Information processing device, information processing method, and information processing program

Abstract

To provide an information processing device, an information processing method, and an information processing program, capable of reducing the work load required to estimate a user's impression of content.SOLUTION: An information processing device comprises a reception unit, a generation unit, and a provision unit. The reception unit receives: a selection of a target content which is an estimate target for impressions that users would have or the users have come to have; and a selection of an impression group which is a group of the impressions. The generation unit generates, by using a generative AI, the impression content indicative of the impressions which are estimated that the users would have or the users have come to have with respect to the target content among the plurality of impressions included in the impression group received by the reception unit. The provision unit provides the impression content generated by the generation unit.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] Traditionally, creators of content such as web content have attempted to create content that would give users a desired impression, but there is a possibility that the impression users actually have of the content may be different.

[0003] Patent document 1 discloses a technology in which an evaluator inputs the evaluation level of the impression they received from viewing content, and the pair of the content and the evaluation level of the impression the evaluator received from the content is used as training data for training a machine learning model. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2019-133455 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the above-described conventional technology requires the evaluator to input the evaluation level of the impression, which poses a problem of a heavy workload.

[0006] The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can reduce the workload required to estimate a user's impression of content. [Means for solving the problem]

[0007] The information processing device according to the present application includes a receiving unit, a generating unit, and a providing unit. The receiving unit receives a selection of target content from which an impression a user has or has had is estimated, and a selection of an impression group, which is a group of impressions. The generating unit uses a generation AI to generate impression content indicating the impression the user has or has had of the target content from among the multiple impressions included in the impression group received by the receiving unit. The providing unit provides the impression content generated by the generating unit. [Effects of the Invention]

[0008] According to one aspect of the embodiment, it is possible to reduce the workload required to estimate a user's impression of content. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram for explaining information processing according to the 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 a user information table stored in the user information storage unit of the information processing device according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of input information input for generation by the estimation processing unit in the processing unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram showing an example of impression content generated by a second generation processing unit in the processing unit of the information processing device according to the embodiment. [Figure 7] FIG. 7 is a flowchart showing an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 8] FIG. 8 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] 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.

[0011] [1. An example of information processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram for explaining information processing according to the embodiment.

[0012] 1 is an information processing device that generates impression content, which is content that indicates the impression that a user U has or is presumed to have had about target content, and is realized, for example, by one or more servers or a cloud system. The user U is a user of a terminal device 2 and a user of an online service for which the target content is provided.

[0013] 1, the information processing device 1 receives an impression content generation request transmitted from the terminal device 3 of a worker O who creates or provides the target content (step S1). The impression content generation request includes target content that is the subject of estimation of the impression that the user U has or has had, information indicating an impression group that is a group of impressions, information specifying the estimation method, information indicating the target content type, and information indicating the impression content type.

[0014] The target content, impression group, estimation method, target content type, and impression content type specified in the impression content generation request are, for example, the target content, impression group, estimation method, target content type, and impression content type selected by worker O.

[0015] The information processing device 1 receives a request to generate impression content, and thereby receives selection of target content, impression group, estimation method, target content type, and impression content type. Note that the worker O is an employee of a company that creates or provides the target content, but may also be an employee of a company commissioned by such company.

[0016] The target content is web content, such as, but not limited to, a web page, a catchphrase, a creative, or a stamp. The target content is content that is a candidate for or is to be provided on, for example, an EC (Electronic Commerce) site, a news site, a restaurant introduction site, an image posting site, a video viewing site, etc., and includes, but is not limited to, advertising content. The EC site is, for example, but not limited to, a shopping site, an auction site, etc.

[0017] The target content is content that can be provided on an online site provided by the information processing device 4, and the user U can use the online site provided by the information processing device 4 by operating the terminal device 2. The online sites provided by the information processing device 4 include, but are not limited to, e-commerce sites, news sites, store introduction sites, image posting sites, video viewing sites, and the like.

[0018] The information processing device 4 accepts product content such as product descriptions introducing products from workers O and the like as posted content on the EC site, and provides such posted content to each user U. The product descriptions can also be referred to as product descriptions. The posted content on the EC site includes not only the product content but also comments and ratings posted about the products.

[0019] Furthermore, the information processing device 4 accepts news articles from workers O and the like as posted content at the news site, and provides such posted content to each user U. At the news site, posted content includes not only news articles but also comments posted on such news articles.

[0020] Furthermore, the information processing device 4 accepts store content such as store introduction texts from workers O that introduce the details of the stores as posted content on the store introduction site, and provides such posted content to each user U. Furthermore, the posted content on the store introduction site includes reviews and comments posted about the stores in addition to the store content. The store introduction site may be, for example, a site for introducing restaurants or other types of stores.

[0021] Furthermore, the information processing device 4 accepts image content (for example, still image content or video content) from workers O and the like as posted content at an image posting site, and provides such posted content to each user U. Furthermore, the information processing device 4 accepts video content and titles and caption texts for the video content as posted content at a video viewing site, and provides such posted content to each user U.

[0022] The impression group specified in the impression content generation request is an impression group designated by the user U from among a plurality of impression groups C1 to Cn (n is an integer equal to or greater than 2). The plurality of impression groups C1 to Cn may be, for example, impression groups classified according to the values ​​of the user U, impression groups classified according to the preferences of the user U, impression groups classified according to the lifestyle of the user U, etc., but are not limited to such examples.

[0023] In the example shown in Figure 1, the impression group based on user U's values ​​is an impression group that classifies values ​​based on Schwartz's value theory as impressions that user U has or has had, and is classified into 10 classification criteria: power, achievement, hedonism, stimulation, self-determination, universalism, philanthropy, tradition, harmony, and security. In the example shown in Figure 1, the impression group based on values ​​based on Schwartz's value theory is further subdivided into multiple classification criteria, and the impressions that user U has or has had are classified into 56 classification criteria.

[0024] Specifically, the classification criterion "power" is subdivided into five classification criteria: "social recognition," "wealth," "authority," "social power," and "saving face." The classification criterion "achievement" is subdivided into five classification criteria: "intelligence," "competence," "success," "ambition," and "influence." The classification criterion "hedonism" is subdivided into two classification criteria: "enjoyment of life" and "fun." The classification criterion "stimulation" is subdivided into three classification criteria: "courage," "a varied life," and "a vibrant life."

[0025] In addition, the classification criterion "self-determination" is further subdivided into six classification criteria: "freedom," "independence," "curiosity," "creativity," "self-selection," and "self-respect." The classification criterion "universalism" is further subdivided into nine classification criteria: "wisdom," "world peace," "a world of beauty," "social justice," "inner harmony," "environmental protection," "equality," "generosity," and "harmony with nature." The classification criterion "philanthropy" is further subdivided into nine classification criteria: "true friendship," "meaning of life," "responsibility," "loyalty," "mature love," "help," "honesty," "tolerance," and "spiritual world."

[0026] The classification criterion "harmony" is further subdivided into four classification criteria: "politeness," "self-discipline," "respect for parents and elders," and "obedience." The classification criterion "tradition" is further subdivided into six classification criteria: "humility," "detachment," "respect for tradition," "piety," "moderation," and "acceptance of fate." The classification criterion "security" is further subdivided into seven classification criteria: "health," "family safety," "social order," "cleanliness," "giving back," "sense of belonging," and "national security."

[0027] The values ​​of user U are not limited to the above-mentioned examples, and may be, for example, values ​​classified as traditionalism, success orientation, self-actualization orientation, coexistence orientation, etc., or other values. For example, if the object is a car, the values ​​of user U may be values ​​classified as prioritizing safety, livability, design, driving performance, etc., and if the object is a house, the values ​​may be values ​​classified as prioritizing location, price, layout, design, future prospects, etc.

[0028] Impression groups based on the lifestyle of user U include, for example, impression groups based on the AIO (Activities Interest Opinions) approach and impression groups based on VALS (Values ​​And LifeStyles). Impression groups based on the AIO approach are impression groups classified into one or more impression groups of activities, interests, opinions, etc. Impression groups based on VALS are impression groups classified into, for example, self-actualizers, successful people, group members, those who maintain their livelihoods, those in poverty, those who aspire to success, those with social conscience, intellectuals, and young intellectuals.

[0029] The impression group may also be, for example, an impression group indicated by the innovator theory, which classifies the diffusion process of new products, such as innovators, early adopters, early majority, late majority, and laggards.

[0030] There are multiple estimation methods for estimating the impression that user U has or has had of target content, including a first estimation method and a second estimation method. The first estimation method is a method in which a generation AI (Artificial Intelligence) directly estimates the impression that user U has or has had of target content. The second estimation method is a method in which, for each impression included in an impression group, a generation AI generates reference content that is estimated to have the impression that user U has, and compares the reference content with the target content to estimate the impression that user U has or has had of the target content.

[0031] The target content type is, for example, the type of target content, and is indicated by, for example, a combination of an online site and a content type. For example, the target content type may be, but is not limited to, a product description on a product page of an e-commerce site, a news article on a news site, a comment on a news article on a news site, image content on an image posting site, or the title and caption text of video content on a video viewing site.

