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

Abstract

To provide an information processor, an information processing method, and an information processing program capable of effectively supporting content provision.SOLUTION: An information processing device according to the present application includes an estimation unit that estimates a sense of values of each user of a user group satisfying a predetermined user condition, a specification unit that specifies a search query having a high affinity with a sense of values satisfying a predetermined sense-of-values condition among the estimated senses of values among search queries input in the past, and a provision unit that provides content based on the specified search query.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] 2. Description of the Related Art Conventionally, techniques have become widespread that assist content providers in providing optimal content to users based on information obtained from the users. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-21469 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the prior art has room for improvement in terms of providing more effective support for content provision.

[0005] The present application has been made in view of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can provide effective support for content provision. [Means for solving the problem]

[0006] The information processing device of the present application includes an estimation unit that estimates the values ​​held by each user of a user group that satisfies specified user conditions, an identification unit that identifies, from among previously input search queries, search queries that have a high affinity with values ​​that satisfy the specified value conditions among the estimated values, and a provision unit that provides content based on the identified search queries. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to provide effective support for content provision. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing a process executed by an information processing apparatus according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of user information. [Figure 5] FIG. 5 is a diagram illustrating an example of value information. [Figure 6] FIG. 6 is a diagram illustrating an example of query information. [Figure 7] FIG. 7 is a diagram illustrating an example of model information. [Figure 8] FIG. 8 is a diagram for explaining a calculation method of the lift value calculated by the specification unit. [Figure 9] FIG. 9 is a diagram showing the content generated by the generation unit. [Figure 10] FIG. 10 is a diagram showing the content generated by the generation unit. [Figure 11] FIG. 11 is a diagram showing the content generated by the generation unit. [Figure 12] FIG. 12 is a diagram showing the content generated by the generation unit. [Figure 13] FIG. 13 is a flowchart illustrating the processing procedure executed by the information processing apparatus according to the embodiment. [Figure 14] FIG. 14 is a diagram illustrating an example of a hardware configuration. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, 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 same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0010] (Embodiment) First, the process executed by the information processing device according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing the process executed by the information processing device according to the embodiment. In the following, an example will be given in which the information processing device 1 provides content relating to measures for an advertisement distributor to distribute advertisements to users. Note that Fig. 1 shows an example of the operation of an information processing system S including the information processing device 1 according to the embodiment.

[0011] As shown in FIG. 1, an information processing system S according to the embodiment includes an information processing device 1, an advertisement distributor terminal 50, a user terminal 100, and a service providing device 200.

[0012] As shown in Figure 1, the information processing system S according to the embodiment estimates the values ​​held by each user in a user group that satisfies specified user conditions, identifies search queries entered in the past that have a high affinity with the estimated values ​​that satisfy the specified value conditions, and provides content based on the identified search queries.

[0013] Specifically, first, a user who owns the user terminal 100 uses a service provided by the service providing device 200 via the user terminal 100 (step S1). The services provided by the service providing device 200 are, for example, online sites such as Q&A sites, news sites, EC (Electronic Commerce) sites, map sites, image posting sites, video viewing sites, etc., but are not limited to these examples. EC sites are, for example, shopping sites, auction sites, etc., but are not limited to these examples.

[0014] The service providing device 200 accepts posted content, which is content posted by each user on the Q&A site, and provides the posted content to each user. On the Q&A site, the posted content includes question content, which is a question text, answer content, which is an answer text to the question text, and the like.

[0015] Furthermore, the service providing device 200 accepts news articles as posted content at a news site and provides the posted content to each user. At a news site, the posted content includes not only the news article but also comments and ratings posted on the news article.

[0016] Furthermore, the service providing device 200 accepts product content, such as product descriptions that introduce products from sellers, as posted content on the EC site, and provides the posted content to each user. Furthermore, the posted content on the EC site includes not only the product content but also comments and ratings posted on the products.

[0017] Furthermore, the service providing device 200 accepts image content (e.g., still image content and video content) as posted content at an image posting site and provides the posted content to each user. Furthermore, the service providing device 200 accepts titles and caption texts of video content at a video viewing site as posted content and provides the posted content to each user.

[0018] Furthermore, the service providing device 200 accepts a location or area specification from the user U on the map site and provides map content showing a map of the location or area specified by the user. The map content includes various information such as roads, various landmarks, various stores, routes, and stations.

