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 improving convenience for a user.SOLUTION: An information processing apparatus includes a reception unit, a generation unit, and a providing unit. The reception unit receives a question for an article for sale. The generation unit inputs, to an AI agent or a trained model configured to generate and output information according to input information, input information including information on the question and information for outputting an answer to the question, to cause the AI agent or the trained model to generate answer information which is information indicating an answer to the question. The providing unit provides the answer information generated by the generation unit.SELECTED DRAWING: Figure 3

Description

[Technical field]

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

[0002] As one type of service related to electronic commerce, there is known a service that mediates the buying and selling of items between users, such as an auction service or a flea market service (hereinafter, may be referred to as an item buying and selling mediation service). As a technology related to the item buying and selling mediation service, for example, Patent Document 1 proposes a technology that simplifies the user's information input work when listing an item (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2002-163492 A Summary of the Invention [Problem to be solved by the invention]

[0004] The above-mentioned conventional technology can reduce the input work required when a user lists a new item, but it does not take into consideration, for example, the effort required for the seller to respond to questions about the item from potential buyers, and there is room for improvement in terms of further improving user convenience.

[0005] The present application has been made in consideration of the above, and has an object to provide an information processing device, an information processing method, and an information processing program that can improve user convenience. [Means for solving the problem]

[0006] The information processing device according to the present application includes a receiving unit, a generating unit, and a providing unit. The receiving unit receives questions about an item for sale. The generating unit inputs input information including question information and information for outputting an answer to the question to an AI agent or a trained model that generates and outputs information according to the input information, and causes the AI ​​agent or the trained model to generate answer information that is information indicating the answer to the question. The providing unit provides the answer information generated by the generating unit. Effect of the Invention

[0007] According to one aspect of the embodiment, an effect is achieved in that it is possible to improve user convenience. [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 a selling history information table stored in the selling history information storage unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a question and answer history information table stored in the auction listing history information storage unit of the information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of a sales history information table stored in the auction sale history information storage unit of the information processing device according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a content table stored in the content storage unit of the information processing device according to the embodiment. [Figure 9]FIG. 9 is a diagram illustrating an example of a flea market home screen displayed on the terminal device according to the embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of notification information displayed on the terminal device according to the embodiment. [Figure 11] FIG. 11 is a diagram showing an example of a seller Q&A screen displayed on the terminal device according to the embodiment. [Figure 12] FIG. 12 is a diagram showing an example of an AI answer support screen displayed on the terminal device according to the embodiment. [Figure 13] FIG. 13 is a diagram illustrating an example of an updated seller Q&A screen displayed on the terminal device according to the embodiment. [Figure 14] FIG. 14 is a diagram showing another example of the updated seller Q&A screen displayed on the terminal device according to the embodiment. [Figure 15] FIG. 15 is a diagram showing an example of an item screen displayed on a terminal device according to an embodiment. [Figure 16] FIG. 16 is a diagram showing an example of a questioner Q&A screen displayed on the terminal device according to the embodiment. [Figure 17] FIG. 17 is a diagram showing an example of an AI question support screen displayed on the terminal device according to the embodiment. [Figure 18] FIG. 18 is a diagram showing an example of an updated questioner Q&A screen displayed on the terminal device according to the embodiment. [Figure 19] FIG. 19 is a flowchart illustrating an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 20] FIG. 20 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, in the example shown in FIG. 1, a plurality of terminal devices 2 are shown, and the information processing device 1 cooperates with each of the plurality of terminal devices 2 and provides various services online to the user U of each terminal device 2.

[0012] The services provided to the user U by the information processing device 1 include, but are not limited to, e-commerce (e.g., flea markets, auctions, online shopping malls, etc.), web searches, and content distribution. In the following, an example of an item buying and selling intermediation service that is mainly provided by the information processing device 1 will be described. Note that, although an item buying and selling intermediation service will be described using a flea market-style e-commerce service as an example, the item buying and selling intermediation service may also be an auction-style e-commerce service.

[0013] Flea market-style electronic commerce is an electronic commerce service between users U (CtoC), in which the selling user U determines the selling price of an item, and if the buying user U agrees to that selling price, the transaction of the item is concluded. In flea market-style electronic commerce, the buying user U can also negotiate a price reduction on the selling price of the selling user U. Hereinafter, a flea market-style electronic commerce service may be referred to as a flea market service. Items for sale are not limited to movable property such as goods, but may also be real estate or intangible assets.

[0014] An application program for using a flea market service (hereinafter, sometimes referred to as a flea market app) is installed in the terminal device 2. The user U can use the flea market app installed in the terminal device 2 to list, view, and purchase items for sale in the flea market service. The terminal device 2 can transmit and receive information to and from the information processing device 1 via an API (Application Programming Interface) using the functions of the flea market app, but may also transmit and receive information to and from the information processing device 1 without using an API.

[0015] When the user U uses the flea market service, the user U operates the terminal device 2 to launch a flea market app. When the flea market app is launched on the terminal device 2, a flea market home screen, which is the home screen of the flea market app, is displayed on the terminal device 2. For example, the terminal device 2 acquires a plurality of pieces of information constituting the flea market home screen from the information processing device 1 using the functions of the flea market app, and displays the flea market home screen including the acquired plurality of pieces of information.

[0016] 1, for convenience of explanation, the two terminal devices 2 are terminal device 2A and terminal device 2B, the user U of terminal device 2A is user UA, and the user U of terminal device 2B is user UB. In the following, the user UA is described as a seller who has put up an item for sale, and the user UB is described as a potential buyer who has a question about the item put up for sale by user UA.

[0017] When the user UA wishes to sell a product or the like that is the subject of auction, the user UA operates the terminal device 2A and selects the "Sell / Belongings" button in the row of buttons arranged at the bottom of the flea market home screen. This causes the "Sell / Belongings" screen to be displayed on the terminal device 2A by the function of the flea market app.

[0018] The items for sale / belongings screen has an item for sale button for selling items for sale. The user UA can operate the terminal device 2A to select the item for sale button to display the item for sale screen on the terminal device 2A and set information about the item for sale on the item for sale screen as selling information. The item for sale is a product that is to be put up for sale in the flea market service.

[0019] User UA can set on the auction screen the listing information of the item being auctioned, for example, information on an image of the item being auctioned, information indicating the title of the item being auctioned, information indicating the category of the item being auctioned, information indicating a description of the item being auctioned, information indicating the condition of the item being auctioned, and information indicating the price of the item being auctioned.

[0020] The listing screen has an auction start button for listing the auction item as an item for sale, and when the user UA operates the terminal device 2A to select the auction start button, an auction request is sent from the terminal device 2A to the information processing device 1. The auction request sent from the terminal device 2A is accepted by the information processing device 1. The information processing device 1 lists the auction item on the flea market service based on the listing information of the auction item included in the accepted auction request. This makes the auction item available for sale on the flea market service and available for purchase.

[0021] The flea market app has, for example, an AI (Artificial Intelligence) support function for supporting the user U's use of the flea market service, and the AI ​​support function can enhance the user U's convenience.

[0022] The AI ​​support function includes, for example, a Q&A (question and answer) support function regarding the item for sale. The Q&A (question and answer) support function includes an answer support function that supports the seller in creating answers to questions from potential purchasers and a question support function that supports the seller in creating questions from potential purchasers.

[0023] Here, the answer support function will be explained. The user UB operates the terminal device 2B to display the flea market home screen on the terminal device 2B, and inputs a search keyword such as the name or category of the item that the user UB is considering purchasing into a search box included in the flea market home screen. After that, when the user UB operates the terminal device 2B to select a search button included in the flea market home screen, a search request for items is transmitted from the terminal device 2B to the information processing device 1 (step S1).

[0024] The information processing device 1 accepts an item search request sent from the terminal device 2B, generates item list information, which is information on a list of items including multiple items corresponding to the search keywords included in the item search request, and transmits the generated item list information to the terminal device 2B (step S2).

[0025] When the terminal device 2B receives the item list information transmitted from the information processing device 1, the terminal device 2B displays an item list screen based on the item list information. The item list screen includes information on a plurality of items (e.g., image information, item titles, etc.) corresponding to the search keyword.

[0026] The user UB can operate the terminal device 2B to select an item that he is considering purchasing or that has caught his eye from among the multiple items whose information is included in the item list screen. The terminal device 2B transmits to the information processing device 1 an item viewing request including information that identifies the item selected by the user UB.

[0027] When the information processing device 1 receives the item viewing request transmitted from the terminal device 2B, it transmits item information including the item information of the item specified in the item viewing request to the terminal device 2B (step S3). Here, it is assumed that the item information transmitted to the terminal device 2B is information on the item that the user UA has put up for sale as a seller.

[0028] When the terminal device 2B receives the item information transmitted from the information processing device 1, it displays an item screen based on the item information. The item screen includes the item information of the item selected by the user UB, a question button, and the like, and the user UB can operate the terminal device 2B to select the question button. When the question button is selected, the terminal device 2B displays a questioner Q&A screen for inputting a question.

[0029] The questioner Q&A screen includes a question input box and a send button. The questioner Q&A screen also includes a question support button, which will be described later. When the user UB operates the terminal device 2B to input a question about the item in the question input box and select the send button, the terminal device 2B transmits question information including information on the question input by the user UB in the question input box to the information processing device 1 (step S4). The question information includes information for identifying the item that is the subject of the question, and hereinafter, the item that is the subject of the question may be referred to as the item that is the subject of the question.

[0030] When the information processing device 1 receives the question information transmitted from the terminal device 2B, it transmits notification information indicating that the question information of the user UB has been received to the terminal device 2A (step S5). When the terminal device 2A receives the notification information transmitted from the information processing device 1, it displays the notification information.