[0032] The impression content type is a type of impression content, and includes, for example, a first content type and a second content type. The first content type is a type of impression content including information indicating the impression that the user U is estimated to have of the target content, and is a type of impression content that supports the creation and review of the target content. The second content type is a type of impression content including information indicating the impression that the user U is estimated to have of the target content, and is a type of impression content that supports the understanding of the impression that the user U has of the target content.

[0033] Next, the information processing device 1 uses a generation AI to estimate the impression that the user U has or is estimated to have had of the target content whose selection was accepted in step S1 from among the multiple impressions included in the selected impression group, which is the group of impressions whose selection was accepted in step S1 (step S2).

[0034] The generation AI used in step S2 is, for example, a text generation AI, an image generation AI, a multimodal AI, etc. Such a generation AI is, for example, arranged in an external information processing device, and the information processing device 1 acquires reference content for each impression by having the generation AI generate it via an API (Application Programming Interface) provided by the external information processing device, but is not limited to this example. For example, the generation AI may be arranged within the information processing device 1.

[0035] Text generation AI is, for example, a language model trained to estimate and output the next token from an input token sequence, such as a transfer-based model or an RNN (Recurrent Neural Network)-based model.

[0036] Examples of transfer-based models include, but are not limited to, GPT (Generative Pre-trained Transformer) and BARD (Bidirectional Auto Regressive Dialogues). Examples of RNN-based models include, but are not limited to, RWKV (Receptance Weighted Key Value). It is desirable to keep input information, such as personal information, confidential by learning it so that it is not used as a new answer.

[0037] Examples of image generation AI include, but are not limited to, StackGAN (Generative Adversarial Networks), AttnGAN, T2I (Text-to-Image) with Transformers, and DALL-E. Examples of multimodal AI include, but are not limited to, models that generate images from text or generate text from images, such as GPT-4V and CM3Leon (Chameleon Multimodal Model).

[0038] In step S2, the information processing device 1 uses a generation AI to estimate the impression that the user U has or has had regarding the target content from among the multiple impressions included in the selected impression group. Specific explanations will be given below. In the following, the multiple impressions included in the selected impression group will be described as multiple impressions IM1 to IMm (m is an integer of 2 or more). Furthermore, when referring to the multiple impressions IM1 to IMm without distinguishing them individually, they may be referred to as impressions IM.

[0039] First, a case will be described in which the estimation method and impression content type selected and accepted by the information processing device 1 in step S1 are the first estimation method and the first content type. In this case, the information processing device 1 causes the generation AI to estimate the impression IM that the user U has of the target content from among multiple impressions IM1 to IMm included in the selected impression group.

[0040] For example, the information processing device 1 inputs, as input information to the generation AI, instruction information instructing the user U to select an impression IM that the user U has of the target content from among multiple impressions IM1 to IMm indicated by the impression information, impression information indicating the multiple impressions IM1 to IMm included in the selected impression group, and information including the target content, and causes the generation AI to output information indicating one or more impressions IM that the user U is estimated to have of the target content.

[0041] For example, suppose the selected impression group is a group of impressions based on the values ​​of user U, and the target content is a catchphrase, "You can tell the difference because it's something you use every day." In this case, the information processing device 1 includes, for example, information such as a character string, "Please select three or more images from the values ​​below that fit the catchphrase, 'You can tell the difference because it's something you use every day.' Please output in CSV format as shown below.\nValue, Reason" in the input information as instruction information.

[0042] Furthermore, the information processing device 1 includes information including the character string "social power, authority, wealth, saving face, social recognition\n success, competence, ambition, influence, intelligence\n fun, enjoying life\n courage, a varied life, a vibrant life\n creativity, curiosity, freedom, choosing goals, self-respect, independence\n environmental protection, the world of beauty, harmony with nature, generosity, social justice, wisdom, equality, world peace, inner harmony\n assistance, honesty, tolerance, loyalty, responsibility, true friendship, the spiritual world, mature love, the meaning of life\n politeness, respect for parents and elders, self-discipline, obedience\n piety, acceptance of fate, humility, moderation, respect for tradition, detachment\n cleanliness, national security, social order, family security, giving back, health, a sense of belonging" in the input information as impression information.

[0043] Furthermore, instead of the information of the character string "Please select three or more images from the values ​​below that fit the catchphrase," the information processing device 1 can use information such as "Please select three or more impressions from the values ​​below that are estimated to be formed by the user for the catchphrase," or information such as "Please estimate a score indicating the degree of impression that the user is estimated to have for the catchphrase for each of the values ​​below. The score should be in the range of 1 to 10, with a higher value representing a higher degree of impression," but is not limited to such examples. Furthermore, the output format is not limited to CSV format.

[0044] The instruction information also includes text information corresponding to the target content type selected in step S1. In the example described above, the target content type is a catchphrase, so the instruction information includes the information of the character string "catchphrase." However, if the target content type is a product description on a product page of an EC site, the instruction information includes the information of the character string "product description."

[0045] In this way, the information processing device 1 generates instruction information according to the target content type by including text information according to the target content type in the instruction information, but it can also input instruction information that is independent of the target content type to the generation AI.

[0046] For example, the information processing device 1 can set instruction information including the information of the character string "Please select three or more images from the values ​​below that fit the input information" as a system message, instead of the character string "Please select three or more images from the values ​​below that fit the catchphrase 'You can tell the difference because it's something you use every day.'" A system message is a message that instructs the behavior of the generating AI, and is, for example, a message set in the input information as the content of "'role':'system'" in OpenAI's GPT model.

[0047] Furthermore, the information processing device 1 can also use a generation AI to estimate the impression that the user U has of the target content from among multiple impressions IM1 to IMm included in the selected impression group by limiting the attributes of the user U. In this case, instead of the information string "Please select three or more images from the values ​​below that fit the catchphrase," the information processing device 1 can use information such as "Please select three or more impressions from the values ​​below that are estimated to be formed by a man in his twenties for the catchphrase." or information such as the information string "Please estimate, for each of the values ​​below, a score indicating the degree of impression that a man in his twenties is estimated to have for the catchphrase. The score should range from 1 to 10, with a higher value indicating a higher degree of impression." When the generation AI is to estimate one or more impressions IM that a user U with an attribute other than a man in his twenties has, the information string "man in his twenties" can be replaced with information indicating another attribute.

[0048] Furthermore, when the target content is image content, the information processing device 1 can input information including the target content and instruction information including information such as a string of characters "Please select three or more images from the values ​​below that fit the input image," to the multimodal AI as input information, and cause the multimodal AI to output a similarity. Note that the information processing device 1 can limit the attributes of the user U and output a score indicating the degree of impression IM, just as when the target content is other than image content.

[0049] Next, a case will be described in which the estimation method and impression content type selected and accepted by the information processing device 1 in step S1 are the first estimation method and the second content type. In this case, the information processing device 1 collects behavioral content, which is content indicating the behavior of the user U related to the target content, from the information processing device 4 or the like.

[0050] The behavioral content is content generated by an action by the user U related to the target content, such as posted content such as reviews, comments, and messages posted by the user U regarding the target content. For example, if the target content is a product description or an image of a product, posted content as behavioral content is a review or comment posted about a product introduced by the target content.

[0051] Furthermore, if the target content is a store description or an image of the store interior, the posted content as behavioral content is a review or comment posted about the store introduced by the target content. If the target content is video content, the posted content as behavioral content is a review or comment posted about the video content.

[0052] The posted content as behavioral content may be content such as a conversation or post by the user U on the official account of the product or store indicated by the target content in the communication application. The posted content as behavioral content may be content such as a post or conversation by the user U on an online bulletin board site, for example.

[0053] For example, the information processing device 1 inputs to the generation AI as input information information including instruction information instructing the user U to select the impression IM that the user U has from the behavioral content from among the multiple impressions IM1 to IMm indicated by the impression information, impression information indicating the multiple impressions IM1 to IMm included in the selected impression group, and the behavioral content, and causes the generation AI to output information indicating the impression IM that the user U is estimated to have had from the target content.

[0054] For example, if the selected impression group is a group of impressions based on the values ​​of user U, the behavioral content is represented by the character string "XXX...XXX." In this case, the information processing device 1 generates instruction information including the information of the character string "'XXX...XXX' is a comment posted by a user regarding the target content below. Please select three or more of the values ​​below that represent the image that user U is presumed to have of the target content below. Please output in CSV format as shown below.\nValue, Reason," impression information, and target content.

[0055] Furthermore, the information processing device 1 can use, for example, information such as "Please estimate a score indicating the degree of impression that user U is estimated to have had of the target content for each of the values ​​below. The score should be in the range of 1 to 10, with a higher value being used for a higher degree of impression," instead of the information in the string "Please select three or more of the values ​​below that represent the image that user U has of the target content," but is not limited to such an example.

[0056] The output format is not limited to CSV. The instruction information may include, instead of the target content, a character string indicating a product, store, or the like identified by the target content. In this case, the character string is used instead of the above-mentioned character string "the following target content." A portion of the above-mentioned instruction information may be set as a system message.

[0057] The information processing device 1 can generate behavioral content that includes the content of multiple users U in the instruction information regardless of the attributes of the users U, or can generate behavioral content that includes the content of multiple users U for each attribute of the users U. When the information processing device 1 includes the content of multiple users U for each attribute of the users U in the instruction information, it can cause the generation AI to output information indicating one or more impressions IM that are estimated to have been held by the users U for each attribute of the users U.

