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

Abstract

To provide an information processing device, information processing method and information processing program, which enable more flexible provision of appropriate prompts.SOLUTION: An information processing device disclosed herein comprises a reception unit, search unit, and provision unit. The reception unit receives user setting information via a predetermined API from another information processing device that received the user setting information set by a user. The search unit searches for a prompt to be input to generative AI used by the other information processing device on the basis of the user setting information received by the reception unit. The provision unit provides the prompt retrieved by the search unit to the other information processing device as a provision prompt via an API.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] In recent years, technologies for generating information using generative AI (Artificial Intelligence) have become known. For example, Patent Document 1 discloses a technology that uses large-scale language models (LLMs) to generate a prompt by adding a valid sentence as an additional sentence to an input question sentence within a set character limit. The prompt is information input to the generative AI, and is, for example, information indicating an instruction or request given to the generative AI to perform a specific task. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7313757 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the above-mentioned conventional technology, since a large-scale language model to which a user's question is input generates additional sentences, depending on the learning state of the large-scale language model, it may be difficult to provide prompts more flexibly, and there is room for further improvement in providing appropriate prompts more flexibly.

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

[0006] The information processing device according to the present application includes a receiving unit, a searching unit, and a providing unit. The receiving unit receives user setting information, which is information set by a user, from another information processing device via a predetermined API. The searching unit searches for a prompt to be input to a generation AI used in the other information processing device based on the user setting information received by the receiving unit. The providing unit provides the prompt searched by the searching unit as a provision prompt to the other information processing device via the API. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to provide an appropriate prompt more flexibly. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram for explaining information processing according to the embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a prompt table stored in the prompt storage unit of the information processing device according to the embodiment. [Figure 5] FIG. 5 is a flowchart showing an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, a detailed description will be given of an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments are denoted by the same reference numerals, and redundant descriptions 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 for explaining information processing according to the embodiment.

[0011] 1 is an information processing device that cooperates with each terminal device 2 of a user U to provide various types of information online to the user U, and is realized by, for example, one or more servers or a cloud system. The terminal devices 2 are, for example, smartphones, tablets, or personal computers.

[0012] The information processing device 3 has a generating AI (Artificial Intelligence) and provides a generating AI provision service that enables a user U to use the generating AI via an API (Application Programming Interface) for the generating AI. The information processing device 3 is an example of another information processing device. Hereinafter, the API for the generating AI may be referred to as a generating AI-API.

[0013] The generative AI may be, for example, a text generation AI, an image generation AI, or a multimodal generation AI. The text generation AI is, for example, a large-scale language model trained to estimate and output the next token from an input token sequence, such as a transformer-based model or an RNN (Recurrent Neural Network)-based model, or may be a hybrid model of these. The text generation AI may also be a composite system combined with an identifier to prevent fraudulent use.

[0014] Examples of the transformer-based model include, but are not limited to, a generative pre-trained transformer (GPT) and a pathways language model version 2 (PaLM2). Examples of the RNN-based model include, but are not limited to, a receptance weighted key value (RWKV).

[0015] Image generation AI is AI that generates images from text, and includes, but is not limited to, StackGAN (Generative Adversarial Networks), AttnGAN, T2I (Text-to-Image) with Transformers, and Diffusion models. Diffusion models include, for example, DALL-E and Stable-Diffusion.

[0016] The multimodal generative AI is, for example, a generative AI that generates at least one of text, image, and audio from at least one of text, image, and audio. Examples of the multimodal generative AI include, but are not limited to, GPT-4 Turbo with vision, Gemini, and CM3Leon (Chameleon Multimodal Model).

[0017] The information processing device 1 is an information processing device that provides a prompt providing service that provides prompts input to a generation AI running on the information processing device 3 to the information processing device 3 via an API, and is realized by, for example, one or more servers or a cloud system. Hereinafter, the API provided by the information processing device 1 may be referred to as a prompt providing API.

[0018] As shown in FIG. 1, the information processing device 3 receives a usage request from a user U (step S1). The usage request includes user-related information including user setting information. For example, the information processing device 3 receives the user-related information from the user U by receiving the usage request transmitted from the terminal device 2 of the user U. The user setting information is information set by the user U.

[0019] The user U operates the terminal device 2 to input user setting information into the terminal device 2, and a usage request including the user setting information is transmitted from the terminal device 2 to the information processing device 3. The user setting information included in the usage request is, for example, a user prompt, which is a prompt entered or selected by the user U, or request information indicating a request by the user U.

[0020] A user prompt is information indicating the string of characters that user U intends to input into the generation AI, such as question information indicating a question sentence, or instruction information indicating instructions for the generation AI to generate, but is not limited to such examples.

[0021] For example, question information indicating a question sentence may be information such as the string "Please tell me a recommended restaurant for lunch in Roppongi this Saturday" or the string "What does the future of work hold with recent advances in AI technology?", and instruction information may be information such as the string "Please suggest a three-day travel itinerary in Tokyo" or the string "Summarize the video at the address below", but is not limited to such examples.

[0022] Furthermore, the request information is, for example, information of a character string indicating a request by the user U, but is not limited to such an example. For example, the request information is information of the character string "Prompt to be able to do ~~~" or information of the character string "Prompt to do ~~~". "~~~" is a character string indicating the action or processing that the user U wants the generated AI to perform.

[0023] For example, the user setting information may be information on a string "a prompt that summarizes the latest information on XXX", information on a string "a prompt that can proofread text", or information on a string "a prompt that functions as a shopping assistant". "XXX" is a specific object (e.g., a person). Note that the request information is not limited to the above examples. For example, the request information may be information on a string that further details the content of the operation or process that the user U desires.

[0024] Furthermore, it is assumed that additional information needs to be input to the generation AI when the generation AI uses the prompt or user prompt requested by the user U based on the request information. In this case, the user U can input the additional information, which is information that needs to be input to the generation AI, by operating the terminal device 2. The additional information is information that is input to the generation AI together with the prompt or user prompt requested by the user U based on the request information.