[0019] Next, the service providing device 200 provides log information, which is a log of the user's behavior when using the service, to the information processing device 1 (step S2). For example, the service providing device 200 provides the user's behavior on the online site provided as log information. Specifically, the service providing device 200 provides log information including browsing behavior, posting behavior, and Q&A search behavior on the Q&A site.

[0020] The service providing device 200 also provides log information including browsing behavior, posting behavior, and news search behavior on news sites. The service providing device 200 also provides log information including browsing behavior, posting behavior, purchasing behavior, and product search behavior on e-commerce sites. The service providing device 200 also provides log information including browsing behavior, posting behavior, and image search behavior on image posting sites. The service providing device 200 also provides log information including location and area specification behavior and location and area search behavior on map sites.

[0021] Next, the information processing device 1 sets a user group that satisfies a predetermined user condition based on the log information (step S3). For example, the information processing device 1 sets a user group that has performed a predetermined behavior on an online site provided by the service providing device 200 as a user group that satisfies the predetermined user condition. The predetermined behavior is, for example, a behavior related to content specified by an advertisement distributor.

[0022] For example, the information processing device 1 sets a group of users who have performed browsing behavior or posting behavior related to specified content on a news site as a group of users who satisfy a predetermined user condition. The information processing device 1 also sets a group of users who have performed browsing behavior or posting behavior related to specified content on a Q&A site as a group of users who satisfy a predetermined user condition. The information processing device 1 also sets a group of users who have performed browsing behavior, posting behavior, or purchasing behavior related to specified content on an EC site as a group of users who satisfy a predetermined user condition. The information processing device 1 also sets a group of users who have performed browsing behavior or posting behavior related to specified content on an image posting site as a group of users who satisfy a predetermined user condition. The information processing device 1 also sets a group of users who have performed specified behavior or posting behavior related to specified content on a map site as a group of users who satisfy a predetermined user condition.

[0023] Next, the information processing device 1 estimates the values ​​held by each user in the set user group (step S4). The values ​​are, for example, values ​​classified as freedom, equality, philanthropy, and peace, but are not limited to these examples and may be, for example, values ​​classified as traditionalism, success-oriented, self-actualization-oriented, and symbiosis-oriented, or other values. For example, if the object is a car, the values ​​may be classified as safety-oriented, livability-oriented, design-oriented, and driving performance-oriented. If the object is a house, the values ​​may be classified as location-oriented, price-oriented, layout-oriented, design-oriented, and future prospects-oriented. Furthermore, the values ​​may be values ​​based on Schwartz's value theory, in which case the values ​​are classified as power, achievement, hedonism, excitement, self-determination, universalism, philanthropy, tradition, harmony, and safety.

[0024] The information processing device 1 generates estimated content for a predetermined set of values ​​(character strings), based on the content likely to be viewed by a user who holds the values. The estimated content can be generated, for example, by using a generation AI and inputting a prompt containing information about the values ​​and the content. The information processing device 1 then assigns a score for each value to each piece of content to be viewed in advance, based on the similarity between the content and the estimated content. The similarity may be, for example, a vector similarity (cosine similarity, Jaccard similarity, etc.) of vectorized content (e.g., embedding using a language model, Doc2Vec, word embedding, etc.). For example, the information processing device 1 sets a score for each value for each user based on the score for each value assigned to the content viewed by the user. For example, the information processing device 1 sums up the scores for each value in a group of content viewed by the user and calculates the score normalized by the number of content groups as the score for each value (hereinafter referred to as the value score).

[0025] Next, the information processing device 1 identifies values ​​that satisfy a predetermined value condition from among the estimated values ​​(step S5). For example, the information processing device 1 calculates a lift value that indicates the likelihood of a value being held by a user group based on the estimated values ​​of each user, and identifies values ​​whose lift value is equal to or greater than a threshold (or less than the threshold) as values ​​that satisfy the predetermined value condition. Details of the method for calculating the lift value will be described later with reference to FIG. 8. Furthermore, hereinafter, values ​​whose lift value is equal to or greater than a threshold will be referred to as positive values, and values ​​whose lift value is less than the threshold will be referred to as negative values. Note that the distinction between positive values ​​and negative values ​​is not limited to using a simple threshold. For example, when a first user group and a second user group exist, values ​​whose lift value for the first user group is higher than that of the second user group (and the difference is equal to or greater than a predetermined threshold) may be defined as positive values. Furthermore, values ​​whose lift value for the first user group is lower than that of the second user group (and the difference is equal to or greater than a predetermined threshold) may be defined as negative values.