[0058] Furthermore, when the target content is an image, the information processing device 1 can input information containing instruction information such as "The following images are images posted by users regarding the following target content" to the multimodal AI as input information instead of the information of the string "'XXX...XXX' is a comment posted by a user regarding the following target content," and cause the multimodal AI to output information indicating one or more impressions IM that are estimated to have been held by the user U.

[0059] In addition, when the behavioral content includes text and images, the information processing device 1 can include the text and images as behavioral content in the instruction information, input information including such instruction information to the multimodal AI as input information, and output it from the multimodal AI.

[0060] Next, a case will be described in which the estimation method and impression content type selected and accepted by the information processing device 1 in step S1 are the second estimation method and the first content type. In this case, the information processing device 1 causes the generation AI to generate reference content that is estimated to have the impression IM of the user U for each impression IM included in the selected impression group, and compares the reference content with the target content to estimate one or more impressions IM that the user U has of the target content.

[0061] For each impression IM classified into a plurality of selected impression groups, the information processing device 1 generates reference content that is estimated to give the impression that the user U will have. When the selected impression group is a group of impressions based on values ​​based on Schwartz's value theory, the plurality of impressions IM classified into the selected impression group are the above-mentioned 10 types of values ​​or 56 types of values.

[0062] For example, the information processing device 1 inputs input information including instruction information, which is information instructing the generation AI to generate reference content that is estimated to give the user U the impression indicated by the impression IM, to the generation AI, and causes the generation AI to generate the reference content. The reference content is, for example, content represented by at least one of text and an image.

[0063] The information processing device 1 stores standard instruction information in advance, and inputs information including the standard instruction information and impression information to the generation AI as instruction information, causing the generation AI to generate reference content for each impression IM. For example, if the target content is a product description, the standard instruction information is a string of information such as "I will post certain values. Please write 10 product descriptions that are likely to share those values ​​with Japanese users. Please do not include too many of the values ​​you have posted directly in the sentences."

[0064] The impression information is, for example, information on the character string "values: social power." As a result, each of 10 product descriptions that are predicted to give the user U the impression IM of social power is generated as reference content.

[0065] When the generation AI is a GPT, the standard instruction information is included in the input information (prompt) as an instruction, and the impression information is included in the input information (prompt) as a user message, but this example is not limited to this. For example, the input information may include information including the string "Social power as a value" as a user message instead of the string "Post a certain value. The value" in the standard instruction information.

[0066] After generating reference content for each impression IM, the information processing device 1 compares target content that is the subject of estimation of the impression IM held by the user U with the reference content for each impression IM. In order to compare the target content with the reference content for each impression IM, the information processing device 1 vectorizes the target content and each reference content.

[0067] The vectorization of the content is performed, for example, by embedding using a language model (for example, a transformer-based model). The vectorized content is represented, for example, by a vector with several hundred dimensions, but is not limited to such an example.

[0068] Embedding using a language model is, for example, embedding using text-embedding-ada provided by OpenAI (registered trademark) or BERT (Bidirectional Encoder Representations from Transformers), but is not limited to these examples.

[0069] Note that content vectorization is not limited to embedding using a language model, and content vectorization may be performed using, for example, Doc2Vec, the average of word embedding, etc. Word2Vec, fastText, etc. are used for word embedding.

[0070] For example, the information processing device 1 classifies the target content into an impression IM corresponding to a reference content whose vector similarity with the target content is equal to or greater than a threshold. For example, the information processing device 1 can classify the target content into only one impression IM, or can classify the target content into two or more impression IMs.

[0071] For example, the information processing device 1 can classify the target content into only one impression IM by classifying the target content into an impression IM corresponding to a reference content whose vector similarity is equal to or greater than a threshold and has the highest similarity.

[0072] Furthermore, when there are two or more reference contents whose vector similarities with the target content are equal to or greater than a threshold, the information processing device 1 can classify the target content into two or more impressions IM corresponding to the two or more reference contents, respectively.

[0073] The similarity between the vectors is cosine similarity, but may also be Jaccard similarity, or the inverse of the Euclidean distance or the inverse of the Manhattan distance. When the Euclidean distance or the Manhattan distance is used, the information processing device 1 classifies, for example, target content whose Euclidean distance or the Manhattan distance from the reference content is less than a threshold into an impression IM corresponding to the reference content.

[0074] In addition, the information processing device 1 can use any method to learn a classification model using vectors and the corresponding hand-labeled data, and then use that model to perform classification, thereby determining the similarity between vectors and classifying vectors, and ultimately determining the similarity between content items and classifying content items.

[0075] In addition, when the reference content and the target content are images, the information processing device 1 can input information including the reference content, the target content, and instruction information indicating an instruction to output the similarity between the reference content and the target content to the multimodal AI as input information, and cause the multimodal AI to output the similarity.

[0076] In this case, the information processing device 1 classifies the impression IM into, for example, an impression IM generated by a multimodal AI that corresponds to the reference content with the highest similarity, which is equal to or greater than a threshold, and an impression IM generated by a multimodal AI that corresponds to the reference content with a similarity equal to or greater than a threshold.

[0077] Furthermore, when the reference content and the target content are images, the information processing device 1 can also cause the multimodal AI to generate explanatory text that explains what images are included in each of the reference content and the target content.

[0078] In this case, the information processing device 1 vectorizes each of the explanatory text of the reference content and the explanatory text of the target content, and calculates the similarity between the vectorized explanatory text of the reference content and the vectorized explanatory text of the target content. The method of calculating the similarity and the group of impressions to the impression IM of the target content are the same as when the reference content and the target content are text.

[0079] When the reference content and the target content are images, the information processing device 1 can also directly vectorize each of the reference content and the target content to calculate the similarity.

[0080] Furthermore, when the reference content and the target content each contain text and an image, the information processing device 1 classifies the reference content into an impression IM corresponding to the reference content whose integrated score, which is a score obtained by weighting the similarity between the texts and the similarity between the images, is equal to or greater than a threshold, and an impression IM corresponding to the reference content whose integrated score is equal to or greater than the threshold and is the largest.

[0081] Next, a case will be described in which the estimation method and impression content type selected and accepted by the information processing device 1 in step S1 are the second estimation method and the second content type. In this case, the information processing device 1 collects behavioral content, which is content indicating the behavior of the user U related to the target content, from the information processing device 4 or the like.

[0082] The behavioral content is content that arises from actions by user U that are related to the target content, and is, for example, posted content such as reviews, comments, and messages posted by user U regarding the target content, as in the case where the estimation method selected and accepted in step S1 is the first estimation method.

[0083] The information processing device 1 causes a generation AI to generate reference content that is estimated to be the impression IM that the user U has had for each impression IM included in the selected impression group, and compares the reference content with the behavioral content to estimate one or more impressions IM that the user U has had for the target content.

[0084] For each impression IM classified into a plurality of selected impression groups, the information processing device 1 generates reference content that is estimated to have had the impression held by the user U. For example, the information processing device 1 inputs input information to the generation AI, including instruction information that is information that instructs the generation of reference content that is content that is estimated to have had the impression indicated by the impression IM and corresponds to the behavioral content, and causes the generation AI to generate the reference content. The reference content is, for example, content that is expressed as at least one of text and an image.

[0085] The information processing device 1 stores first standard instruction information in advance, and inputs information including the standard instruction information and impression information to the generation AI as instruction information, causing the generation AI to generate reference content for each impression IM. For example, if the target content is a product description, the standard instruction information is the following character string: "I will post certain values. Please write 10 comments by users who are presumed to have held those values. Please do not include too many of the values ​​you posted directly in the sentences."

[0086] The impression information is, for example, information on the character string "values: social power." As a result, each of the ten comments of the user U that are estimated to have given the impression IM of social power to the user U is generated as a reference content.

[0087] After generating the reference content for each impression IM, the information processing device 1 compares the impression IM held by the user U or the behavioral content that is the subject of estimation of the impression IM held by the user U with the reference content for each impression IM using the same comparison method as when the estimation method selected and accepted in step S1 is the first estimation method.

[0088] For example, the information processing device 1 compares, for each dynamic content, the behavioral content that is the subject of estimation of the impression IM held by the user U with the reference content for each impression IM, and estimates one or more impressions IM held by the user U regarding the target content based on the comparison results.

[0089] The information processing device 1 compares, for each behavioral content, the behavioral content that is the subject of estimation of the impression IM held by the user U with the reference content for each impression IM. In order to compare the behavioral content with the reference content for each impression IM, the information processing device 1 vectorizes each behavioral content and each reference content.

[0090] The information processing device 1 performs a process of vectorizing the behavioral content and calculating the similarity between the vector of each reference content for each behavioral content. Then, the information processing device 1 estimates, for example, impressions IM corresponding to reference content whose average value of the vector similarity with each behavioral content is equal to or greater than a threshold, as one or more impressions IM that the user U has had about the target content.

[0091] Furthermore, the information processing device 1 estimates, for example, impressions IM corresponding to reference content whose median value of the vector similarity with each behavioral content is equal to or greater than a threshold value as one or more impressions IM that the user U has had with respect to the target content.

