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

Abstract

To provide an information processing apparatus, an information processing method, and an information processing program capable of accurately applying an event that draws a lot of attention with advertisement information.SOLUTION: An information processing apparatus includes an acquisition unit, a determination unit, a generation unit, and a providing unit. The acquisition unit acquires post information. The determination unit determines an attention event, which is an event that draws a lot of attention, on the basis of the post information acquired by the acquisition unit. The generation unit inputs input information to a generative AI or an AI agent configured to generate and output information according to input information, the input information including information indicating the attention event determined by the determination unit and information indicating an instruction for outputting at least part of advertisement information based on the attention information, and causes the generative AI or the AI agent to generate at least part of the advertisement information. The providing unit provides the advertisement information at least part of which is generated by the generative AI or the AI agent.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] With the spread of the Internet, the electronic advertising market that delivers advertisements to users using the Internet is expanding rapidly. For example, Patent Document 1 proposes a technology for generating advertisement information based on advertisement parts and advertisement templates associated with keywords corresponding to trend words, which are character strings with a large increase in search frequency, from an advertisement database that manages keywords, advertisement parts, and advertisement templates in association with each other. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2012-141682 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the above-mentioned conventional technology, keywords, advertising parts, and advertising templates are associated in advance, and if there is no keyword that corresponds to an event that is attracting a lot of attention, such as a trending word, it is difficult to generate advertising information.

[0005] 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 apply events that are attracting a lot of attention to advertising information with higher accuracy. [Means for solving the problem]

[0006] The information processing device according to the present application includes an acquisition unit, a determination unit, a generation unit, and a provision unit. The acquisition unit acquires posted information. The determination unit determines an event of interest that is an event with a high level of attention based on the posted information acquired by the acquisition unit. The generation unit inputs input information including information indicating the event of interest determined by the determination unit and information indicating an instruction to output at least a portion of the advertising information based on the event of interest to a generation AI or AI agent that generates and outputs information according to the input information, and causes the generation AI or AI agent to generate at least a portion of the advertising information. The provision unit provides the advertising information at least a portion of which has been generated by the generation AI or AI agent. Effect of the Invention

[0007] According to one aspect of the embodiment, it is possible to provide an effect that events that are attracting a lot of attention can be applied to advertisement information with higher accuracy. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Diagram 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. [Diagram 5] FIG. 5 is a diagram illustrating an example of an advertisement information table stored in the advertisement information storage unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of an advertisement delivery history table stored in the advertisement delivery history storage unit of the information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of a chat screen including advertisement information displayed on the terminal device according to the embodiment. [Figure 8]FIG. 8 is a diagram illustrating an example of a home screen including advertisement information displayed on the terminal device according to the embodiment. [Figure 9] FIG. 9 is a flowchart illustrating an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 10] FIG. 10 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the information processing device, the information processing method, and the 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. In addition, each embodiment can be appropriately combined as long as the processing contents are not contradictory. In addition, the same parts in each of the following embodiments are given the same reference numerals, and duplicated explanations will be omitted.

[0010] [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 showing an example of information processing according to the embodiment.

[0011] 1 is an information processing device that cooperates with a terminal device 2 of a user U and provides various types of information to the user U online, and is realized by, for example, one or more servers or a cloud system. Note that, although one terminal device 2 is shown in the example shown in FIG. 1, the information processing device 1 cooperates with each of a plurality of terminal devices 2 and provides various services online to the user U of each terminal device 2.

[0012] The information processing device 1 receives an advertisement provision request from the advertiser's terminal device 3 or the like (step S1). The advertisement provision request includes advertiser information, advertisement-related information, etc. The advertisement-related information includes, for example, advertisement target information which is information on the product or service to be advertised, user demographic information which is information on the user demographic targeted by the advertisement, and information such as the advertisement information distribution period and advertisement budget.

[0013] The advertising target information includes information indicating the name of the product or service to be advertised, information indicating the category of the product or service to be advertised, information indicating a description of the product or service to be advertised, etc. The information related to the advertisement includes, for example, information such as default advertising text and default advertising image, but may not include one or both. The information related to the advertisement also includes information indicating an information type, which is the type of information to be generated by a generation AI, etc. The information type is, for example, advertising text, advertising image, etc.

[0014] In addition, a personalization request, which is a request for personalizing the advertisement information, can be received from the advertiser. Personalizing the advertisement information means, for example, customizing according to the user U to which the advertisement is to be delivered, and thus it is possible to deliver advertisement information with appropriate content to the user U to which the advertisement is to be delivered.

[0015] Note that the personalization request or information related to the personalization request may be included in the request to provide an advertisement. In this case, the information processing device 1 accepts the personalization request by accepting the request to provide an advertisement.

[0016] Next, the information processing device 1 acquires a plurality of pieces of posted information from an internal storage unit or an external information providing device (step S2). The posted information is information posted to various online sites provided by the information processing device 1 or other information processing devices. The online sites are, for example, social media, news sites, bulletin board sites, Q&A sites, etc., but are not limited to these examples. For example, the online sites may be shopping sites, price comparison sites, and word-of-mouth sites.

[0017] Examples of social media include, but are not limited to, Instagram (registered trademark), TikTok (registered trademark), YouTube (registered trademark), X (formerly Twitter: registered trademark) (registered trademark), and Facebook (registered trademark).

[0018] News sites include, but are not limited to, aggregation sites such as Yahoo (registered trademark), news sites provided by various news organizations, etc. Information posted to news sites includes, for example, information indicating news content, information indicating comments and ratings on the news content, etc., but may also include comments on comments on the news content, etc.

[0019] Bulletin board sites include 2chan and 5chan, where users post and exchange information on a wide range of topics. Q&A sites include Yahoo! Answers, where users post and exchange information on a wide range of topics, from everyday questions to specialized questions.

[0020] The information processing device 1 can acquire various types of posted information by using, for example, APIs (Application Programming Interfaces) of various sites.

[0021] Next, the information processing device 1 determines an event of interest that is an event with a high degree of attention based on the plurality of pieces of posted information acquired in step S2 (step S3). The information processing device 1, for example, performs a morphological analysis on the text included in the plurality of pieces of posted information acquired in step S2 to extract a plurality of words, and extracts a plurality of character strings from the extracted plurality of words. Each character string extracted by the information processing device 1 includes, for example, a keyword or a phrase, and may be referred to as a target character string below.

[0022] The target character string is, for example, a character string obtained using N-gram, or a character string that matches a specific part-of-speech pattern. The specific part-of-speech pattern is, for example, a combination of a noun and a verb, a combination of an adjective and a noun, or a combination of an adjective, a noun, and a verb. Note that a noun is a character string formed by combining one noun or multiple nouns, and may include a particle such as "no".

[0023] Furthermore, the information processing device 1 may have, for example, a character string extraction dictionary that defines a plurality of character strings to be extracted, and may extract a plurality of target character strings from text included in a plurality of pieces of posted information using the character string extraction dictionary.

[0024] The information processing device 1 can also extract a plurality of target character strings from a plurality of pieces of posted information using a language model. The language model is, for example, a model generated using learning information including each of character strings to be extracted and character strings not to be extracted, and information indicating whether or not the character strings are to be extracted. The information processing device 1 inputs information including the posted information and information for extracting phrases from the posted information to the language model as input information, and extracts phrases output from the input language model as target character strings.

[0025] The language model is, for example, a model such as a transformer that is trained to estimate and output the next token from an input token string. Such a language model is stored in an internal storage unit or an external information providing device, and is created independently by the operator of the information processing device 1. It is preferable that the input information is trained so as not to be used as a new answer, thereby concealing the input information, such as personal information.

[0026] In addition, for example, when the posted information acquired in step S2 is information posted on social media and the posted information contains a character string with a hashtag, the information processing device 1 can extract the character string with the hashtag as a target character string.

[0027] Furthermore, the information processing device 1 may be configured to have, for example, a negative-positive string dictionary that includes negative strings and positive strings, and such a negative-positive string dictionary can be used to extract, as a target string, either a negative string or a positive string from among the strings extracted by the above-mentioned method or the like as strings contained in posted information.

[0028] For example, the information processing device 1 extracts as target strings strings other than negative strings from among the strings extracted by the above-mentioned method or the like as strings contained in the posted information, or extracts as target strings positive strings from among the strings extracted by the above-mentioned method or the like as strings contained in the posted information.

[0029] The information processing device 1 calculates the number of each extracted target string for each predetermined unit period (e.g., 1 hour, 3 hours, 1 day, etc.) and determines, for example, an event indicated by a target string whose number of posts is greater than or equal to a threshold and whose increase rate in the number of posts is greater than or equal to the threshold, to be a noteworthy event.

[0030] For example, the information processing device 1 determines an event indicated by a target character string in which the number of posts is equal to or greater than a threshold and the increase rate of the number of posts is equal to or greater than a threshold, as a noteworthy event. The information processing device 1 can also determine a noteworthy event using a determination model that inputs information indicating the number of posts per unit period and outputs information indicating whether or not the event is a noteworthy event.

[0031] The above-mentioned judgment model is, for example, a linear regression model, a Gradient Boosting Decision Tree (GBDT), or a machine learning model such as Recurrent Neural Networks (RNNs) such as a Long Short-Term Memory (LSTM) or a Gated Recurrent Unit (GRU).