[0031] When the user UA operates the terminal device 2A to select the notification information, the terminal device 2A launches a flea market app and sends a question information request to the information processing device 1, thereby obtaining from the information processing device 1 the question information notified of its occurrence in the notification information, and displays a seller Q&A screen including the obtained question information (step S6).

[0032] The seller Q&A screen includes question information, an answer input box, an answer support button, and a send button, etc. When the user UA operates the terminal device 2A to check the question information, input an answer to the question indicated by the question information in the answer input box, and then selects the send button, the terminal device 2A transmits answer information, which is information indicating the answer input in the answer input box, to the information processing device 1. The answer information is transmitted from the information processing device 1 to the terminal device 2B.

[0033] Furthermore, when the user UA selects the answer support button by operating the terminal device 2A, the terminal device 2A transmits an answer support request including the question information shown on the seller Q&A screen or information identifying the question information to the information processing device 1 (step S7). The answer support request is an example of a request to generate an answer to a question.

[0034] When the information processing device 1 receives an answer support request transmitted from the terminal device 2A, it causes an AI agent or a trained model that generates and outputs information according to the input information to generate answer information that indicates an answer to the question specified in the answer support request (step S8).

[0035] For example, the information processing device 1 inputs input information including question information and information for outputting an answer to the question indicated in the question information to an AI agent or a trained model that generates and outputs information according to the input information, and causes the AI ​​agent or trained model to generate answer information that is information indicating the answer to the question.

[0036] First, we will explain how to generate answer information using an AI agent. The AI ​​agent is, for example, an autonomous AI agent such as AutoGPT (Generative Pre-trained Transformer), but it may also be an autonomous AI agent created specifically for the AI ​​support function of the flea market app.

[0037] For example, when an autonomous AI agent is given a goal, it has a generative AI generate tasks for achieving that goal, collects information for the generative AI to execute the generated tasks, and outputs information for achieving the goal by repeating the process of having the generative AI execute the tasks.

[0038] The generative AI is, for example, a text generation AI, but may also be a combination of a text generation AI and an image processing 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.

[0039] Examples of transfer models 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 input information such as personal information. The generation AI may be trained (for example, fine-tuned) specifically for generating answer information, question information, and the like by an AI agent.

[0040] The generative AI may be a multimodal generative AI, which is a model that generates images from text or generates text from images, such as CM3Leon (Chameleon Multimodal Model), but is not limited to such examples.

[0041] Here, the information of the item that is the subject of the question is assumed to be "XX···XX" (where "XX···XX" is information string indicating the item), and the question information identified in the answer support request is assumed to be "YY···YY" (where "XX···XX" is information string indicating the question).

[0042] In this case, the information processing device 1 inputs the following string of information to the AI ​​agent as input information: "The following question was asked about the item listed below. Please tell me the answer to this question. The question is 'YY...YY'. The item listed is 'XX...XX'."

[0043] 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 answer information indicating an answer to the question specified in the answer support request. The input information input to the AI ​​agent is instruction information in natural language, and is also called a prompt.

[0044] In an AI agent, for example, a generative AI can generate a task in response to input information, and the information required to execute such a task can be collected from an internal memory unit or an external information providing device in response to a request from the generative AI, and the task can be executed by having the generative AI analyze the collected information.

[0045] The information collected by the AI ​​agent may be, for example, answer information to questions about items that were previously listed and sold (purchased) on a flea market service and were highly rated by purchasers or questioners, but is not limited to such examples. For example, the information collected by the AI ​​agent may be answer information to questions about items that were highly rated and were sold shortly after being listed (for example, within a threshold period), or other information.

[0046] The information collected by the AI ​​agent may include answer information previously generated by the AI ​​agent, or may include answer information to questions about items currently being sold on the flea market service. The information collected by the AI ​​agent is answer information to questions about other items that are the same as the item identified by the input information, but may also include answer information to questions about other items similar to the item identified by the input information.

[0047] In addition to the string of characters indicating the answer, the answer information may also include, for example, information for controlling the flea market app (for example, information indicating a command to automatically operate the imaging unit of the terminal device 2A on the seller Q&A screen).

[0048] Furthermore, the information processing device 1 can cause the AI ​​agent to generate answer information using, as input information, information further including answer consideration information that is information to be taken into consideration in generating answer information.

[0049] The answer consideration information includes, for example, at least one of answer information to a question about an item in the same category as the item in question, information on the price (selling price) of an item the same as the item in question, information on the item in question in news content, information on the item in question in SNS (Social Networking Service), information on the season when the item was listed, and information on the weather when the item was listed. News content is content provided by a news distribution service, but is not limited to such examples.

[0050] For example, if the item in question is a drum-type washing machine, the category of the item in question may be washing machine, home appliance, etc. For example, if the item in question is a perfume, the category of the item in question may be beauty, cosmetics, etc.

[0051] The information on the item being questioned about in news content or on SNS may be, but is not limited to, information indicating whether the item being questioned about is trending, information indicating whether the item being questioned about is becoming trending, information indicating whether the trend of the item being questioned about is about to end, etc. For example, the information on the item being questioned about in news content or on SNS may be information on news content or on SNS that positively covers the item being questioned about.

[0052] The information processing device 1 can cause the AI ​​agent to generate answer information using, for example, the information of the character string "Please give us an answer taking into consideration the following answer consideration information" and information further including the answer consideration information as input information. The information processing device 1 can also replace the information of the character string "Please give us an answer to this question" with the information of the character string "Please give us an appropriate answer taking into consideration the following answer consideration information" and further cause the AI ​​agent to generate answer information using information including the answer consideration information as input information.

[0053] When information including an instruction to consider the answer consideration information is input as input information, the AI ​​agent further collects information corresponding to the answer consideration information and analyzes the collected information. For example, when the answer consideration information includes the information of the string "answers to other items in the same category as the item," the AI ​​agent collects answer information regarding questions about other items in the same category as the item.

[0054] In this case, the AI ​​agent can generate answer information based on, for example, answer information to questions about the questioned item and answer information to questions about other items in the same category as the questioned item, which allows the AI ​​agent to appropriately increase the answer information to refer to and appropriately generate answer information to questions about the questioned item.

[0055] Furthermore, when the answer consideration information includes information on the price (selling price) of an item that is the same as the item that is the subject of the question, the AI ​​agent collects information on the price (selling price) of an item that is the same as the item that is the subject of the question. As a result, for example, when the question information is about a price reduction, the AI ​​agent can use the generative AI to generate answer information that includes whether or not the price can be reduced and the amount of the reduction.

[0056] In addition, when the answer consideration information includes information about items listed in news content, the AI ​​agent collects information about items listed in news content, and when the answer consideration information includes information about items that are the subject of questions on SNS, the AI ​​agent collects information about the items that are the subject of questions on SNS. This allows the AI ​​agent to appropriately generate answer information to questions about, for example, the contents of the items that are the subject of questions.

[0057] Furthermore, when the answer consideration information includes information on the listing time (e.g., season) or weather at the listing time, the AI ​​agent collects answer information for items that were listed or sold at the listing time of the item in question or at the listing time (e.g., season) corresponding to the current time, answer information for items that were listed or sold in the weather at that time, etc. The listing time is the time of listing. This allows the AI ​​agent to appropriately generate answer information according to, for example, the season or weather.

[0058] The information processing device 1 can inquire of the generative AI what kind of answer consideration information should be included in the input information together with the question information, and obtain an answer from the generative AI in response to the inquiry. The information processing device 1 can also obtain answer consideration information corresponding to the questioned item from the correspondence information including answer consideration information for each item name or answer consideration information for each item category.

[0059] In addition, when the user UA inputs or selects desired information, the information processing device 1 can also cause the AI ​​agent to generate answer information using information further including the desired information as input information. The desired information is information of the character string "I want to sell quickly" or information of the character string "I want to sell at a high price".

[0060] For example, when the desired information is the character string "I want to sell it quickly" or the character string "Please give me an answer that will help me sell it as quickly as possible," the information processing device 1 uses information further including the desired information as input information to cause the AI ​​agent to generate answer information. The character string "I want to sell it quickly" and the character string "Please give me an answer that will help me sell it as quickly as possible" are examples of information indicating the seller's desire regarding the timing of selling the item.

[0061] Furthermore, for example, when the desired information is the character string "I want to sell it for a high price" or the character string "Please give me an answer that will sell it for as high as possible," the information processing device 1 uses information further including the desired information as input information to cause the AI ​​agent to generate answer information. The character string "I want to sell it for a high price" or the character string "Please give me an answer that will sell it for as high as possible" are examples of information indicating the seller's desire regarding the price of the item.

[0062] In addition, the information processing device 1 can cause the AI ​​agent to generate answer information using as input information information further including information on the user UA who is the seller of the item being questioned. The information on the user UA is, for example, attribute information on the user UA, behavior history information on the user UA, etc.

[0063] The attribute information of the user UA is information indicating the attributes of the user UA, and the attributes of the user UA are, for example, the demographic attributes of the user UA and the psychographic attributes of the user UA. The demographic attributes are demographic attributes, for example, age, sex, occupation, place of residence, annual income, family structure, etc. The psychographic attributes are psychological attributes, for example, lifestyle, values, interests, etc.

[0064] The behavior history information of the user UA is information indicating the past behavior of the user UA, and includes information on the user UA's past usage history of online services, etc. The information on the user UA's past usage history of online services includes, for example, information on the user UA's past purchase history of items for sale and the user UA's past response information.