[0025] An additional information required prompt, which is a prompt that requires additional information, is, for example, character string information that specifies the content of the task that the generation AI will execute based on the input information. The character string information that specifies the task includes, for example, character string information that indicates a task definition, task constraints, a definition of the behavior or tone of the generation AI, an output format of the generation AI, and an example of the operation of the generation AI, but is not limited to such examples and may be some or all of this information.

[0026] The additional information is an additional prompt if the generation AI is a text generation AI, and is at least one of an additional prompt and additional image data if the generation AI is a multimodal generation AI.

[0027] For example, if the prompt or user prompt desired by the user U is an additional information required prompt, the user U can input the additional information into the terminal device 2 by operating the terminal device 2. As a result, a usage request including the user-related information and the additional information is transmitted from the terminal device 2 to the information processing device 1. Note that the additional information may be transmitted from the terminal device 2 after the information processing device 3 acquires the provision prompt provided from the information processing device 1 based on the usage request.

[0028] The additional information required prompt is, for example, a string of information such as "You are an experienced travel planner. Based on the user's specific request, we will propose a three-day travel plan. The plan includes places to visit, accommodation, places to eat, and activities." In this case, the additional information is, for example, a string of information such as "Please create a plan for a trip to Okinawa. Your interests are history and gourmet food. The budget is 200,000 yen per person."

[0029] The prompt for additional information is, for example, information on the string "You are an excellent proofreader. Detect up to 20 errors in the input text and suggest corrections. The output format is the incorrect sentence, the correct sentence, and an explanation of the error." In this case, the additional information is information on the string to be proofread.

[0030] The user-related information of the usage request further includes user information. The user information is information about the user U who will be the user of the prompt provided by the information processing device 1. The user information includes identification information of the user U. The identification information of the user U is, for example, the ID (Identifier) ​​of the user U or a cookie of the browser of the terminal device 2, but is not limited to these examples.

[0031] Next, when the information processing device 3 receives a usage request from the user U, the information processing device 3 transmits a prompt request to the information processing device 1 via the prompt providing API based on the information included in the received usage request (step S2).

[0032] For example, if the usage request does not include additional information, the information processing device 3 transmits a prompt request including user setting information to the information processing device 1 via the prompt providing API based on the information included in the usage request.

[0033] In addition, if the usage request includes additional information, the information processing device 3 sends a prompt request including user setting information and the additional information to the information processing device 1 via the prompt providing API based on the information included in the usage request.

[0034] The information processing device 3 can determine the attributes of the user U based on the user information included in the usage request, and in this case, attribute information indicating the attributes of the user U can be included in the prompt request.

[0035] In step S2, when the information processing device 3 receives, for example, a prompt request, which is information from a user U, if the user U corresponding to the received user information is a predetermined user U, it sends the prompt request to the information processing device 1 via the prompt providing API.

[0036] The predetermined user U is, for example, a user U who subscribes to a prompt provision service provided by the operator of the information processing device 3, a user U who has been preset by the operator of the information processing device 3, or a user U of the terminal device 2 that has sent specific information together with the user information. The specific information is information indicating that the user U wishes to try the prompt provision service, but is not limited to such examples.

[0037] The information processing device 3 can also send a prompt request to the information processing device 1 via the prompt providing API, regardless of whether the user U corresponding to the user information is a predetermined user U or not.

[0038] Next, the information processing device 1 accepts a prompt request including user setting information transmitted from the information processing device 3 via the prompt providing API (step S3). The information processing device 1 accepts the user setting information by accepting the prompt request.

[0039] Furthermore, when the prompt request includes additional information, the information processing device 1 accepts the prompt request to receive the additional information. Furthermore, when the prompt request includes attribute information, the information processing device 1 accepts the prompt request to receive the attribute information.

[0040] Next, the information processing device 1 searches for a prompt to be input to the generation AI used in the information processing device 3, based on the information included in the prompt request received in step S3 (step S4).

[0041] The information processing device 1 has a prompt database containing information on a plurality of prompts, and searches the prompt database for a prompt to be input to the generation AI used in the information processing device 3.

[0042] Each prompt included in the prompt database is, for example, a prompt provided by a prompt provider that is a business different from the operator of the information processing device 3, such as a prompt provided by the operator of the information processing device 1. Note that the prompt included in the prompt database may be a prompt provided by the user U as a prompt provider.

[0043] For example, if the generation AI is GPT from OpenAI (registered trademark), the prompt includes information about a character string included in the input information input to the generation AI in association with information indicating a role. The role is a system, a user, or the like. The prompt is a prompt that includes at least one of a system message whose role is the system and a user message whose role is the user.

[0044] A system message is, for example, a prompt indicating that the role is a message indicating the role of the generating AI, and a user message is, for example, a prompt indicating that the role is a message of the user.

[0045] The system message is, for example, character string information that specifies the content of the task to be executed by the generation AI. The character string information that specifies the task includes, for example, a definition of the task, constraints on the task in the generation AI, definitions of the behavior and tone of the generation AI, the output format of the generation AI, and examples of the operation of the generation AI, but is not limited to such examples and may include some of this information.

[0046] Furthermore, the system message may be, for example, a message indicating a scenario, and in this case, may further include, for example, character string information indicating the end condition of a task in the generation AI described above.

[0047] The user message is, for example, but not limited to, character string information indicating a question, inquiry, instruction, etc. to be processed based on the role of the generation AI indicated in the system message. For example, if a system message is not included in the prompt, the user message may include character string information that specifies the content of the task to be performed by the generation AI and character string information indicating the question, inquiry, instruction, etc. to be processed in the task to be performed by the generation AI.