[0032] In addition, for example, when the posted information is information posted on social media, the information processing device 1 can determine the corrected post count by weighting and adding the number of shares and retweets, etc. to the number of posts, and determine an event indicated by a target string for which the corrected post count is equal to or greater than a threshold and the increase rate of the corrected post count is equal to or greater than the threshold, as an event of interest.

[0033] The information processing device 1 can determine an attention event that has become apparent by the above-mentioned method, but can also determine a potential attention event that has not yet become apparent. For example, the information processing device 1 determines, as an attention event, an event indicated by a target character string whose degree of coincidence with the change pattern of the number of posts or the corrected number of posts before the attention event becomes apparent is equal to or greater than a threshold value. Note that the determination of an attention event using the number of posts or the corrected number of posts is not limited to the above-mentioned example.

[0034] Furthermore, for example, the information processing device 1 can determine a potential event of interest using a determination model that inputs information indicating the number of posts per unit period and outputs information indicating whether or not the event is a potential event of interest. Such a determination model is, for example, a machine learning model, and is generated using learning information including the number of posts per unit period and information indicating whether or not the event is a potential event of interest.

[0035] Furthermore, the information processing device 1 can determine whether or not a noteworthy event has occurred. For example, the information processing device 1 determines whether or not an event indicated by a target character string has changed from a non-noteworthy event to a noteworthy event.

[0036] For example, the information processing device 1 determines that a notable event has occurred when, for example, the number of posts or the corrected number of posts is greater than or equal to a threshold and the rate of increase in the number of posts or the corrected number of posts changes from less than the threshold to greater than or equal to the threshold, or when the output of the judgment model switches from information indicating that the event is not a notable event to information indicating that it is a notable event.

[0037] The information processing device 1 can also determine an event of interest for each category of a product or service that is the subject of advertising. If the product that is the subject of advertising is men's sneakers, the category is men's sneakers, sneakers, shoes, etc., and if the product that is the subject of advertising is beer, the category is beer, beer-related products, alcoholic beverages, etc. Men's sneakers and beer are lower-level categories, sneakers and beer-related products are middle-level categories, and shoes and alcoholic beverages are upper-level categories.

[0038] The information processing device 1 can also determine an event of interest for each combination of the category of the product or service to be advertised and the demographic of the contributor corresponding to the target demographic of the advertisement. The information processing device 1 can also determine an event of interest for each form (e.g., color or shape) of the product or service to be advertised.

[0039] The information processing device 1 can also determine a category with a high level of attention as a notable event based on the multiple pieces of post information acquired in step S2. The information processing device 1 determines a category with a high level of attention as a notable event, for example, by a process similar to that for the target character string. For example, the information processing device 1 determines a category with a high level of attention as a notable event, the category having a number of posts equal to or greater than a threshold and an increase rate of the number of posts equal to or greater than a threshold, or the category having a corrected number of posts equal to or greater than a threshold and an increase rate of the corrected number of posts equal to or greater than a threshold.

[0040] Next, the information processing device 1 causes a generating AI (Artificial Intelligence) or an AI agent that generates and outputs information according to the input information to generate at least a part of the advertisement information (step S4).

[0041] In step S4, the information processing device 1 inputs input information to the generation AI or AI agent, the input information including, for example, information indicating the event of interest determined in step S3 and information indicating instructions for outputting advertising information based on the event of interest, and causes the generation AI or AI agent to generate advertising information.

[0042] At least a portion of the advertisement information generated in step S4 is, for example, one or more of advertisement text and advertisement image. The advertisement text is information represented by a character string, and includes information such as font, color, character size, etc. The advertisement image is information represented by one or more of a still image, a moving image, and an animation.

[0043] First, the generation of advertising information using a generation AI will be described. The generation AI is, for example, a text generation AI, an image generation AI, or a multimodal generation AI. The text generation AI is, for example, a language model trained to estimate and output the next token from an input token string, such as an attenuation model or a transfer model.

[0044] Examples of the transfer model include, but are not limited to, GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers). It is preferable that the input information is trained so that it is not used as a new answer, thereby concealing the input information such as personal information. The generation AI may be trained (for example, fine-tuned) specifically for generating advertising information.

[0045] The image generation AI is a generation AI that generates images from text, such as StackGAN (Generative Adversarial Networks), AttnGAN, T2I (Text-to-Image) with Transformers, DALL-E, etc., but is not limited to such examples.

[0046] A multimodal generative AI is, for example, a generative AI that generates images from text or generates text from images, and examples of such AI include GPT-4 and CM3Leon (Chameleon Multimodal Model), but are not limited to such examples.

[0047] The AI ​​agent may be, for example, an autonomous AI agent such as AutoGPT, or may be an autonomous AI agent created specifically for generating advertising information.

[0048] For example, when a goal is given to an autonomous AI agent, the autonomous AI agent causes a generation AI to generate a task for achieving the goal, collects information for causing the generation AI to execute the generated task, and outputs information for achieving the goal by repeating a process of making the generation AI execute the task. Note that the AI ​​agent may be a non-autonomous AI agent that causes the generation AI to generate at least a portion of the advertising information by using the generation AI multiple times according to a predetermined procedure.

[0049] The information processing device 1, for example, inputs input information to the generation AI using an API provided by a business providing the generation AI and acquires information generated by the generation AI, but the information processing device 1 may be configured to include the generation AI. Also, the information processing device 1 has an AI agent, but may be configured to use the AI ​​agent using an API provided by a business providing the AI ​​agent.

[0050] First, the generation of at least a part of the advertisement information by the generation AI will be described. It is assumed that the information indicating the event of interest determined in step S3 is "XXXXX" ("XXXXX" is a character string indicating the event of interest).

[0051] In this case, if advertisement text is specified as the information type in the advertisement provision request, the information processing device 1 inputs, as input information, information including the information of the character string "Please create advertisement text using part of 'XXXXX'" to the generation AI. The input information input to the generation AI is instruction information in natural language, and is also called a prompt.

[0052] This allows the information processing device 1 to acquire the advertising text output from the generation AI as at least a part of the advertising information. The information "Please create advertising text using a part of the character string" is an example of information indicating an instruction to output advertising information based on the event of interest.

[0053] In addition, instead of the information "Please create advertising text using part of the string "XXXXX," the information processing device 1 can also use information such as "Please create advertising text that parodies the string "XXXXX."' or "Please create advertising text that implicitly uses the string "XXXXX."'

[0054] In this case, the information "Please create advertising text that parodies the string ." and the information "Please create advertising text that implicitly uses the string ." are examples of information indicating instructions for outputting advertising information based on a phenomenon of interest.

[0055] In addition, the information processing device 1 can input, for example, input information further including information including one or more pieces of information showing examples of the input information and the output information to the generation AI. This allows the generation AI to perform simple learning and generate at least a part of the advertisement information.

[0056] The information showing examples of input information and output information is, for example, information including the character string "I don't know" and the character string "advertising text" as input information, and information including the character string "There's no reason not to buy it! I don't know" as output information.

[0057] In addition, the information processing device 1 can also input input information to the generation AI that includes, for example, information indicating the role of the generation AI, such as the string "I will use part of the information you entered to generate appropriate advertising text that is in line with the information you entered.", and information about the string "XXXXX."

[0058] In addition, if advertising text and advertising image are specified as the information type in the advertisement provision request, the information processing device 1 includes, for example, a string "Please create advertising information including advertising text and advertising image" in the above-mentioned input information instead of the string "Please create advertising text."

[0059] In addition, if an advertising image is specified as the information type in the advertisement provision request, the information processing device 1, for example, includes, in the input information described above to the generation AI, the string "Please create an advertising image" instead of the string "Please create advertising text."

[0060] The information processing device 1 can also input input information further including information on a product or service specified in the advertisement provision request to the generation AI. The product or service information is, for example, information indicating the name of the product or service, information indicating the category of the product or service, etc.

[0061] For example, assume that the name or category of a product or service is represented by a character string "YYYYY." In this case, the information processing device 1 inputs, as input information, information including, for example, the character string "Please create an appropriate advertising text for 'YYYYY' and using a part of 'XXXXX'." to the generation AI. In this way, the information processing device 1 can cause the generation AI to generate advertising text that is in line with the product or service.

[0062] In addition, the information processing device 1 can input input information further including information on a target demographic specified in the request to provide an advertisement to the generation AI. For example, it is assumed that the target demographic specified in the request to provide an advertisement is men in their 30s.

[0063] In this case, the information processing device 1 inputs, as input information, information including the character string "Please create advertising text targeting men in their 30s and using part of 'XXXXX'" to the generation AI. This allows the information processing device 1 to cause the generation AI to generate advertising text appropriate for the target demographic.

[0064] Furthermore, when the advertisement provision request includes one or more pieces of information of advertisement text and advertisement image, the information processing device 1 can also input input information further including such information to the generation AI. In this case, for example, the information processing device 1 inputs, as input information, to the generation AI, information including the information of the character string "Please change part or all of the following advertisement text to advertisement text using part of 'XXXXX'." and the advertisement text specified in the advertisement provision request. In this way, the information processing device 1 can cause the generation AI to generate advertisement text by referring to the advertisement text specified in the advertisement provision request.

[0065] In addition, when the information processing device 1 accepts a personalization request, it can also input input information further including user information, which is information about a user U to whom the advertisement information is to be provided, to the generation AI. The user information includes, for example, at least one of attribute information and history information of the user U. The attribute information of the user U is information indicating the attributes of the user U.

