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

Abstract

To support selection of a delivery destination of content such as an advertisement.SOLUTION: An information processing apparatus according to the present application includes a setting unit, a selection unit, a scoring unit, an extraction unit, and a provision unit. The setting unit sets a condition of a user to be classified into a user group from input data input by an operator. The selection unit selects the analysis target group for each condition based on the attribute of the user corresponding to each condition. The scoring unit scores, for each condition, each user satisfying the condition based on the behavior history of each user corresponding to the condition. The extraction unit extracts a visible layer user having a higher score than other users based on the scoring result. The provision unit specifies information related to a characteristic behavior of the overt layer user from a comparison result between the behavior information of the overt layer user and the behavior information of the comparison target user, and provides the operator with the specified information related to the characteristic behavior and attribute information indicating an attribute corresponding to the overt layer user.SELECTED DRAWING: Figure 11

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] Conventionally, various technologies related to the distribution of content such as advertisements have been provided. For example, a technology related to an advertising campaign (reservation-based advertising) that distributes advertisements based on conditions such as budget, period, and target audience has been proposed (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6621954 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional technologies have room for improvement in supporting the selection of destinations for content such as advertisements. For example, while it is desirable to appropriately select destinations for advertisements, selecting destinations is not necessarily easy due to various factors such as implementation costs, delivery track record, and advertiser requests.

[0005] The present application has been made in view of the above, and aims to realize support for selecting a distribution destination for content such as advertisements. [Means for solving the problem]

[0006] The information processing device according to the present application includes a setting unit, a selection unit, a scoring unit, an extraction unit, and a providing unit. The setting unit sets conditions for classifying users into user groups based on input data entered by an operator. The selection unit selects an analysis target group for each condition based on the attributes of the users corresponding to each condition. The scoring unit scores each user who matches each condition based on the behavioral history of each user corresponding to each condition. The extraction unit extracts apparent layer users in the analysis target group who have higher scores than other users in the analysis target group based on the scoring results by the scoring unit. The providing unit selects comparison target users from the analysis target group to be compared with the apparent layer users, identifies information on characteristic behaviors of the apparent layer users based on the comparison results between the behavioral information of the apparent layer users and the behavioral information of the comparison target users, and provides the identified information on characteristic behaviors and attribute information indicating attributes corresponding to the apparent layer users to a terminal device used by the operator by transmitting the information to the operator. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to assist in the selection of a distribution destination for content such as advertisements. [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 specifically illustrating an overview of information processing according to the embodiment. [Figure 3] FIG. 3 is a diagram specifically illustrating an overview of information processing according to the embodiment. [Figure 4] FIG. 4 is a diagram specifically illustrating an overview of information processing according to the embodiment. [Figure 5] FIG. 5 is a diagram specifically illustrating an overview of information processing according to the embodiment. [Figure 6] FIG. 6 is a diagram specifically illustrating an overview of information processing according to the embodiment. [Figure 7] FIG. 7 is a diagram specifically illustrating an overview of information processing according to the embodiment. [Figure 8] FIG. 8 is a diagram specifically illustrating an overview of information processing according to the embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of proposal information according to the embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of the system configuration of an information processing system according to the embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of the configuration of an information processing device according to the embodiment. [Figure 12] FIG. 12 is a diagram illustrating an outline of user information stored in the user information storage unit according to the embodiment. [Figure 13] FIG. 13 is a diagram illustrating an outline of the behavior history stored in the behavior history storage unit according to the embodiment. [Figure 14] FIG. 14 is a flowchart illustrating an example of the procedure of information processing executed by the information processing device according to the embodiment. [Figure 15] FIG. 15 is a hardware configuration diagram showing 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. 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] The information processing according to the embodiment is realized by an information processing system SYS (see, for example, FIG. 10) including the terminal device 10 shown in FIG. 1 and the information processing device 100 shown in FIG. 1. The terminal device 10 and the information processing device 100 are each connected to a network N (see, for example, FIG. 10) by wire or wirelessly. The terminal device 10 and the information processing device 100 can communicate with other devices through the network N.

[0012] 1, the terminal device 10 transmits input data of an operator OP to the information processing device 100. The operator OP inputs a URL and a prompt for determining a delivery destination (target) of content such as a predetermined advertisement, for example, through a predetermined tool displayed on the terminal device 10 as a user interface.