[0048] In addition, if the generating AI is GPT from OpenAI, the prompt may further include an assistant message whose role is assistant. The assistant message is an output message by the generating AI or a message treated as an output message.

[0049] The prompt database contains, for each prompt, information about the prompt, including, for example, prompt identification information, prompt title, prompt heading information, vector information of the prompt heading information, information indicating the prompt, etc. Such a prompt database contains multiple prompts in a searchable manner.

[0050] The prompt header information is information indicating a description of the function of the prompt (e.g., an overview of the function), and the prompt header information is vectorized by, for example, embedding using a sentence embedding model (e.g., a transformer-based model). The vector information of the prompt header information is represented by, for example, a vector with several hundred dimensions, but is not limited to this example.

[0051] Embedding using a sentence embedding model is, for example, embedding using text-embedding-ada provided by OpenAI, BERT (Bidirectional Encoder Representations from Transformers), etc., but is not limited to these examples.

[0052] Note that the vectorization of prompt heading information is not limited to embedding using a sentence embedding model, and may be performed using, for example, Doc2Vec, the average of word embedding, etc. Word2Vec, fastText, etc. are used for word embedding.

[0053] The information processing device 1 vectorizes the user setting information included in the prompt request using a method similar to that used to vectorize the prompt's heading information. The information processing device 1 then retrieves, as prompt candidates, from the prompt database, prompts corresponding to the top m (m is 2 or greater) heading information items whose vector similarity to the user setting information is equal to or greater than a threshold value or whose vector similarity is highest.

[0054] The prompt database may contain information on each of the keywords included in the prompt or its heading information instead of the vector information on the heading information of the prompt. In this case, the information processing device 1 retrieves, from the prompt database, as prompt candidates, prompts that correspond to the prompts or heading information that include one or more terms included in the user setting information included in the search request.

[0055] The prompt database may also include vector information of prompts instead of or in addition to the vector information of the prompt's header information. In this case, the information processing device 1 acquires, as prompt candidates, the top m prompts (m is 2 or more) whose vector similarity with the user setting information is equal to or greater than a threshold value or whose similarity is highest.

[0056] The prompt database may also include information indicating the prompt provision fee, information indicating the number of prompt selections, information indicating the prompt evaluation, etc. The prompt provision fee is a fee paid by the operator of the information processing device 3 or the user U for the use of the prompt.

[0057] The information processing device 1 determines whether the type of the user setting information is a user prompt or request information. For example, when the prompt request includes type information indicating the type of the user setting information, the information processing device 1 determines whether the type of the user setting information is a user prompt or request information based on the type information.

[0058] In addition, the information processing device 1 has, for example, a type determination model, which is a language model different from the generation AI of the information processing device 3, and can use such type determination model to determine whether the type of user setting information is a user prompt or requested information.

[0059] The type determination model is, for example, a large-scale language model that is trained to determine whether the type of user setting information is a user prompt or requested information by inputting user setting information, but is not limited to such examples.

[0060] For example, the type determination model may be a general-purpose large-scale language model. In this case, the information processing device 1 inputs information including instruction information and user setting information into the type determination model, causing the type determination model to determine whether the type of the user setting information is a user prompt or desired information. The instruction information is, for example, information that instructs the type determination model to determine whether the type of the user setting information is a user prompt or desired information.

[0061] When the type of user setting information is a user prompt, the information processing device 1 uses, for example, a prompt comparison and determination model to determine whether a prompt candidate can obtain more appropriate information than the user prompt. The information processing device 1 determines, as a search result in response to the prompt request, the prompt candidate determined by the prompt comparison and determination model to be capable of obtaining more appropriate information than the user prompt.

[0062] The prompt comparison and judgment model is, for example, a large-scale language model that is trained to determine whether a prompt candidate is more appropriate than a user prompt by inputting the user prompt and a prompt candidate, but is not limited to such examples.

[0063] For example, the prompt comparison and judgment model may be a model that has been trained to determine whether a prompt candidate is more appropriate than a user prompt by inputting information including attribute information of user U in addition to the user prompt and prompt candidate.

[0064] The prompt comparison and determination model may be a general-purpose large-scale language model. In this case, the information processing device 1 inputs information including, for example, instruction information, a user prompt, and a prompt candidate into the prompt comparison and determination model, and causes the prompt comparison and determination model to determine whether the prompt candidate is more appropriate than the user prompt.

[0065] In this case, the instruction information may be, for example, information instructing a determination as to whether the prompt candidate is more appropriate than the user prompt. Such instruction information may include, for example, information indicating items for comparing the prompt candidate with the user prompt and the score for each item, and information instructing a determination as to whether the prompt candidate is more appropriate than the user prompt based on the total score. The items may include, but are not limited to, the clarity of the string, the degree of relevance between the strings, the degree of conciseness of the strings, the degree of specificity of the strings, and the presence or absence of examples.

[0066] In addition, the information processing device 1 can input information including attribute information of user U in addition to instruction information, user prompt, and prompt candidate into the prompt comparison and judgment model, and have the prompt comparison and judgment model determine whether the prompt candidate is more appropriate than the user prompt.

[0067] In this case, the instruction information is, for example, information that instructs a user U having the attributes indicated in the attribute information to determine whether the prompt candidate is more appropriate than the user prompt, and includes, for example, information indicating the items for comparing the prompt candidate with the user prompt and the score for each item, and information that instructs a determination of whether the prompt candidate is more appropriate than the user prompt based on the total score.

[0068] Furthermore, when the user prompt is a prompt that does not require additional information, the information processing device 1 transmits the user prompt and each of the prompt candidates to the information processing device 3, for example, via the generation AI-API. A prompt that does not require additional information is a prompt that does not require additional information.

[0069] In this case, the information processing device 3 inputs information including a user prompt as input information to the generation AI, causes the generation AI to generate information corresponding to the user prompt, inputs information including a prompt candidate as input information to the generation AI, and causes the generation AI to generate information corresponding to the prompt candidate. The information processing device 3 provides the information corresponding to the user prompt and the information corresponding to the prompt candidate to the information processing device 1.