[0065] The information processing device 1 can cause the AI ​​agent to generate answer information using, as input information, information further including, for example, a character string "The following question has been asked about the item listed below, which has been listed by a user corresponding to the user information below. Please tell me the answer to this question. The question is 'YY...YY'. The item is 'XX...XX'" and user information. Furthermore, the information processing device 1 can further include answer consideration information, desired information, and the like in the input information.

[0066] For example, when a question is about the condition or contents of the item being asked about, the AI ​​agent can appropriately generate answer information based on information about the purchase history or sales history of the item being asked about by the seller, the user UA.

[0067] Furthermore, the AI ​​agent can appropriately generate answer information according to the age, sex, occupation, place of residence, interests, etc. of the user UA, who is the seller, based on, for example, attribute information of the user UA. Furthermore, the AI ​​agent can appropriately generate answer information that is more natural to the user UA, based on, for example, past answer information of the user UA.

[0068] Next, generation of answer information using a trained model without using an AI agent will be described. The trained model is, for example, the above-mentioned generation AI. Such a generation AI is, for example, a text generation AI, but may be a combination of a text generation AI and an image processing AI.

[0069] The information processing device 1 has a trained model that has been trained using learning information that includes, for each question, answer information to questions about items that have been previously listed and sold (purchased) on a flea market service and that were highly rated by purchasers or questioners.

[0070] For example, the learning information is a dataset that takes as input information including information about the item for sale and information about questions about the item for sale, and targets answer information to the questions about the item for sale, and learning is, for example, fine tuning, but is not limited to such an example.

[0071] In this case, the information processing device 1 inputs information including information regarding the item that is the subject of the question (e.g., part or all of the listing information), question information regarding the item that is the subject of the question, and information for outputting an answer to the question indicated in the question information, as input information to the trained model, and causes the trained model to generate answer information to the question regarding the item that is the subject of the question.

[0072] The trained model may be a model trained using training information further including answer consideration information for each answer. In this case, the information processing device 1 inputs information further including answer consideration information as input information to the trained model, and causes the trained model to generate answer information according to the answer consideration information.

[0073] The trained model may be a model trained using training information further including desired information for each item, for example. In this case, the information processing device 1 inputs information including information on the questioned item and question information and desired information for the questioned item as input information to the trained model, and causes the trained model to generate answer information corresponding to the question information and desired information.

[0074] The desired information is, for example, information including the character string “I want to sell it at a high price” or information including the character string “I want to sell it quickly.” In this case, the learning information is, for example, a data set that takes information further including the desired information as an input and targets the response information.

[0075] The trained model may be a model trained using training information further including answer consideration information and desired information for each question. In this case, the information processing device 1 inputs information further including answer consideration information and desired information as input information to the trained model, and causes the trained model to generate information on the question target item, question information, answer consideration information, and answer information corresponding to the desired information.

[0076] The trained model may be a model trained using training information for each answer that further includes user information of the user UA who is the seller of the item. In this case, the information processing device 1 inputs information further including the user information as input information to the trained model, and causes the trained model to generate information on the questioned item, question information, answer consideration information, desired information, and answer information corresponding to the user information.

[0077] The input information input to the trained model may be similar to the input information input to the AI ​​agent, and input information for generating appropriate answer information is input to the trained model.

[0078] Next, the information processing device 1 transmits the answer information generated in step S2 to the terminal device 2A, thereby providing the answer information generated in step S2 to the user UA who is the questioner (step S9).

[0079] The terminal device 2A receives the answer information transmitted from the information processing device 1, and updates the seller Q&A screen based on the received answer information. As a result, the seller Q&A screen contains the answer information generated by the information processing device 1, so that the user UA, who is the seller, can save or reduce the effort of inputting the answer information into the seller Q&A screen, and the information processing device 1 can improve the convenience of the user UA, who is the seller.

[0080] On the seller Q&A screen, the user UA can change the answer information generated by the information processing device 1, which also improves the convenience of the user UA. In addition, the user UA can select an answer re-support button on the seller Q&A screen, which allows the answer information on the seller Q&A screen to be replaced with answer information regenerated by the information processing device 1.

[0081] In this way, the information processing device 1 inputs input information including question information and information for outputting an answer to the question to an AI agent or a trained model that generates and outputs information according to the input information, causes the AI ​​agent or trained model to generate answer information that is information indicating the answer to the question, and provides the answer information. This allows the information processing device 1 to improve the convenience of the user UA who is the seller.

[0082] The configuration of an information processing system including an information processing device 1 that performs such processing and a plurality of terminal devices 2 will be described in detail below.

[0083] 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, an information processing system 100 according to an embodiment includes an information processing device 1 and a plurality of terminal devices 2.

[0084] The multiple terminal devices 2 are used by different users U. The terminal devices 2 are, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, a tablet PC, or a wearable device. The wearable device is, for example, a smart glass or a smart watch, but is not limited to such examples.

[0085] The information processing device 1 and the terminal device 2 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.

[0086] 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).

[0087] The terminal device 2 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.

[0088] 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.

[0089] [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 via the network N.

[0090] [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, a listing history information storage unit 21, and a content storage unit 22.

[0091] 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".

[0092] 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.

[0093] The "history information" includes information on the behavior history of the user U associated with the "user ID." The behavior history of the user U includes, for example, information on the movement history of the user U and information on the behavior history of the user U in online services. 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.

[0094] 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. 3.2.2. Listing History Information Storage Unit 21 The selling history information storage unit 21 stores information about items put up for sale on the electronic commerce site. The selling history information storage unit 21 includes, for example, a selling history information table, a question and answer history information table, and a sales history information table.

[0095] 5 is a diagram showing an example of a listing history information table stored in the listing history information storage unit 21 of the information processing device 1 according to the embodiment. The listing history information table shown in FIG. 5 includes items such as "listing ID", "category", "name", "status", "description", and "price".

[0096] "Item ID" is identification information that identifies an item. "Category" is information that indicates the category of the item corresponding to the "Item ID". "Product name" is information that indicates the name of the item corresponding to the "Item ID". "Status" is information that indicates the status of the item corresponding to the "Item ID".

[0097] "Description" is information on the item corresponding to the "Item ID", which is information that describes the item, i.e., information on the description of the item. "Price" is information that indicates the price at which the item corresponding to the "Item ID" was put up for sale, e.g., information that indicates the price set by the seller.

[0098] In addition, although not shown, the listing history information table includes information such as the listing title of the item, information indicating the seller of the item, information indicating the listing date and time of the item (listing start date and time), information indicating the listing end date and time of the item, and information indicating the content of negotiations with potential buyers.

[0099] 6 is a diagram showing an example of a question and answer history information table stored in the listing history information storage unit 21 of the information processing device 1 according to the embodiment. The question and answer history information table shown in FIG. 6 includes items such as "Question ID," "Questioner ID," "Item ID," "Question," and "Answer."

[0100] "Question ID" is identification information that identifies a question. "Asker ID" is the user ID of user U who asked the question corresponding to "Question ID". "Item ID" is the item ID of the item that was the subject of the question corresponding to "Question ID". "Question" is question information that is information indicating the question corresponding to "Question ID". "Answer" is answer information that is information indicating the answer to the question corresponding to "Question ID".

[0101] 7 is a diagram showing an example of a sales history information table stored in the listing history information storage unit 21 of the information processing device 1 according to the embodiment. The sales history information table shown in FIG 7 includes items such as "listing ID", "sales flag", "sales price", "sales date and time", and "purchaser".

[0102] The "item ID" is identification information that identifies the item being sold. The "sale / buy flag" is flag information that indicates whether the item corresponding to the "item ID" has been sold or bought. If the item has been sold or bought, the sale flag is set to "1," and if the item has not been sold or bought, the sale flag is set to "0."

[0103] "Sales price" is information indicating the sales price (buying and selling price) of the item corresponding to the "item ID." "Sales date and time" is information indicating the date and time when the sale (buying and selling) of the item corresponding to the "item ID" was completed. "Purchaser" is identification information (e.g., user ID) of user U who purchased the item corresponding to the "item ID."

[0104] 3.2.3. Content storage unit 22 The content storage unit 22 stores information about content. Fig. 8 is a diagram showing an example of a content table stored in the content storage unit 22 of the information processing device 1 according to the embodiment. The content table shown in Fig. 8 includes items such as "content ID" and "content". "Content ID" is identification information that identifies content.

[0105] "Content" refers to information on content provided by various sites including e-commerce sites, and includes, for example, layout information on the content, text information constituting the content, information on images constituting the content, etc. Text information constituting the content includes, for example, text information indicating the title of the content, text information indicating details of the content, etc.

[0106] [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.

[0107] 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).

[0108] 3, the processing unit 12 has an acquisition unit 30, a reception unit 31, a generation unit 32, and a provision unit 33, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be other configurations as long as they perform the information processing described below.

[0109] [3.3.1. Acquisition part 30] The acquisition unit 30 acquires various information from an external information processing device, the terminal device 2, etc. The acquisition unit 30 acquires various 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.

[0110] Furthermore, the acquiring unit 30 acquires content from an external information processing device, and updates the content table by adding the acquired content to the content table stored in the content storage unit 22. Furthermore, the acquiring unit 30 acquires various information included in the request accepted by the accepting unit 31. For example, when the request accepted by the accepting unit 31 is an answer support request or a question support request, the acquiring unit 30 acquires information included in the answer support request or the question support request.