[0066] The attributes of the user U are, for example, demographic attributes, psychographic attributes, etc. The history information of the user U includes information on the behavior history of the user U. The behavior history of the user U includes, for example, information on the behavior history of the user U in online services.

[0067] In this case, the information processing device 1 inputs, as input information, information including the character string "Please create advertising text using part of 'XXXXX', which targets users having the following user information," and the user information to the generation AI. This enables the information processing device 1 to cause the generation AI to generate advertising text according to the user U.

[0068] The information processing device 1 can also cause the generation AI to generate at least a part of the advertising information using as input information information including information specifying the number of characters in the advertising text as information for outputting at least a part of the advertising information based on the event of interest. For example, the information processing device 1 inputs to the generation AI input information further including information of a character string "The number of characters in the advertising text should be within the range of 10 to 15 characters." This allows the information processing device 1 to prevent the number of characters in the advertising text from becoming too long or too short.

[0069] For example, the information processing device 1 can determine whether or not an event of interest has occurred, and when it determines that an event of interest has occurred, can cause the generation AI to generate at least a part of the advertisement information. This allows the information processing device 1 to appropriately catch up with the event of interest and cause the generation AI to generate at least a part of the advertisement information.

[0070] Next, the generation of at least a part of the advertisement information by the AI ​​agent will be described. For example, if advertisement text is specified as the information type in the advertisement provision request, the information processing device 1 inputs, as input information, information including the information "Please create advertisement text that uses a part of the character string "XXXXX" and has high advertising effectiveness and does not overlap with advertisement text of other companies." to the AI ​​agent.

[0071] As a result, the AI ​​agent sets the input information as a goal, generates and executes a task according to the goal, and generates and outputs the advertising text. The input information input to the AI ​​agent is instruction information in natural language, and is also called a prompt.

[0072] The AI ​​agent has functions such as having the generation AI generate tasks based on input information, collecting information from an internal memory unit or an external information providing device in response to requests from the generation AI, and having the generation AI analyze the collected information.

[0073] For example, an AI agent has a generation AI generate a task based on input information, collects the information necessary to execute the task from an internal memory unit or an external information providing device, etc., in response to a request from the generation AI, and executes the task by having the generation AI analyze the collected information.

[0074] The input information input to the AI ​​agent includes, for example, information specified as an information type in the advertisement provision request. The information specified as the information type is one or more of information indicating advertisement text and information indicating advertisement images. Here, it is assumed that the information specified as the information type in the advertisement provision request is information indicating advertisement text.

[0075] The information collected by the AI ​​agent is, for example, advertising text included in advertising information with high advertising effectiveness among past advertising information, advertising text included in advertising information within a distribution period, etc. For example, the AI ​​agent collects advertising text included in advertising information with high advertising effectiveness among past advertising information, and advertising text included in advertising information within a distribution period from an internal storage unit or an external information providing device, etc.

[0076] The AI ​​agent can make the generation AI (e.g., text generation AI or multimodal generation AI) learn advertising text with high advertising effectiveness by inputting information further including advertising text included in advertising information with high advertising effectiveness among past advertising information. In this way, the AI ​​agent can make the text generation AI generate advertising information with high advertising effectiveness from the learned advertising text with high advertising effectiveness and information indicating the phenomenon of interest.

[0077] In addition, by using information including advertising text contained in advertising information during the distribution period as input information, the AI ​​agent can have the generation AI learn advertising text that does not overlap with advertising text contained in other companies' advertising information.

[0078] For example, if advertising text is specified as the information type in the advertisement provision request, the information processing device 1 inputs, as input information, information including the character string "Please change part or all of the following advertising text to advertising text that uses part of 'XXXXX' and has high advertising effectiveness and does not overlap with advertising text of other companies." In this way, the information processing device 1 can cause the AI ​​agent to generate advertising text by referring to the advertising text specified in the advertisement provision request.

[0079] Furthermore, when the information identified as the information type includes information indicating an advertising image, the AI ​​agent causes a generation AI (e.g., an image generation AI or a multimodal generation AI) to generate an advertising image by processing similar to that for advertising text. For example, the AI ​​agent collects advertising images included in advertising information that had a high advertising effect among past advertising information and advertising images included in advertising information within a distribution period. Then, the AI ​​agent causes the generation AI to generate an advertising image based on the collected information.

[0080] The information processing device 1 can also input input information further including information indicating that the advertising information is indicative of a target demographic to the AI ​​agent. In this case, the AI ​​agent collects at least a portion of advertising information with high advertising effectiveness among the advertising information previously delivered to the target demographic specified in the advertisement provision request, and inputs the input information further including the collected information to the generation AI.

[0081] Furthermore, when the information processing device 1 receives a personalization request, it can also input to the AI ​​agent input information further including user information, which is information about a user U to whom the advertising information is to be provided. In this case, the AI ​​agent collects at least a portion of advertising information that has had an advertising effect among pieces of advertising information that have been previously delivered to the user U having the user information specified in the advertising provision request, and inputs to the generation AI input information further including the collected information.

[0082] The AI ​​agent, for example, uses as input information information including instructions to output advertising text and advertising images corresponding to a phenomenon of interest by referring to advertising information that has been effective for user U having user information specified in the advertisement provision request, and causes the generation AI to generate at least a part of the advertising information. In this way, the information processing device 1 can cause the AI ​​agent to generate advertising text corresponding to user U.

[0083] The information processing device 1 can also cause the AI ​​agent to generate at least a part of the advertising information using as input information information including information specifying the number of characters in the advertising text as information for outputting at least a part of the advertising information based on the event of interest. For example, the information processing device 1 inputs to the AI ​​agent input information further including information of a character string "The number of characters in the advertising text should be within the range of 10 to 15 characters." This allows the information processing device 1 to prevent the number of characters in the advertising text from becoming too long or too short.

[0084] For example, the information processing device 1 can determine whether or not a noteworthy event has occurred, and when it determines that a noteworthy event has occurred, can cause the AI ​​agent to generate at least a part of the advertisement information. This allows the information processing device 1 to appropriately catch up with the noteworthy event and cause the AI ​​agent to generate at least a part of the advertisement information.

[0085] The information processing device 1 can also determine whether or not an advertising target, which is the target of advertising by the advertising information, has a predetermined relationship with the event of interest. In this case, when it is determined that the advertising target and the event of interest have a predetermined relationship, the information processing device 1 can cause the generation AI or AI agent to generate at least a part of the advertising information.

[0086] The predetermined relationship is, for example, a condition that the advertising text or advertising image is not used in the advertisement of the advertising target or in the category of the advertising target in the past. In this case, the information processing device 1 determines whether or not the advertising target and the event of interest have a predetermined relationship based on, for example, an advertising history including advertising information used in the advertisement of the advertising target or in the category of the advertising target in the past.

[0087] The predetermined relationship is a condition that the NG words and NG images for each category of the advertising target are not included. In this case, the information processing device 1 determines whether or not the advertising target and the attention event have a predetermined relationship based on NG information including NG words and NG images for each category of the advertising target.

[0088] The predetermined relationship is a condition that the affinity between the advertising target and the event of interest is equal to or greater than a predetermined threshold. The information processing device 1 receives as input information information including information on the advertising target and information indicating the event of interest, and uses a language model that outputs information indicating the affinity between the advertising target and the event of interest to determine whether the affinity between the advertising target and the event of interest is equal to or greater than a predetermined threshold. The input information includes, for example, information such as a character string "What value would be obtained if the affinity between the following advertising target and the event of interest were expressed in degree?" The language model is, for example, the attenuation model or transfer model described above.

[0089] For example, when a portion of the advertising information is generated by a generation AI or an AI agent, the information processing device 1 generates the advertising information by replacing the information generated by the generation AI or AI agent with corresponding information among the advertising information included in the advertisement provision request.

[0090] For example, when the advertisement text in the advertisement information is generated by the generation AI or AI agent, the information processing device 1 generates the advertisement information by replacing the advertisement text generated by the generation AI or AI agent with the advertisement text included in the advertisement information included in the advertisement provision request. For example, the information processing device 1 generates the advertisement information by superimposing the advertisement text generated by the generation AI or AI agent on the advertisement image in the advertisement information included in the advertisement provision request.

[0091] For example, when an advertising image of the advertising information is generated by a generation AI or an AI agent, the information processing device 1 generates the advertising information by replacing the advertising image generated by the generation AI or AI agent with the advertising image included in the advertising information included in the request to provide the advertisement. For example, the information processing device 1 generates the advertising information by superimposing the advertising text of the advertising information included in the request to provide the advertisement on the advertising image generated by the generation AI or AI agent.

[0092] In addition, when advertising text or advertising image is generated again by the generation AI or AI agent, the information processing device 1 generates advertising information by replacing the advertising text and advertising image generated this time by the generation AI or AI agent with the advertising text and advertising image generated previously by the generation AI or AI agent.

[0093] Next, the information processing device 1 provides the advertising information at least partially generated by the generation AI or AI agent in step S4 to the user U who is the advertisement recipient (step S5). For example, the information processing device 1 provides the advertising information at least partially generated by the generation AI or AI agent to the user U who is the advertisement recipient by transmitting the advertising information at least partially generated by the generation AI or AI agent in step S4 to the terminal device 2 of the user U who is the advertisement recipient.

[0094] The advertising information transmitted from the information processing device 1 to the terminal device 2 is information in which advertising text is superimposed on an advertising image, but is not limited to this example and may be, for example, advertising information that includes advertising text and advertising image separately. In this case, the advertising text is superimposed on the advertising image and displayed by the terminal device 2. Also, the advertising information transmitted from the information processing device 1 to the terminal device 2 may be one of the advertising text and the advertising image.