[0070] The information processing device 1 inputs information including information corresponding to the user prompt and information corresponding to the prompt candidate provided by the information processing device 3 into the result comparison and determination model, thereby causing the result comparison and determination model to determine whether the prompt candidate is more appropriate than the user prompt. If the information processing device 1 can obtain information more appropriate than the user prompt, it determines the prompt candidate determined by the comparison and determination model as the search result corresponding to the prompt request.

[0071] In this case, the result comparison and judgment model is a model that is trained to determine whether the prompt candidate is more appropriate than the user prompt by inputting information including information corresponding to the user prompt and information corresponding to the prompt candidate, but is not limited to such an example.

[0072] The result comparison and determination model may be a general-purpose large-scale language model. In this case, the information processing device 1 inputs information including, for example, instruction information, information corresponding to the user prompt, and information corresponding to the prompt candidate into the result comparison and determination model, and causes the prompt comparison and determination model to determine whether the prompt candidate is more appropriate than the user prompt.

[0073] In this case, the instruction information may be, for example, information instructing a determination as to whether the information corresponding to the prompt candidate is more appropriate than the information corresponding to the user prompt. Such instruction information may include, for example, information indicating items for comparing the information corresponding to the prompt candidate with the information corresponding to the user prompt, scores for each item, and information instructing a determination as to whether the prompt candidate is more appropriate than the user prompt based on the total score. The items may include, but are not limited to, the clarity of the character string, the degree of relevance between the character strings, the degree of conciseness of the character strings, the degree of specificity of the character strings, and the presence or absence of examples.

[0074] In addition, the information processing device 1 can input information including attribute information of user U into the result comparison and judgment model in addition to the instruction information, information corresponding to the user prompt, and information corresponding to the prompt candidate, and have the result comparison and judgment model determine whether the prompt candidate is more appropriate than the user prompt.

[0075] In this case, the instruction information is, for example, information that instructs a user U having the attributes indicated in the attribute information to determine whether the prompt candidate is more appropriate than the user prompt, and includes, for example, information indicating the items for comparing information corresponding to the prompt candidate with information corresponding to the user prompt and the score for each item, and information that instructs a determination of whether the prompt candidate is more appropriate than the user prompt based on the total score.

[0076] In this way, when the user setting information included in the prompt request received in step S3 is a user prompt, the information processing device 1 can search for a prompt that is estimated to provide more appropriate information than the user prompt from the generation AI.

[0077] Furthermore, based on the user prompt received in step S3 and the attributes of the user U, the information processing device 1 can also search for a prompt that is estimated to provide more appropriate information than the user prompt from the generation AI.

[0078] Furthermore, if the user setting information received in step S3 is information indicating a request from the user U, the information processing device 1 determines the above-described prompt candidates as prompts corresponding to the information indicating the request.

[0079] In this way, when the user setting information received in step S3 is a request from the user U, the information processing device 1 can search for a prompt that meets the request and is to be provided as a provision prompt.

[0080] Next, the information processing device 1 provides the prompt searched for in step S4 as a provision prompt to the information processing device 3 via the prompt providing API (step S5). The information processing device 3 acquires the provision prompt sent from the information processing device 1 via the prompt providing API, inputs information including the provision prompt to the generation AI as input information, and causes the generation AI to generate information according to the provision prompt.

[0081] In addition, if the provision prompt is a prompt that requires additional information, the information processing device 3 inputs information including the additional information included in the usage request and the provision prompt as input information to the generation AI, and causes the generation AI to generate information corresponding to the provision prompt and the additional information.

[0082] Next, the information processing device 3 transmits the information generated by the generation AI to the terminal device 2 as provided information, thereby providing the generated information, which is the information generated by the generation AI, or information based on the generated information, to the user U as provided information (step S6).

[0083] Next, the information processing device 1 determines a usage fee for the provision prompt (step S7). For example, the information processing device 1 determines a higher fee as the provision fee for a provision prompt that is estimated to have a higher possibility of obtaining appropriate information from the generation AI.

[0084] The information processing device 1 can estimate the likelihood of obtaining appropriate information from the generation AI through the provision prompt, for example, based on the user U's evaluation of the provided information obtained using the provision prompt. Information indicating the evaluation of the provided information by each user U is provided to the information processing device 1 from the information processing device 3.

[0085] The information processing device 1 estimates that the higher the average value of the evaluations of the provided information by each user U for a provision prompt, the higher the possibility that appropriate information will be obtained from the generation AI, and determines a higher fee as the provision fee.

[0086] Furthermore, the information processing device 1 can estimate the likelihood of obtaining appropriate information from the generation AI through the provision prompts, based on the user U's evaluation of the provision information obtained using the provision prompts and the number of provision prompts provided to the information processing device 3. The number of provision prompts provided can also be considered the number of uses of the provision prompts by the user U.

[0087] For example, the information processing device 1 estimates that the higher the score obtained by weighting and adding the average evaluation of the provided information by each user U and the number of provided prompts provided to user U, the higher the likelihood that appropriate information will be obtained from the generation AI.

[0088] In addition, the information processing device 1 can also, for example, charge a higher provision fee when a prompt based on the attributes of user U is provided as a provision prompt compared to when a prompt not based on the attributes of user U is provided as a provision prompt.

[0089] Next, the information processing device 1 performs billing processing on the billee (step S8). The billee is, for example, the operator of the information processing device 3 that provided the provision prompt in step S5 or the user U to whom the provision information generated using the provision prompt in step S7 is provided. The billing processing is, for example, processing to bill the billee for the provision fee for the provision prompt provided in step S5.