[0111] The acquisition unit 30 also acquires various information from the storage unit 11. For example, the acquisition unit 30 acquires user information, listing history information, sales history information, question and answer history information, content, and the like from the storage unit 11. The acquisition unit 30 acquires, for example, user information, listing history information, sales history information, question and answer history information, content, and the like from the storage unit 11 as information corresponding to the result of acceptance by the acceptance unit 31.

[0112] In addition, for example, when answer information, question information, etc. are generated by the generation unit 32 using a learned model, the acquisition unit 30 acquires information to be used as input information, which is information to be input to such a learned model, from the memory unit 11, etc.

[0113] For example, the acquisition unit 30 acquires, as information to be input to the trained model, information on the item, answer consideration information, desired information, user information, and the like from the storage unit 11, etc. Also, the acquisition unit 30 acquires, as information to be input to the trained model, information on the item, question consideration information, desired information, user information, and the like from the storage unit 11, etc.

[0114] The information on the item being sold includes selling history information, sales history information, etc. The desired information is, for example, information indicating the desire of the user U, who is the seller of the item being sold, regarding at least one of the sales time and price of the item being sold. Note that the input information, which is information to be input to the trained model, may be acquired by the generation unit 32 instead of the acquisition unit 30.

[0115] In addition, when the generation unit 32 generates listing information using an AI agent, information to be input to the AI ​​agent and used as input information is acquired by the AI ​​agent from the memory unit 11, an external information providing device, or the terminal device 2, etc., but the acquisition unit 30 can also acquire information to be input to the AI ​​agent and used as input information from the memory unit 11, etc.

[0116] [3.3.2. Reception Unit 31] The reception unit 31 receives various requests and various information from the terminal device 2 or an external information processing device.

[0117] For example, the reception unit 31 receives an auction request transmitted from the terminal device 2 to the information processing device 1. Such a auction request includes information such as the user ID of the seller, and auction content information, which is information related to the auction.

[0118] The listing content information includes, for example, listing information of the item to be put up for sale, information indicating a delivery method for the item to be put up for sale, etc. When the reception unit 31 receives a listing request from the terminal device 2, the reception unit 31 updates the listing history information table based on the information included in the received listing request. By receiving a listing request from the terminal device 2, the reception unit 31 accepts the listing of the item to be put up for sale.

[0119] The reception unit 31 also receives a purchase request transmitted from the terminal device 2 to the information processing device 1. Such a purchase request includes the user ID of the purchaser, information for identifying the item to be purchased (e.g., an item ID), etc. When the reception unit 31 receives a purchase request from the terminal device 2, it updates the sales history information table based on the information included in the received purchase request.

[0120] The reception unit 31 also receives an item viewing request transmitted from the terminal device 2 to the information processing device 1. Such an item viewing request includes information such as the user ID of the viewer, and the item ID or name of the item to be viewed.

[0121] The reception unit 31 also receives questions about the items for sale by receiving a question request transmitted from the terminal device 2 to the information processing device 1. Such a question request includes information about the question, the user ID of the user U who asked the question, the item ID of the item that the question was about, etc. When the reception unit 31 receives a question request from the terminal device 2, it updates the question and answer history information table based on the information included in the received question request.

[0122] Furthermore, the receiving unit 31 receives an answer request transmitted from the terminal device 2 to the information processing device 1. Such an answer request includes the question ID of the question to be answered, information on the answer to the question, the listing ID of the item to be answered, etc. When the receiving unit 31 receives an answer request from the terminal device 2, it updates the question answer history information table based on the information included in the received answer request.

[0123] For example, the reception unit 31 receives an answer support request transmitted from the terminal device 2 to the information processing device 1. Such an answer support request includes the user ID of the user who is the seller of the item about which the question has been asked, information identifying the question, information about the item about which the question has been asked, etc. The information identifying the question is, for example, question information or a question ID. The answer support request is an example of a request to generate an answer to a question.

[0124] The reception unit 31 also receives a question support request transmitted from the terminal device 2 to the information processing device 1. Such a question support request includes the user ID of the user U of the terminal device 2 that transmitted the question support request, information for identifying the item that is the subject of the question (e.g., the item ID), and the like. The question support request is an example of a request to generate a question for an item.

[0125] The reception unit 31 also receives an item search request, a question information request, an answer information request, an answer support screen request, a question support screen request, and the like, which are transmitted from the terminal device 2 to the information processing device 1. The reception unit 31 also receives questions from the user U about the items for sale and answers to the questions.

[0126] [3.3.3. Generation unit 32] The generation unit 32 causes an AI agent or a trained model that generates and outputs information according to input information to generate answer information, question information, and the like.

[0127] For example, the generation unit 32 inputs input information including information corresponding to the answer support request received by the reception unit 31 to the AI ​​agent or the trained model, and causes the AI ​​agent or the trained model to generate answer information.

[0128] In addition, the generation unit 32 inputs input information including information corresponding to the question support request received by the reception unit 31 to the AI ​​agent or the trained model, and causes the AI ​​agent or the trained model to generate question information.

[0129] The generation unit 32 is configured to have an AI agent or a learned model, but the AI ​​agent or the learned model may be configured to be possessed by an external information processing device. In this case, the generation unit 32 sends a generation request to generate answer information, question information, etc. to the external information processing device via the communication unit 10, and acquires the answer information, question information, etc. generated by the AI ​​agent or the learned model in the external information processing device.

[0130] The generation unit 32, for example, inputs input information including information on the question specified in the answer support request and information for outputting an answer to the question to an AI agent or a trained model that generates and outputs information according to the input information, and causes the AI ​​agent or trained model to generate answer information that is information indicating the answer to the question.

[0131] In addition, the generation unit 32 inputs input information including information about the item identified in the question support request and information for outputting a question about the item to an AI agent or a trained model that generates and outputs information according to the input information, and causes the AI ​​agent or trained model to generate question information, which is information indicating a question.

[0132] First, we will explain how to generate listing information using an AI agent. The AI ​​agent is, for example, an autonomous AI agent such as AutoGPT, but it may also be an autonomous AI agent created specifically for the AI ​​support function of the flea market app.

[0133] For example, when an autonomous AI agent is given a goal, it causes a generative AI to generate tasks for achieving that goal, collects information for the generative AI to execute the generated tasks, and outputs information for achieving the goal by repeating the process of having the generative AI execute the tasks.

[0134] The generative AI is, for example, a text generation AI, but may also be a combination of a text generation AI and an image processing 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.

[0135] 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 learning so that the input information is not used as a new answer. The generation AI may be specially trained (for example, fine-tuned) for generating answer information, question information, etc. by an AI agent.

[0136] The generative AI may be a multimodal generative AI, which is a model that generates images from text or generates text from images, such as CM3Leon, but is not limited to such examples.

[0137] [3.3.3.1. Generation of Answer Information] First, the generation of answer information when the answer support request is received by the receiving unit 31 will be described.

[0138] Here, the information of the item that is the subject of the question is assumed to be "XX···XX" (where "XX···XX" is information string indicating the item), and the question information identified in the answer support request is assumed to be "YY···YY" (where "XX···XX" is information string indicating the question).

[0139] In this case, the generation unit 32 inputs the following string of information to the AI ​​agent as input information: "The following question was asked about the item listed below. Please tell me the answer to this question. The question is 'YY...YY'. The item listed is 'XX...XX'."

[0140] 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 answer information indicating an answer to the question specified in the answer support request. The input information input to the AI ​​agent is instruction information in natural language, and is also called a prompt.

[0141] In an AI agent, for example, a task can be generated by a generative AI in response to input information, and the information required to execute the task can be collected from the memory unit 11 or an external information providing device, etc., in response to a request from the generative AI, and the task can be executed by having the generative AI analyze the collected information.

[0142] The information collected by the AI ​​agent may be, for example, answer information to questions about items that were previously listed and sold (purchased) on a flea market service and were highly rated by purchasers or questioners, but is not limited to such examples. For example, the information collected by the AI ​​agent may be answer information to questions about items that were highly rated and were sold shortly after being listed (for example, within a threshold period), or other information.

[0143] The information collected by the AI ​​agent may include answer information previously generated by the AI ​​agent, or may include answer information to questions about items currently being sold on the flea market service. The information collected by the AI ​​agent is answer information to questions about other items that are the same as the item identified by the input information, but may also include answer information to questions about other items similar to the item identified by the input information.

[0144] The answer information may include, in addition to information of a string indicating the answer, information for controlling the flea market app (for example, information indicating a command to automatically operate the imaging unit of the terminal device 2 of the seller who is the answerer on the questioner Q&A screen).

[0145] Furthermore, the generating unit 32 can cause the AI ​​agent to generate answer information using, as input information, information further including answer consideration information, which is information to be taken into consideration when generating answer information.

[0146] The answer consideration information includes, for example, at least one of answer information to a question about an item in the same category as the item in question, information on the price (selling price) of an item the same as the item in question, information on the item in question in news content, information on the item in question on SNS, information on the season when the item was listed, and information on the weather when the item was listed. The news content is content provided by a news distribution service, but is not limited to such examples.

[0147] For example, if the item in question is a drum-type washing machine, the category of the item in question may be washing machine, home appliance, etc. For example, if the item in question is a perfume, the category of the item in question may be beauty, cosmetics, etc.

[0148] The information on the item being questioned about in news content or on SNS may be, but is not limited to, information indicating whether the item being questioned about is trending, information indicating whether the item being questioned about is becoming trending, information indicating whether the trend of the item being questioned about is about to end, etc. For example, the information on the item being questioned about in news content or on SNS may be information on news content or on SNS that positively covers the item being questioned about.

