user information of the target cluster, and instruction information that instructs the generation of information that describes typical user profiles corresponding to multiple service users U belonging to the target cluster based on user characteristics including behavior and degree of interest in the product, to a generation AI that has been trained to generate answers to input questions.

[0126] The generation unit 135 can generate persona information using a generation AI such as a transfer-based model or an RNN-based model, which is a language model trained to estimate and output the next token from an input token sequence.

[0127] Furthermore, the generation unit 135 can use, for example, "GPT" or "BARD" as a transfer-based model, but is not limited to such examples.

[0128] The generation unit 135 may use, for example, "RWKV" as an RNN-based model, but is not limited to this example. It is desirable that the generation AI conceals input information, such as personal information, by learning the model so that the input information is not used as a new answer.

[0129] Furthermore, the generation unit 135 can use a multimodal AI that generates images from text or generates text from images as a generation AI for generating persona information. The generation unit 135 can use, for example, "GPT-4-Trubo," "GPT-4V," "CM3Leon," "Stable Diffusion," or the like as the multimodal AI, but is not limited to these examples.

[0130] For example, the generation unit 135 can input to the generation AI an instruction sentence instructing the generation of text information describing a representative user image of multiple users belonging to the target cluster, using product information about the product to be advertised and user information about users belonging to the target cluster, as well as the results of a personality assessment questionnaire, a user profile, and affinity with the product. The generation unit 135 can also input an instruction sentence instructing the generation of image information showing a representative user image of multiple users belonging to the target cluster, using the user information about the users belonging to the target cluster. The generation unit 135 can then generate persona information by arranging the text information and image information output from the generation AI according to a predetermined template.

[0131] (Provider 136) The providing unit 136 provides the persona information generated by the generating unit 135 to the operator OP. The providing unit 136 can provide the persona information to the operator OP by transmitting the persona information to the operator device 20 via the communication unit 110.

[0132] 4. Processing Procedure According to the Embodiment (4-1. Information Processing Procedures (Part 1)) The following describes the procedure of information processing executed by the information processing device 100 according to the embodiment. First, the procedure (part 1) of information processing executed by the information processing device 100 according to the embodiment will be described with reference to Fig. 10. Fig. 10 is a flowchart showing an example of the procedure (part 1) of information processing executed by the information processing device 100 according to the embodiment. The processing procedure shown in Fig. 10 is executed by the control unit 130 of the information processing device 100. The processing procedure shown in Fig. 10 is repeatedly executed while the information processing device 100 is operating.

[0133] As shown in FIG. 10, the reception unit 133 receives product information from an operator OP (step S101).

[0134] Furthermore, the selection unit 134 selects, from among the plurality of clusters, a target cluster that is estimated to have a high possibility of purchasing a product corresponding to the product information received from the operator OP (step S102).

[0135] Furthermore, the generation unit 135 generates persona information indicating a typical user profile of the service user U belonging to the target cluster, using the product information and the user information of the service user U belonging to the target cluster (Step S103).

[0136] Furthermore, the providing unit 136 provides the persona information to the operator OP by transmitting the persona information to the operator device 20 (step S104), and the processing procedure shown in FIG. 10 ends.

[0137] (4-2. Information Processing Procedures (Part 2)) Next, the information processing procedure (part 2) executed by the information processing device 100 according to the embodiment will be described with reference to Fig. 11. Fig. 11 is a flowchart showing an example of the information processing procedure (part 2) executed by the information processing device 100 according to the embodiment. The processing procedure shown in Fig. 11 is executed by the control unit 130 of the information processing device 100. The processing procedure shown in Fig. 11 is repeatedly executed while the information processing device 100 is operating.

[0138] As shown in FIG. 11, the reception unit 133 receives product information from an operator OP (step S201).

[0139] Furthermore, the selection unit 134 selects, from among the plurality of clusters, a target cluster that is estimated to have a low possibility of purchasing the product corresponding to the product information received from the operator OP (step S202).

[0140] Furthermore, the generation unit 135 generates persona information indicating a typical user profile of the service user U belonging to the target cluster, using the product information and the user information of the service user U belonging to the target cluster (step S203).