[0090] The information processing device 1 can, for example, perform billing processing by sending billing information including information indicating the provision fee for the provision prompt and information identifying the person to be billed to a financial institution's device, or by sending billing information including information indicating the provision fee for the provision prompt and information identifying the credit card number of the person to be billed to a credit card company's device.

[0091] Furthermore, if the person to be billed is user U, the information processing device 1 can also bill the provision fee for the provision prompt in points instead of or in addition to a specific currency. For example, the information processing device 1 can perform billing processing by transmitting billing information including information indicating the number of points corresponding to the provision fee for the provision prompt and information identifying the person to be billed to a device of a point management company.

[0092] Points are, for example, rewards given to user U by a points management company when user U, the person to be billed, makes a purchase using a credit card or cash, or when user U, the person to be billed, subscribes to a particular service, but are not limited to such examples.

[0093] In this way, the information processing device 1 searches for a prompt to be input to the generation AI used in the information processing device 3 based on the user setting information received via the provision prompt API (an example of a predetermined API) from the information processing device 3 (an example of another information processing device) that has received the user setting information, which is information set by the user U. The information processing device 1 provides the searched prompt as a provision prompt to the information processing device 3 via the provision prompt API. This allows the information processing device 1 to provide appropriate prompts more flexibly.

[0094] The configuration of an information processing system including the information processing device 1 and terminal device 2 that perform such processing will be described in detail below.

[0095] [2. Information Processing System Configuration] 2 is a diagram illustrating an example of a configuration of an information processing system according to an embodiment. As illustrated in FIG. 2, the information processing system 100 according to the embodiment includes an information processing device 1, a plurality of terminal devices 2, and an information processing device 3.

[0096] The multiple terminal devices 2 are used by different users U. The terminal devices 2 are, for example, laptop personal computers (PCs), desktop PCs, smartphones, tablet PCs, and wearable devices. The wearable devices are, for example, smart glasses or smart watches, but are not limited to these examples.

[0097] The information processing device 1, the terminal device 2, and the information processing device 3 are connected to each other via a network N so as to be able to communicate with each other by wire or wirelessly. Note that the information processing system 100 shown in FIG. 2 may include a plurality of information processing devices 1 and information processing devices 3.

[0098] The network N includes, for example, a WAN (Wide Area Network) such as the Internet and a mobile communication network such as LTE (Long Term Evolution), 4G (4th Generation), and 5G (5th Generation: 5th generation mobile communication system).

[0099] 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 wireless LAN (Local Area Network), and communicate with the information processing device 3, etc. The information processing device 3 can connect to the network N via short-range wireless communication such as a mobile communication network, Bluetooth, or wireless LAN, and communicate with the information processing device 1, etc.

[0100] 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.

[0101] [3.1. Communication Unit 10] The communication unit 10 is realized by, for example, a communication module or a network interface card (NIC). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from the information processing device 3 via the network N.

[0102] [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 includes a prompt storage unit 20.

[0103] 3.2.1. Prompt Storage Unit 20 The prompt storage unit 20 stores various types of information related to prompts. Fig. 4 is a diagram showing an example of a prompt table stored in the prompt storage unit 20 of the information processing device 1 according to the embodiment.

[0104] 4, the prompt table stored in the prompt storage unit 20 is an example of the prompt database described above, and includes information on items such as "prompt ID," "prompt," "related information," "number of provided items," and "evaluation information." The "prompt ID" is an identifier that identifies a prompt, and is information assigned to each prompt.

[0105] A "prompt" is a prompt associated with a "prompt ID." The prompt is, for example, a prompt provided by a prompt provider other than the operator of the information processing device 3, such as a prompt provided by the operator of the information processing device 1. Note that the prompt included in the prompt database may be a prompt provided by the user U as a prompt provider.

[0106] For example, if the generation AI used in the information processing device 3 is GPT from OpenAI, the prompt includes information on a character string included in input information input to the generation AI in association with information indicating a role. The role is a system, a user, or the like. The prompt is a prompt that includes at least one of a system message whose role is the system and a user message whose role is the user.

[0107] A system message is, for example, a prompt indicating that the role is a message indicating the role of the generating AI, and a user message is, for example, a prompt indicating that the role is a message of the user.

[0108] The system message is, for example, character string information that specifies the content of a task to be executed by a generation AI used in the information processing device 3. The character string information that specifies a task includes, for example, character string information indicating a definition of the task, constraints on the task in the generation AI, definitions of the behavior and tone of the generation AI, output format of the generation AI, and examples of operation of the generation AI, but is not limited to such examples and may include part of this information.

[0109] Furthermore, the system message may be, for example, a message indicating a scenario, and in this case, may further include, for example, character string information indicating the end condition of a task in the generation AI described above.

[0110] The user message is, for example, but not limited to, character string information indicating a question, inquiry, instruction, etc. to be processed based on the role of the generation AI indicated in the system message. For example, if a system message is not included in the prompt, the user message may include character string information that specifies the content of the task to be performed by the generation AI and character string information indicating the question, inquiry, instruction, etc. to be processed in the task to be performed by the generation AI.

[0111] The prompt may also include intention definition information for extracting an intention type and an intention content. The intention definition information includes, for example, instruction information including an instruction to extract the intention type and the intention content from the user setting information, and definition information including the intention type and information defining the intention type. For example, if the generation AI-API is an API from OpenAI (registered trademark), the information processing device 3 can cause the generation AI to generate the intention information by using a function calling function.

[0112] The intention type is, for example, the type of intention of the additional information, and the information indicating the intention type is, for example, information specifying a function or a function corresponding to the intention type. The intention content is, for example, the content of the intention of the additional information, and the information indicating the intention content is, for example, information indicating an argument of a function or a parameter of a function corresponding to the intention type.

[0113] In this case, the generation AI generates intention information including information indicating the intention type and information indicating the intention content. The information processing device 3 acquires information from an external information processing device or an internal storage unit using the intention information generated by the generation AI, inputs information including the acquired information and instruction information indicating an instruction to generate generated information using the acquired information to the generation AI, and causes the generation AI to generate the generated information.