[0013] When the information processing device 100 receives input data input by an operator OP from the terminal device 10, it sets conditions for users to be classified into user groups from the input data (step S01). If it is assumed that user groups are created from the input data, the user conditions are information that can become audience categories for categorizing each user. By inputting the input data into a generation AI (Artificial Intelligence), the information processing device 100 can set information output from the generation AI as the user conditions. The information processing device 100 can use a text generation AI, which is a language model capable of generating sentences using natural language processing, as the generation AI.

[0014] Furthermore, the information processing device 100 selects a group to be analyzed for each set user condition based on the user attributes corresponding to each condition (step S02). For example, the information processing device 100 can use a generation AI to convert each condition into any of the attribute information indicating the attributes of service users of the online service, thereby acquiring the user attributes corresponding to each condition, and select a group to be analyzed based on the acquired attributes.

[0015] Furthermore, the information processing device 100 scores each user belonging to the analysis target group for each condition based on the behavior history of each user corresponding to each condition (step S03). For example, the information processing device 100 can use a generation AI to acquire information on search queries that each user corresponding to each condition is likely to search for, and score each user based on the acquired search query information.

[0016] Furthermore, the information processing device 100 extracts potential users who have higher scores than other users in the analysis target group based on the scoring results (step S04).

[0017] In addition, the information processing device 100 selects a comparison target user from the analysis target group to be compared with the apparent layer user, and identifies information regarding the characteristic behavior of the apparent layer user from the comparison results between the behavioral history of the apparent layer user and the behavioral history of the comparison target user (step S05).

[0018] Then, the information processing device 100 provides information regarding the characteristic behavior of the identified apparent layer users and attribute information indicating the attributes corresponding to the apparent layer users to the terminal device 10 used by the operator OP.

[0019] An outline of the information processing according to the embodiment will be specifically described below with reference to Fig. 2 to Fig. 8. Fig. 2 to Fig. 8 are diagrams for specifically describing an outline of the information processing according to the embodiment.

[0020] As shown in FIG. 2, the operator OP specifies as input data a URL (+summary) corresponding to a web page such as a product introduction page or a review page that contains information about the product being advertised, or a prompt for identifying users to whom the advertisement will be delivered (step S1-1).

[0021] The summary entered along with the URL specified as input data is information summarizing the content of the web page corresponding to the URL. The prompt is instruction information that instructs the generation AI to extract conditions for classifying users into user groups from the input data.

[0022] The information processing device 100 executes extraction of user conditions by inputting a URL designated by the operator OP as input data or a prompt to the generation AI (step S1-2).

[0023] The processing when a URL is acquired as input data will be specifically described. The information processing device 100 inputs the URL acquired as input data and the summary acquired together with the URL to the generation AI. The generation AI analyzes the content of the web page corresponding to the URL in accordance with the viewpoints described in the summary, extracts conditions for users who are interested in the products and services posted on the web page (e.g., users who are likely to purchase the products and services) without omission or duplication, and outputs the extracted conditions. At this time, the generation AI outputs a weight for each extracted condition indicating whether the extracted condition contributes to a typical user profile of a user who is interested in the products and services posted on the web page. The information processing device 100 acquires the user conditions output from the generation AI. FIG. 5 shows an example of user conditions extracted from a URL according to the embodiment.

[0024] As shown in Figure 5, if the product listed on the webpage corresponding to the URL is a "facial beauty device," the generation AI analyzes the content of the webpage according to the input summary: "This is an introduction page for a facial beauty device called XX." The generation AI then extracts multiple conditions for users interested in "facial beauty devices," such as "people who are interested in beauty appliances and skin care" and "people over 40 years old."

[0025] A specific description will be given of processing when a prompt is acquired as input data. An example of a prompt according to the embodiment is shown in Fig. 6. For example, the information processing device 100 inputs prompt Pro1-1 and prompt Pro1-2 shown in Fig. 6 to the generation AI.

[0026] For example, if "users who are likely to listen to live classical music streaming" is set in prompt Pro1-1 shown in Figure 6, the generation AI will, in accordance with prompt Pro1-1 and prompt Pro1-2, extract multiple conditions from an existing database that can be referenced, such as "age: 25-50 years old" and "user of music streaming service," without omission or duplication, as conditions for users who are likely to listen to live classical music streaming, and output the extracted conditions.

[0027] Returning to FIG. 2, when the information processing device 100 acquires the user's conditions, it inputs the acquired conditions and a prompt to the generation AI. The generation AI converts each condition into one of the attribute information indicating the attributes of the service user of the online service held by the information processing device 100 according to the input prompt (step S1-3). The service user's attributes include demographic attributes such as age, gender, and annual income, and psychographic attributes such as interests, purchasing intentions, and lifestyle. FIG. 7 shows an example of the prompt and attribute information converted by the generation AI according to the embodiment.