[0149] The generation unit 32 can cause the AI ​​agent to generate answer information using, for example, the information of the character string "Please give us an answer taking into consideration the answer consideration information below" and information further including the answer consideration information as input information. The generation unit 32 can also replace the information of the character string "Please give us an answer to this question" with the information of the character string "Please give us an appropriate answer taking into consideration the answer consideration information below" and further cause the AI ​​agent to generate answer information using information including the answer consideration information as input information.

[0150] When information including an instruction to consider the answer consideration information is input as input information, the AI ​​agent further collects information corresponding to the answer consideration information and analyzes the collected information. For example, when the answer consideration information includes the information of the string "answers to other items in the same category as the item," the AI ​​agent collects answer information regarding questions about other items in the same category as the item.

[0151] In this case, the AI ​​agent can generate answer information based on, for example, answer information to questions about the questioned item and answer information to questions about other items in the same category as the questioned item, which allows the AI ​​agent to appropriately increase the answer information to refer to and appropriately generate answer information to questions about the questioned item.

[0152] Furthermore, when the answer consideration information includes information on the price (selling price) of an item that is the same as the item that is the subject of the question, the AI ​​agent collects information on the price (selling price) of an item that is the same as the item that is the subject of the question. As a result, for example, when the question information is about a price reduction, the AI ​​agent can use the generative AI to generate answer information that includes whether or not the price can be reduced and the amount of the reduction.

[0153] In addition, when the answer consideration information includes information about items listed in news content, the AI ​​agent collects information about items listed in news content, and when the answer consideration information includes information about items that are the subject of questions on SNS, the AI ​​agent collects information about the items that are the subject of questions on SNS. This allows the AI ​​agent to appropriately generate answer information to questions about, for example, the contents of the items that are the subject of questions.

[0154] Furthermore, when the answer consideration information includes information on the listing time (e.g., season) or weather at the listing time, the AI ​​agent collects answer information for items that were listed or sold at the listing time of the item in question or at the listing time (e.g., season) corresponding to the current time, answer information for items that were listed or sold in the weather at that time, etc. The listing time is the time of listing. This allows the AI ​​agent to appropriately generate answer information according to, for example, the season or weather.

[0155] The generation unit 32 can inquire of the generation AI what kind of answer consideration information should be included in the input information together with the question information, and obtain an answer from the generation AI in response to the inquiry. The generation unit 32 can also obtain answer consideration information corresponding to the questioned item from the correspondence information including answer consideration information for each item name or answer consideration information for each item category.

[0156] In addition, for example, when the user U inputs or selects desired information, the generating unit 32 can cause the AI ​​agent to generate answer information using information further including the desired information as input information. The desired information is information of the character string "I want to sell quickly" or information of the character string "I want to sell at a high price".

[0157] For example, when the desired information is the character string "I want to sell quickly" or the character string "Please give me an answer that will help me sell as quickly as possible," the generating unit 32 uses information further including the desired information as input information to cause the AI ​​agent to generate answer information. The character string "I want to sell quickly" and the character string "Please give me an answer that will help me sell as quickly as possible" are examples of information indicating the seller's desire regarding the timing of selling the item.

[0158] Furthermore, for example, when the desired information is the character string "I want to sell it for a high price" or the character string "Please give me an answer that will sell it for as high as possible", the generation unit 32 uses information further including the desired information as input information and causes the AI ​​agent to generate answer information. The character string "I want to sell it for a high price" or the character string "Please give me an answer that will sell it for as high as possible" are examples of information indicating the seller's desire regarding the price of the item. Note that the desired information may be, for example, the character string "I want to sell it quickly and for a high price" or the character string "Please give me an answer that will sell it as quickly and for as high as possible".

[0159] The generation unit 32 can also cause the AI ​​agent to generate answer information using as input information information further including user information, which is information about the user U who is the seller of the item being questioned. The information about the user U is, for example, attribute information about the user U, behavior history information about the user U, and the like.

[0160] The attribute information of the user U is information indicating the attributes of the user U, and the attributes of the user U are, for example, the demographic attributes and psychographic attributes of the user U. The demographic attributes are demographic attributes, for example, age, sex, occupation, place of residence, annual income, family structure, etc. The psychographic attributes are psychological attributes, for example, lifestyle, values, interests, etc.

[0161] The behavior history information of the user UA is information indicating the past behavior of the user UA, and includes information on the user UA's past usage history of online services, etc. The information on the user UA's past usage history of online services includes, for example, information on the user UA's past purchase history of items for sale and the user UA's past response information.

[0162] The generation unit 32 can cause the AI ​​agent to generate answer information using, as input information, information further including, for example, a character string "The following question has been asked about the item listed below, which has been listed by a user corresponding to the user information below. Please tell me the answer to this question. The question is 'YY...YY'. The item is 'XX...XX'" and user information. The generation unit 32 can also include answer consideration information, desired information, and the like in the input information.

[0163] The AI ​​agent can appropriately generate answer information when the question is about the condition or contents of the item in question, for example, based on information about the purchase history or sales history of the item in question by the seller, user U. The condition of the item in question may be, for example, unused, nearly unused, no noticeable scratches or stains, slightly scratched or stained, scratched or stained, etc., but may also be in good condition, average condition, poor condition, etc.

[0164] Furthermore, the AI ​​agent can appropriately generate answer information according to the age, sex, occupation, place of residence, interests, etc. of the user U, who is the seller, based on attribute information of the user U. Furthermore, the AI ​​agent can appropriately generate answer information that is more natural to the user U, based on, for example, past answer information of the user U.

[0165] Furthermore, the input information to be input to the AI ​​agent may include information about the user U who is the asker asking a question about the item being asked about, in addition to information about the user U who is the seller of the item being asked about.

[0166] Next, generation of answer information using a trained model without using an AI agent will be described. The trained model is, for example, the above-mentioned generation AI. Such a generation AI is, for example, a text generation AI, but may be a combination of a text generation AI and an image processing AI.

[0167] The generation unit 32 has a trained model that has been trained using learning information that includes, for each question, answer information to questions about items that have been previously listed and sold (purchased) on a flea market service and that were highly rated by purchasers or questioners.

[0168] For example, the learning information is a dataset that takes as input information including information about the item for sale, information about questions about the item for sale, and information for outputting answers to the questions, and targets answer information to the questions about the item for sale, and learning is, for example, fine tuning, but is not limited to such an example.

[0169] In this case, the generation unit 32 inputs information including information about the item that is the subject of the question (e.g., part or all of the listing information), question information about the item that is the subject of the question, and information for outputting an answer to the question indicated in the question information, as input information to the trained model, and causes the trained model to generate answer information to the question about the item that is the subject of the question.

[0170] The trained model may be a model trained using training information further including answer consideration information for each answer. In this case, the generation unit 32 inputs information further including the answer consideration information as input information to the trained model, and causes the trained model to generate answer information according to the answer consideration information.

[0171] The trained model may be a model trained using training information further including desired information for each item, for example. In this case, the generating unit 32 inputs information including information on the questioned item and question information and desired information for the questioned item as input information to the trained model, and causes the trained model to generate answer information corresponding to the question information and desired information.

[0172] The desired information is, for example, information including the character string “I want to sell it at a high price” or information including the character string “I want to sell it quickly.” In this case, the learning information is, for example, a data set that takes information further including the desired information as an input and targets the response information.

[0173] The trained model may be a model trained using training information further including answer consideration information and desired information for each question. In this case, the generating unit 32 inputs information further including answer consideration information and desired information as input information to the trained model, and causes the trained model to generate information on the questioned item, question information, answer consideration information, and answer information corresponding to the desired information.

[0174] The trained model may be a model trained using training information for each answer that further includes user information of the user UA who is the seller of the item. In this case, the generating unit 32 inputs information further including the user information as input information to the trained model, and causes the trained model to generate information on the questioned item, question information, answer consideration information, desired information, and answer information corresponding to the user information.

[0175] The input information input to the trained model may be similar to the input information input to the AI ​​agent, and input information for generating appropriate answer information is input to the trained model.

[0176] [3.3.3.2. Generation of Question Information] Next, generation of question information when a question support request is received by the receiving unit 31 will be described.

[0177] The generation unit 32 inputs input information including information of a user U whose question support request, which is a request for generating a question, has been accepted by the acceptance unit 31, and information for outputting a question, to an AI agent or a trained model that generates and outputs information according to the input information, and causes the AI ​​agent or trained model to generate question information, which is information indicating a question.

[0178] Here, assume that the information of the item that is the subject of the question is "XX···XX" (where "XX···XX" is information of a string indicating the item). In this case, the generation unit 32 inputs the string "Please tell us your question about the item with the information shown below. The item is 'XX···XX'." as input information to the AI ​​agent.

[0179] As a result, the AI ​​agent uses the input information as a goal, generates and executes a task according to the goal, and generates and outputs question information indicating a question regarding the item identified in the question support request.

[0180] The information collected by the AI ​​agent is, for example, information on questions about items that were previously listed and sold (purchased) on a flea market service and were highly rated by buyers or questioners, but is not limited to such examples. For example, the information collected by the AI ​​agent may be information on questions about items that were highly rated and were sold shortly after being listed (for example, a period below a threshold), or other information.

[0181] The information collected by the AI ​​agent may include question information previously generated by the AI ​​agent, or may include information on questions about items currently being sold on the flea market service. The information collected by the AI ​​agent is information on questions about other items that are the same as the item identified by the input information as the item being asked about, but may also include information on questions about other items similar to the item being asked about.

[0182] The question information may include, in addition to information of a string indicating a question, information for controlling a flea market app (for example, information indicating a command to automatically operate the imaging unit of the terminal device 2 of the questioner user U on the questioner Q&A screen).