[0114] Furthermore, if the generation AI used in the information processing device 3 is GPT from OpenAI, the prompt may further include an assistant message whose role is assistant. The assistant message is an output message by the generation AI or a message treated as an output message.

[0115] "Related information" is information about the prompt associated with the "prompt ID," and includes, for example, prompt identification information, prompt title, prompt header information, vector information of the prompt header information, prompt vector information, information indicating the prompt, information indicating the prompt provision fee, etc. The prompt provision fee is the fee paid by the billee for the use of the prompt.

[0116] The prompt header information is information indicating a description that explains the function of the prompt (e.g., an overview of the function), and the vectorization of the prompt header information or the vectorization of the prompt is performed, for example, by embedding using a sentence embedding model (e.g., a transformer-based model). The vector information of the prompt header information is represented, for example, by a vector of several hundred dimensions, but is not limited to such an example.

[0117] Embedding using a sentence embedding model is, for example, embedding using text-embedding-ada or BERT provided by OpenAI, but is not limited to these examples. Note that vectorization of prompt header information and vectorization of prompts are not limited to embedding using a sentence embedding model, and may be performed using, for example, Doc2Vec or the average of word embeddings. For word embedding, for example, Word2Vec or fastText is used.

[0118] The "number of times provided" is information indicating the number of times the prompt associated with the "prompt ID" has been provided to the information processing device 3 as a provision prompt. The "rating information" is information indicating each user U's rating of the provided information generated by the processing unit 12 using the prompt associated with the "prompt ID." The rating of the provided information is, for example, a 10-point rating, but may also be a rating of 9 points or less, or 11 points or more. The information indicating the rating may also be character string information such as a review or comment.

[0119] [3.3. Processing Unit 12] The processing unit 12 is a controller, and is realized by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to examples of information processing programs) stored in a storage device inside the information processing device 1 using RAM or the like as a working area.

[0120] 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).

[0121] 3, the processing unit 12 has a reception unit 30, an acquisition unit 31, a search unit 32, a provision unit 33, a determination unit 34, and a request unit 35, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be any other configuration that performs the information processing described below.

[0122] 3.3.1. Reception unit 30 The receiving unit 30 receives various information and requests via the network N and the communication unit 10. For example, the receiving unit 30 receives a prompt request transmitted from the information processing device 3 via a prompt providing API. The prompt providing API is an example of a predetermined API.

[0123] The receiving unit 30 receives the prompt request sent from the information processing device 3 via the prompt providing API, thereby receiving the user setting information included in the prompt request. The user setting information is information set by the user U, such as a user prompt that is a prompt input or selected by the user U, or request information that indicates a request by the user U. The user prompt is a prompt input or selected by the user U. The request information is information that indicates a request by the user U.

[0124] Furthermore, when the prompt request includes additional information, the receiving unit 30 receives the additional information by receiving the prompt request. Furthermore, when the prompt request includes attribute information of the user U, the receiving unit 30 receives the attribute information by receiving the prompt request.

[0125] Furthermore, the receiving unit 30 receives evaluation information indicating the evaluation of the user U on the provided information, the evaluation information being information indicating the evaluation of the user U. Note that the receiving unit 30 can also acquire the evaluation information from a device other than the information processing device 3 (for example, the terminal device 2).

[0126] [3.3.2. Acquisition part 31] The acquisition unit 31 acquires various types of information from external devices or the like via the network N and the communication unit 10, and acquires various types of information from the storage unit 11.

[0127] For example, when a prompt request is accepted by the accepting unit 30, the acquiring unit 31 acquires user setting information included in the prompt request accepted by the accepting unit 30. Furthermore, when additional information is included in the prompt request accepted by the accepting unit 30, the acquiring unit 31 acquires the additional information included in the prompt request.

[0128] The acquisition unit 31 also acquires information about the prompt stored in the prompt storage unit 20 of the storage unit 11. The information about the prompt includes, for example, identification information of the prompt, a title of the prompt, heading information of the prompt, vector information of the heading information of the prompt, vector information of the prompt, information indicating the prompt, and information indicating the provision fee of the prompt.

[0129] [3.3.3. Search Unit 32] The search unit 32 searches for a prompt to be input to a generation AI used in the information processing device 3, which is another information processing device, based on information included in the prompt request accepted by the acceptance unit 30. The prompt request includes, for example, user setting information, additional information, and attribute information, and the search unit 32 searches for a prompt based on this information.

[0130] The search unit 32 searches for a prompt to be input to the generation AI used in the information processing device 3 from a prompt table stored in the prompt storage unit 20 included in the storage unit 11. The prompt table is an example of the prompt database described above.

[0131] The search unit 32 vectorizes the user-defined information included in the prompt request using a method similar to that used to vectorize the prompt's header information (for example, embedding using a sentence embedding model).The search unit 32 then retrieves, as prompt candidates, from the prompt table in the prompt storage unit 20, prompts corresponding to the top m (m is 2 or more) header information whose vector similarity with the user-defined information is equal to or greater than a threshold value or whose vector similarity is highest.

[0132] Note that instead of vector information about the heading information of a prompt, the prompt table in the prompt storage unit 20 may contain information about each of the prompts or multiple keywords included in the heading information. In this case, the search unit 32 retrieves, as prompt candidates, from the prompt table in the prompt storage unit 20, prompts that include one or more terms included in the user setting information included in the search request or prompts that correspond to heading information.

[0133] The search unit 32 determines whether the type of the user setting information is a user prompt or request information. For example, when the prompt request includes type information indicating the type of the user setting information, the search unit 32 determines whether the type of the user setting information is a user prompt or request information based on the type information.