[0026] Next, the information processing device 1 identifies search queries that have a high affinity with the identified values ​​(positive values ​​and negative values) from among previously input search queries (step S6). For example, the information processing device 1 vectorizes the search query and the values ​​using Word2Vec or the like, and identifies search queries and values ​​with high vector similarity (above a threshold) using cosine similarity or the like as having a high affinity. The information processing device 1 may also use a generation AI to inquire whether the affinity between the search query and the values ​​is high. Note that the search query is, for example, a search query input on a search site, but is not limited to this, and may also be, for example, a search query input in various search behaviors included in log information.

[0027] Next, the information processing device 1 generates content based on the identified search query (step S7), and provides the generated content to the advertisement distributor terminal 50 (step S8).

[0028] For example, the information processing device 1 provides the advertisement distributor with information on search queries that have a high affinity with both positive and negative values. Furthermore, the information processing device 1 extracts search queries that have a high affinity with positive values ​​(or negative values) and for which the number of users who have entered the search query in a user group is less than a threshold (or greater than or equal to a threshold), and provides information on the extracted search queries to the advertisement distributor. This allows the advertisement distributor to accurately determine distribution strategies for search query-linked advertisement distribution (such as when to distribute an advertisement for which search query).

[0029] Furthermore, the information processing device 1 may provide the content generated by the generation AI to the advertisement distributor using the specified or extracted search query as a prompt. Details of this point will be described later with reference to FIGS. 9 to 12.

[0030] In this way, the information processing device 1 according to the embodiment can provide content (for example, advertising distribution measures, etc.) based on a search query that has a high affinity with the user's values ​​to the advertisement distributor. This allows the advertisement distributor to distribute advertisements that match the user's values. In other words, the information processing device 1 according to the embodiment can provide effective support for content provision to the advertisement distributor, etc.

[0031] Next, a configuration example of an information processing system S according to an embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing a configuration example of the information processing system S according to an embodiment. As shown in Fig. 2, in the information processing system S according to an embodiment, an information processing device 1, a plurality of advertisement distributor terminals 50, a plurality of user terminals 100, and a service providing device 200 are connected to a network N by wire or wirelessly. The network N is, for example, a network such as the Internet, a WAN (Wide Area Network), or a LAN (Local Area Network).

[0032] The information processing device 1 is a server device that executes an information processing method according to an embodiment. The information processing device 1 estimates the values ​​held by each user of a user group that satisfies predetermined user conditions, identifies search queries that have a high affinity with the estimated values ​​that satisfy the predetermined value conditions from among previously input search queries, and provides content based on the identified search queries.

[0033] In addition, the information processing device 1 is an information processing device that cooperates with multiple advertisement distributor terminals 50, multiple user terminals 100, and service providing device 200, and provides API (Application Programming Interface) services for various applications (hereinafter, apps), etc., and various data to the multiple advertisement distributor terminals 50, multiple user terminals 100, and service providing device 200, and is realized by a server device, a cloud system, etc.

[0034] Furthermore, the information processing device 1 may be an information processing device that provides some kind of online web service to a plurality of advertisement distributor terminals 50, a plurality of user terminals 100, and the service providing device 200. For example, the information processing device 1 may provide services such as internet connection, search service, SNS (Social Networking Service), electronic commerce (EC), electronic payment, online games, online banking, online trading, hotel and ticket reservations, video and music distribution, news, maps, route search, route guidance, line information, operation information, and weather forecasts as the web services. In practice, the information processing device 1 may cooperate with various servers that provide the above-mentioned web services and act as an intermediary for the web services or may be responsible for processing the web services.

[0035] The advertisement distributor terminal 50 is a terminal device managed by a distributor that distributes advertisements to users. The advertisement distributor terminal 50 can be any type of terminal device, such as a smartphone, a desktop PC, a notebook PC, or a tablet PC. The advertisement distributor terminal 50 transmits various types of information to the information processing device 1, etc., and receives information provided by the information processing device 1, etc.