[0183] Furthermore, the generating unit 32 can cause the AI ​​agent to generate question information using, as input information, information further including question consideration information, which is information to be taken into consideration when generating question information.

[0184] The question consideration information includes, for example, at least one of information on questions about items in the same category as the item being questioned about, information on the price (selling price) of an item the same as the item being questioned about, information on items being offered in news content, information on the item being questioned about on SNS, information on the season when the item was offered, and information on the weather when the item was offered. The news content is content provided by a news distribution service, but is not limited to such examples.

[0185] For example, if the item in question is a drum-type washing machine, the category of the item in question may be washing machine, home appliance, etc. For example, if the item in question is a perfume, the category of the item in question may be beauty, cosmetics, etc.

[0186] The information on the item being questioned about in news content or on SNS may be, but is not limited to, information indicating whether the item being questioned about is trending, information indicating whether the item being questioned about is becoming trending, information indicating whether the trend of the item being questioned about is about to end, etc. For example, the information on the item being questioned about in news content or on SNS may be information on news content or on SNS that positively covers the item being questioned about.

[0187] The generation unit 32 can cause the AI ​​agent to generate question information using, for example, the information of the character string "Please tell us a question in consideration of the following question consideration information" and information further including the question consideration information as input information. The generation unit 32 can also replace the information of the character string "Please tell us a question for this question" with the information of the character string "Please tell us an appropriate question in consideration of the following question consideration information" and further cause the AI ​​agent to generate question information using information including the question consideration information as input information.

[0188] When information including an instruction to consider the question consideration information is input as input information, the AI ​​agent further collects information corresponding to the question consideration information and analyzes the collected information. For example, when the question consideration information includes the information of the string "questions about other items in the same category as the item," the AI ​​agent collects information about questions about other items in the same category as the item.

[0189] In this case, the AI ​​agent can generate question information based on, for example, information on questions for the item in question and information on questions for other items in the same category as the item in question, which allows the AI ​​agent to appropriately increase the amount of question information to refer to and appropriately generate information on questions for the item in question.

[0190] In addition, when the question consideration information includes information on the price (selling price) of an item that is the same as the item in question, the AI ​​agent collects information on the price (selling price) of an item that is the same as the item in question. This allows the AI ​​agent to use a generative AI to generate question information that includes information such as whether or not a price reduction is possible and the desired price reduction amount.

[0191] In addition, when the question consideration information includes information about the items listed in the news content, the AI ​​agent collects information about the items listed in the news content, and when the question consideration information includes information about the items on the SNS that are the subject of the question, the AI ​​agent collects information about the items on the SNS that are the subject of the question. This allows the AI ​​agent to appropriately generate question information about, for example, the contents of the items on the SNS that are the subject of the question.

[0192] Furthermore, when the question consideration information includes information on the listing time (e.g., season) or the weather at the listing time, the AI ​​agent collects answer information for items that were listed or sold at the listing time of the item in question or the listing time (e.g., season) corresponding to the current time, question information for items that were listed or sold during the weather at that time, etc. The listing time is the time of listing. This allows the AI ​​agent to appropriately generate question information according to, for example, the season or weather.

[0193] The generation unit 32 can inquire of the generation AI what kind of question consideration information should be included in the input information together with the question information, and obtain the answer of the generation AI in response to the inquiry. The generation unit 32 can also obtain question consideration information corresponding to the question target item from the response information including question consideration information for each name of the item or question consideration information for each category of the item to be listed.

[0194] In addition, for example, when the user U inputs or selects desired information, the generating unit 32 can cause the AI ​​agent to generate question information using as input information information further including the desired information or information corresponding to the desired information. The desired information is information of the character string "I want to buy it quickly" or information of the character string "I want to buy it cheaply."

[0195] For example, when the desired information is the character string "I want to buy it soon" or the character string "Please ask a question that will allow me to buy as soon as possible," the generating unit 32 uses as input information information further including the desired information and causes the AI ​​agent to generate question information. The character string "Please ask a question that will allow me to buy as soon as possible" and the character string "I want to buy it soon" are examples of information indicating the desire of a questioner who is a potential purchaser regarding the timing of purchasing the item.

[0196] Furthermore, for example, when the desired information is the information of the character string "I want to buy it cheaply" or the information of the character string "Please ask a question so that I can buy it as cheaply as possible," the generating unit 32 uses information further including such desired information as input information to cause the AI ​​agent to generate question information. The information of the character string "Please ask a question so that I can buy it as cheaply as possible" and the information of the character string "I want to buy it cheaply" are examples of information indicating a questioner who is considering purchasing the seller's item regarding the price of the item.

[0197] The generation unit 32 can also cause the AI ​​agent to generate question information using as input information further including information on the user U who is the seller of the item being questioned. The information on the user U is, for example, attribute information on the user U, action history information on the user U, and the like.

[0198] The generation unit 32 can cause the AI ​​agent to generate question information using as input information information including, for example, a character string "What question do you have about the item shown below, which was listed by the user corresponding to the user information below. The item is 'XX...XX'" and user information. The generation unit 32 can also include question consideration information, desired information, and the like in the input information.

[0199] For example, the AI ​​agent can appropriately generate question information when the question is about the condition or contents of the item being asked about, based on information about the purchase history of the item being asked about by the seller, user U.

[0200] Furthermore, the AI ​​agent can appropriately generate question information according to the age, sex, occupation, place of residence, interests, etc. of the user U, who is the seller, based on attribute information of the user U. Furthermore, the AI ​​agent can appropriately generate question information that is more natural to the user U, based on, for example, past question information of the user U.

[0201] Furthermore, the input information to be input to the AI ​​agent may include information about the user U who is the asker asking a question about the item being asked about, in addition to information about the user U who is the seller of the item being asked about.

[0202] Next, the generation of question information using a trained model without using an AI agent will be described. The trained model is, for example, the above-mentioned generation AI. Such a generation AI is, for example, a text generation AI, but may also be a combination of a text generation AI and an image processing AI.

[0203] The generation unit 32 has a trained model that has been trained using learning information that includes, for each question, information on questions about items that have been listed and sold (purchased) in the past on a flea market service and that were highly rated by purchasers or questioners.

[0204] For example, the learning information is a data set that inputs information including information on the item and information for outputting a question, and targets question information for questions about the item, and the learning is, for example, fine tuning, but is not limited to such an example. In this case, the generation unit 32 inputs information including information on the item to be questioned (for example, part or all of the listing information) and information for outputting a question for the item to be questioned as input information to the trained model, and causes the trained model to generate question information that is information on a question for the item to be questioned.

[0205] The trained model may be a model trained using training information further including question consideration information for each question. In this case, the generation unit 32 inputs information further including the question consideration information as input information to the trained model, and causes the trained model to generate information on the question target item and question information corresponding to the question consideration information.

[0206] The trained model may be a model trained using training information further including desired information for each question. In this case, the generating unit 32 inputs information further including the desired information as input information to the trained model, and causes the trained model to generate information on the item to be questioned and question information corresponding to the desired information.

[0207] The desired information is, for example, information including the character string "I want to buy it at a high price" or information including the character string "I want to buy it quickly." In this case, the learning information is, for example, a data set that uses information including information about the item being asked about and the desired information as input and targets the question information.

[0208] The trained model may be a model trained using training information further including question consideration information and desired information for each question. In this case, the generating unit 32 inputs information further including the question consideration information and desired information as input information to the trained model, and causes the trained model to generate information on the item to be questioned, the question consideration information, and question information corresponding to the desired information.

[0209] The trained model may be a model trained using learning information for each question, which further includes user information of a user U who is a seller of an item to be put up for sale. In this case, the generation unit 32 inputs information further including user information as input information to the trained model, and causes the trained model to generate question information, which is information on the item to be asked about, question consideration information (or question consideration response information), desired information, and information on a question about the item to be asked about according to the user information.

[0210] The input information input to the trained model may be similar to the input information input to the AI ​​agent, and input information for generating appropriate question information is input to the trained model.

[0211] [3.3.4.Providing Department 33] The providing unit 33 transmits various pieces of information to the terminal device 2 via the communication unit 10, thereby providing various pieces of information to the user U. The providing unit 33 transmits information to the terminal device 2 via, for example, an API.

[0212] For example, the providing unit 33 transmits the content acquired by the acquiring unit 30 from the content storage unit 22 to the terminal device 2, thereby providing the content to the user U. The terminal device 2 displays the content transmitted from the providing unit 33.

[0213] Furthermore, when an item search request is received by the receiving unit 31, the providing unit 33 generates item list information, which is information on an item list including multiple items corresponding to the search keyword included in the item search request, based on the listing history information table and the buying and selling history information table stored in the listing history information storage unit 21. The providing unit 33 transmits the generated item list information to the terminal device 2, thereby providing the item list information to the user U. The terminal device 2 displays an item list screen based on the item list information transmitted from the providing unit 33.

[0214] Furthermore, when the receiving unit 31 receives an item viewing request, the providing unit 33 extracts item information (including, for example, item information) which is information on the item specified in the item viewing request from the auction history information table stored in the auction history information storage unit 21. The providing unit 33 transmits the extracted item information to the terminal device 2, thereby providing the user U with item information corresponding to the item viewing request. The terminal device 2 displays an item screen based on the item information transmitted from the providing unit 33.

[0215] Furthermore, the providing unit 33 transmits the answer information, question information, etc. generated by the generating unit 32 to the terminal device 2, thereby providing the answer information, question information, etc. generated by the generating unit 32 to the user U. For example, when an answer support request is accepted by the accepting unit 31, the providing unit 33 provides the answer information generated by the generating unit 32 to the user U, and when a question support request is accepted by the accepting unit 31, the providing unit 33 provides the question information generated by the generating unit 32 to the user U.