[0028] The information processing device 100 inputs prompt Pro2-1 and prompt Pro2-2 as shown in Fig. 7 to the generation AI. The generation AI converts the user's conditions set in prompt Pro2-1 into attribute information included in a predetermined attribute group, such as an age group or lifestyle, according to the format specified by prompt Pro2-2. For example, according to Fig. 7, the generation AI converts the user's condition "Age: 25-50 years old" shown in Fig. 2 into attribute information for the corresponding age groups of "Over 30" and "Under 50 years old."

[0029] 2, the information processing device 100 converts the user's conditions into attribute information, and then uses the converted attribute information to select a group to be analyzed (step S1-4). The information processing device 100 generates attribute information and any combination of attribute information, and can select a group to be analyzed from the generated combination. For example, the information processing device 100 generates a combination of the conditions of age and gender from the attribute information and any one of psychographic attributes such as interests, purchasing intentions, and lifestyle, and selects a group to be analyzed from the generated combination of attributes.

[0030] After selecting the analysis target group, the information processing device 100 extracts a base query (hereinafter referred to as a "base query") as appropriate, as shown in FIG. 3 (step S2-1). Specifically, the information processing device 100 uses a generation AI to acquire a query that is likely to be searched by a user and that is likely to match the user's conditions. FIG. 8 shows an example of a prompt according to the embodiment and a base query extracted by the generation AI.

[0031] The information processing device 100 inputs prompt Pro3-1 and prompt Pro3-2 as shown in Fig. 8 to the generation AI. The generation AI lists queries that users who are likely to match the user conditions set in prompt Pro3-1 are likely to search for, in accordance with the format specified by prompt Pro3-2. If "user of music distribution service" is set as the user condition in prompt Pro3-1 shown in Fig. 8, the generation AI lists, from an existing database that can be referenced, search keywords such as "You&Me Music," "recital," and "ticket" as keywords that users who match the user of the music distribution service are likely to search for, in accordance with prompt Pro3-1 and prompt Pro3-2.

[0032] Returning to FIG. 3, after extracting the base query, the information processing device 100 converts the extracted base query into an actual query (hereinafter referred to as an "actual query") that has been used by a service user of the online service (step S2-2). Specifically, the information processing device 100 attempts to convert the base query by referring to the search history of the service user in the online service and extracting an actual query that partially matches the base query. The information processing device 100 eliminates noise by narrowing down the extracted actual queries to queries that are searched by more than a certain number of users.

[0033] After converting the base query into an actual query, the information processing device 100 performs scoring for the user to be analyzed (step S2-3). Specifically, the information processing device 100 refers to the search history of each user to be analyzed, and adds "1" to the score corresponding to the condition for the user to be analyzed for the number of actual queries with search history in a predetermined period of time in the past. Next, the information processing device 100 standardizes the score of each user to be analyzed for each condition, and multiplies the score by a weight corresponding to each condition. Then, the information processing device 100 derives the score of the user to be analyzed by adding up the scores corresponding to each condition for each user to be analyzed.

[0034] After scoring the users to be analyzed, the information processing device 100 extracts apparent layer users from the users to be analyzed (step S3-1), as shown in Fig. 4. Specifically, the information processing device 100 extracts users who have higher scores than other users in the group to be analyzed (for example, a predetermined number of users with the highest scores) as apparent layer users. The information processing device 100 assumes that the extracted apparent layer users are users to be analyzed who meet the conditions.

[0035] After extracting the apparent layer users, the information processing device 100 identifies queries that are characteristically searched by the apparent layer users and URLs that are visited by the apparent layer users (step S3-2).

[0036] Specifically, the information processing device 100 selects comparison users from the analysis target group to be compared with the apparent layer users. For example, the information processing device 100 selects, from the analysis target users, users whose attribute information and search counts match those of the apparent layer users as comparison target users. Next, the information processing device 100 compares the search history and browsing history of the apparent layer users with the search history and browsing history of the comparison target users. Then, based on the comparison results between the search history and browsing history of the apparent layer users and the search history and browsing history of the comparison target users, the information processing device 100 identifies queries searched more frequently by apparent layer users than by the comparison target users and URLs visited more frequently by apparent layer users than by the comparison target users.

[0037] The information processing device 100 also calculates the distinctiveness of the identified query and URL. For example, the information processing device 100 divides the search rate of the query among apparent users by the search rate of the query among comparison users, and calculates a value indicating how likely the query is to be searched by apparent users compared to comparison users as the distinctiveness. For example, if the search rate among apparent users is "10%" and the search rate among comparison users is "1%, the distinctiveness is "10". Using a similar procedure, the information processing device 100 can calculate the distinctiveness of a URL.