[0036] The user terminal 100 is a terminal device owned by a user who uses a service provided by the service providing device 200. The user terminal 100 can be any type of terminal device, such as a smartphone, a desktop PC, a notebook PC, or a tablet PC. The user terminal 100 transmits various types of information to the information processing device 1 or the like, and receives information provided by the information processing device 1 or the like.

[0037] The service providing device 200 is an information processing device that provides various services to users. The service providing device 200 is realized by a server device, a cloud system, or the like.

[0038] Next, an example of the configuration of the information processing device 1 will be described with reference to FIG.

[0039] Fig. 3 is a diagram showing an example of the configuration of an information processing device 1 according to an embodiment. As shown in Fig. 3, the information processing device 1 has a communication unit 2, a control unit 3, and a storage unit 4. The control unit 3 includes an acquisition unit 31, a setting unit 32, an estimation unit 33, an identification unit 34, a generation unit 35, and a provision unit 36. The storage unit 4 stores user information 41, value information 42, query information 43, and model information 44.

[0040] The communication unit 2 is realized by, for example, a network interface card (NIC), etc. The communication unit 2 is connected to a network by wire or wirelessly.

[0041] The control unit 3 is a controller, and is realized by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 1 using a RAM or the like as a work area. The control unit 3 is also a controller, and may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a GPGPU (General Purpose Graphic Processing Unit).

[0042] The storage unit 4 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk.

[0043] The user information 41 is information about the user.

[0044] Fig. 4 is a diagram showing an example of the user information 41. As shown in Fig. 4, the user information 41 includes items such as "user ID," "attribute information," and "behavior history."

[0045] "User ID" is identification information that identifies a user. "Attribute information" is information about a user's attributes. Attribute information includes, for example, psychographic attributes and demographic attributes. "Behavioral history" is information about a user's behavioral history, such as search behavior, purchasing behavior, and posting behavior.

[0046] The value information 42 is information including estimated content that is used by the estimation unit 33, which will be described later, to estimate values.

[0047] Fig. 5 is a diagram showing an example of the value information 42. As shown in Fig. 5, the value information 42 includes items such as "value ID", "name", and "estimated content".

[0048] "Value ID" is identification information that identifies each value. "Name" is a name (character string) that indicates a value. For example, names include freedom, equality, philanthropy, peace, traditionalism, success-oriented, self-actualization-oriented, coexistence-oriented, safety-oriented, livability-oriented, design-oriented, drivability-oriented, location-oriented, price-oriented, layout-oriented, design-oriented, future prospects-oriented, power, achievement, hedonism, stimulation, self-determination, universalism, philanthropy, tradition, harmony, and safety. "Presumed content" is content that is likely to be viewed by users with certain values, such as content generated by a generation AI.

[0049] The query information 43 is information about search queries previously entered by the user.

[0050] Fig. 6 is a diagram showing an example of the query information 43. As shown in Fig. 6, the query information 43 includes items such as "query ID," "query content," "input date and time," and "input user."

[0051] "Query ID" is identification information that identifies each search query. "Query content" is the word (character string) that becomes the search query. "Input date and time" is information about the date and time when the search query was input. "Input user" is information about the user who input the search query, and for example, the user ID in the user information 41 described above is input.

[0052] The model information 44 is information including a model of a generation AI used by the generation unit 35 (described later) to generate content.

[0053] Fig. 7 is a diagram showing an example of the model information 44. As shown in Fig. 7, the model information 44 includes items such as "model ID," "output content," and "model parameters."

[0054] "Model ID" is identification information that identifies each model. "Output content" is information that indicates the content output by the model, and details will be described later with reference to Figures 9 to 12. "Model parameters" are weight values ​​and the like used in the neural network and deep learning algorithm that make up the model.

[0055] Next, each function (acquisition unit 31, setting unit 32, estimation unit 33, identification unit 34, generation unit 35, and provision unit 36) of the control unit 3 of the information processing device 1 will be described.

[0056] The acquisition unit 31 acquires various types of information. For example, the acquisition unit 31 acquires log information from the service providing device 200. The acquisition unit 31 also acquires log information of a search query from a search server (not shown).