[0095] In this way, the information processing device 1 determines an event of interest that is an event with a high level of attention based on the posted information, inputs input information including information indicating the event of interest and information indicating instructions for outputting at least a portion of the advertising information based on the event of interest to a generation AI or AI agent that generates and outputs information according to the input information, and has the generation AI or AI agent generate at least a portion of the advertising information. This allows the information processing device 1 to more accurately apply the event of interest that is an event with a high level of attention to the advertising information.

[0096] The configuration of an information processing system including the information processing device 1, the terminal device 2, and the terminal device 3 that perform such processing will be described in detail below.

[0097] 2. Configuration of the Information Processing System 2 is a diagram showing an example of a configuration of an information processing system according to an embodiment. As shown in FIG. 2, the information processing system 100 according to the embodiment includes an information processing device 1, a plurality of terminal devices 2, and a plurality of terminal devices 3.

[0098] The multiple terminal devices 2 are used by different users U. The multiple terminal devices 3 are used by different advertisers O. The terminal devices 2 and 3 are, for example, notebook PCs (Personal Computers), desktop PCs, smartphones, tablet PCs, and wearable devices. The wearable device is, for example, smart glasses or a smart watch, but is not limited to such examples.

[0099] The information processing device 1, the terminal device 2, and the terminal device 3 are connected to each other so as to be able to communicate with each other by wire or wirelessly via a network N. Note that the information processing system 100 shown in FIG. 2 may include a plurality of information processing devices 1 and the like.

[0100] The network N includes, for example, a Wide Area Network (WAN) such as the Internet and mobile communication networks such as Long Term Evolution (LTE), 4th Generation (4G), and 5th Generation (5G: fifth generation mobile communication system).

[0101] The terminal devices 2 and 3 can connect to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or a wireless LAN (Local Area Network), and communicate with the information processing device 1.

[0102] 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.

[0103] [3.1. Communication unit 10] The communication unit 10 is realized by, for example, a communication module or a NIC (Network Interface Card). 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 the terminal device 2 and the terminal device 3 via the network N.

[0104] [3.2. Storage section 11] The storage unit 11 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 11 stores a user information storage unit 20, an advertisement information storage unit 21, an advertisement delivery history storage unit 22, and a posted information storage unit 23.

[0105] 3.2.1. User information storage unit 20 The user information storage unit 20 stores 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 (Identifier)", "Attribute Information", and "History Information".

[0106] The "user ID" is identification information for identifying the user U. The "attribute information" is information on the user attributes of the user U corresponding to the "user ID", and includes information on psychographic attributes and information on demographic attributes. The demographic attributes are, for example, gender, age, place of residence, and occupation, while the psychographic attributes are interests such as travel, clothes, cars, and religion, lifestyle, thoughts, and thought trends.

[0107] The "history information" includes information on the behavioral history of the user U associated with the "user ID." The behavioral history of the user U includes, for example, information on the movement history of the user U, information on the behavioral history of the user U in online services, and information indicating the advertising effectiveness of advertising information provided to the user U. The information on the movement history of the user U includes, for example, information on the route traveled by the user U and information on the places visited by the user U.

[0108] The information on the user U's behavioral history in the online service includes, for example, search history information, browsing history information, and transaction history information in the online service of the user U. The search history information of the user U includes, for example, information on the search history of content by the user U in a web search service. The browsing history information of the user U includes, for example, information on the browsing history of content by the user U in the online service. The transaction history information includes, for example, information on the transaction history of products by the user U in the online service.

[0109] 3.2.2. Advertising information storage unit 21 The advertisement information storage unit 21 stores various pieces of information related to advertisements. Fig. 5 is a diagram showing an example of an advertisement information table stored in the advertisement information storage unit 21 of the information processing device 1 according to the embodiment.

[0110] 5, the advertisement information table stored in the advertisement information storage unit 21 includes information items such as "advertisement ID" and "advertisement information." The "advertisement ID" is an identifier that identifies an advertisement, and is information attached to the advertisement.

[0111] The "advertising information" is advertising information associated with the "advertising ID", and is, for example, a banner advertisement, a listing advertisement, a native advertisement, a social media advertisement, a video advertisement, etc., but is not limited to these examples.

[0112] 5, the advertisement information table also includes information on the budget for providing advertisement information, information on the period for distributing advertisement information, and information on target attributes, which are attributes of the target user U, associated with the "advertising ID." Furthermore, the advertisement information storage unit 21 is not limited to the above, and can store various kinds of information according to the purpose.

[0113] [3.2.3. Advertisement distribution history storage unit 22] The advertisement delivery history storage unit 22 stores various information related to the delivery history of advertisement information. Fig. 6 is a diagram showing an example of an advertisement delivery history table stored in the advertisement delivery history storage unit 22 of the information processing device 1 according to the embodiment.

[0114] In the example shown in Fig. 6, the advertisement delivery history table stored in the advertisement delivery history storage unit 22 includes information items such as "advertising ID" and "advertising effectiveness". The "advertising ID" is an identifier that identifies the advertisement information, and is the same as the advertisement ID shown in Fig. 5. The "advertising effectiveness" is information that indicates the advertising effectiveness of the advertisement information corresponding to the "advertising ID", and is, for example, CTR (Click Through Rate), CVR (Conversion Rate), CPA (Cost Per Action), etc.

[0115] CTR is a value obtained by dividing the number of clicks on advertising information by the number of times the advertising information is displayed. CVR is a value obtained by dividing the number of clicks on advertising information by the number of conversions (e.g., the number of purchases of the product or service targeted by the advertisement). CPA is the advertising cost for obtaining a specific action by user U, and the specific action is, for example, visiting a site, registering as a member, accepting a survey, etc., but is not limited to such examples.

[0116] 3.2.4. Posted information storage unit 23 The posted information storage unit 23 stores a plurality of pieces of posted information. The posted information is information posted to various online sites provided by the information processing device 1 or other information processing devices. The online sites are, for example, social media, news sites, bulletin board sites, Q&A sites, etc., but are not limited to these examples. For example, the online sites may be shopping sites, price comparison sites, and word-of-mouth sites.

[0117] Examples of social media include, but are not limited to, Instagram, TikTok, YouTube, X (formerly Twitter), Facebook, etc. Examples of news sites include, but are not limited to, aggregation sites such as Yahoo, and news sites provided by various news organizations.

[0118] Information posted to a news site is, for example, information indicating news content, information indicating comments and ratings on the news content, and the like, but may also be comments on comments on the news content.

[0119] Bulletin board sites include 2chan and 5chan, where users post and exchange information on a wide range of topics. Q&A sites include Yahoo! Answers, where users post and exchange information on a wide range of topics, from everyday questions to specialized questions.

[0120] [3.3. Processing section 12] The processing unit 12 is a controller, and is realized by a processor such as a CPU (Central Processing Unit) or MPU (Micro Processing Unit) by executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 1 using a RAM or the like as a working area.

[0121] Furthermore, 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).

[0122] 3, the processing unit 12 has an acquisition unit 30, a reception unit 31, a determination unit 32, a generation unit 33, and a provision unit 34, 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 other configurations as long as they perform the information processing described below.

[0123] [3.3.1. Acquisition part 30] The acquisition unit 30 acquires various pieces of information from an external information processing device, the terminal device 2, etc. via the communication unit 10. The acquisition unit 30 acquires various pieces of information from the storage unit 11. For example, the acquisition unit 30 acquires user information from the external information processing device or the terminal device 2, and updates the user information table stored in the user information storage unit 20 based on the acquired user information.

[0124] Furthermore, the acquisition unit 30 acquires various types of information included in the request accepted by the acceptance unit 31. For example, when the request accepted by the acceptance unit 31 is a request to provide an advertisement, the acquisition unit 30 acquires information included in the request to provide an advertisement. The request to provide an advertisement includes information on the advertiser O, information on the advertisement, and the like.

[0125] The information related to the advertisement includes, for example, advertisement target information which is information on the product or service to be advertised, user demographic information which is information on the user demographic targeted by the advertisement, information on the period of distribution of the advertisement information, the advertisement budget, etc. The advertisement target information includes information indicating the name of the product or service to be advertised, information indicating the category of the product or service to be advertised, information indicating a description of the product or service to be advertised, etc.

[0126] The information about the advertisement may include, for example, information such as default advertisement text and default advertisement image, but may not include one or both. The information about the advertisement may also include information indicating an information type, which is the type of information to be generated by the generation AI, etc. The information type may be, for example, advertisement text or advertisement image.

[0127] Furthermore, the acquisition unit 30 acquires a plurality of pieces of posted information from an external information providing device or the like, and stores the acquired plurality of pieces of posted information in the posted information storage unit 23. The acquisition unit 30 can acquire various pieces of posted information by using, for example, APIs of various sites.

[0128] Furthermore, the acquisition unit 30 acquires various pieces of information from the storage unit 11. For example, the acquisition unit 30 acquires a plurality of pieces of posted information from the storage unit 11. The posted information is information posted on various online sites provided by the information processing device 1 or other information processing devices.

[0129] Furthermore, the acquisition unit 30 acquires user information, advertisement information, history information of advertisement information, and the like from the storage unit 11. For example, when the advertisement information is generated by the generation unit 33 using a generation AI, the acquisition unit 30 acquires information to be used as input information, which is information to be input to the generation AI, from the storage unit 11, an external information providing device, or the like.