[0092] Next, the information processing device 1 generates, as impression content, content including information indicating one or more impressions IM into which the target content has been classified based on the above-mentioned estimation result (step S3). For example, the information processing device 1 generates, as impression content, content that maps a plurality of impressions IM1 to IMm classified into specific impression groups and that includes information indicating impressions IM that the user U has or is estimated to have had about the target content.

[0093] Next, the information processing device 1 provides the impression content generated in step S3 to the worker O (step S4). In step S4, the information processing device 1 provides the impression content generated in step S3 to the worker O, for example, by transmitting the impression content generated in step S3 to the terminal device 3 of the worker O.

[0094] The impression content shown in Fig. 1 is a content in which a plurality of values ​​based on Schwartz's value theory is mapped as a plurality of impressions IM1 to IMm (m=56 in Fig. 1), and the impressions IM that user U has of values ​​based on Schwartz's value theory or impressions IM that have been classified as impressions IM that user U has had are highlighted. In the example shown in Fig. 1, the target content is content that shows introductions or introduction images of four different models of a certain car model.

[0095] In the impression content shown in Figure 1, model A automobiles are classified into the impressions "freedom," "independence," and "self-respect," which are subdivisions of the impression "self-determination," and into the impression "inner harmony," which is a subdivision of the impression "universalism."

[0096] In addition, in the impression content shown in Figure 1, the model B car is classified into the impressions "Variety of life" and "Vibrant life" which are subdivisions of the impression "Stimulation," the impressions "Enjoyment of life" and "Fun" which are subdivisions of the impression "Hedonism," and the impression "Sense of belonging" which is subdivisions of the impression "Safety."

[0097] Furthermore, in the impression content shown in Figure 1, the model C car is classified into the impression "freedom" and impression "goal selection" which are subdivided from the impression "self-determination," the impression "enjoyment of life" and impression "fun" which are subdivided from the impression "hedonism," the impression "competent" which is subdivided from the impression "achievement," and the impression "healthy" and classification "family safety" which are subdivided from the impression "safety."

[0098] In addition, in the impression content shown in Figure 1, the model D car is classified into the impressions "creativity," "freedom," and "goal choice," which are subdivisions of the impression "self-determination," the impression "enjoyment of life," which is a subdivision of the impression "hedonism," the impression "influence," which is a subdivision of the impression "achievement," and the impression "wealth," which is a subdivision of the impression "power."

[0099] In this way, the information processing device 1 receives a selection of target content that is the subject of estimation of the impression IM that the user U has or has had, and a selection of an impression group that is a group of impressions IM, and uses a generation AI to generate impression content that indicates the impression IM that the user U has or is estimated to have had of the target content from among the multiple impressions IM included in the received impression group. This enables the information processing device 1 to reduce the workload required to estimate the impression that the user U has of the target content.

[0100] The configuration of an information processing system including an information processing device 1 that performs such processing, a plurality of terminal devices 2, a terminal device 3, and an information processing device 4 will be described in detail below.

[0101] [2. Information Processing System Configuration] 2 is a diagram illustrating an example of a configuration of an information processing system according to an embodiment. As illustrated in FIG. 2, the information processing system 100 according to the embodiment includes an information processing device 1, a plurality of terminal devices 2, a terminal device 3, and an information processing device 4.

[0102] The multiple terminal devices 2 are used by different users U. The terminal device 3 is, for example, a terminal device of a worker O. The terminal devices 2 and 3 are, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, a tablet PC, or a wearable device. The wearable device is, for example, smart glasses or a smart watch, but is not limited to such examples.

[0103] The information processing device 4 provides various online services to the user U. For example, the information processing device 4 provides the user U with content from various sites such as an e-commerce site, a news site, a store introduction site, an image posting site, a video viewing site, and an online bulletin board site, but is not limited to these examples.

[0104] For example, on an EC site, the information processing device 4 accepts product content such as product descriptions from workers O or the like as posted content, and provides such posted content to each user U. The product descriptions can also be referred to as product descriptions. In addition to the product content, the posted content on the EC site includes comments and ratings posted about the product.

[0105] Furthermore, the information processing device 4 accepts news articles from workers O and the like as posted content at the news site, and provides such posted content to each user U. At the news site, posted content includes not only news articles but also comments posted on such news articles.

[0106] Furthermore, the information processing device 4 accepts store content such as store introduction texts from workers O that introduce the details of the stores as posted content on the store introduction site, and provides such posted content to each user U. Furthermore, the posted content on the store introduction site includes reviews and comments posted about the stores in addition to the store content. The store introduction site may be, for example, a site for introducing restaurants or other types of stores.

[0107] Furthermore, the information processing device 4 accepts image content (for example, still image content or video content) from workers O and the like as posted content at an image posting site, and provides such posted content to each user U. Furthermore, the information processing device 4 accepts video content and titles and caption texts for the video content as posted content at a video viewing site, and provides such posted content to each user U.

[0108] The information processing device 1, the terminal device 2, the terminal device 3, and the information processing device 4 are connected to each other via a network N so as to be able to communicate with each other by wire or wirelessly. Note that the information processing system 100 shown in FIG. 2 may include a plurality of information processing devices 1, etc.

[0109] 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), and 5G (5th Generation: 5th generation mobile communication system).

[0110] The terminal devices 2 and 3 are connected to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or wireless LAN (Local Area Network), and can communicate with the information processing device 1, the information processing device 4, and the like.

[0111] 3. Configuration of Information Processing Device 1 3 is a diagram showing an example of the configuration of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.

[0112] [3.1. Communication Unit 10] The communication unit 10 is realized by, for example, a communication module or a network interface card (NIC). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from each of the terminal device 2, the terminal device 3, and the information processing device 4 via the network N.

[0113] [3.2. Storage section 11] The storage unit 11 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. The storage unit 11 has a user information storage unit 20.

[0114] [3.2.1. User information storage unit 20] The user information storage unit 20 stores user information including information about the user U. Fig. 4 is a diagram showing an example of a user information table stored in the user information storage unit 20 of the information processing device 1 according to the embodiment. As shown in Fig. 4, the user information table stored in the user information storage unit 20 includes items such as "user ID," "attribute information," and "behavioral history."

[0115] The "user ID" is identification information that identifies the user U. The "attribute information" is attribute information of the user U that corresponds to the "user ID," and includes, for example, psychographic attribute information and demographic attribute information. Demographic attributes include, for example, gender, age, place of residence, and occupation, while psychographic attributes include interests such as travel, clothing, cars, and religion, lifestyle, thoughts, and ideological tendencies.

[0116] "Behavioral history" refers to the behavioral history of user U in online services, and includes, for example, search history, browsing history, posting history, and purchase history. Search history includes information on search queries used by user U in past searches and content viewed by user U from among the search results. Search query information includes, for example, search keywords and search phrases.

[0117] The browsing history includes, for example, information indicating the content that the user U has viewed on the online service, the posting history includes, for example, information indicating the content (e.g., reviews, comments, etc.) that the user U has posted in the past on the online service, and the purchase history includes information on the items of transactions that the user U has made in the past.

[0118] [3.3. Processing Unit 12] The processing unit 12 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 examples of information processing programs) stored in a storage device inside the information processing device 1 using RAM or the like as a working area.

[0119] The processing unit 12 is a controller, and 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).

[0120] 3, the processing unit 12 has a receiving unit 30, an acquiring unit 31, a generating unit 32, and a providing unit 33, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be any other configuration as long as it performs the information processing described below.

[0121] 3.3.1. Reception unit 30 The reception unit 30 receives various information and requests from the terminal device 2 and the terminal device 3 via the network N and the communication unit 10. For example, the reception unit 30 receives a selection of target content that is to be used to estimate an impression IM that the user U has or has had, and a selection of an impression group that is a group of impressions IM.

[0122] For example, an impression content generation request transmitted from the terminal device 3 of a worker O who creates or provides the target content is accepted. The impression content generation request includes target content that is the target of estimation of the impression IM held by the user U or the impression IM held by the user U, information indicating an impression group that is a group of the impressions IM, information specifying the estimation method, information indicating the type of the target content, and information indicating the type of the impression content.

[0123] The target content, impression group, estimation method, target content type, and impression content type specified in the impression content generation request are, for example, the target content, impression group, estimation method, target content type, and impression content type selected by worker O.

[0124] The receiving unit 30 receives a request to generate impression content, and thereby receives selection of target content, impression group, estimation method, target content type, and impression content type. Note that the worker O is an employee of a company that creates or provides the target content, but may also be an employee of a company commissioned by such company.

[0125] The target content is web content, such as, but not limited to, a web page, a catchphrase, a creative, or a stamp. The target content is content that is a candidate for or a target for provision on, for example, an e-commerce site, a news site, a restaurant introduction site, an image posting site, a video viewing site, or the like, and includes, but is not limited to, advertising content. The e-commerce site is, for example, but not limited to, a shopping site, an auction site, or the like.

[0126] The target content is content that can be provided on an online site provided by the information processing device 4, and the user U can use the online site provided by the information processing device 4 by operating the terminal device 2. The online sites provided by the information processing device 4 include, but are not limited to, e-commerce sites, news sites, store introduction sites, image posting sites, video viewing sites, and the like.