[0057] The setting unit 32 sets a user group that satisfies a predetermined user condition based on the information acquired by the acquisition unit 31. For example, the setting unit 32 sets a user group that satisfies the predetermined user condition based on log information. For example, the setting unit 32 sets a user group that has performed a predetermined behavior on an online site provided by the service providing device 200 as a user group that satisfies the predetermined user condition. The predetermined behavior is, for example, behavior related to content specified by an advertisement distributor.

[0058] For example, the setting unit 32 sets a user group that has performed browsing behavior or posting behavior related to specified content on a news site as a user group that satisfies a predetermined user condition. The setting unit 32 also sets a user group that has performed browsing behavior or posting behavior related to specified content on a Q&A site as a user group that satisfies a predetermined user condition. The setting unit 32 also sets a user group that has performed browsing behavior, posting behavior, or purchasing behavior related to specified content on an EC site as a user group that satisfies a predetermined user condition. The setting unit 32 also sets a user group that has performed browsing behavior or posting behavior related to specified content on an image posting site as a user group that satisfies a predetermined user condition. The setting unit 32 also sets a user group that has performed specified behavior or posting behavior related to specified content on a map site as a user group that satisfies a predetermined user condition.

[0059] The estimation unit 33 estimates the values ​​held by each user in the set user group. The values ​​are, for example, values ​​classified as freedom, equality, philanthropy, and peace. However, the values ​​are not limited to these examples and may be, for example, values ​​classified as traditionalism, success-oriented, self-actualization-oriented, and symbiosis-oriented, or other values. For example, if the object is a car, the values ​​may be classified as safety-oriented, livability-oriented, design-oriented, and driving performance-oriented. If the object is a house, the values ​​may be classified as location-oriented, price-oriented, layout-oriented, design-oriented, and future prospects-oriented. Furthermore, the values ​​may be values ​​based on Schwartz's value theory. In this case, the values ​​are classified as power, achievement, hedonism, excitement, self-determination, universalism, philanthropy, tradition, harmony, and safety.

[0060] The estimation unit 33 generates estimated content based on a character string of a predetermined value that is likely to be viewed by a user who holds the value. The estimated content can be generated by, for example, using a generation AI and inputting a prompt containing information about the value and the content. The estimation unit 33 then assigns a score for each value to each piece of content to be viewed in advance, based on the similarity between the content and the estimated content. The similarity may be, for example, vector similarity (cosine similarity, Jaccard similarity, etc.) of vectorized content (e.g., embedding using a language model, Doc2Vec, word embedding, etc.). For example, the estimation unit 33 assigns a score for each value to each user based on the score for each value assigned to the content viewed by the user. For example, the estimation unit 33 sums up the scores for each value in a group of content viewed by the user and calculates the score for each value (hereinafter, the value score) normalized by the number of content groups. The estimation unit 33 then estimates values ​​whose calculated value scores are equal to or greater than a threshold as values ​​held by the user. The estimated content is not limited to content viewed by the user, but may be any content related to the user, such as content posted by the user.

[0061] The identification unit 34 identifies values ​​that satisfy a predetermined value condition from among the estimated values. For example, the identification unit 34 calculates a lift value that indicates the likelihood of a value being held by a user group based on the estimated values ​​of each user, and identifies values ​​whose lift value is equal to or greater than a threshold (or less than the threshold) as values ​​that satisfy the predetermined value condition. Details of the calculation method of the lift value will be described later with reference to FIG. 8. Furthermore, hereinafter, values ​​whose lift value is equal to or greater than the threshold will be referred to as positive values, and values ​​whose lift value is less than the threshold will be referred to as negative values. Note that the distinction between positive values ​​and negative values ​​is not limited to using a simple threshold. For example, when a first user group and a second user group exist, values ​​whose lift value for the first user group is higher than that of the second user group (and the difference is equal to or greater than a predetermined threshold) may be defined as positive values. Furthermore, values ​​whose lift value for the first user group is lower than that of the second user group (and the difference is equal to or greater than a predetermined threshold) may be defined as negative values.

[0062] Next, the identification unit 34 identifies search queries that have a high affinity with the identified values ​​(positive values ​​and negative values) from among previously input search queries. For example, the identification unit 34 vectorizes the search query and the values ​​using Word2Vec or the like, and identifies search queries and values ​​with high vector similarity (above a threshold) using cosine similarity or the like as having a high affinity. The identification unit 34 may also use a generation AI to inquire whether the affinity between the search query and the values ​​is high. Note that the search query is, for example, a search query input on a search site, but is not limited to this, and may also be, for example, a search query input in various search behaviors included in log information.