[0038] The information processing device 100 transmits the identified characteristic query and URL information and attribute information indicating attributes corresponding to the apparent layer users to the terminal device 10, thereby providing the information to the operator OP. FIG. 9 is a diagram showing an example of suggested information according to the embodiment. For example, when the information processing device 100 receives a prompt from the operator OP in which "users likely to listen to classical music in live streaming" is set, the information processing device 100 provides suggested information such as the example shown in FIG. 9 as "users likely to listen to classical music in live streaming."

[0039] As described above, the information processing device 100 according to the embodiment can provide the operator OP with suggested information for identifying a user corresponding to a URL or a prompt, in accordance with the URL or the prompt specified by the operator OP, thereby assisting in the selection of a distribution destination for content such as an advertisement.

[0040] The operator OP creates user segments by any method using the characteristic query and URL information received from the information processing device 100 by specifying a URL or a prompt (step S3-3). For example, the operator OP can set segment extraction conditions by referring to the proposed information exemplified in FIG. 9 and create user segments corresponding to each extraction condition. For example, the operator OP can extract a user segment of an UPPER tier that extracts users corresponding to specific attribute information from all service users, a user segment of a MIDDLE tier that classifies users from all service users who correspond to specific attribute information and have search history for queries with a characteristic score of 1.5 or more or have browsed web pages corresponding to URLs with a characteristic score of 1.5 or more, or a user segment of a LOWER tier that classifies users from all service users who correspond to specific attribute information and have search history for queries with a characteristic score of 2.0 or more or have browsed web pages corresponding to URLs with a characteristic score of 2.0 or more.

[0041] [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. 10. Fig. 10 is a diagram showing an example of the system configuration of the information processing system SYS according to the embodiment.

[0042] 10, the information processing system SYS according to the embodiment includes a terminal device 10 and an information processing device 100. Note that Fig. 10 merely illustrates an example of the configuration of the information processing system SYS according to the embodiment, and the information processing system SYS may include multiple terminal devices 10.

[0043] The terminal device 10 and the information processing device 100 are connected to a network N by wire or wirelessly. Each of the terminal device 10 and the information processing device 100 can communicate with other devices via the network N.

[0044] The network N includes, for example, a WAN (Wide Area Network) such as the Internet, and a mobile communication network such as LTE (Long Term Evolution), 4G (4th Generation), or 5G (5th Generation: fifth generation mobile communication system).

[0045] The terminal device 10 is connected to a network N by 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 information processing device 100 through the network N.

[0046] The terminal device 10 is used by an operator OP. The operator OP may be an advertisement distributor that proposes advertisement distribution to an advertiser that submits advertisement information to the information processing device 100 and requests advertisement distribution, or the advertiser itself. The terminal device 10 may be, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, or a tablet PC.

[0047] The operator OP operates the terminal device 10 to access the information processing device 100 using an API (Application Programming Interface) provided by a service provider that manages the information processing device 100, and inputs a URL and a prompt for determining a delivery destination (target) of predetermined content such as an advertisement through a predetermined tool displayed on the terminal device 10 as a user interface. The predetermined tool may be a dedicated application program (hereinafter referred to as a "dedicated app") equipped with various functions for setting a URL and a prompt, or may be a predetermined website that can be displayed by a web browser.

[0048] Furthermore, the terminal device 10 can display content provided from the information processing device 100, for example, using a dedicated application or a web browser. When the terminal device 10 receives control information for realizing information display processing from the information processing device 100, the terminal device 10 realizes the display processing in accordance with the control information.

[0049] The control information is written in, for example, a script language such as JavaScript (registered trademark), a style sheet language such as CSS (Cascading Style Sheets), a programming language such as Java (registered trademark), a markup language such as HTML (HyperText Markup Language), etc. Note that a predetermined application itself delivered from the information processing device 100 or the like may be regarded as control information.

[0050] The information processing device 100 is operated and managed by an advertisement distribution company that provides proposal information related to advertisement distribution from an advertiser. The advertisement distribution company may be a service provider that provides various online services to service users.

[0051] The various online services may include, for example, news sites, search services, travel information services, SNS (Social Networking Services), e-commerce services, electronic payment services, online games, online banking services, online trading services, hotel reservation services, ticket reservation services, video distribution services, music distribution services, map information services, route search services, route guidance services, line information services, operation information services, weather information services, question services, etc. The various online services may also include API (Application Programming Interface) services corresponding to various applications.