[0141] Furthermore, the providing unit 136 provides the persona information to the operator OP by transmitting the persona information to the operator device 20 (step S204), and the processing procedure shown in FIG. 11 ends.

[0142] (4-3. Information Processing Procedures (Part 3)) Next, the information processing procedure (part 3) executed by the information processing device 100 according to the embodiment will be described with reference to Fig. 12. Fig. 12 is a flowchart showing an example of the information processing procedure (part 3) executed by the information processing device 100 according to the embodiment. The processing procedure shown in Fig. 12 is executed by the control unit 130 of the information processing device 100. The processing procedure shown in Fig. 12 is repeatedly executed while the information processing device 100 is operating.

[0143] As shown in FIG. 12, the reception unit 133 receives product information from an operator OP (step S301).

[0144] The acquiring unit 131 also acquires first cluster information from the cooperating device 50 (step S302). The selecting unit 134 also selects, from the plurality of pieces of second cluster information, a second cluster having an attribute similar to an attribute of the first cluster as a target cluster to be processed (step S303).

[0145] Furthermore, the generation unit 135 generates persona information indicating a typical user profile of multiple service users U belonging to the target cluster, using the product information and the user information of the service users U belonging to the target cluster (step S304).

[0146] Furthermore, the providing unit 136 provides the persona information to the operator OP by transmitting the persona information to the operator device 20 (step S305), and the processing procedure shown in FIG. 12 ends.

[0147] [5. Modifications] In the above-described information processing, an example has been described in which the generation unit 135 generates persona information using product information and user information belonging to a target cluster, but the present invention is not limited to such an example. The generation unit 135 may generate persona information indicating a typical user profile corresponding to the service user U belonging to each of the plurality of clusters determined by the determination unit 132, using the user information of the service user U belonging to the cluster.

[0148] Furthermore, as described above, when the generation unit 135 generates a plurality of pieces of persona information in advance, the provision unit 136 may identify, from the plurality of pieces of persona information generated by the generation unit 135, persona information that has a high affinity with the target product corresponding to the product information received by the reception unit 133, and provide the identified persona information to the operator OP. The determination of whether or not the affinity is high can be realized using the first trained model and the second trained model described in the above embodiment.

[0149] For example, the providing unit 136 inputs product information into the first trained model, thereby acquiring feature information corresponding to the target product output from the first trained model (i.e., feature information corresponding to a service user U who is estimated to be highly likely to purchase the target product).The providing unit 136 then selects one persona from among the multiple personas, and inputs the feature information of the selected persona and the feature information corresponding to the target product into the second trained model described above, thereby acquiring a score indicating the similarity between the feature information of the persona and the feature information corresponding to the target product.The providing unit 136 acquires scores for all personas, and identifies the persona with the highest score as the persona with the highest affinity with the target product.

[0150] Furthermore, in the above-described other information processing, an example in which the advertiser device 40 determines the first cluster has been described, but the present invention is not limited to such an example. For example, the coordinating device 50 may determine the first cluster. In this case, the advertiser device 40 transmits customer information to the coordinating device 50. The coordinating device 50 determines multiple first clusters by classifying multiple customers based on the customer information. Then, the coordinating device 50 registers first cluster information indicating attributes of the first cluster for each of the determined multiple first clusters in a clean room or the like. Furthermore, the coordinating device 50 may accept in advance from the advertiser business Ad, which is the advertiser, designation of the first cluster information to be provided to the information processing device 100, or may transmit an inquiry about the first cluster to be provided to the information processing device 100 when receiving a request from the information processing device 100 requesting acquisition of first cluster information.

[0151] Furthermore, in the other information processing described above, a plurality of pieces of first cluster information may be provided from the coordinating device 50 to the information processing device 100. In this case, the information processing device 100 uses each of the plurality of pieces of first cluster information acquired from the coordinating device 50 to individually select, as target clusters, second clusters having attributes similar to the attributes of the first clusters, and generates persona information for each selected target cluster in the same manner as the method described above.

[0152] [6. Hardware Configuration] Moreover, the information processing device 100 according to the above-described embodiment and each modified example is realized, for example, by a computer 1000 configured as shown in Fig. 13. Fig. 13 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100 according to the embodiment and each modified example.