[0063] The generation unit 35 generates content based on the identified search query. For example, the generation unit 35 generates information on search queries that have a high affinity with both positive and negative values. Furthermore, the generation unit 35 extracts search queries that have a high affinity with positive values ​​(or negative values) and for which the number of users who have entered the search query in the user group is less than a threshold (or greater than or equal to a threshold), and generates information on the extracted search queries.

[0064] Furthermore, the generation unit 35 may generate content using a generation AI with the specified or extracted search query as a prompt, but details of this point will be described later with reference to FIGS.

[0065] The providing unit 36 ​​provides the various information generated by the generating unit 35 to the advertisement distributor via the advertisement distributor terminal 50.

[0066] Next, a method for calculating the lift value will be described with reference to Fig. 8. Fig. 8 is a diagram for explaining a method for calculating the lift value calculated by the specification unit 34.

[0067] The lift value is an index indicating the degree to which each value is likely to be held by an arbitrary user group (a user group set by the setting unit 32). In other words, the lift value is a value indicating how many times more likely the arbitrary user group is to hold a value than general users (all users), and the specification unit 34 calculates this value as B value / A value.

[0068] Specifically, the A value is a value indicating the proportion of users who hold each value to all users. That is, for example, the A value is calculated for value A as the number of users who hold value A among all users / the total number of users. The identification unit 34 calculates the A value for each value. In the example shown in FIG. 8, the A values ​​are 10% for value A, 5% for value B, and 20% for value C.

[0069] Next, the B value is a value indicating the proportion of users who hold each value in an arbitrary user group (a user group set by the setting unit 32) relative to the entire arbitrary user group. That is, for example, the B value is calculated for value A as the number of users who hold value A in the arbitrary user group / the number of users in the arbitrary user group. The identification unit 34 calculates the B value for each value. In the example shown in FIG. 8, the B value is 20% for value A, 2.5% for value B, and 30% for value C.

[0070] Then, the specification unit 34 calculates the lift value by dividing the B value by the A value. In the example shown in Fig. 8, the lift value of value A is 20% / 10% = 2.0. The lift value of value B is 2.5% / 5% = 0.5. The lift value of value C is 30% / 20% = 1.5.

[0071] That is, in the example shown in FIG. 8, it can be ascertained by calculating the lift value that, in an arbitrary user group, value A is the value that is most likely to be held, and value B is the value that is least likely to be held.

[0072] In this way, by calculating the lift value, the identification unit 34 can determine which values ​​users of a certain user group are likely to hold and which values ​​they are unlikely to hold (they are no different from general users in terms of ease of holding).

[0073] Next, the content generated by the generating unit 35 will be described with reference to Fig. 9 to Fig. 12. Fig. 9 to Fig. 12 are diagrams showing the content generated by the generating unit 35.

[0074] 9 to 12 show examples of content related to a user group who purchased Company A's Beer A (satisfying the user conditions) and a user group who purchased Company B's Beer B (satisfying the user conditions). In the example shown in FIG. 9, "A-ya Bento," "Sightseeing," "Comedy Show A," and "Yakiniku" are identified as search queries that have a high affinity with the positive values ​​of the user group who purchased Company A's Beer A. Furthermore, "Beer Coupon," "New Year's Card," and "Takeout Gyoza" are identified as search queries that have a high affinity with the positive values ​​of the user group who purchased Company B's Beer B. In FIG. 9, underlined search queries indicate that the number of times entered by users of the target user group is less than a threshold, and non-underlined search queries indicate that the number of times entered by users of the target user group is greater than or equal to a threshold. In other words, the values ​​held by the user group who purchased Company A's A Beer have a high affinity with the search queries "Manzai Program A" and "Yakiniku," but these users do not enter these as search queries very often; they also have a high affinity with the search queries "A Shop Bento" and "Sightseeing," which these users do enter as search queries.

[0075] The generation unit 35 generates information on search queries that have a high affinity with the user's positive values, as shown in Figure 9, and provides it via the provision unit 36, thereby allowing advertisement distributors to understand which search queries would be effective in linking their advertisements to them.

[0076] While Figure 9 shows an example of providing information on search queries that have a high affinity with the user's positive values, it is also possible to provide information on search queries that have a high affinity with the user's negative values. This allows ad distributors to understand search queries that should not be linked with ads (that are not expected to be effective).