[0052] The information processing device 100 is typically a server device, but may also be realized by a mainframe, a workstation, etc. Furthermore, when the information processing device 100 is realized by a server device, it may be realized by a single server device, or may be realized by a cloud system in which multiple server devices and multiple storage devices operate in cooperation with each other.

[0053] [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. 11. Fig. 11 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 11, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0054] (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 terminal device 10 via the network N.

[0055] (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 storage unit 121, a behavior history storage unit 122, and a model information storage unit 123. Note that the storage unit 120 is not particularly limited to the example shown in FIG. 11 and can store data and the like required for executing the information processing according to the embodiment as appropriate.

[0056] (User information storage unit 121) The user information storage unit 121 stores user information related to service users of various online services. Fig. 12 is a diagram showing an overview of the user information stored in the user information storage unit 121 according to the embodiment.

[0057] 12, the user information stored in the user information storage unit 121 has a plurality of items such as a "user ID" item, an "age" item, a "gender" item, an "interests" item, a "purchase intention" item, and a "lifestyle" item. These items in the user information are associated with each other.

[0058] The "User ID" field stores identification information for identifying service users of various online services. The "Age" field stores information indicating the age of the service user. The "Gender" field stores information indicating the gender of the service user.

[0059] The "Interests" field stores information indicating the interests of the service user. The "Purchase Intentions" field stores information indicating the purchase intentions of the service user. The "Lifestyles" field stores information indicating the lifestyles of the service user.

[0060] The user information stored in the user information storage unit 121 may include, in addition to the information shown in FIG. 12, information on the demographic attributes of the service user, such as educational background, occupation, annual income, and place of residence.

[0061] (Behavioral history storage unit 122) The behavior history storage unit 122 stores behavior history, which is information indicating various behaviors of service users in various online services. Fig. 13 is a diagram showing an overview of the behavior history stored in the behavior history storage unit 122 according to the embodiment.

[0062] 13, the behavior history stored in the behavior history storage unit 122 has multiple items such as a "user ID" item, a "search history" item, a "browsing history" item, etc. These items in the behavior history are associated with each other.

[0063] The "User ID" field stores identification information for identifying service users of various online services. The "Search History" field stores information such as the queries (search keywords) used by service users to search various online services and the search date and time. The "Browsing History" field stores information such as the URLs of websites viewed by service users on various online services and the date and time of viewing.

[0064] (Model information storage unit 123) The model information storage unit 123 stores information about a model that executes information processing according to the embodiment. The information about the model stored in the model information storage unit 123 includes information about a generation AI that has been trained to generate answers to input questions, and is used to extract user conditions (see, for example, FIGS. 5 and 6), convert each condition into attribute information (see, for example, FIG. 7), and extract a base query that a user is likely to search for corresponding to each condition (see, for example, FIG. 8).

[0065] Generative AI is realized by AI (Artificial Intelligence) such as GPT (Generative Pre-trained Transformer). GPT is a text generation AI, a language model that can generate sentences using natural language processing.

[0066] (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.

[0067] 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).

[0068] As shown in FIG. 11, the control unit 130 has a setting unit 131, a selection unit 132, a scoring unit 133, an extraction unit 134, and a provision unit 135, and each of these units realizes or executes the information processing functions and actions described below.

[0069] 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. Also, control unit 130 is not limited to the configuration shown in Fig. 11, 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. 11.

[0070] (Setting unit 131) The setting unit 131 sets conditions for users to be classified into user groups from input data entered by an operator. Specifically, the setting unit 131 executes extraction of user conditions by inputting a URL or a prompt specified by the operator OP as input data to the generation AI.

[0071] For example, when the setting unit 131 receives a URL and summary information summarizing the information of the website corresponding to the URL as input data from an operator OP, the setting unit 131 inputs the URL and summary information to a first generation AI that has been trained to generate answers to input questions, and sets the information output from the first generation AI (see, for example, Figure 5) as a condition.

[0072] Also, for example, when the setting unit 131 receives a prompt as input data from an operator OP, it sets the information output from the first generation AI (for example, see Figure 6) as a condition by inputting information of an instruction sentence that instructs the first generation AI, which has been trained to generate answers to input questions, to generate conditions for each user (analysis target user) belonging to the analysis target group.

[0073] (Selection Department 132) The selection unit 132 selects a group to be analyzed for each condition set by the setting unit 131, based on the attributes of the users corresponding to each condition.