[0130] In addition, when advertising information is generated by the generation unit 33 using an AI agent, information to be used as input information to be input to the AI ​​agent is acquired by the AI ​​agent from the memory unit 11, an external information providing device, or a terminal device 2, etc., but the acquisition unit 30 can also acquire information to be used as input information to be input to the AI ​​agent from the memory unit 11, etc.

[0131] [3.3.2. Reception Unit 31] The reception unit 31 receives various requests and various pieces of information from the terminal device 2, the terminal device 3, an external information processing device, or the like via the communication unit 10. For example, the reception unit 31 receives an advertisement request from the terminal device 2.

[0132] In addition, the receiving unit 31 receives an advertisement provision request, a personalization request, and the like transmitted from the terminal device 3 of the advertiser O to the information processing device 1. As described above, the advertisement provision request includes information about the advertiser O, information about the advertisement, and the like.

[0133] The reception unit 31 also receives a personalization request or the like transmitted from the terminal device 3 of the advertiser O to the information processing device 1. The personalization request is a request for personalizing advertisement information. Personalizing advertisement information refers to customizing the advertisement information according to a user U to which the advertisement is to be delivered, for example.

[0134] Note that the personalization request or information regarding the personalization request may be included in the advertisement provision request. In this case, the receiving unit 31 receives the personalization request by receiving the advertisement provision request.

[0135] Furthermore, the reception unit 31 receives posting information, which is information posted to an online service using an online site. For example, when the provision unit 34 provides an online service that provides news content using a news site, the reception unit 31 receives posting information, which is information posted on the news content.

[0136] [3.3.3. Judgment unit 32] The determination unit 32 performs various determinations. For example, the determination unit 32 determines a noteworthy event, which is an event having a high degree of attention, based on a plurality of pieces of posted information acquired by the acquisition unit 30.

[0137] The determination unit 32 extracts a plurality of words by performing a morphological analysis on the text included in the plurality of pieces of posted information acquired by the acquisition unit 30, and extracts a plurality of character strings from the extracted plurality of words. Each character string extracted by the determination unit 32 includes, for example, a keyword or a phrase, and may be referred to as a target character string below.

[0138] The target character string is, for example, a character string obtained using N-gram, or a character string that matches a specific part-of-speech pattern. The specific part-of-speech pattern is, for example, a combination of a noun and a verb, a combination of an adjective and a noun, or a combination of an adjective, a noun, and a verb. Note that a noun is a character string formed by combining one noun or multiple nouns, and may include a particle such as "no".

[0139] Furthermore, the determination unit 32 can have, for example, a character string extraction dictionary that defines a plurality of character strings to be extracted, and can extract a plurality of target character strings from text included in a plurality of pieces of posted information using the character string extraction dictionary.

[0140] The determination unit 32 can also extract a plurality of target character strings from a plurality of pieces of posted information using a language model. The language model is, for example, a model generated using learning information including each of character strings to be extracted and character strings not to be extracted, and information indicating whether or not the character strings are to be extracted. The determination unit 32 inputs information including the posted information and information for extracting phrases from the posted information to the language model as input information, and extracts phrases output from the input language model as target character strings.

[0141] The language model is, for example, a model such as a transformer that is trained to estimate and output the next token from an input token string. Such a language model is stored in the storage unit 11 or an external information providing device, and is created independently by the operator of the information processing device 1. It is preferable that the input information is trained so as not to be used as a new answer, thereby concealing the input information, such as personal information.

[0142] In addition, for example, when the posted information acquired by the acquisition unit 30 is information posted on social media and the posted information contains a character string with a hashtag, the determination unit 32 can extract the character string with the hashtag as a target character string.

[0143] In addition, the determination unit 32 may be configured to have, for example, a negative-positive string dictionary that includes negative strings and positive strings, and such a negative-positive string dictionary can be used to extract, as a target string, either a negative string or a positive string from among the strings extracted by the above-mentioned method as strings contained in the posted information.

[0144] For example, the determination unit 32 extracts as target strings character strings other than negative character strings from among the character strings extracted by the above-mentioned method or the like as character strings contained in the posted information, or extracts as target strings positive character strings from among the character strings extracted by the above-mentioned method or the like as character strings contained in the posted information.

[0145] The determination unit 32 calculates the number of each extracted target string for each predetermined unit period (e.g., 1 hour, 3 hours, 1 day, etc.), and determines, for example, an event indicated by a target string whose number of posts is greater than or equal to a threshold and whose increase rate in the number of posts is greater than or equal to the threshold, to be a noteworthy event.

[0146] The determination unit 32, for example, determines an event indicated by a target character string in which the number of posts is equal to or greater than a threshold and the increase rate of the number of posts is equal to or greater than a threshold, as a notable event. The determination unit 32 can also determine a notable event using a determination model that inputs information indicating the number of posts per unit period and outputs information indicating whether or not the event is a notable event. The above-mentioned determination model is, for example, a machine learning model such as a linear regression model, GBDT, or RNN such as LSTM or GRU.

[0147] In addition, for example, when the posted information is information posted on social media, the determination unit 32 can determine the number obtained by weighting and adding the number of shares and retweets to the number of posts as the corrected number of posts, and determine an event indicated by a target string for which the corrected number of posts is equal to or greater than a threshold and the increase rate of the corrected number of posts is equal to or greater than the threshold, as an event of interest.

[0148] The determination unit 32 can determine an attention event that has become apparent by the above-mentioned method, but can also determine a potential attention event that has not yet become apparent. For example, the determination unit 32 determines, as an attention event, an event indicated by a target character string whose degree of coincidence with the change pattern of the number of posts or the corrected number of posts before the attention event becomes apparent is equal to or greater than a threshold value. Note that the determination of an attention event using the number of posts or the corrected number of posts is not limited to the above-mentioned example.

[0149] In addition, for example, the determination unit 32 can determine a potential event of interest using a determination model that inputs information indicating the number of posts per unit period and outputs information indicating whether or not the event is a potential event of interest. Such a determination model is, for example, a machine learning model, and is generated using learning information including the number of posts per unit period and information indicating whether or not the event is a potential event of interest.

[0150] Furthermore, the determination unit 32 can determine whether or not a noteworthy event has occurred. For example, the determination unit 32 determines whether or not an event indicated by a target character string has changed from a non-noteworthy event to a noteworthy event.

[0151] For example, the judgment unit 32 judges that a notable event has occurred when the number of posts or the corrected number of posts is greater than or equal to a threshold and the rate of increase in the number of posts or the corrected number of posts changes from less than the threshold to greater than or equal to the threshold, or when the output of the judgment model switches from information indicating that the event is not a notable event to information indicating that it is a notable event.

[0152] The determination unit 32 can also determine an attention phenomenon for each category of the product or service that is the subject of the advertisement. If the product that is the subject of the advertisement is men's sneakers, the category is men's sneakers, sneakers, shoes, etc., and if the product that is the subject of the advertisement is beer, the category is beer, beer-related products, alcoholic beverages, etc. Men's sneakers and beer are lower-level categories, sneakers and beer-related products are middle-level categories, and shoes and alcoholic beverages are upper-level categories.

[0153] The determination unit 32 can also determine an attention event for each combination of the category of the product or service to be advertised and the demographic of the contributor corresponding to the target demographic of the advertisement. The determination unit 32 can also determine an attention event for each form (e.g., color or shape) of the product or service to be advertised.

[0154] The determination unit 32 can also determine a category with a high level of attention as a noteworthy event based on a plurality of pieces of post information acquired by the acquisition unit 30. The determination unit 32 determines a category with a high level of attention as a noteworthy event, for example, by a process similar to that for the target character string. For example, the determination unit 32 determines a category with a high level of attention as a noteworthy event, the category having a number of posts equal to or greater than a threshold and an increase rate of the number of posts equal to or greater than a threshold, or the category having a corrected number of posts equal to or greater than a threshold and an increase rate of the corrected number of posts equal to or greater than a threshold.

[0155] The determination unit 32 can also determine whether or not an advertising target, which is the target of advertising by the advertising information, has a predetermined relationship with the event of interest. The predetermined relationship is, for example, a condition that the advertising text or advertising image is not used in the advertisement of the advertising target or in the category of the advertising target in the past. In this case, the determination unit 32 determines whether or not an advertising target has a predetermined relationship with the event of interest based on, for example, an advertising history including advertising information used in the advertisement of the advertising target or in the category of the advertising target in the past.

[0156] The predetermined relationship is a condition that the NG words and NG images for each category of the advertising target are not included. In this case, the determination unit 32 determines whether or not the advertising target and the attention event have a predetermined relationship based on NG information including NG words and NG images for each category of the advertising target.

[0157] The predetermined relationship is a condition that the affinity between the advertising target and the event of interest is equal to or greater than a predetermined threshold. The determination unit 32 receives information including the advertising target and information indicating the event of interest as input information, and determines whether the affinity between the advertising target and the event of interest is equal to or greater than a predetermined threshold using a language model that outputs information indicating the affinity between the advertising target and the event of interest. The input information includes, for example, a character string such as "What value would be obtained if the affinity between the following advertising target and the event of interest were expressed in degree?" The language model is, for example, the attenuation model or transfer model described above.

[0158] [3.3.4. Generation unit 33] The generation unit 33 generates various information. For example, the generation unit 33 causes a generation AI or an AI agent that generates and outputs information according to input information to generate at least a part of the advertisement information.