[0153] The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected by a bus 1090.

[0154] The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device, such as a RAM, that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), HDD, flash memory, or the like.

[0155] The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a monitor or a printer, and is realized by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (High Definition Multimedia Interface), etc. The input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, and scanner, and is realized by, for example, USB.

[0156] The input device 1020 may be a device that reads information from an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. The input device 1020 may also be an external storage medium such as a USB memory.

[0157] The network IF 1080 receives data from other devices via the network N and sends it to the arithmetic device 1030, and also transmits data generated by the arithmetic device 1030 to other devices via the network N.

[0158] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0159] For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the arithmetic device 1030 of the computer 1000 executes a program (for example, an information processing program) loaded onto the primary storage device 1040, thereby realizing the same functions as the control unit 130. That is, the arithmetic device 1030 cooperates with the program (for example, an information processing program) loaded onto the primary storage device 1040 to realize the processing by the information processing device 100 according to the embodiment.

[0160] [7. Other] Of 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 a known method. 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.

[0161] Furthermore, the components of each device shown in the figure are conceptual functional components and do 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.

[0162] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0163] The above describes in detail the embodiments of the present application based on several drawings, but these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have been modified and improved in various ways based on the knowledge of those skilled in the art.

[0164] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, a control section can be read as control means or a control circuit.

[0165] [8. Effects] The information processing device 100 according to the embodiment includes a receiving unit 133, an acquiring unit 131, a selecting unit 134, a generating unit 135, and a providing unit 136. The receiving unit 133 accepts input of product information related to a product from an operator OP. The acquiring unit 131 acquires first cluster information, which is information registered in an area where access to registered data is restricted and indicates attributes of a first cluster into which customers are classified based on customer information about customers of a business that advertises the product. The selecting unit 134 selects, as a target cluster to be processed, a second cluster having attributes similar to the attributes of the first cluster indicated in the first cluster information from among multiple different second clusters into which multiple service users are classified based on the same predetermined conditions used to classify customers, using user information about multiple service users who use online services. The generating unit 135 generates persona information, which is information indicating typical user profiles corresponding to multiple service users belonging to the target cluster, using the product information and user information about service users belonging to the target cluster. The providing unit 136 provides the persona information generated by the generating unit 135 to the operator.

[0166] As described above, the information processing device 100 according to the embodiment has the above-described characteristic configuration, and can provide the operator OP with persona information related to the customers of the advertiser Ad by, for example, expanding the first cluster into which customers of the advertiser Ad are classified to the second cluster into which service users of the online service are classified. The operator OP can create a report on the advertisement delivery logic based on the persona information and use it in sales activities for the advertisement strategy of the advertiser Ad. In this way, the information processing device 100 shown in FIG. 1 can support an efficient approach to the consumer demographic that is the target of the advertisement.

[0167] Furthermore, the customer information and user information include information that is not directly related to the product, which allows the information processing device 100 to perform processing using general-purpose clusters obtained by classifying multiple service users U based on information that is not related to the product.

[0168] Furthermore, the customer information includes information indicating the attributes of the customer, and the user information includes information indicating the attributes of the service user U. This allows the information processing device 100 to perform processing using general-purpose clusters obtained by classifying multiple service users U based on attribute information unrelated to products.

[0169] Furthermore, the customer information includes information on the results of a personality assessment questionnaire administered to the customer to determine the customer's personality traits, and the user information includes information on the results of a personality assessment questionnaire administered to the service user U to determine the service user U's personality traits. This allows the information processing device 100 to perform processing using general-purpose clusters obtained by classifying the service user U based on behavioral information unrelated to products.

[0170] Furthermore, the generation unit 135 generates persona information by inputting, to the generation AI trained to generate answers to input questions, product information, user information of service users U belonging to the target cluster, and instruction information instructing the generation AI to generate information describing typical user profiles of multiple service users U belonging to the target cluster based on user characteristics including behavior and degree of interest in products using the product information and the user information of service users U belonging to the target cluster. This enables the information processing device 100 to provide the operator OP with information showing a user profile with information appropriately summarized.