[0074] Specifically, the selection unit 132 acquires attribute information (see, for example, Figure 7) output from the second generation AI by inputting an instruction sentence to the second generation AI, which has been trained to generate answers to input questions, instructing it to convert the conditions set by the setting unit 131 into any of the attribute information indicating the attributes of service users of the online service, and selects a group to be analyzed based on the acquired attribute information.

[0075] For example, the selection unit 132 can generate a group to be analyzed based on attribute information and any combination of attribute information. For example, the information processing device 100 generates a combination of the attribute information, such as age and gender conditions, and any one of psychographic attributes such as interests, purchasing intentions, and lifestyles, and selects a group to be analyzed from the generated combination of attributes.

[0076] (Scoring Section 133) The scoring unit 133 scores each user who meets the conditions for each condition based on the behavioral history of each user corresponding to each condition. Specifically, by inputting an instruction sentence to the third generation AI, which has been trained to generate answers to input questions, instructing the third generation AI to list base queries that are queries that each user who meets the conditions is likely to search for, the scoring unit 133 acquires information on the base queries output from the third generation AI, and scores each user who meets the conditions based on the acquired information on the base queries.

[0077] For example, after extracting a base query, the scoring unit 133 converts the extracted base query into an actual query that has been used by a service user of the online service (hereinafter referred to as an "actual query") as appropriate. Specifically, the scoring unit 133 attempts to convert the base query by referring to the search history of the service user in the online service and extracting actual queries that partially match the base query. Note that the scoring unit 133 eliminates noise by narrowing down the extracted actual queries to queries that are searched by more than a certain number of users.

[0078] Furthermore, after converting the base query into an actual query, the scoring unit 133 performs scoring for the user to be analyzed. Specifically, the scoring unit 133 refers to the search history of each user to be analyzed, and adds "1" to the score corresponding to the condition for the user to be analyzed for the number of actual queries with search history in a predetermined period of time in the past. Next, the scoring unit 133 standardizes the score of the user to be analyzed for each condition and multiplies it by a weight corresponding to each condition. Then, the scoring unit 133 derives the score of the user to be analyzed by adding up the scores corresponding to each condition for each user to be analyzed.

[0079] (Extraction part 134) The extraction unit 134 extracts apparent layer users who have higher scores than other users in the analysis target group based on the scoring result by the scoring unit 133. Specifically, the extraction unit 134 extracts users who have higher scores than other users in the analysis target group (for example, a predetermined number of users with higher scores) as apparent layer users. The extraction unit 134 assumes that the extracted apparent layer users are analysis target users who meet the conditions.

[0080] (Provider 135) The provision unit 135 selects a comparison user from the analysis target group to be compared with the apparent layer user, identifies information regarding the characteristic behavior of the apparent layer user from the comparison results between the behavioral history of the apparent layer user and the behavioral history of the comparison target user, and provides the identified information regarding the characteristic behavior and attribute information indicating attributes corresponding to the apparent layer user to the terminal device 10 used by the operator OP.

[0081] Specifically, the providing unit 135 selects, from among the users to be analyzed, users whose attribute information (demographic attributes and psychographic attributes) and search count (number of times a search keyword is entered in an online service) match those of the apparent layer users as comparison users. Next, the providing unit 135 compares the search history and browsing history of the apparent layer users with the search history and browsing history of the comparison user. Then, from the comparison result between the search history and browsing history of the apparent layer users and the search history and browsing history of the comparison user, the providing unit 135 identifies queries that are more frequently searched by apparent layer users than the comparison user and URLs that are more frequently visited by apparent layer users than the comparison user.

[0082] The providing unit 135 also calculates the distinctiveness of the identified query and URL. For example, the providing unit 135 divides the search rate of the query among apparent users by the search rate of the query among comparison target users, and calculates a value indicating how likely the query is to be searched by apparent users compared to comparison target users as the distinctiveness. For example, if the search rate among apparent users is "10%" and the search rate among comparison target users is "1%, the distinctiveness is "10". Using a similar procedure, the information processing device 100 can calculate the distinctiveness of a URL.

[0083] In addition, after calculating the characteristic degree, the providing unit 135 provides the operator OP with information on the identified characteristic query and URL, and attribute information indicating the attributes corresponding to the apparent layer users, by transmitting it to the terminal device 10 via the communication unit 110.

[0084] 4. Processing Procedure According to the Embodiment The following describes the procedure of information processing executed by the information processing device 100 according to the embodiment. Fig. 14 is a flowchart showing an example of the procedure of information processing executed by the information processing device 100 according to the embodiment. The procedure of processing shown in Fig. 14 is executed by the control unit 130 of the information processing device 100. The procedure of processing shown in Fig. 14 is repeatedly executed while the information processing device 100 is operating.