[0077] Next, Figure 10 shows an example of content when a request for measures to acquire new customers for Company A's Beer A (users who meet the user conditions) is received from a client (such as an advertising distributor or an employee of Company A).

[0078] In the case of FIG. 10, the generation unit 35 creates a prompt including the search query information shown in FIG. 9 and inputs it to the model of the generation AI in the model information 44. Specifically, the generation unit 35 creates a prompt such as "The search query 'A store bento, sightseeing, stand-up comedy program A, yakiniku' is a search query that is value-oriented and compatible with users who have purchased 'A company A beer.' Based on this, please consider measures to acquire new customers for 'A company A beer.'" and inputs it to the generation AI. The generation unit 35 then acquires text output from the generation AI, such as "In the case of 'A company A beer,' it is expected to be effective if they appear in a commercial for stand-up comedy program A and advertise a combination of yakiniku and beer." and provides it to the client as content.

[0079] Next, Figure 11 shows an example of content when a request is received from a client (such as an advertising distributor or an employee of Company B) for measures to attract customers of Company A's Beer A to Company B's Beer B (users who meet the user conditions).

[0080] In the case of FIG. 11, the generation unit 35 creates a prompt including the search query information shown in FIG. 9 and inputs it to the model of the generation AI in the model information 44. Specifically, the generation unit 35 creates a prompt such as "The search query 'A-ya bento, sightseeing, stand-up comedy show A, yakiniku' is a search query that is value-oriented with users who have purchased 'Company A beer'. The search query 'beer voucher, New Year's card, gyoza takeout' is a search query that is value-oriented with users who have purchased 'Company B beer'. Based on this, please consider measures that can be expected to attract customers from 'Company A beer' to 'Company B beer'." The generation unit 35 then acquires text output from the generation AI, such as "By taking advantage of the fact that 'Company A beer' is strong in tourism, if an advertisement combining 'tourism' and 'Company B beer' is placed, it is possible to attract customers from 'Company A beer'," and provides it to the client as content.

[0081] In this way, the generation unit 35 generates content indicating measures such as sales strategies (advertising strategies) based on search queries that have a high affinity with the user's positive values, and provides the content through the provision unit 36, thereby enabling the client to receive effective measures.

[0082] In addition to the examples shown in FIGS. 10 and 11, for example, text to be included in an advertisement may be provided as content, as shown in FIG.

[0083] Specifically, the generation unit 35 creates a prompt such as, "The search query 'A-ya bento, sightseeing, stand-up comedy program A, yakiniku' is a search query that is value-wise compatible with users who have purchased 'A-company A beer.' Based on this, please think of a sentence to be placed in a search ad to promote 'A-company A beer.'" and inputs it to the generation AI. The generation unit 35 then acquires the output from the generation AI, along with the title "'A-ya beer' - To enjoy your 'likes' even more," as well as text outputs such as, "Make A-ya bento even more special by accompanying it with your bento. Enhance the depth of its deliciousness with A-ya beer," "Along with the traditional flavor, the local cuisine you savor at a tourist spot is also perfect with A-ya beer," "Enrich your dining table. Any cuisine, such as yakiniku at home, will be even more enjoyable with A-ya beer," and "To accompany entertainment, make your laughter even more enjoyable with A-ya beer while watching A-ya beer." and provides these as content to the client.

[0084] In this way, the generation unit 35 generates content indicating the text to be included in the advertisement based on a search query that has a high affinity with the user's positive values, and provides it through the provision unit 36, thereby reducing the burden of the client's text writing work involved in creating the advertisement.

[0085] Next, a processing procedure of the processing executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 13. Fig. 13 is a flowchart showing the processing procedure of the processing executed by the information processing device 1 according to the embodiment.

[0086] As shown in FIG. 13, the control unit 3 first sets a user group that satisfies a predetermined condition based on the log information acquired from the service providing device 200 (step S101).

[0087] Next, the control unit 3 estimates the values ​​held by each user in the set user group (step S102).

[0088] Next, the control unit 3 identifies values ​​that satisfy a predetermined condition from among the estimated values ​​(step S103).

[0089] Next, the control unit 3 identifies search queries that have a high affinity with the identified values ​​(step S104).