[0127] The impression group specified in the impression content generation request is an impression group designated by the user U from among a plurality of impression groups C1 to Cn (n is an integer equal to or greater than 2). The plurality of impression groups C1 to Cn may be, for example, impression groups classified according to the values ​​of the user U, impression groups classified according to the preferences of the user U, impression groups classified according to the lifestyle of the user U, etc., but are not limited to such examples.

[0128] The group of impressions based on the values ​​of user U is, for example, a group of impressions that classify values ​​based on Schwartz's value theory as impressions IM that user U holds or impressions IM that user U has held, and each of the 10 classification conditions mentioned above is further subdivided into multiple classification conditions, resulting in 56 classification conditions, but is not limited to such examples.

[0129] The values ​​of user U are not limited to the above-mentioned examples, and may be, for example, values ​​classified as traditionalism, success orientation, self-actualization orientation, coexistence orientation, etc., or other values. For example, if the object is a car, the values ​​of user U may be values ​​classified as prioritizing safety, livability, design, driving performance, etc., and if the object is a house, the values ​​may be values ​​classified as prioritizing location, price, layout, design, future prospects, etc.

[0130] Impression groups based on the lifestyle of user U include, for example, impression groups based on the AIO approach and impression groups based on VALS. Impression groups based on the AIO approach are impression groups classified into one or more impression groups of activities, interests, opinions, etc. Impression groups based on VALS are impression groups classified into, for example, self-actualizers, successful people, group members, those who maintain their livelihoods, those in poverty, those who aspire to success, those with social conscience, intellectuals, and young intellectuals.

[0131] The impression group may also be, for example, an impression group indicated by the innovator theory, which classifies the diffusion process of new products, such as innovators, early adopters, early majority, late majority, and laggards.

[0132] There are multiple estimation methods for estimating the impression IM that a user U has or has had on target content, including a first estimation method and a second estimation method. The first estimation method is a method in which a generation AI directly estimates the impression IM that a user U has or has had on target content. The second estimation method is a method in which, for each impression IM included in a group of impressions IM, a generation AI generates reference content that is estimated to have the impression IM that the user U has, and compares the reference content with the target content to estimate the impression IM that the user U has on the target content or has had on target content.

[0133] The target content type is, for example, the type of target content, and is indicated by, for example, a combination of an online site and a content type. For example, the target content type may be, but is not limited to, a product description on a product page of an e-commerce site, a news article on a news site, a comment on a news article on a news site, image content on an image posting site, or the title and caption text of video content on a video viewing site.

[0134] The impression content type is a type of impression content, and includes, for example, a first content type and a second content type. The first content type is a type of impression content including information indicating the impression IM that the user U is estimated to have had about the target content, and is a type of impression content that supports the creation and consideration of the target content. The second content type is a type of impression content including information indicating the impression IM that the user U is estimated to have had about the target content, and is a type of impression content that supports the understanding of the impression IM that the user U is estimated to have had about the target content.

[0135] [3.3.2. Acquisition part 31] The acquisition unit 31 acquires various pieces of information from the information processing device 4 and the storage unit 11. For example, the acquisition unit 31 acquires various pieces of content and information about each user U from the information processing device 4 via the network N and the communication unit 10. The acquisition unit 31 also acquires information about each user U from the user information storage unit 20 of the storage unit 11.

[0136] For example, when the reception unit 30 receives a request for impression content generation, the acquisition unit 31 acquires, from the request for impression content generation, target content that is to be used to estimate the impression IM held by the user U or the impression IM held by the user U, information indicating an impression group that is a group of the impressions IM, information specifying the estimation method, information indicating the type of target content, and information indicating the type of impression content.

[0137] In addition, when the target content type indicated in the impression content generation request received by the receiving unit 30 is the second content type, the acquisition unit 31 collects behavior content, which is content indicating the behavior of the user U regarding the target content, from the information processing device 4, etc.

[0138] The behavioral content is content generated by an action by the user U related to the target content, such as posted content such as reviews, comments, and messages posted by the user U regarding the target content. For example, if the target content is a product description or an image of a product, posted content as behavioral content is a review or comment posted about a product introduced by the target content.

[0139] Furthermore, if the target content is a store description or an image of the store interior, the posted content as behavioral content is a review or comment posted about the store introduced by the target content. If the target content is video content, the posted content as behavioral content is a review or comment posted about the video content.

[0140] The posted content as behavioral content may be content such as a conversation or post by the user U on the official account of the product or store indicated by the target content in the communication application. The posted content as behavioral content may be content such as a post or conversation by the user U on an online bulletin board site, for example.

[0141] [3.3.3. Generation unit 32] The generation unit 32 uses a generation AI to generate impression content that indicates an impression IM that the user U has or is estimated to have had about the target content from among the multiple impressions IM included in the impression group received by the reception unit 30.

[0142] The generation AI used in step S2 is, for example, a text generation AI, an image generation AI, a multimodal AI, etc. Such a generation AI is, for example, disposed in an external information processing device, and the generation unit 32 acquires reference content for each impression by having the generation AI generate it via an API provided by the external information processing device, but is not limited to this example. For example, the generation AI may be disposed within the generation unit 32.

[0143] Text generation AI is, for example, a language model trained to predict and output the next token from an input token sequence, such as a transfer-based model or an RNN-based model.

[0144] Examples of transfer-based models include, but are not limited to, GPT and BARD. Examples of RNN-based models include, but are not limited to, RWKV. It is desirable to keep input information, such as personal information, confidential by learning it so that it is not used as a new answer.

[0145] Examples of image generation AI include, but are not limited to, StackGAN, AttnGAN, T2I (Text-to-Image) with Transformers, and DALL-E. Examples of multimodal AI include, but are not limited to, models that generate images from text or generate text from images, such as GPT-4V and CM3Leon.

[0146] The generation unit 32 can use a plurality of estimation methods, including a second estimation method based on a first estimation method, as an estimation method for estimating the impression IM that the user U has or has had, regarding the target content. The first estimation method is a method in which the generation AI directly estimates the impression IM that the user U has or has had, regarding the target content.

[0147] The second estimation method is a method in which, for each impression included in the impression group, a generation AI generates reference content that is estimated to be the impression that user U has or has had, and compares this reference content with the target content to estimate the impression IM that user U has or has had of the target content.

[0148] Here, it is assumed that the estimation method and impression content type indicated in the impression content request received by the receiving unit 30 are a first estimation method and a first content type. In this case, the generation unit 32 inputs, as input information to the generation AI, information including, for example, instruction information instructing the user to select an impression IM that the user U has of the target content from among the multiple impressions IM1 to IMm indicated by the impression information, impression information indicating the multiple impressions IM1 to IMm included in the selected impression group, and the target content, and causes the generation AI to output information indicating one or more impressions IM that the user U is estimated to have of the target content.

[0149] Furthermore, it is assumed that the estimation method and impression content type indicated in the impression content request received by the receiving unit 30 are the first estimation method and the second content type. In this case, the generation unit 32 inputs, as input information to the generation AI, information including, for example, instruction information instructing the user to select an impression IM formed by the user U from the behavioral content from among the plurality of impressions IM1 to IMm indicated by the impression information, impression information indicating the plurality of impressions IM1 to IMm included in the selected impression group, and the behavioral content, and causes the generation AI to output information indicating the impression IM estimated to have been formed by the user U with respect to the target content.

[0150] Furthermore, it is assumed that the estimation method and impression content type indicated in the impression content request received by the receiving unit 30 are the second estimation method and the first content type. In this case, the generating unit 32 causes the generation AI to generate reference content that is estimated to have the impression IM that the user U has for each impression IM included in the selected impression group, and compares the reference content with the target content to estimate one or more impressions IM that the user U has of the target content.

[0151] Furthermore, it is assumed that the estimation method and impression content type indicated in the impression content request received by the receiving unit 30 are the second estimation method and the second content type. In this case, the generating unit 32 causes the generation AI to generate reference content that is estimated to have been the impression IM that the user U had for each impression IM included in the selected impression group, and compares the reference content with the behavioral content to estimate one or more impressions IM that the user U had for the target content.

[0152] The generation unit 32 includes a first generation processing unit 40, an estimation processing unit 41, and a second generation processing unit 42. The first generation processing unit 40 executes processing when the estimation method indicated in the impression content request received by the reception unit 30 is the second estimation method.

[0153] 3.3.3.1. First Generation Processing Unit 40 When the estimation method indicated in the impression content request received by the receiving unit 30 is the second estimation method, the first generation processing unit 40 generates reference content that is estimated to be the impression that the user U has or has had for each impression IM classified into multiple categories in the selected impression group.

[0154] [3.3.3.2. Processing for the first content type] First, a case will be described in which the impression content type indicated in the impression content request received by the receiving unit 30 is the first content type. In this case, the first generation processing unit 40 generates, for each impression IM classified into a plurality of categories in the selected impression group, reference content that is estimated to give the user U the impression.

[0155] For example, the first generation processing unit 40 causes the generation AI to generate, for each impression IM included in the selected impression group, reference content that is estimated to have the impression IM held by the user U. When the selected impression group is an impression group based on values ​​based on Schwartz's value theory, the multiple impressions IM classified in the selected impression group are the 10 types of values ​​or 56 types of values ​​described above.