[0216] Furthermore, when the user U launches the flea market app, the providing unit 33 provides information included in the flea market home screen displayed on the terminal device 2 based on a request from the terminal device 2. Fig. 9 is a diagram showing an example of the flea market home screen displayed on the terminal device 2 according to the embodiment. The flea market home screen 50 shown in Fig. 9 includes search content 51, a tab row 52, ​​content 53, and a button row 54. The content 53 includes information indicating brand rankings and information on multiple items for sale.

[0217] The search content 51 includes a search frame and a search button. When the user U inputs a search keyword into the search frame and operates the search button, an item search request including the search keyword input into the search frame is transmitted from the terminal device 2 to the information processing device 1. When the providing unit 33 of the information processing device 1 accepts the item search request, it transmits information on items corresponding to the search keyword as search results to the terminal device 2. The search results are displayed on the terminal device 2.

[0218] The tab column 52 includes a plurality of tabs for the user U to operate information displayed on the terminal device 2. The tab column 52 shown in Fig. 9 includes a plurality of tabs such as "Saved Search Conditions", "Recommendations", "Following", "Posts", etc. When the user U operates a desired tab among the plurality of tabs included in the tab column 52, information corresponding to the operated tab is transmitted from the providing unit 33 to the terminal device 2 and displayed on the terminal device 2.

[0219] The content 53 is, for example, content corresponding to a predetermined tab among the multiple tabs included in the tab column 52, or content corresponding to a tab selected by the user U. The button column 54 includes multiple buttons for the user U to operate information displayed on the terminal device 2. The button column 54 shown in Fig. 9 includes multiple buttons such as "Home", "Search", "Items for Sale / Belongings", "Wanted Items", and "My Page".

[0220] When the user U operates a desired button among the multiple buttons included in the button row 54, a request corresponding to the operated button is transmitted from the providing unit 33 to the terminal device 2 and is displayed on the terminal device 2.

[0221] When question information from a potential purchaser or the like is accepted by the acceptance unit 31, the providing unit 33 transmits notification information indicating that the question information has been accepted by the acceptance unit 31 to the terminal device 2 of the seller who is offering an item corresponding to the question via the communication unit 10. When the terminal device 2 receives the notification information transmitted from the providing unit 33 via the communication unit 10, it displays the notification information.

[0222] Fig. 10 is a diagram showing an example of notification information displayed on the terminal device 2 according to the embodiment. Notification information 60 shown in Fig. 10 is information indicating that there is new question information, and includes information such as a character string "A question has been received about the drum type washing machine 7 kg washing machine C."

[0223] When user U, who is a seller, operates terminal device 2 to select notification information 60 displayed on terminal device 2, a question information request is transmitted from terminal device 2 to information processing device 1. When providing unit 33 receives the question information request transmitted from terminal device 2, it transmits question information corresponding to the question information request via communication unit 10. Terminal device 2 acquires from information processing device 1 the question information notified of its occurrence in the notification information, and displays a seller Q&A screen including the acquired question information.

[0224] Fig. 11 is a diagram showing an example of a seller Q&A screen displayed on the terminal device 2 according to the embodiment. The seller Q&A screen 70 shown in Fig. 11 includes item information 71, a Q&A area 72, an answer input box 73, a send button 74, and an answer support button 75. The Q&A area 72 includes question information 721 from potential buyers and the like.

[0225] The user U checks the question information 721, operates the terminal device 2 to input information indicating an answer to the question indicated in the question information 721 into the answer input box 73, and selects the send button 74. This causes the terminal device 2 to transmit answer information, which is information indicating the answer input into the answer input box 73, to the information processing device 1. When the answer information transmitted from the seller's terminal device 2 is accepted by the accepting unit 31, the providing unit 33 transmits the answer information from the information processing device 1 to the questioner's terminal device 2.

[0226] Furthermore, when the answer support button 75 is selected by the user U operating the terminal device 2, the terminal device 2 transmits an answer support screen request to the information processing device 1. When the answer support screen request transmitted from the terminal device 2 is accepted by the acceptance unit 31, the providing unit 33 transmits and provides information included in the AI ​​answer support screen to the terminal device 2. As a result, the AI ​​answer support screen is displayed on the terminal device 2.

[0227] Fig. 12 is a diagram showing an example of an AI answer support screen displayed on the terminal device 2 according to the embodiment. The AI ​​answer support screen 80 shown in Fig. 12 includes a consideration information selection area 81, a desired information selection area 82, and a request start button 83. The consideration information selection area 81 is an area for selecting answer consideration information, and is, for example, a combo box for selecting one answer consideration information from multiple types of predetermined answer consideration information.

[0228] The desired information selection area 82 is an area for selecting desired information, for example, a combo box for selecting multiple predetermined types of desired information. The request start button 83 is a button for causing the information processing device 1 to execute a reply support function.

[0229] When the user U selects the request start button 83, the terminal device 2 transmits an answer support request to the information processing device 1. The answer support request includes the question information shown on the seller Q&A screen 70 or information identifying such question information, answer consideration information selected by the user U on the AI ​​answer support screen 80, desired information, and the like.

[0230] The providing unit 33 transmits, to the terminal device 2 via the communication unit 10, answer information generated by the generating unit 32 in response to the answer support request transmitted from the terminal device 2 received by the receiving unit 31.

[0231] The terminal device 2 receives the answer information transmitted from the providing unit 33, and updates the seller Q&A screen 70 based on the received answer information. Fig. 13 is a diagram showing an example of the updated seller Q&A screen 70 displayed on the terminal device 2 according to the embodiment.

[0232] Since the answer input box 73 of the seller Q&A screen 70 shown in FIG. 13 contains answer information generated by the generation unit 32, the seller, user U, can eliminate or reduce the effort required to input answer information into the seller Q&A screen 70, and the information processing device 1 can increase the convenience for the seller, user U.

[0233] On the seller Q&A screen 70, the answer information generated by the generation unit 32 can be changed by the user U operating the terminal device 2, which also improves the convenience of the user U. In addition, the user U can select the answer support button 76 and select the request start button 83 on the AI ​​answer support screen 80, which allows the answer information on the seller Q&A screen 70 to be replaced with answer information regenerated by the information processing device 1.

[0234] 14 is a diagram showing another example of the updated seller Q&A screen 70 displayed on the terminal device 2 according to the embodiment. In the seller Q&A screen 70 shown in FIG. 14, the question information 721 is information of the character string "I am considering purchasing. Could you also take a picture of the inside of the washing machine?"

[0235] In this case, when the user U selects the answer support button 75 and then selects the start request button 83 on the AI ​​answer support screen 80, the terminal device 2 sends an answer support request to the information processing device 1, the request including the question information shown on the seller Q&A screen 70 or information identifying such question information.

[0236] The providing unit 33 transmits answer information generated by the generating unit 32 in response to the answer support request transmitted from the terminal device 2 received by the receiving unit 31 to the terminal device 2 via the communication unit 10. The answer information includes information indicating a command to automatically operate the imaging unit of the terminal device 2 on the seller Q&A screen 70.

[0237] When terminal device 2 receives the answer information transmitted from providing unit 33, it starts the imaging unit based on the received answer information and displays imaging screen 77 that captures an image of the washing machine. Imaging screen 77 includes information such as the character string "Please take an image of the inside of the washing machine" in area 78 where the image captured by the imaging unit is displayed.

[0238] This allows user U, the seller, to open the lid of the washing machine and easily obtain image information of the inside of the washing machine drum as part of the answer information to the question by the imaging unit of terminal device 2. In this case, part of the answer information to the question also includes information such as the character string "We will send you images taken inside the washing machine."

[0239] Furthermore, the user U can operate the terminal device 2 to select information on a desired item from information on a plurality of items included in the content 53 on the flea market home screen 50, or select information on a desired item from information on a plurality of items included in the search results. The providing unit 33 transmits an item viewing request including information identifying the item selected by the user U to the information processing device 1.

[0240] When the information processing device 1 accepts an item viewing request transmitted from the terminal device 2, it transmits to the terminal device 2 item information including the item information of the item specified in the item viewing request.

[0241] When the acquisition unit 30 acquires the item information transmitted from the information processing device 1, the providing unit 33 displays an item screen based on the item information acquired by the acquisition unit 30. Fig. 15 is a diagram showing an example of the item screen displayed on the terminal device 2 according to the embodiment.

[0242] 15 includes an item image 91, item information 92, 93, and a question button 94. The user U can select the question button 94 by operating the terminal device 2. When the question button 94 is selected by the user U operating the terminal device 2, the terminal device 2 displays a questioner Q&A screen.

[0243] Fig. 16 is a diagram showing an example of a questioner Q&A screen displayed on the terminal device 2 according to the embodiment. The questioner Q&A screen 101 shown in Fig. 16 includes item information 102, a Q&A area 103, a question input frame 104, a send button 105, and a question support button 106.

[0244] When the user U inputs information indicating a question into the question input box 104 and selects the send button 105, the terminal device 2 transmits the question information, which is the information indicating the question input into the question input box 104, to the information processing device 1. When the question information transmitted from the terminal device 2 of the questioner is accepted by the accepting unit 31, the providing unit 33 transmits notification information corresponding to the question information from the information processing device 1 to the terminal device 2 of the seller.