[0159] The generation unit 33 inputs input information to the generation AI or AI agent, the input information including, for example, information indicating the event of interest determined by the determination unit 32 and information indicating instructions for outputting advertising information based on the event of interest, and causes the generation AI or AI agent to generate advertising information.

[0160] At least a part of the advertisement information generated by the generation unit 33 is, for example, one or more pieces of information among advertisement text and advertisement image. The advertisement text is information represented by a character string, and includes information such as font, color, and character size. The advertisement image is information represented by one or more pieces of information among a still image, a moving image, and an animation.

[0161] First, the generation of advertising information using a generation AI will be described. The generation AI is, for example, a text generation AI, an image generation AI, or a multimodal generation AI. The text generation AI is, for example, a language model trained to estimate and output the next token from an input token string, such as an attenuation model or a transfer model.

[0162] The transfer model is, for example, GPT or BERT, but is not limited to such examples. It is desirable to conceal input information such as personal information by performing learning so that the input information is not used as a new answer. In addition, the generation AI may be one that is specially trained (for example, fine-tuned) for generating advertising information.

[0163] The image generation AI is a generation AI that generates images from text, such as, but not limited to, StackGAN, AttnGAN, T2I with Transformers, DALL-E, etc.

[0164] A multimodal generative AI is, for example, a generative AI that generates images from text or generates text from images, such as GPT-4 and CM3Leon, but is not limited to such examples.

[0165] The AI ​​agent may be, for example, an autonomous AI agent such as AutoGPT, or may be an autonomous AI agent created specifically for generating advertising information.

[0166] For example, when a goal is given to an autonomous AI agent, the autonomous AI agent causes a generation AI to generate a task for achieving the goal, collects information for causing the generation AI to execute the generated task, and outputs information for achieving the goal by repeating a process of making the generation AI execute the task. Note that the AI ​​agent may be a non-autonomous AI agent that causes the generation AI to generate at least a portion of the advertising information by using the generation AI multiple times according to a predetermined procedure.

[0167] The generation unit 33, for example, inputs input information to the generation AI using an API provided by a business providing the generation AI and obtains information generated by the generation AI, but the generation AI may be included in the information processing device 1 or the generation unit 33. In addition, the generation unit 33 has an AI agent, but may also be configured to use the AI ​​agent using an API provided by a business providing the AI ​​agent.

[0168] First, generation of at least a part of the advertising information by the generation AI will be described. It is assumed that the information indicating the attention event determined by the determination unit 32 is "XXXXX" ("XXXXX" is a character string indicating the attention event).

[0169] In this case, if advertising text is specified as the information type in the advertisement provision request, the generation unit 33 inputs, as input information, information including the information of the character string "Please create advertising text using part of 'XXXXX'" to the generation AI. The input information input to the generation AI is instruction information in natural language, and is also called a prompt.

[0170] This allows the generation unit 33 to acquire the advertising text output from the generation AI as at least a part of the advertising information. The information "Please create advertising text using a part of the character string" is an example of information indicating an instruction to output advertising information based on the event of interest.

[0171] In addition, instead of the information "Please create advertising text using part of the string "XXXXX", the generation unit 33 can also use information such as "Please create advertising text that parodies the string "XXXXX".' or "Please create advertising text that uses the string "XXXXX" implicitly.'

[0172] In this case, the information "Please create advertising text that parodies the string ." and the information "Please create advertising text that implicitly uses the string ." are examples of information indicating instructions for outputting advertising information based on a phenomenon of interest.

[0173] In addition, the generation unit 33 can input, for example, input information further including information including one or more pieces of information showing examples of the input information and the output information to the generation AI. This allows the generation AI to perform simple learning and then generate at least a part of the advertisement information.

[0174] The information showing examples of input information and output information is, for example, information including the character string "I don't know" and the character string "advertising text" as input information, and information including the character string "There's no reason not to buy it! I don't know" as output information.

[0175] In addition, the generation unit 33 can also input input information to the generation AI, which includes information indicating the role of the generation AI, such as the character string "I will use part of the information you entered to generate appropriate advertising text that is in line with the information you entered.", and information about the character string "XXXXX."

[0176] In addition, if advertising text and advertising images are specified as the information type in the advertisement provision request, the generation unit 33 includes, for example, a string "Please create advertising information including advertising text and advertising images" in the above-mentioned input information instead of the string "Please create advertising text."

[0177] In addition, if an advertising image is specified as the information type in the advertisement provision request, the generation unit 33, for example, includes information such as the string "Please create an advertising image" in the input information described above to the generation AI instead of the string "Please create advertising text."

[0178] The generation unit 33 can also input input information further including information on the product or service specified in the advertisement provision request to the generation AI. The product or service information is, for example, information indicating the name of the product or service, information indicating the category of the product or service, etc.

[0179] For example, assume that the name or category of a product or service is represented by a character string "YYYYY." In this case, the generation unit 33 inputs, as input information, information including, for example, the character string "Please create an appropriate advertising text for 'YYYYY' and using a part of 'XXXXX'." to the generation AI. In this way, the generation unit 33 can cause the generation AI to generate advertising text that is in line with the product or service.

[0180] In addition, the generation unit 33 can input input information further including information on the target demographic specified in the advertisement provision request to the generation AI. For example, it is assumed that the target demographic specified in the advertisement provision request is men in their 30s.

[0181] In this case, the generation unit 33 inputs, as input information, information including, for example, the character string "Please create advertising text that targets men in their 30s and uses part of 'XXXXX.'" to the generation AI. This enables the generation unit 33 to cause the generation AI to generate advertising text that corresponds to the target demographic.

[0182] Furthermore, when the advertisement provision request includes one or more pieces of information of advertisement text and advertisement image, the generation unit 33 can also input input information further including such information to the generation AI. In this case, for example, the generation unit 33 inputs, as input information, to the generation AI, information including the information of the character string "Please change part or all of the following advertisement text to advertisement text using part of 'XXXXX'." and the advertisement text specified in the advertisement provision request. In this way, the generation unit 33 can cause the generation AI to generate advertisement text with reference to the advertisement text specified in the advertisement provision request.

[0183] In addition, when the generation unit 33 receives a personalization request, the generation unit 33 can also input input information further including user information, which is information about the user U to whom the advertisement information is to be provided, to the generation AI. The user information includes, for example, at least one of attribute information and history information of the user U. The attribute information of the user U is information indicating the attributes of the user U.

[0184] The attributes of the user U are, for example, demographic attributes, psychographic attributes, etc. The history information of the user U includes information on the behavior history of the user U. The behavior history of the user U includes, for example, information on the behavior history of the user U in online services.

[0185] In this case, the generation unit 33 inputs, as input information, information including the character string "Please create advertising text targeting users having the following user information and using part of 'XXXXX'" and the user information to the generation AI. In this way, the generation unit 33 can cause the generation AI to generate advertising text according to the user U.

[0186] The generation unit 33 can also cause the generation AI to generate at least a part of the advertising information using as input information information including information specifying the number of characters in the advertising text as information for outputting at least a part of the advertising information based on the event of interest. For example, the generation unit 33 inputs input information further including information of a character string "The number of characters in the advertising text should be within the range of 10 to 15 characters" to the generation AI. This allows the generation unit 33 to prevent the number of characters in the advertising text from becoming too long or too short.

[0187] The generation unit 33 can also cause the generation AI to generate at least a part of the advertisement information when, for example, the determination unit 32 determines that a noteworthy event has occurred. In this way, the generation unit 33 can appropriately catch up with the noteworthy event and cause the generation AI to generate at least a part of the advertisement information.

[0188] Next, the generation of at least a part of the advertisement information by the AI ​​agent will be described. For example, if advertisement text is specified as the information type in the advertisement provision request, the generation unit 33 inputs information including the information "Please create advertisement text using a part of the character string "XXXXX" that has high advertising effectiveness and does not overlap with advertisement text of other companies" to the AI ​​agent as input information.

[0189] As a result, the AI ​​agent sets the input information as a goal, generates and executes a task according to the goal, and generates and outputs the advertising text. The input information input to the AI ​​agent is instruction information in natural language, and is also called a prompt.

[0190] The AI ​​agent has, for example, a function to have the generation AI generate a task according to input information, a function to collect information from the memory unit 11 or an external information providing device according to a request from the generation AI, and a function to have the generation AI analyze the collected information.

[0191] For example, the AI ​​agent causes a generation AI to generate a task in response to input information, collects information necessary to execute the task from the memory unit 11 or an external information providing device, etc., in response to a request from the generation AI, and executes the task by having the generation AI analyze the collected information.

[0192] The input information input to the AI ​​agent includes, for example, information specified as an information type in the advertisement provision request. The information specified as the information type is one or more of information indicating advertisement text and information indicating advertisement images. Here, it is assumed that the information specified as the information type in the advertisement provision request is information indicating advertisement text.

[0193] The information collected by the AI ​​agent is, for example, advertising text included in advertising information with high advertising effectiveness among past advertising information, advertising text included in advertising information within a distribution period, etc. For example, the AI ​​agent collects advertising text included in advertising information with high advertising effectiveness among past advertising information, and advertising text included in advertising information within a distribution period from an internal storage unit or an external information providing device, etc.