[0085] As shown in FIG. 14, the setting unit 131 sets conditions for users to be classified into user groups from input data input by an operator (step S101).

[0086] Furthermore, the selection unit 132 selects a group to be analyzed for each condition based on the attributes of the users corresponding to each condition (step S102).

[0087] Furthermore, for each condition, the scoring unit 133 scores each user who matches the condition based on the behavior history of each user corresponding to the condition (step S103).

[0088] Furthermore, the extraction unit 134 extracts potential users who have higher scores than other users in the analysis target group based on the scoring result by the scoring unit 133 (step S104).

[0089] In addition, the providing unit 135 selects a comparison target user from the analysis target group to be compared with the apparent layer user, identifies information regarding the characteristic behavior of the apparent layer user from the comparison result between the behavioral information of the apparent layer user and the behavioral information of the comparison target user, and provides the identified information regarding the characteristic behavior and attribute information indicating the attributes corresponding to the apparent layer user to the terminal device 10 used by the operator by transmitting the information to the operator (step S105), and then terminates the processing procedure shown in Figure 11.

[0090] [5. Hardware Configuration] The information processing device 100 according to the above-described embodiment and each of the modified examples is realized, for example, by a computer 1000 having a configuration as shown in Fig. 15. Fig. 15 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] [6. Other] In the above embodiment, the information processing device 100 may use the proposal information to generate proposed segment information for proposing user segments and provide the generated proposed segment information to the operator OP. For example, the providing unit 135 may generate, for example, a user segment for the upper tier, a user segment for the middle tier, and a user segment for the lower tier according to preset segment extraction conditions. For example, the segment conditions may be overlapping conditions so that target users are narrowed down from the upper tier to the lower tier. Furthermore, the segment extraction conditions may be received from the operator OP or may be default settings in the system. Only specific attribute information may be set, and the providing unit 135 may provide information about the generated user segments to the operator OP by transmitting it as proposed segment information to the terminal device 10 via the communication unit 110.

[0099] 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.

[0100] 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.

[0101] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0102] 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.

[0103] 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.

[0104] [7. Effects] The information processing device 100 according to the embodiment includes a setting unit 131, a selection unit 132, a scoring unit 133, an extraction unit 134, and a providing unit 135. The setting unit 131 sets conditions for users to be classified into user groups from input data entered by an operator OP. The selection unit 132 selects an analysis target group for each condition based on the attributes of users corresponding to each condition. The scoring unit 133 scores each user who matches the condition based on the behavioral history of each user corresponding to each condition. The extraction unit 134 extracts potential users who have higher scores than other users in the analysis target group based on the scoring results by the scoring unit 133. The provision unit 135 selects a comparison user from the analysis target group to be compared with the apparent layer user, identifies information regarding the characteristic behavior of the apparent layer user from the comparison result between the behavioral information of the apparent layer user and the behavioral information of the comparison target user, and provides the information regarding the identified characteristic behavior and attribute information indicating attributes corresponding to the apparent layer user to the terminal device 10 used by the operator OP.

[0105] In addition, the setting unit 131 sets the information output from the generation AI as a condition by inputting a URL and summary information that summarizes the information on the website corresponding to the URL as input data to the generation AI, which has been trained to generate answers to input questions.

[0106] In addition, the setting unit 131 sets the information output from the generation AI as conditions by inputting information of instruction sentences that instruct the generation AI, which has been trained to generate answers to input questions, to generate conditions for each user belonging to the group to be analyzed.

[0107] In addition, the selection unit 132 acquires attribute information output from the generation AI by inputting an instruction sentence to the generation AI, which has been trained to generate answers to input questions, instructing it to convert the conditions into any of the attribute information indicating the attributes of service users of the online service, and selects a group to be analyzed based on the acquired attribute information.

[0108] In addition, the scoring unit 133 acquires query information output from the generation AI by inputting an instruction sentence to the generation AI, which has been trained to generate answers to input questions, instructing it to list queries that each user corresponding to the group to be analyzed is likely to search for, and scores each user belonging to the group to be analyzed based on the acquired query information.

[0109] In addition, the providing unit 135 identifies queries that are more frequently searched by the apparent layer users than the comparison user and URLs that are more frequently visited by the apparent layer users than the comparison user based on the comparison results between the search history and browsing history of the apparent layer users and the search history and browsing history of the comparison user.