[0156] For example, the first generation processing unit 40 inputs input information including instruction information, which is information instructing the generation AI to generate reference content that is estimated to give the user U the impression indicated by the impression IM, to the generation AI, and causes the generation AI to generate the reference content. The reference content is, for example, content represented by at least one of text and images.

[0157] The first generation processing unit 40 stores standard instruction information in advance, and inputs information including the standard instruction information and impression information to the generation AI as instruction information, causing the generation AI to generate reference content for each impression IM. For example, if the target content is a product description, the standard instruction information is the following character string: "I will post certain values. Please write 10 product descriptions that are likely to share those values ​​with Japanese users. Please do not include too many of the values ​​you have posted directly in the sentences."

[0158] The impression information is, for example, information on the character string "values: social power." As a result, each of 10 product descriptions that are predicted to give the user U the impression IM of social power is generated as reference content.

[0159] When the generation AI is a GPT, the standard instruction information is included in the input information (prompt) as an instruction, and the impression information is included in the input information (prompt) as a user message, but this example is not limited to this. For example, the input information may include information including the string "Social power as a value" as a user message instead of the string "Post a certain value. The value" in the standard instruction information.

[0160] [3.3.3.3. Processing for the second content type] Next, a case will be described in which the impression content type indicated in the impression content request received by the receiving unit 30 is the second content type. In this case, the first generation processing unit 40 generates, for each impression IM classified into multiple categories in the selected impression group, reference content that is estimated to have given the impression to the user U.

[0161] The first generation processing unit 40 generates, for each impression IM classified into a plurality of selected impression groups, reference content that is estimated to have been held by the user U. For example, the first generation processing unit 40 inputs input information to the generation AI that includes instruction information that is information that instructs the generation of reference content that is content that is estimated to have been held by the user U and corresponds to the behavioral content indicated by the impression IM, and causes the generation AI to generate the reference content. The reference content is, for example, content that is expressed as at least one of text and an image.

[0162] The first generation processing unit 40 stores first standard instruction information in advance, and inputs information including the standard instruction information and impression information to the generation AI as instruction information, causing the generation AI to generate reference content for each impression IM. For example, if the target content is a product description, the standard instruction information is the following string: "I will post a certain value. Please write 10 comments by users who are presumed to have held the value. Please do not include too many of the posted values ​​directly in the sentences."

[0163] The impression information is, for example, information on the character string "values: social power." As a result, each of the ten comments of the user U that are estimated to have given the impression IM of social power to the user U is generated as a reference content.

[0164] [3.3.3.4. Estimation Processing Unit 41] The estimation processing unit 41 estimates the impression IM that the user U has or has had with respect to the target content. The estimation processing unit 41 estimates the impression IM that the user U has or has had with respect to the target content, based on the estimation method and impression content type indicated in the impression content request received by the receiving unit 30.

[0165] [3.3.3.4.1. Processing for the First Estimation Method and the First Content Type] A case will be described in which the estimation method and impression content type indicated in the impression content request received by the receiving unit 30 are the first estimation method and the first content type. In this case, the estimation processing unit 41 causes the generation AI to estimate the impression IM that the user U has of the target content from among the multiple impressions IM1 to IMm included in the selected impression group.

[0166] For example, the estimation processing unit 41 inputs, as input information to the generation AI, instruction information instructing the user U to select the impression IM that the user U has of the target content from among the multiple impressions IM1 to IMm indicated by the impression information, impression information indicating the multiple impressions IM1 to IMm included in the selected impression group, and information including the target content, and causes the generation AI to output information indicating one or more impressions IM that the user U is estimated to have of the target content.

[0167] Figure 5 is a diagram showing an example of input information input to the generation AI by the estimation processing unit 41 in the processing unit 12 of the information processing device 1 according to the embodiment, in which the selected impression group is a group of impressions based on the values ​​of the user U, and the target content is a catchphrase that reads, "You can tell the difference because it's something you use every day."

[0168] In the input information 50 shown in FIG. 5, the estimation processing unit 41 includes information such as the character string "Please select three or more images from the values ​​below that fit the catchphrase 'You can tell the difference because it's something you use every day.' The output format should be in CSV format as shown below.\nValue, Reason" in the input information as instruction information.

[0169] Furthermore, in the input information 50, the estimation processing unit 41 includes information including the character strings “Social power, Authority, Wealth, ..., Family security, Reciprocation of favors, Health, Sense of belonging” as impression information.

[0170] For example, instead of the information of the character string "Please select three or more images from the values ​​below that fit the catch phrase," the estimation processing unit 41 can use information such as "Please select three or more impressions from the values ​​below that are estimated to be formed by the user for the catch phrase," or information such as "Please estimate a score indicating the degree of impression that the user is estimated to have for the catch phrase for each of the values ​​below. The score should be in the range of 1 to 10, with a higher value representing a higher degree of impression," but is not limited to such examples. Furthermore, the output format is not limited to CSV format.

[0171] The instruction information also includes character information according to the type of target content. In the example described above, the type of target content is a catchphrase, so the instruction information includes the information of the character string "catchphrase." However, if the type of target content is a product description on a product page of an e-commerce site, the instruction information includes the information of the character string "product description."

[0172] In this way, the estimation processing unit 41 generates instruction information according to the type of target content by including character information according to the type of target content in the instruction information, but it can also input instruction information that is independent of the type of target content to the generation AI.

[0173] For example, the estimation processing unit 41 can set instruction information including the information of the character string "Please select three or more images from the values ​​below that fit the input information" as the system message, instead of the character string "Please select three or more images from the values ​​below that fit the catchphrase 'You can tell the difference because it's something you use every day.'" The system message is a message that instructs the behavior of the generating AI, and is, for example, a message set in the input information as the content of "'role':'system'" in OpenAI's GPT model.

[0174] Furthermore, the estimation processing unit 41 can also use the generation AI to estimate the impression IM that the user U has of the target content from among multiple impressions IM1 to IMm included in the selected impression group by limiting the attributes of the user U. In this case, instead of the information of the string "Please select three or more images from the values ​​below that fit the catchphrase," the estimation processing unit 41 can use information such as "Please select three or more impressions from the values ​​below that are estimated to be formed by a man in his twenties for the catchphrase." or information such as the string "Please estimate, for each of the values ​​below, a score indicating the degree of impression that a man in his twenties is estimated to have for the catchphrase. The score should range from 1 to 10, with a higher value indicating a higher degree of impression." When the generation AI is to estimate one or more impressions IM that a user U with an attribute other than a man in his twenties has, the information of the string "man in his twenties" can be replaced with information indicating another attribute.

[0175] Furthermore, when the target content is image content, the estimation processing unit 41 can input information including the target content and instruction information including information such as a string of characters "Please select three or more images from the values ​​below that fit the input image," to the multimodal AI as input information, and cause the multimodal AI to output a similarity. Note that, as in the case when the target content is other than image content, the estimation processing unit 41 can limit the attributes of the user U and output a score indicating the degree of impression IM.

[0176] [3.3.3.4.2. Processing for the First Estimation Method and the Second Content Type] A case where the estimation method and impression content type indicated in the impression content request received by the receiving unit 30 are the first estimation method and the second content type will be described.

[0177] In this case, the estimation processing unit 41 inputs, as input information to the generation AI, information including, for example, instruction information instructing the user U to select the impression IM that the user U has from the behavioral content from among the multiple impressions IM1 to IMm indicated by the impression information, impression information indicating the multiple impressions IM1 to IMm included in the selected impression group, and the behavioral content, and causes the generation AI to output information indicating the impression IM that is estimated to have been held by the user U regarding the target content.

[0178] For example, if the selected impression group is a group of impressions based on the values ​​of user U, the behavioral content is represented by the character string "XXX...XXX." In this case, the estimation processing unit 41 generates instruction information including the information of the character string "'XXX...XXX' is a comment posted by a user regarding the target content below. Please select three or more of the values ​​below that are the images that user U is estimated to have had about the target content below. Please output in CSV format as shown below.\nValue, Reason," impression information, and target content.

[0179] Furthermore, the estimation processing unit 41 can use, for example, information such as "Please estimate a score indicating the degree of impression that user U is estimated to have had of the target content for each of the values ​​below. The score should be in the range of 1 to 10, with a higher value being used for a higher degree of impression," instead of the information in the string "Please select three or more of the values ​​below that represent the image that user U has of the target content," but is not limited to such an example.

[0180] The output format is not limited to CSV. The instruction information may include, instead of the target content, a character string indicating a product, store, or the like identified by the target content. In this case, the character string is used instead of the above-mentioned character string "the following target content." A portion of the above-mentioned instruction information may be set as a system message.

[0181] The estimation processing unit 41 can generate behavioral content that includes the content of multiple users U in the instruction information regardless of the attributes of the users U, or can generate behavioral content that includes the content of multiple users U for each attribute of the users U. When the estimation processing unit 41 includes the content of multiple users U for each attribute of the users U in the instruction information, it can cause the generation AI to output information indicating one or more impressions IM that are estimated to have been held by the users U for each attribute of the users U.