[0090] Next, the control unit 3 generates content based on the identified search query (step S105), provides the generated content (step S106), and ends the process.

[0091] 〔others〕 Furthermore, among the processes described in the above embodiments, some of the processes described as being performed automatically can also be performed manually. Alternatively, all or some of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0092] 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.

[0093] 3 may be held in a storage server or the like, rather than being held by each device. In this case, each device obtains various pieces of information by accessing the storage server.

[0094] [Hardware configuration] The information processing device 1 according to the embodiment described above is realized by, for example, a computer 1000 configured as shown in Fig. 14. Fig. 14 is a diagram showing an example of a hardware configuration. 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 via a bus 1090.

[0095] 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), an HDD (Hard Disk Drive), a flash memory, or the like.

[0096] 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, scanner, etc., and is realized by a USB, etc.

[0097] The input device 1020 may be a device that reads information from, for example, 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.

[0098] 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.

[0099] 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.

[0100] For example, when the computer 1000 functions as the information processing device 1, the arithmetic unit 1030 of the computer 1000 executes a program loaded onto the primary storage device 1040, thereby realizing the functions of the control unit 3.

[0101] 〔effect〕 As described above, the information processing device 1 according to the embodiment includes an estimation unit 33 that estimates the values ​​held by each user in a user group that satisfies predetermined user conditions, an identification unit 34 that identifies, from among previously input search queries, search queries that have a high affinity with values ​​that satisfy the predetermined value conditions among the estimated values, and a provision unit 36 ​​that provides content based on the identified search queries.

[0102] According to the information processing device 1 according to each of the above-described embodiments, it is possible to provide effective support for content provision.

[0103] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, 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 undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0104] 〔others〕 Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0105] 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.

[0106] Furthermore, the processes described in the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the process contents.

[0107] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, the control unit 3 can be read as control means or a control circuit. [Explanation of symbols]

[0108] 1. Information processing equipment 2. Communications Department 3. Control Unit 4 Storage section 31 Acquisition Department 32 Setting section 33 Estimation part 34 Specific part 35 Generation part 36 Providing Department 41 User Information 42 Values ​​Information 43 Query Information 44 Model Information 50 Advertiser Terminal 100 user terminals 200 Service Providing Device S Information Processing System

Claims

1. an estimation unit that estimates values ​​held by each user of a user group that satisfies a predetermined user condition; an identification unit that identifies, from previously input search queries, search queries that have a high affinity with values ​​that satisfy a predetermined value condition among the estimated values; a providing unit that provides content based on the identified search query; An information processing device comprising:

2. The user group that satisfies the predetermined user condition is a user group that has performed a predetermined action. The information processing device according to claim 1 .

3. The estimation unit generating estimated content that is likely to be related to a user having a preset value, and estimating a similarity between the content related to the user and the estimated content as a score of the value; The identification unit Identifying the search query that has a high affinity with the values ​​and that has a score equal to or greater than a threshold The information processing device according to claim 1 .

4. The identification unit A lift value is calculated by dividing the percentage of users in the user group who have the value whose score is equal to or greater than a threshold by the percentage of users who have the value among all users, and the search query with the high affinity is identified based on the lift value. The information processing device according to claim 3 .

5. The providing unit providing the content generated based on a search query that has been input by the user of the user group less than a threshold number of times among the search queries with high affinity; The information processing device according to claim 4 .

6. The providing unit providing the content generated based on a search query that has been input by the user of the user group a threshold or more in number of times, among the search queries with high affinity; The information processing device according to claim 4 .

7. The providing unit and providing the content indicating measures for the user to satisfy the user conditions based on the identified search query. The information processing device according to claim 4 .

8. 1. A computer-implemented information processing method, comprising: an estimation step of estimating values ​​held by each user of a user group that satisfies a predetermined user condition; an identifying step of identifying, from among previously input search queries, search queries that have a high affinity with values ​​that satisfy predetermined value conditions among the estimated values; providing content based on the identified search query; An information processing method including:

9. an estimation procedure for estimating values ​​held by each user of a user group that satisfies a predetermined user condition; an identifying step of identifying a search query that has a high affinity with values ​​that satisfy a predetermined value condition among the estimated values ​​from among previously input search queries; a serving step of serving content based on the identified search query; An information processing program that causes a computer to execute the above.

Images