[0171] Furthermore, the above-described effects can also be realized by the processing executed by each of the above-described units, or by any combination of the processing executed by each unit. [Explanation of symbols]

[0172] SYS Information Processing System SYS-1 Information Processing System SYS-2 Information Processing System N Network 10 Terminal Equipment 20 Operator device 30 Service providing device 40 Advertiser Equipment 50 Linkage Device 100 Information processing device 110 Communications Department 120 Storage section 121 User information DB 122 Cluster Information DB 123 Model DB 130 Control Unit 131 Acquisition Department 132 Decision Section 133 Reception Department 134 Selection Section 135 Generation part 136 Provision Department

Claims

1. a reception unit that receives input of product information relating to the product from an operator; an acquisition unit that acquires cluster information indicating attributes of a first cluster into which the customer is classified based on customer information about the customer of the business that is the advertiser of the product, the cluster information being registered in an area where access to registered data is restricted; a selection unit that selects, as a target cluster to be processed, a second cluster having an attribute similar to an attribute of the first cluster indicated in the cluster information from a plurality of different second clusters into which the service users who are users of an online service are classified based on the same predetermined conditions as those used to classify the customers, using user information on the plurality of service users; a generation unit that generates persona information, which is information indicating a typical user profile corresponding to a plurality of service users belonging to the target cluster, using the product information and the user information of the service users belonging to the target cluster; a providing unit that provides the persona information generated by the generating unit to the operator; An information processing device comprising:

2. The customer information and the user information are Contains information that is not directly related to the product 2. The information processing apparatus according to claim 1, wherein:

3. The customer information is information indicating attributes of the customer; The user information is Including information indicating the attributes of the service user 3. The information processing apparatus according to claim 2, wherein:

4. The customer information is The information includes the result of a personality assessment questionnaire administered to the customer to determine the customer's personality characteristics, The user information is Including information on the results of a personality test questionnaire administered to the service user to determine the character traits of the service user 3. The information processing apparatus according to claim 2, wherein:

5. The generation unit The persona information is generated by inputting the product information, the user information of the service users belonging to the target cluster, and instruction information for instructing generation of information describing typical user images corresponding to the plurality of service users belonging to the target cluster based on user characteristics including behavior and degree of interest in the product using the product information and the user information of the service users belonging to the target cluster to a generation AI that has been trained to generate answers to input questions.

5. The information processing device according to claim 1, wherein:

6. 1. A computer-implemented information processing method, comprising: a receiving step of receiving input of product information relating to the product from an operator; an acquisition step of acquiring cluster information indicating attributes of a first cluster into which the customer is classified based on customer information about the customer of the business that is the advertiser of the product, the cluster information being registered in an area where access to registered data is restricted; a selection step of selecting, as a target cluster to be processed, from a plurality of different second clusters into which the service users are classified based on the same predetermined conditions as those used to classify the customers, using user information on the plurality of service users who are users of the online service, the second cluster having an attribute similar to an attribute of the first cluster indicated in the cluster information; a generation step of generating persona information, which is information indicating a typical user profile corresponding to a plurality of service users belonging to the target cluster, using the product information and the user information of the service users belonging to the target cluster; a providing step of providing the persona information generated by the generating step to the operator; An information processing method comprising:

7. On the computer, a receiving procedure for receiving input of product information about the product from an operator; an acquisition step of acquiring cluster information indicating attributes of a first cluster into which the customer is classified based on customer information about the customer of the business that is the advertiser of the product, the cluster information being registered in an area where access to registered data is restricted; a selection step of selecting, as a target cluster to be processed, from a plurality of different second clusters into which the service users are classified based on the same predetermined conditions as those used to classify the customers, using user information on the plurality of service users who are users of the online service, the second cluster having an attribute similar to an attribute of the first cluster indicated in the cluster information; a generation step of generating persona information, which is information indicating a typical user profile corresponding to a plurality of service users belonging to the target cluster, using the product information and the user information of the service users belonging to the target cluster; a providing step of providing the persona information generated by the generating step to the operator; An information processing program characterized by causing the program to execute the above.

Images