[0182] Furthermore, when the target content is an image, the estimation processing unit 41 can input information including instruction information such as "The following images are images posted by users regarding the following target content" to the multimodal AI as input information, instead of the information of the string "'XXX...XXX' is a comment posted by a user regarding the following target content," and cause the multimodal AI to output information indicating one or more impressions IM that are estimated to have been held by the user U.

[0183] In addition, when the behavioral content includes text and images, the estimation processing unit 41 can include the text and images as behavioral content in the instruction information, input information including such instruction information to the multimodal AI as input information, and output it from the multimodal AI.

[0184] [3.3.3.4.3. Processing for the second estimation method and the first content type] A case where the estimation method and impression content type indicated in the impression content request received by the receiving unit 30 are the second estimation method and the first content type will be described.

[0185] In this case, the estimation processing unit 41 compares the target content that is the subject of estimation of the impression IM held by the user U with the reference content for each impression IM, and estimates one or more impressions IM held by the user U regarding the target content based on the comparison result.

[0186] The estimation processing unit 41 compares the target content that is the subject of estimation of the impression IM held by the user U with the reference content for each impression IM. In order to compare the target content with the reference content for each impression IM, the estimation processing unit 41 vectorizes the target content and each reference content.

[0187] The vectorization of the content is performed, for example, by embedding using a language model (e.g., a transformer-based model). The vectorized content is represented, for example, by a vector with several hundred dimensions, but is not limited to such examples. Embedding using a language model is, for example, embedding using text-embedding-ada provided by OpenAI (registered trademark), BERT, etc., but is not limited to such examples.

[0188] Note that content vectorization is not limited to embedding using a language model, and content vectorization may be performed using, for example, Doc2Vec, the average of word embedding, etc. Word2Vec, fastText, etc. are used for word embedding.

[0189] The estimation processing unit 41 classifies the target content into an impression IM corresponding to a reference content whose vector similarity with the target content is equal to or greater than a threshold. The estimation processing unit 41 can classify the target content into only one impression IM, or into two or more impression IMs.

[0190] For example, the estimation processing unit 41 can classify the target content into only one impression IM by classifying the target content into an impression IM corresponding to the reference content whose vector similarity is equal to or greater than a threshold and has the highest similarity.

[0191] Furthermore, when there are two or more reference contents whose vector similarities with the target content are equal to or greater than a threshold, the estimation processing unit 41 can classify the target content into two or more impressions IM corresponding to the two or more reference contents, respectively.

[0192] The similarity between the vectors is cosine similarity, but may also be Jaccard similarity, or the inverse of the Euclidean distance or the inverse of the Manhattan distance. When the Euclidean distance or the Manhattan distance is used, the estimation processing unit 41 classifies, for example, target content whose Euclidean distance or Manhattan distance from the reference content is less than a threshold, into an impression IM corresponding to the reference content.

[0193] In addition, the estimation processing unit 41 can use any method to learn a classification model using vectors and the corresponding hand-labeled data, and then use that model to perform classification, or it can identify the similarity between vectors or classify vectors, and ultimately the similarity between content items or classify content items.

[0194] In addition, when the reference content and the target content are images, the estimation processing unit 41 can input information including the reference content, the target content, and instruction information indicating an instruction to output the similarity between the reference content and the target content to the multimodal AI as input information, and cause the multimodal AI to output the similarity.

[0195] In this case, the estimation processing unit 41 classifies the impression IM into, for example, an impression IM generated by multimodal AI that corresponds to the reference content with the highest similarity, which is equal to or greater than a threshold, and an impression IM generated by multimodal AI that corresponds to the reference content with a similarity equal to or greater than a threshold.

[0196] In addition, when the reference content and the target content are images, the estimation processing unit 41 can also cause the multimodal AI to generate explanatory text that explains what images are contained in each of the reference content and the target content.

[0197] In this case, the estimation processing unit 41 vectorizes each of the explanatory sentences of the reference content and the target content, and calculates the similarity between the vectorized explanatory sentences of the reference content and the vectorized explanatory sentences of the target content. The method of calculating the similarity and the group of impressions to the impression IM of the target content are the same as when the reference content and the target content are text.

[0198] When the reference content and the target content are images, the estimation processing unit 41 can also calculate the similarity by directly vectorizing each of the reference content and the target content.

[0199] Furthermore, when the reference content and the target content each contain text and an image, the estimation processing unit 41 classifies the impressions into an impression IM corresponding to the reference content whose integrated score, which is a score obtained by weighting and adding the similarity between the texts and the similarity between the images, is equal to or greater than a threshold, and an impression IM corresponding to the reference content whose integrated score is equal to or greater than the threshold and is the largest.

[0200] [3.3.3.4.4. Processing for the second estimation method and second content type] Next, a case where the estimation method and impression content type indicated in the impression content request received by the receiving unit 30 are the second estimation method and the second content type will be described.

[0201] In this case, the estimation processing unit 41 compares, for each dynamic content, the behavioral content that is the subject of estimation of the impression IM held by the user U with the reference content for each impression IM, and estimates one or more impressions IM held by the user U regarding the target content based on the comparison result.

[0202] The estimation processing unit 41 compares, for each behavioral content, the behavioral content that is the subject of estimation of the impression IM held by the user U with the reference content for each impression IM. In order to compare the behavioral content with the reference content for each impression IM, the estimation processing unit 41 vectorizes each behavioral content and each reference content. The method for vectorizing the content is as described above.

[0203] The estimation processing unit 41 performs a process of vectorizing the behavioral content and calculating the similarity between the vector of each reference content for each behavioral content. Then, the estimation processing unit 41 estimates, for example, impressions IM corresponding to reference content whose average value of the vector similarity with each behavioral content is equal to or greater than a threshold, as one or more impressions IM that the user U has had with the target content.

[0204] Furthermore, the estimation processing unit 41 estimates, for example, impressions IM corresponding to reference content whose median value of the vector similarity with each behavioral content is equal to or greater than a threshold value as one or more impressions IM that the user U has had with respect to the target content.

[0205] 3.3.3.5. Second Generation Processing Unit 42 Based on the estimation result by the estimation processing unit 41, the second generation processing unit 42 generates, as impression content, content including information indicating one or more impressions IM into which the target content has been classified.

[0206] For example, the second generation processing unit 42 generates, as impression content, content that maps multiple impressions IM1 to IMm classified into specific impression groups and that includes information indicating the impression IM that the user U has or is presumed to have had about the target content.

[0207] [3.3.4.Providing Department 33] The providing unit 33 provides the impression content generated by the generating unit 32. For example, the providing unit 33 provides the impression content generated by the generating unit 32 to the worker O by transmitting the impression content generated by the generating unit 32 to the terminal device 3 of the worker O via the communication unit 10 and the network N.

[0208] The terminal device 3 receives the impression content transmitted from the providing unit 33 of the information processing device 1 via the communication unit 10 and the network N, and displays the received impression content. Fig. 6 is a diagram showing an example of the impression content generated by the second generation processing unit 42 in the processing unit 12 of the information processing device 1 according to the embodiment.

[0209] Impression content 60 shown in Fig. 6 is content in which impressions IM classified as impressions that user U has of values ​​based on Schwartz's value theory are highlighted in content in which a plurality of values ​​based on Schwartz's value theory are mapped as a plurality of impressions IM1 to IMm (m=56 in Fig. 1). In the example shown in Fig. 1, content showing introductions or introduction images of four different models of a certain car model is shown as the target content.

[0210] In impression content 60, the model A car is classified into the impressions "freedom," "independence," and "self-respect," which are subdivisions of the impression "self-determination," and into the impression "inner harmony," which is a subdivision of the impression "universalism."

[0211] In impression content 60, the model B car is classified into the impressions "varied life" and "vibrant life" which are subdivisions of the impression "stimulation," the impressions "enjoyment of life" and "fun" which are subdivisions of the impression "hedonism," and the impression "belonging" which is subdivisions of the impression "safety."

[0212] Furthermore, in impression content 60, the model C automobile is classified into the impression "freedom" and impression "goal selection" which are subdivided from the impression "self-determination," the impression "enjoyment of life" and impression "fun" which are subdivided from the impression "hedonism," the impression "competence" which is subdivided from the impression "achievement," and the impression "health" and classification "family safety" which are subdivided from the impression "safety."

[0213] In impression content 60, the model D automobile is classified into the impressions "creativity," "freedom," and "goal choice," which are subdivisions of the impression "self-determination," the impression "enjoyment of life," which is a subdivision of the impression "hedonism," the impression "influence," which is a subdivision of the impression "achievement," and the impression "wealth," which is a subdivision of the impression "power."

[0214] [4. Processing Procedure] Next, a procedure of information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. Fig. 7 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0215] 7, the processing unit 12 of the information processing device 1 determines whether or not an impression content request has been received (step S10). If the processing unit 12 determines that the impression content request has been received (step S10: Yes), the processing unit 12 estimates the impression that the user U has or is estimated to have had, based on the information included in the impression content request, using a generation AI (step S11).

[0216] Next, the processing unit 12 generates impression content based on the impression estimated in step S11 (step S12), and then provides the impression content generated in step S12 to the worker O (step S13).