[0134] In addition, the search unit 32 has, for example, a type determination model, which is a language model different from the generation AI of the information processing device 3, and can use such type determination model to determine whether the type of user setting information is a user prompt or requested information.

[0135] The type determination model is, for example, a large-scale language model that is trained to determine whether the type of user setting information is a user prompt or requested information by inputting user setting information, but is not limited to such examples.

[0136] For example, the type determination model may be a general-purpose large-scale language model. In this case, the search unit 32 inputs information including instruction information and user setting information into the type determination model, causing the type determination model to determine whether the type of the user setting information is a user prompt or request information. The instruction information is, for example, information that instructs the type determination model to determine whether the type of the user setting information is a user prompt or request information.

[0137] The search unit 32 searches for a prompt that is estimated to provide more appropriate information than the user prompt received by the reception unit 30 from the generation AI and is to be provided as a provision prompt.

[0138] For example, when the type of user setting information is a user prompt, the search unit 32 determines, for example, using a prompt comparison and determination model, whether a prompt candidate can obtain more appropriate information than the user prompt. The search unit 32 determines, as the search result in response to the prompt request, the prompt candidate determined by the prompt comparison and determination model to be capable of obtaining more appropriate information than the user prompt.

[0139] The prompt comparison and judgment model is, for example, a large-scale language model that is trained to determine whether a prompt candidate is more appropriate than a user prompt by inputting the user prompt and a prompt candidate, but is not limited to such examples.

[0140] For example, the prompt comparison and determination model may be a model that is trained to determine whether a prompt candidate is more appropriate than a user prompt by inputting information that further includes attribute information of user U in addition to the user prompt and prompt candidate. This allows the search unit 32 to search for a prompt to be provided as a delivery prompt based on the user prompt received by the reception unit 30 and the attributes of user U.

[0141] The prompt comparison and determination model may also be a general-purpose large-scale language model. In this case, the search unit 32 inputs information including, for example, instruction information, a user prompt, and a prompt candidate into the prompt comparison and determination model, and causes the prompt comparison and determination model to determine whether the prompt candidate is more appropriate than the user prompt.

[0142] In this case, the instruction information may be, for example, information instructing a determination as to whether the prompt candidate is more appropriate than the user prompt. Such instruction information may include, for example, information indicating items for comparing the prompt candidate with the user prompt and the score for each item, and information instructing a determination as to whether the prompt candidate is more appropriate than the user prompt based on the total score. The items may include, but are not limited to, the clarity of the string, the degree of relevance between the strings, the degree of conciseness of the strings, the degree of specificity of the strings, and the presence or absence of examples.

[0143] In addition, the search unit 32 can input information including attribute information of user U in addition to the instruction information, user prompt, and prompt candidate into the prompt comparison and judgment model, and have the prompt comparison and judgment model determine whether the prompt candidate is more appropriate than the user prompt.

[0144] In this case, the instruction information is, for example, information that instructs a user U having the attributes indicated in the attribute information to determine whether the prompt candidate is more appropriate than the user prompt, and includes, for example, information indicating the items for comparing the prompt candidate with the user prompt and the score for each item, and information that instructs a determination of whether the prompt candidate is more appropriate than the user prompt based on the total score.

[0145] Furthermore, if the user prompt is a prompt that does not require additional information, the search unit 32 transmits the user prompt and each of the prompt candidates to the information processing device 3, for example, via the generation AI-API. A prompt that does not require additional information is a prompt that does not require additional information.

[0146] In this case, the information processing device 3 inputs information including a user prompt as input information to the generation AI, causes the generation AI to generate information corresponding to the user prompt, inputs information including a prompt candidate as input information to the generation AI, and causes the generation AI to generate information corresponding to the prompt candidate. The information processing device 3 provides the information corresponding to the user prompt and the information corresponding to the prompt candidate to the information processing device 1.

[0147] The search unit 32 inputs information including information corresponding to the user prompt and information corresponding to the prompt candidate provided by the information processing device 3 into the result comparison and determination model, thereby causing the result comparison and determination model to determine whether the prompt candidate is more appropriate than the user prompt. If the search unit 32 can obtain information more appropriate than the user prompt, the prompt candidate determined by the comparison and determination model is determined to be the search result corresponding to the prompt request.

[0148] In this case, the result comparison and judgment model is a model that is trained to determine whether the prompt candidate is more appropriate than the user prompt by inputting information including information corresponding to the user prompt and information corresponding to the prompt candidate, but is not limited to such an example.

[0149] The result comparison and determination model may be a general-purpose large-scale language model. In this case, the search unit 32 inputs information including, for example, the instruction information, information corresponding to the user prompt, and information corresponding to the prompt candidate into the result comparison and determination model, and causes the prompt comparison and determination model to determine whether the prompt candidate is more appropriate than the user prompt.

[0150] In this case, the instruction information may be, for example, information instructing a determination as to whether the information corresponding to the prompt candidate is more appropriate than the information corresponding to the user prompt. Such instruction information may include, for example, information indicating items for comparing the information corresponding to the prompt candidate with the information corresponding to the user prompt, scores for each item, and information instructing a determination as to whether the prompt candidate is more appropriate than the user prompt based on the total score. The items may include, but are not limited to, the clarity of the character string, the degree of relevance between the character strings, the degree of conciseness of the character strings, the degree of specificity of the character strings, and the presence or absence of examples.

[0151] In addition, the search unit 32 can input information including attribute information of user U in addition to the instruction information, information corresponding to the user prompt, and information corresponding to the prompt candidate into the result comparison and judgment model, thereby causing the result comparison and judgment model to determine whether the prompt candidate is more appropriate than the user prompt.

[0152] In this case, the instruction information is, for example, information that instructs a user U having the attribute indicated by the attribute information to determine whether the prompt candidate is more appropriate than the user prompt, and includes, for example, information indicating items for comparing information corresponding to the prompt candidate with information corresponding to the user prompt and the score for each item, and information that instructs a determination of whether the prompt candidate is more appropriate than the user prompt based on the total score. Note that the result comparison and determination model can also use information that further includes the user prompt and the prompt candidate as input information.