[0194] The AI ​​agent can make the generation AI (e.g., text generation AI or multimodal generation AI) learn advertising text with high advertising effectiveness by inputting information further including advertising text included in advertising information with high advertising effectiveness among past advertising information. In this way, the AI ​​agent can make the text generation AI generate advertising information with high advertising effectiveness from the learned advertising text with high advertising effectiveness and information indicating the phenomenon of interest.

[0195] In addition, by using information including advertising text contained in advertising information during the distribution period as input information, the AI ​​agent can have the generation AI learn advertising text that does not overlap with advertising text contained in other companies' advertising information.

[0196] For example, if advertising text is specified as the information type in the advertisement provision request, the generation unit 33 inputs, as input information, information including the character string "Please change part or all of the following advertising text to advertising text that uses part of 'XXXXX' and has high advertising effectiveness and does not overlap with advertising text of other companies." In this way, the generation unit 33 can cause the AI ​​agent to generate advertising text by referring to the advertising text specified in the advertisement provision request.

[0197] Furthermore, when the information identified as the information type includes information indicating an advertising image, the AI ​​agent causes a generation AI (e.g., an image generation AI or a multimodal generation AI) to generate an advertising image by processing similar to that for advertising text. For example, the AI ​​agent collects advertising images included in advertising information that had a high advertising effect among past advertising information and advertising images included in advertising information within a distribution period. Then, the AI ​​agent causes the generation AI to generate an advertising image based on the collected information.

[0198] The generation unit 33 can also input input information further including information indicating that the advertising information indicates a target demographic to the AI ​​agent. In this case, the AI ​​agent collects at least a portion of advertising information with high advertising effectiveness among the advertising information previously delivered to the target demographic specified in the advertisement provision request, and inputs the input information further including the collected information to the generation AI.

[0199] Furthermore, when the generation unit 33 receives a personalization request, it can also input, to the AI ​​agent, input information further including user information, which is information about a user U to whom the advertising information is to be provided. In this case, the AI ​​agent collects at least a portion of advertising information that has had an advertising effect among pieces of advertising information that have been delivered in the past to the user U who has the user information specified in the advertising provision request, and inputs, to the generation AI, input information further including the collected information.

[0200] The AI ​​agent, for example, uses as input information information including instructions to output advertising text and advertising images corresponding to a phenomenon of interest by referring to advertising information that has been effective for user U having user information specified in the advertisement provision request, and causes the generation AI to generate at least a part of the advertising information. In this way, the generation unit 33 causes the AI ​​agent to generate advertising text corresponding to user U.

[0201] Furthermore, the generation unit 33 can cause the AI ​​agent to generate at least a part of the advertising information using as input information information including information specifying the number of characters in the advertising text as information for outputting at least a part of the advertising information based on the event of interest. For example, the generation unit 33 inputs to the AI ​​agent input information further including information of a character string "The number of characters in the advertising text should be within the range of 10 to 15 characters." This allows the generation unit 33 to prevent the number of characters in the advertising text from becoming too long or too short.

[0202] For example, the generation unit 33 can cause the AI ​​agent to generate at least a part of the advertising information when the determination unit 32 determines that a target event has occurred. This allows the generation unit 33 to appropriately catch up with the target event and cause the AI ​​agent to generate at least a part of the advertising information.

[0203] Furthermore, when the determination unit 32 determines that the advertising target and the event of interest have a predetermined relationship, the generation unit 33 can cause the generation AI or the AI ​​agent to generate at least a part of the advertising information.

[0204] For example, when a portion of the advertising information is generated by a generation AI or an AI agent, the generation unit 33 generates the advertising information by replacing the information generated by the generation AI or AI agent with corresponding information among the advertising information included in the advertisement provision request.

[0205] For example, when the advertisement text of the advertisement information is generated by the generation AI or AI agent, the generation unit 33 generates the advertisement information by replacing the advertisement text generated by the generation AI or AI agent with the advertisement text included in the advertisement information included in the advertisement provision request. For example, the information processing device 1 generates the advertisement information by superimposing the advertisement text generated by the generation AI or AI agent on the advertisement image of the advertisement information included in the advertisement provision request.

[0206] For example, when an advertising image of the advertising information is generated by a generation AI or an AI agent, the generation unit 33 generates the advertising information by replacing the advertising image generated by the generation AI or AI agent with the advertising image included in the advertising information included in the request to provide the advertisement. For example, the generation unit 33 generates the advertising information by superimposing the advertising text of the advertising information included in the request to provide the advertisement on the advertising image generated by the generation AI or AI agent.

[0207] In addition, when advertising text or advertising image is generated again by the generation AI or AI agent, the generation unit 33 generates advertising information by replacing the advertising text and advertising image generated this time by the generation AI or AI agent with the advertising text and advertising image generated previously by the generation AI or AI agent.

[0208] [3.3.5.Providing Department 34] The providing unit 34 provides various pieces of information via the communication unit 10. The providing unit 34 provides various pieces of information to the terminal device 2 or the terminal device 3 via the communication unit 10, for example.

[0209] For example, the providing unit 34 provides an online service to the user U of the terminal device 2 using an online site or the like. For example, the providing unit 34 provides news content to the user U by transmitting news content using a news site to the terminal device 2 of the user U.

[0210] Furthermore, the providing unit 34 provides the advertising information at least a part of which has been generated by the generation AI or AI agent in the generation unit 33 to the user U who is the advertisement recipient. For example, the providing unit 34 provides the advertising information at least a part of which has been generated by the generation AI or AI agent in the generation unit 33 to the terminal device 2 of the user U who is the advertisement recipient, thereby providing the advertising information at least a part of which has been generated by the generation AI or AI agent to the user U.

[0211] The advertising information transmitted from the information processing device 1 to the terminal device 2 is information in which advertising text is superimposed on an advertising image, but is not limited to this example and may be, for example, advertising information that includes advertising text and advertising image separately. In this case, the advertising text is superimposed on the advertising image and displayed by the terminal device 2. Also, the advertising information transmitted from the information processing device 1 to the terminal device 2 may be one of the advertising text and the advertising image.

[0212] The provision unit 34 provides advertising information at least in part generated by the generation AI or AI agent to the user U by transmitting the advertising information at least in part generated by the generation AI or AI agent to the terminal device 2 to be provided.

[0213] For example, the providing unit 34 provides advertisement information to the user U using a screen of a chat application such as the LINE (registered trademark) application. For example, an application capable of chatting (hereinafter, referred to as a terminal application) is installed in the terminal device 2, and the terminal application can launch the chat application and display the advertisement information on the screen of the chat application. Note that the terminal application may be a chat application, or may have a configuration including a chat application.

[0214] 7 is a diagram showing an example of a chat screen including advertisement information displayed on the terminal device 2 according to the embodiment, which is an example of a screen of a chat application. A chat screen 50 shown in FIG. 7 includes advertisement information 51.

[0215] 7 includes advertisement text 51a and advertisement image 51b. Advertisement text 51a is information on the character string "Let's toast 1 millimeter," and includes, for example, information on the character string "1 millimeter," which is part of information on the character string "miracle 1 millimeter" indicating the event of interest. Advertisement text 51a also includes information on the character string "cheers," which is information on beer, which is the advertising target. In this way, the providing unit 34 can apply the event of interest, which is an event with a high degree of interest, to the advertisement information with higher accuracy.

[0216] Furthermore, the providing unit 34 uses the screen of the portal site to provide the advertising information to the user U. For example, a terminal app that is an application capable of displaying the screen of the portal site is installed in the terminal device 2, and the terminal app can display the advertising information on the home screen of the portal site.

[0217] 8 is a diagram showing an example of a home screen including advertisement information displayed on the terminal device 2 according to the embodiment. A home screen 60 shown in FIG. 8 includes a search frame 61, a search button 62, advertisement information 63, button rows 64, 65, and 67, and a news content group 66.

[0218] 8 includes advertisement text 63a and advertisement image 63b. Advertisement text 63a is information of a character string "Cheers to a 1 mm miracle" and includes, for example, "1 mm" and "miracle" which are part of the information of the character string "1 mm of miracle" indicating the event of interest. Furthermore, advertisement text 51a includes information of the character string "Cheers" which is information about beer which is the target of advertisement. In this way, the providing unit 34 can apply the event of interest, which is an event with high attention, to the advertisement information with high accuracy.

[0219] 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. 9 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0220] 9, the processing unit 12 of the information processing device 1 determines whether or not an advertisement provision request transmitted from the terminal device 3 has been accepted (Step S10). When the processing unit 12 determines that the advertisement provision request has been accepted (Step S10: Yes), the processing unit 12 stores information included in the advertisement provision request (Step S11).

[0221] When the processing of step S11 is completed or when it is determined that the advertisement provision request has not been accepted (step S10: No), the processing unit 12 judges whether or not an update trigger has occurred (step S12). The update trigger may be, for example, a timing that arrives at a predetermined cycle, a timing when an update request transmitted from the terminal device 3 of the advertiser O is accepted, or a timing set by the operator of the information processing device 1.

[0222] When the processing unit 12 determines that an update trigger has occurred (step S12: Yes), it acquires multiple high school information from the storage unit 11 or an external information providing device (step S13). The processing unit 12 determines an attention event that is an event with a high level of attention based on the multiple posted information acquired in step S13 (step S14). The processing unit 12 generates at least a part of the advertising information using a generation AI or an AI agent (step S15).

[0223] When the processing of step S15 is completed or when it is determined that the update trigger has not arrived (step S12: No), the processing unit 12 determines whether or not the provision trigger has arrived (step S16). The provision trigger may be the timing of receiving an advertisement request transmitted from the terminal device 2, a timing that arrives at a predetermined cycle, or a timing set by the operator of the information processing device 1.