[0110] For this reason, the information processing device 100 according to the embodiment can provide the operator OP with suggested information for identifying a user corresponding to a URL or a prompt, in accordance with the URL or the prompt specified by the operator OP, thereby assisting in the selection of a distribution destination for content such as an advertisement.

[0111] 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]

[0112] SYS Information Processing System N Network 10 Terminal Equipment 100 Information processing device 110 Communications Department 120 Storage section 121 User information storage unit 122 Action History Memory Unit 123 Model information storage unit 130 Control Unit 131 Setting section 132 Selection Department 133 Scoring Department 134 Extraction part 135 Provision Department

Claims

1. a setting unit that sets conditions for classifying users into user groups based on input data input by an operator; a selection unit that selects an analysis target group for each of the conditions based on the attributes of users corresponding to each of the conditions; a scoring unit that scores each user who meets each of the conditions based on a behavior history of each user corresponding to each of the conditions; an extraction unit that extracts potential users who have higher scores than other users in the analysis target group based on the scoring result by the scoring unit; a provision unit that selects a comparison target user from the analysis target group to be compared with the apparent layer user, identifies information on characteristic behavior of the apparent layer user from the comparison result between the behavior information of the apparent layer user and the behavior information of the comparison target user, and provides the identified information on the characteristic behavior and attribute information indicating the attributes corresponding to the apparent layer user to the terminal device used by the operator, thereby providing the information to the operator; An information processing device comprising:

2. The setting unit The information output from the generation AI is set as the condition by inputting, as input data, a URL and summary information summarizing information on the website corresponding to the URL to the generation AI that has been trained to generate an answer to an input question.

2. The information processing apparatus according to claim 1, wherein:

3. The setting unit By inputting information about instruction sentences instructing a generation AI that has been trained to generate answers to input questions to generate conditions for each user belonging to the analysis target group, the information output from the generation AI is set as the conditions.

2. The information processing apparatus according to claim 1, wherein:

4. The selection unit By inputting an instruction sentence to the generation AI that has been trained to generate answers to input questions, instructing the AI ​​to convert the conditions into any of the attribute information indicating the attributes of service users of the online service, the attribute information output from the generation AI is acquired, and the analysis target group is selected based on the acquired attribute information.

4. The information processing device according to claim 1, wherein the information processing device is a computer.

5. The scoring unit By inputting an instruction sentence to the generation AI that has been trained to generate answers to input questions, instructing the AI ​​to list queries that each user corresponding to the group to be analyzed is likely to search, information on the queries output from the generation AI is acquired, and each user belonging to the group to be analyzed is scored based on the acquired information on the queries.

5. The information processing apparatus according to claim 4,

6. The providing unit From the comparison results between the search history and browsing history of the apparent user and the search history and browsing history of the comparison target user, queries searched more frequently by the apparent user than by the comparison target user and URLs visited more frequently by the apparent user than by the comparison target user are identified.

6. The information processing apparatus according to claim 5,

7. An information processing method carried out by a computer, comprising: a setting step of setting conditions for users to be classified into user groups based on input data input by an operator; a selection step of selecting an analysis target group for each of the conditions based on the attributes of users corresponding to each of the conditions; a scoring step of scoring each user who meets each of the conditions based on the behavior history of each user corresponding to each of the conditions; an extraction step of extracting potential users who have higher scores than other users in the analysis target group based on the scoring result obtained by the scoring step; a provision process of selecting a comparison target user to be compared with the apparent layer user from the analysis target group, identifying information on characteristic behavior of the apparent layer user from the comparison result between the behavior information of the apparent layer user and the behavior information of the comparison target user, and transmitting the identified information on the characteristic behavior and attribute information indicating the attributes corresponding to the apparent layer user to a terminal device used by the operator, thereby providing the information to the operator; An information processing method comprising:

8. On the computer, a setting procedure for setting conditions for classifying users into user groups based on input data entered by an operator; a selection step of selecting a group to be analyzed for each of the conditions based on the attributes of users corresponding to each of the conditions; a scoring procedure for scoring each user who meets each of the conditions based on the behavioral history of each user corresponding to each of the conditions; an extraction step of extracting potential users who have higher scores than other users in the analysis target group based on the scoring result of the scoring step; a provision step of selecting a comparison target user to be compared with the apparent layer user from the analysis target group, identifying information on characteristic behavior of the apparent layer user from the comparison result between the behavior information of the apparent layer user and the behavior information of the comparison target user, and transmitting the identified information on the characteristic behavior and attribute information indicating the attributes corresponding to the apparent layer user to a terminal device used by the operator, thereby providing the information to the operator; An information processing program characterized by causing the program to execute the above.

Images