[0217] When the processing of step S13 is completed or when it is determined that the request for the image content has not been received (step S10: No), the processing unit 12 determines whether or not the operation end timing has arrived (step S14). The processing unit 12 determines that the operation end timing has arrived when, for example, the power of the information processing device 1 is turned off.

[0218] If the processing unit 12 determines that the operation end time has not yet arrived (step S14: No), it proceeds to step S10, and if it determines that the operation end time has arrived (step S14: Yes), it terminates the processing shown in Figure 7.

[0219] [5. Modifications] In the above example, the generation unit 32 estimated the impression IM that the user U had based on the behavioral content of the user U, but it can also estimate the impression IM that the user U had of the target content based on attribute information (e.g., psychographic attributes, etc.) of the user U who performed an action related to the target content and other behavioral information.

[0220] Furthermore, the generation unit 32 can also estimate the impression IM that the user U has or has had regarding the target content by performing a weighted addition of the impression IM estimated using the first estimation method and the impression IM estimated using the second estimation method.

[0221] In addition, the generation unit 32 can estimate an impression IM that is equal to or greater than a threshold value as the impression IM that the user U has or has had regarding the target content, by performing a weighted addition of the score of each impression IM estimated using the first estimation method and the score of each impression IM estimated using the second estimation method.

[0222] Furthermore, the generation unit 32 can estimate an impression IM for which the estimation results from the first estimation method and the second estimation method match as the impression IM that the user U has or has had with respect to the target content.

[0223] Furthermore, the generation unit 32 can also estimate a plurality of impressions IM, including an impression IM estimated by the first estimation method and an impression IM estimated by the second estimation method, as the impression IM that the user U has or has had regarding the target content.

[0224] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by, for example, a computer 80 configured as shown in Fig. 8. Fig. 8 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, an HDD (Hard Disk Drive) 84, a communication interface (I / F) 85, an input / output interface (I / F) 86, and a media interface (I / F) 87.

[0225] The CPU 81 operates and controls each part based on programs stored in the ROM 83 or the HDD 84. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 starts up, programs that depend on the hardware of the computer 80, and the like.

[0226] The HDD 84 stores programs executed by the CPU 81, data used by such programs, etc. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 81, and transmits data generated by the CPU 81 to other devices via the network N.

[0227] The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard or a mouse, via the input / output interface 86. The CPU 81 acquires data from the input devices via the input / output interface 86. The CPU 81 also outputs generated data to the output devices via the input / output interface 86.

[0228] The media interface 87 reads a program or data stored in a recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads the program or data from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0229] For example, when the computer 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 executes programs loaded onto the RAM 82 to realize the functions of the processing unit 12. In addition, the HDD 84 stores data in the storage unit 11. The CPU 81 of the computer 80 reads and executes these programs from a recording medium 88, but as another example, the CPU 81 may obtain these programs from another device via the network N.

[0230] [7. Other] 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.

[0231] 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.

[0232] For example, the information processing device 1 described above may be realized by a terminal device and a server computer, or may be realized by multiple server computers. Furthermore, depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API or network computing.

[0233] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0234] [8. Effects] As described above, the information processing device 1 according to the embodiment includes a receiving unit 30, a generating unit 32, and a providing unit 33. The receiving unit 30 receives a selection of target content that is the target of estimation of an impression IM that the user U has or has had, and a selection of an impression group that is a group of impressions IM. The generating unit 32 uses a generation AI to generate impression content that indicates an impression IM that the user U has or is estimated to have had of the target content from among the multiple impressions IM included in the impression group received by the receiving unit 30. The providing unit 33 provides the impression content generated by the generating unit 32. This enables the information processing device 1 to reduce the workload required to estimate the user U's impression of the target content.

[0235] Furthermore, the generation unit 32 causes the generation AI to estimate, from among the multiple impressions IM, the impression IM that the user U has or is estimated to have had about the target content. This allows the information processing device 1 to reduce the workload required to estimate the impression that the user U has about the target content.

[0236] Furthermore, the generation unit 32 inputs, as input information to the generation AI, information including impression information indicating the multiple impressions IM included in the impression group and instruction information instructing the user U to select an impression IM that the user U has or has had about the target content from the multiple impressions IM indicated by the impression information, and causes the generation AI to output information indicating the impression IM that the user U has or is estimated to have had about the target content. This enables the information processing device 1 to accurately estimate the impression of the user U about the target content.

[0237] Furthermore, the generation unit 32 inputs information further including the target content as input information to the generation AI, and causes the generation AI to output information indicating the impression IM that the user U is estimated to have of the target content. This allows the information processing device 1 to accurately estimate the impression the user U has of the target content.

[0238] The generation unit 32 also inputs information including the target content or behavioral content, which is content generated by an action by the user U related to the target content, to the generation AI as input information, and causes the generation AI to output information indicating the impression that the user U is estimated to have had of the target content. This allows the information processing device 1 to accurately estimate the impression that the user U has of the target content.

[0239] The generation unit 32 also includes a first generation processing unit 40, an estimation processing unit 41, and a second generation processing unit 42. The first generation processing unit 40 generates, for each impression IM included in the impression group, reference content that is estimated to have given or has given the user U the impression IM. The estimation processing unit 41 estimates the impression IM that the user U has or is estimated to have given, based on a comparison result between each reference content and either action content, which is content resulting from an action by the user U that is related to the target content, or the target content. The second generation processing unit 42 generates impression content based on the estimation result by the estimation processing unit 41. This allows the information processing device 1 to accurately estimate the user U's impression of the target content.

[0240] Furthermore, the receiving unit 30 receives the selection of one impression group from a plurality of predetermined impression groups, thereby enabling the information processing device 1 to reduce the workload required to estimate the user U's impression of the target content.

[0241] Furthermore, the generating unit 32 generates, as impression content, content that maps multiple impressions included in the impression group received by the receiving unit 30 and that includes information indicating the impression IM that the user U has or is presumed to have had regarding the target content. This allows the information processing device 1 to enable the worker O to easily understand the impression that the user U has regarding the target content.

[0242] The above describes the embodiments of the present application in detail based on the drawings, but this is merely an example, 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.

[0243] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0244] 1,4 Information processing equipment 2,3 Terminal equipment 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 30 Reception 31 Acquisition Department 32 Generation part 33 Providing Department 40 First generation processing unit 41 Estimation processing unit 42 Second generation processing unit 100 Information Processing Systems N Network

Claims

1. a reception unit that receives a selection of target content that is a target of an impression held by a user or an impression that has been held by a user, and a selection of an impression group that is a group of impressions; a generation unit that generates, using a generation AI, impression content indicating an impression that the user has or is presumed to have had on the target content from among a plurality of impressions included in the impression group received by the reception unit; a providing unit that provides the impression content generated by the generating unit.

1. An information processing device comprising:

2. The generation unit The generation AI is caused to estimate the impression that the user has or is estimated to have had regarding the target content from among the plurality of impressions.

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

3. The generation unit Information including impression information indicating the plurality of impressions included in the impression group and instruction information instructing the user to select an impression that the user has or has had with respect to the target content from the plurality of impressions indicated by the impression information is input to the generation AI as input information, and information indicating the impression that the user has or is estimated to have had with respect to the target content is output from the generation AI.

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

4. The generation unit Inputting information further including the target content as the input information to the generation AI, and outputting information indicating an impression that the user is estimated to have of the target content from the generation AI.

4. The information processing apparatus according to claim 3,

5. The generation unit Inputting information further including the target content or behavioral content, which is content generated by an action by the user related to the target content, into the generation AI as the input information, and outputting information indicating an impression that the user is presumed to have had of the target content from the generation AI.

4. The information processing apparatus according to claim 3,

6. The generation unit a first generation processing unit that generates, for each impression included in the group of impressions, reference content that is estimated to be the impression that the user has or has had; an estimation processing unit that estimates an impression that the user has or is estimated to have had based on a comparison result of comparing the target content or behavioral content, which is content generated by an action by the user related to the target content, with each of the reference contents; a second generation processing unit that generates the impression content based on the estimation result by the estimation processing unit.

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

7. The reception unit Accepting selection of one impression group from a plurality of predetermined impression groups 6. The information processing device according to claim 1, wherein:

8. The generation unit The impression content is generated by mapping the plurality of impressions included in the impression group received by the receiving unit, and includes information indicating the impression that the user has or is presumed to have had regarding the target content.

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

9. 1. A computer-implemented information processing method, comprising: a receiving step of receiving a selection of target content for which the impression held by the user or the impression held by the user is to be estimated, and a selection of an impression group which is a group of impressions; a generating step of generating impression content indicating an impression that the user has or is presumed to have had regarding the target content from among a plurality of impressions included in the impression group received by the receiving step, using a generating AI; a providing step of providing the impression content generated by the generating step. An information processing method comprising:

10. a receiving step for receiving a selection of target content for which the user has an impression or an impression that has been received by the user is to be estimated, and a selection of an impression group that is a group of impressions; a generation procedure for generating, using a generation AI, impression content indicating an impression that the user has or is presumed to have had regarding the target content from among a plurality of impressions included in the impression group accepted by the acceptance procedure; a providing step of providing the impression content generated by the generating step, An information processing program characterized by:

Images