[0245] Furthermore, when the user U operates the terminal device 2 to select the question support button 106, the terminal device 2 transmits a question support screen request to the information processing device 1. When the request for a question support screen transmitted from the terminal device 2 is received by the receiving unit 31, the providing unit 33 transmits information contained in the AI ​​question support screen displayed on the terminal device 2 to the terminal device 2 and provides it to the terminal device 2. As a result, the AI ​​question support screen is displayed on the terminal device 2.

[0246] Fig. 17 is a diagram showing an example of an AI question support screen displayed on the terminal device 2 according to the embodiment. The AI ​​question support screen 110 shown in Fig. 17 includes a consideration information selection area 111, a desired information selection area 112, and a request start button 113. The consideration information selection area 111 is an area for selecting question consideration information, and is, for example, a combo box for selecting one piece of question consideration information from multiple types of predetermined question consideration information.

[0247] The desired information selection area 112 is an area for selecting desired information, for example, a combo box for selecting multiple predetermined types of desired information. The request start button 83 is a button for causing the information processing device 1 to execute the question support function.

[0248] When the user U selects the request start button 113, the terminal device 2 transmits a question support request to the information processing device 1. The question support request includes information for identifying the item that is the subject of the question, question consideration information and desired information selected by the user U on the AI ​​question support screen 110, and the like.

[0249] The providing unit 33 transmits, to the terminal device 2 via the communication unit 10, question information generated by the generating unit 32 in response to a question support request transmitted from the terminal device 2 and received by the receiving unit 31.

[0250] The terminal device 2 receives the question information transmitted from the providing unit 33, and updates the questioner Q&A screen 101 based on the received question information. Fig. 18 is a diagram showing an example of the updated questioner Q&A screen 101 displayed on the terminal device 2 according to the embodiment.

[0251] Since the question input box 104 of the questioner Q&A screen 101 shown in FIG. 18 contains question information generated by the generation unit 32, the questioner, user U, can eliminate or reduce the effort required for inputting question information into the questioner Q&A screen 101, and the information processing device 1 can increase the convenience for the questioner, user U.

[0252] On the questioner Q&A screen 101, the question information generated by the generation unit 32 can be changed by the user U operating the terminal device 2, which also improves convenience for the user U. In addition, the user U can select the question re-support button 107 or the request start button 113, which allows the question information on the questioner Q&A screen 101 to be replaced with question information regenerated by the information processing device 1.

[0253] 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. 19 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0254] 19, the processing unit 12 of the information processing device 1 determines whether or not a support request transmitted from the terminal device 2 has been accepted (step S10). The support request is, for example, a support request for an answer or a support request for a question. When the processing unit 12 determines that a support request has been accepted (step S10: Yes), it generates information corresponding to the support request (step S11) and provides the information corresponding to the support request (step S12).

[0255] When the processing of step S12 is completed or when it is determined that a support request has not been accepted (step S10: No), the processing unit 12 determines whether or not question information transmitted from the terminal device 2 has been accepted (step S13). When it is determined that question information has been accepted (step S13: Yes), the processing unit 12 performs question processing (step S14).

[0256] When the processing of step S14 is completed or when it is determined that the question information has not been accepted (step S13: No), the processing unit 12 determines whether or not answer information transmitted from the terminal device 2 has been accepted (step S15). When it is determined that the answer information has been accepted (step S15: Yes), the processing unit 12 performs answer processing (step S16).

[0257] When the processing of step S16 is completed or when it is determined that the viewing request has not been accepted (step S15: No), the processing unit 12 determines whether or not another request transmitted from the terminal device 2 has been accepted (step S17). When it is determined that another request has been accepted (step S17: Yes), the processing unit 12 performs another process (step S18).

[0258] When the process of step S18 is completed or when it is determined that no other request has been received (step S17: No), the processing unit 12 determines whether or not the operation end timing has arrived (step S19). 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.

[0259] If the processing unit 12 determines that the operation end time has not arrived (step S19: No), it transitions to step S10, and if it determines that the operation end time has arrived (step S19: Yes), it terminates the processing shown in FIG. 19.

[0260] 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 generation unit 32, and the provision unit 33. 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.

[0261] In the above example, the user information to be included in the input information has been described as the user information of user U, the seller, but the user information to be included in the input information may also include user information of user UA, the inquirer, in addition to or instead of the user information of user U, the seller.

[0262] [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. 20, for example. Fig. 20 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.

[0263] 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.

[0264] 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.

[0265] 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.

[0266] 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.

[0267] 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.

[0268] [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.

[0269] 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.

[0270] 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.

[0271] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0272] 8. Effects As described above, the information processing device 1 according to the embodiment includes a receiving unit 31, a generating unit 32, and a providing unit 33. The receiving unit 31 receives a question about an item for sale. The generating unit 32 inputs input information including question information and information for outputting an answer to the question to an AI agent or a trained model that generates and outputs information according to the input information, and causes the AI ​​agent or the trained model to generate answer information that is information indicating an answer to the question. The providing unit 33 provides the answer information generated by the generating unit 32. This allows the information processing device 1 to improve the convenience of the user U.

[0273] In addition, the generation unit 32 uses as input information information further including answer consideration information, which is information to be considered in generating the answer information, to cause the AI ​​agent or the trained model to generate the answer information. This allows the information processing device 1 to improve the convenience of the user U.

[0274] The answer consideration information includes at least one of the following information: listing information of other items in the same category as the item for sale, information about the item in news content, information about the item for sale in social networking services, seasonal information, and weather information. This allows the information processing device 1 to improve the convenience of the user U.

[0275] In addition, the generation unit 32 causes the AI ​​agent or the trained model to generate answer information using, as input information, information further including user information that is information about the user U whose question has been accepted by the acceptance unit 31. This enables the information processing device 1 to improve the convenience of the user U.

[0276] In addition, the generation unit 32 uses as input information information further including desired information, which is information indicating the seller's desire regarding at least one of the sales time and price of the item, to cause the AI ​​agent or the trained model to generate answer information. This allows the information processing device 1 to improve the convenience of the user U.

[0277] Furthermore, the reception unit 31 receives a request to generate a question for an item for sale, and the generation unit 32 inputs input information including information of the user U whose question was received by the reception unit 31 and information for outputting the question to an AI agent or trained model that generates and outputs information according to the input information, and causes the AI ​​agent or trained model to generate question information that is information indicating the question, and the provision unit 33 provides the question information generated by the generation unit 32. This enables the information processing device 1 to improve convenience for the user U.

[0278] In addition, the generation unit 32 uses information further including question consideration information, which is information to be considered in generating the question information, as input information, to cause the AI ​​agent or the trained model to generate the question information. This enables the information processing device 1 to improve the convenience of the user U.

[0279] The question consideration information includes at least one of the following information: listing information of other items in the same category as the item for sale, information about the item for sale in news content, information about the item for sale in social networking services, seasonal information, and weather information. This allows the information processing device 1 to improve the convenience of the user U.

[0280] 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.

[0281] 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]

[0282] 1. Information processing device 2, 2A, 2B Terminal equipment 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 21 Listing history information storage unit 22 Content storage unit 30 Acquisition Department 31 Reception 32 Generation part 33 Providing Department 100 Information Processing Systems N Network

Claims

1. a reception section for receiving questions regarding the items on sale; A generation unit inputs input information including information on the question and information for outputting an answer to the question to an AI agent or a trained model that generates and outputs information according to the input information, and causes the AI ​​agent or the trained model to generate answer information that is information indicating the answer to the question; a providing unit that provides the answer information generated by the generating unit.

23. An information processing apparatus comprising:

2. The generation unit is The AI ​​agent or the trained model is caused to generate the answer information using, as the input information, information further including answer consideration information that is information to be considered in generating the answer information.

2. The information processing apparatus according to claim 1,

3. The answer consideration information is The information includes at least one of the following: listing information for other listings in the same category as the listing, information about the listing in news content, information about the listing in social networking services, seasonal information, and weather information.

3. The information processing apparatus according to claim 2.

4. The generation unit is The input information further includes user information, which is information about a user whose question has been accepted by the accepting unit, and the AI ​​agent or the trained model is caused to generate the answer information.

3. 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 desired information, which is information indicating the seller's desire regarding at least one of the sales time and price of the item, and the AI ​​agent or the trained model is caused to generate the answer information.

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

6. The reception unit is accepting a request to generate a question for the item; The generation unit is inputting input information including information of a user whose question has been accepted by the accepting unit and information for outputting the question to an AI agent or a trained model that generates and outputs information corresponding to the input information, and causing the AI ​​agent or the trained model to generate question information that is information indicating the question; The providing unit is Providing the question information generated by the generation unit 3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

7. The generation unit is The AI ​​agent or the trained model is caused to generate the question information using, as the input information, information further including question consideration information that is information to be considered in generating the question information.

7. The information processing apparatus according to claim 6,

8. The question consideration information is The information includes at least one of the following: listing information for other listings in the same category as the listing, information about the listing in news content, information about the listing in social networking services, seasonal information, and weather information.

8. The information processing apparatus according to claim 7,

9. 1. A computer-implemented information processing method, comprising: A reception process for receiving questions about the items on sale; A generation process of inputting input information including information on the question and information for outputting an answer to the question to an AI agent or a trained model that generates and outputs information according to the input information, and causing the AI ​​agent or the trained model to generate answer information that is information indicating the answer to the question; and providing the answer information generated by the generating step.

23. An information processing method comprising:

10. The procedure for accepting questions about the items on sale; A generation step of inputting input information including information on the question and information for outputting an answer to the question to an AI agent or a trained model that generates and outputs information according to the input information, and causing the AI ​​agent or the trained model to generate answer information that is information indicating the answer to the question; a providing step of providing the answer information generated by the generating step, 2. An information processing program comprising:

Images