[0224] If the processing unit 12 determines that an update trigger has occurred (step S16: Yes), it transmits the advertising information, at least a portion of which has been generated by the generating AI or AI agent, to the terminal device 2 to provide the advertising information to the user U (step S17).

[0225] When the process of step S17 is completed or when it is determined that the update trigger has not occurred (step S16: No), the processing unit 12 determines whether or not the operation end timing has arrived (step S18). The processing unit 12 determines that the operation end timing has arrived when, for example, the power supply of the information processing device 1 is turned off.

[0226] If the processing unit 12 determines that the operation end time has not arrived (step S18: No), it transitions to step S10, and if it determines that the operation end time has arrived (step S18: Yes), it terminates the processing shown in FIG. 9.

[0227] 5. Modifications A part or all of the processes of the information processing device 1 described above may be performed by the terminal device 2. In this case, the terminal device 2 has a part or all of the functions of the acquisition unit 30, the reception unit 31, the determination unit 32, the generation unit 33, and the provision unit 34. In this case, the information processing device 1 and the terminal device 2 function as an information processing device, or the terminal device 2 functions as an information processing device instead of the information processing device 1.

[0228] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by a computer 200 having a configuration as shown in Fig. 10, for example. Fig. 10 is a hardware configuration diagram showing an example of the computer 200 that realizes the functions of the information processing device 1 according to the embodiment. The computer 200 has a CPU 201, a RAM 202, a ROM (Read Only Memory) 203, a HDD (Hard Disk Drive) 204, a communication interface (I / F) 205, an input / output interface (I / F) 206, and a media interface (I / F) 207.

[0229] The CPU 201 operates and controls each unit based on a program stored in the ROM 203 or the HDD 204. The ROM 203 stores a boot program executed by the CPU 201 when the computer 200 is started up, and programs that depend on the hardware of the computer 200.

[0230] The HDD 204 stores programs executed by the CPU 201, data used by such programs, etc. The communication interface 205 receives data from other devices via a network N (see FIG. 2) and sends it to the CPU 201, and transmits data generated by the CPU 201 to other devices via the network N.

[0231] The CPU 201 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 206. The CPU 201 acquires data from the input devices via the input / output interface 206. The CPU 201 also outputs generated data to the output devices via the input / output interface 206.

[0232] The media interface 207 reads a program or data stored in the recording medium 208 and provides it to the CPU 201 via the RAM 202. The CPU 201 loads the program from the recording medium 208 onto the RAM 202 via the media interface 207, and executes the loaded program. The recording medium 208 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.

[0233] For example, when the computer 200 functions as the information processing device 1 according to the embodiment, the CPU 201 of the computer 200 executes a program loaded on the RAM 202 to realize the function of the processing unit 12. In addition, the HDD 204 stores data in the storage unit 11. The CPU 201 of the computer 200 reads and executes these programs from the recording medium 208, but as another example, these programs may be obtained from another device via the network N.

[0234] [7. Other] In addition, 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 by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0235] In addition, each component of each device shown in the figure is a functional concept, and does 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 according to various loads, usage conditions, etc.

[0236] For example, the above-mentioned information processing device 1 may be realized by a terminal device and a server computer, or may be realized by multiple server computers. Also, depending on the functions, the configuration can be flexibly changed, such as by calling an external platform using an API or network computing.

[0237] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0238] 8. Effects As described above, the information processing device 1 according to the embodiment includes an acquisition unit 30, a determination unit 32, a generation unit 33, and a provision unit 34. The acquisition unit 30 acquires posted information. The determination unit 32 determines an attention event, which is an event with a high level of attention, based on the posted information acquired by the acquisition unit 30. The generation unit 33 inputs input information including information indicating the attention event determined by the determination unit 32 and information indicating an instruction for outputting at least a part of the advertising information based on the attention event to a generation AI or AI agent that generates and outputs information according to the input information, and causes the generation AI or AI agent to generate at least a part of the advertising information. The provision unit 34 provides the advertising information at least a part of which is generated by the generation AI or AI agent. This allows the information processing device 1 to apply the attention event, which is an event with a high level of attention, to the advertising information with higher accuracy.

[0239] The generation unit 33 causes the generation AI or the AI ​​agent to generate the advertisement text as at least a part of the advertisement information.

[0240] The generation unit 33 causes the generation AI or the AI ​​agent to generate information further including an advertisement image on which the advertisement text is superimposed, as at least a part of the advertisement information.

[0241] The determination unit 32 determines whether or not a noteworthy event has occurred, and the generation unit 33 causes the generation AI or AI agent to generate at least a portion of the advertising information when the determination unit 32 determines that a noteworthy event has occurred.

[0242] The generation unit 33 uses information further including information on the user U to whom the advertisement information is to be provided as input information, and causes the generation AI or AI agent to generate at least a part of the advertisement information.

[0243] The generation unit 33 uses information further including information on the target demographic of the advertisement information as input information and causes the generation AI or AI agent to generate at least a part of the advertisement information.

[0244] The determination unit 32 determines whether or not an advertising target, which is the subject of advertising through the advertising information, has a predetermined relationship with the event of interest determined by the determination unit 32, and when the determination unit 32 determines that the advertising target and the event of interest have a predetermined relationship, the generation unit 33 causes the generation AI or AI agent to generate at least a portion of the advertising information.

[0245] The acquiring unit 30 acquires information posted on at least one of social media and news sites as posted information.

[0246] The determination unit 32 determines, based on the posted information acquired by the acquisition unit 30, a category with a high degree of attention as a phenomenon of interest.

[0247] The generation unit 33 uses information including information specifying the number of characters in the advertising text as input information for outputting at least a portion of the advertising information based on the event of interest, and causes the generation AI or AI agent to generate at least a portion of the advertising information.

[0248] The above describes the embodiment 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 various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.

[0249] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, an acquisition section can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0250] 1. Information processing device 2,3 Terminal Equipment 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 21 Advertising information storage unit 22 Advertisement delivery history memory unit 23 Posted information storage unit 30 Acquisition Department 31 Reception 32 Judgment section 33 Generation part 34 Providing Department 100 Information Processing Systems N Network

Claims

1. An acquisition unit that acquires posted information; a determination unit that determines an attention event that is an event having a high degree of attention based on the posted information acquired by the acquisition unit; a generation unit that inputs input information including information indicating the event of interest determined by the determination unit and information indicating an instruction to output at least a portion of advertising information based on the event of interest to a generation AI or AI agent that generates and outputs information according to the input information, and causes the generation AI or AI agent to generate at least a portion of the advertising information; A provision unit that provides the advertising information at least partially generated by the generating AI or the AI ​​agent.

23. An information processing apparatus comprising:

2. The generation unit is The advertisement text is generated by the generating AI or the AI ​​agent as at least a part of the advertisement information.

2. The information processing apparatus according to claim 1,

3. The generation unit is The generating AI or the AI ​​agent generates information further including an advertisement image on which the advertisement text is superimposed as at least a part of the advertisement information.

3. The information processing apparatus according to claim 2.

4. The determination unit is determining whether the event of interest has occurred; The generation unit is When the determination unit determines that the event of interest has occurred, the generation AI or the AI ​​agent is caused to generate at least a part of the advertising information.

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

5. The generation unit is The input information further includes information about a user to whom the advertisement information is to be provided, and the generation AI or the AI ​​agent is caused to generate at least a part of the advertisement information.

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

6. The generation unit is The input information further includes information on a target demographic of the advertisement information, and the generation AI or the AI ​​agent generates at least a part of the advertisement information.

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

7. The determination unit is determining whether or not an advertising target that is a target of advertising according to the advertising information has a predetermined relationship with the event of interest determined by the determination unit; The generation unit is When the determination unit determines that the advertising target and the event of interest have the predetermined relationship, the generation AI or the AI ​​agent is caused to generate at least a part of the advertising information.

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

8. The acquisition unit is Information posted on at least one of a social media site and a news site is acquired as the posted information.

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

9. The generation unit is The input information includes information specifying the number of characters of the advertising text as information for outputting at least a part of the advertising information based on the event of interest, and the generating AI or the AI ​​agent is caused to generate at least a part of the advertising information.

3. The information processing apparatus according to claim 2.

10. 1. A computer-implemented information processing method, comprising: An acquisition step of acquiring posted information; a determination step of determining an attention event that is an event having a high degree of attention based on the posted information acquired by the acquisition step; a generation process for inputting input information including information indicating the event of interest determined by the determination process and information indicating an instruction to output at least a portion of advertising information based on the event of interest to a generation AI or AI agent that generates and outputs information according to the input information, and causing the generation AI or AI agent to generate at least a portion of the advertising information; and providing the advertising information generated at least in part by the generating AI or the AI ​​agent.

23. An information processing method comprising:

11. A procedure for acquiring posted information; a determination step of determining an attention event that is an event having a high degree of attention based on the posted information acquired by the acquisition step; a generation procedure for inputting input information including information indicating the event of interest determined by the determination procedure and information indicating an instruction to output at least a portion of advertising information based on the event of interest to a generation AI or AI agent that generates and outputs information according to the input information, and causing the generation AI or AI agent to generate at least a portion of the advertising information; and a provision step of providing the advertising information at least partially generated by the generating AI or the AI ​​agent.

2. An information processing program comprising:

Images