[0153] In this way, when the user setting information included in the prompt request accepted by the accepting unit 30 is a user prompt, the search unit 32 can search for a prompt that is estimated to provide more appropriate information than the user prompt from the generation AI.

[0154] Furthermore, based on the user prompt received by the receiving unit 30 and the attributes of the user U, the information processing device 1 can also search for a prompt that is estimated to provide more appropriate information than the user prompt from the generation AI.

[0155] Furthermore, when the user setting information received by the receiving unit 30 is information indicating a request of the user U, the search unit 32 determines the above-mentioned prompt candidate as a prompt corresponding to the information indicating the request. In this way, when the user setting information received by the receiving unit 30 is a request of the user U, the search unit 32 can search for a prompt that is in accordance with the request and is to be provided as a provision prompt.

[0156] [3.3.4.Providing Department 33] The providing unit 33 provides the prompt searched for by the searching unit 32 as a provision prompt to the information processing device 3 via a prompt provision API.

[0157] The information processing device 3 acquires a provision prompt sent from the information processing device 1 via the prompt provision API, inputs information including the provision prompt to the generation AI as input information, and causes the generation AI to generate information according to the provision prompt.

[0158] In addition, if the provision prompt is a prompt that requires additional information, the information processing device 3 inputs information including the additional information included in the usage request and the provision prompt as input information to the generation AI, and causes the generation AI to generate information corresponding to the provision prompt and the additional information.

[0159] [3.3.5. Decision Unit 34] The determination unit 34 determines a higher fee as the provision fee for a provision prompt that is estimated to have a higher possibility of obtaining appropriate information from the generation AI.

[0160] The determination unit 34 can estimate the degree of possibility that appropriate information will be obtained from the generation AI by the provision prompt, for example, based on the user U's evaluation of the provision information obtained by using the provision prompt.

[0161] For example, the determination unit 34 estimates the degree of possibility that appropriate information will be obtained from the generation AI through the provision prompt based on the evaluation information stored in the prompt memory unit 20 of the memory unit 11 and acquired by the acquisition unit 31.

[0162] The determination unit 34 estimates that the higher the average value of the evaluation of the provided information by each user U for a provision prompt, the higher the possibility that appropriate information will be obtained from the generation AI, and determines a higher fee as the provision fee.

[0163] Furthermore, the determination unit 34 can estimate the degree of possibility that appropriate information will be obtained from the generation AI by the provision prompt, based on the user U's evaluation of the provision information obtained using the provision prompt and the number of provision prompts provided to the information processing device 3. The number of provision prompts provided can also be said to be the number of uses of the provision prompt by the user U.

[0164] For example, the determination unit 34 estimates that the higher the score obtained by weighting and adding the average evaluation of the provided information by each user U and the number of provided prompts provided to user U, the higher the likelihood that appropriate information will be obtained from the generation AI.

[0165] In addition, the decision unit 34 can also, for example, set a higher provision fee when a prompt based on the attributes of user U is set as the provision prompt compared to when a prompt not based on the attributes of user U is set as the provision prompt.

[0166] A prompt based on the attributes of user U is a prompt searched for by the search unit 32 using the attribute information of user U, and a prompt not based on the attributes of user U is a prompt searched for by the search unit 32 without using the attribute information of user U.

[0167] [3.3.6. Claims Department 35] When the providing unit 33 provides the provision prompt to the information processing device 3, the billing unit 35 performs a billing process to bill the billee for the provision fee of the provision prompt.

[0168] The billing target is, for example, the operator of the information processing device 3 to which the provision prompt is provided by the providing unit 33, or a user U to whom the provision information generated using the provision prompt provided by the providing unit 33 is provided from the information processing device 3. The billing process is, for example, the process of billing the billing target for the provision fee for the provision prompt provided by the providing unit 33.

[0169] The billing unit 35 can, for example, perform billing processing by sending billing information including information indicating the provision fee for the provision prompt and information identifying the person to be billed to a device of a financial institution, or by sending billing information including information indicating the provision fee for the provision prompt and information identifying the credit card number of the person to be billed to a device of a credit card company.

[0170] Furthermore, if the person to be billed is user U, the billing unit 35 can also bill the provision fee for the provision prompt in points instead of or in addition to a specific currency. For example, the billing unit 35 can perform billing processing by transmitting billing information including information indicating the number of points corresponding to the provision fee for the provision prompt and information identifying the person to be billed to a device of a point management company.

[0171] Points are, for example, rewards given to user U by a points management company when user U, the person to be billed, makes a purchase using a credit card or cash, or when user U, the person to be billed, subscribes to a particular service, but are not limited to such examples.

[0172] [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. 5 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0173] 5, the processing unit 12 of the information processing device 1 determines whether a prompt request has been received via the prompt providing API (step S10). If the processing unit 12 determines that a prompt request has been received via the prompt providing API (step S10: Yes), the processing unit 12 searches for a prompt corresponding to the prompt request (step S11). Then, the processing unit 12 provides the searched prompt as a prompt to be provided (step S12).

[0174] When the processing of step S12 is completed or when it is determined that a prompt request has not been received via the prompt providing API (step S10: No), the processing unit 12 determines whether or not it is time to charge the provision fee (step S13). When it is determined that it is time to charge the provision fee (step S13: Yes), the processing unit 12 charges the provision fee (step S14).

[0175] When the processing of step S14 is completed or when it is determined that the timing for charging the provision fee has not come (step S13: No), the processing unit 12 determines whether the timing for determining the provision fee has come (step S15). When it is determined that the timing for determining the provision fee has come (step S15: Yes), the processing unit 12 determines the provision fee (step S16).

[0176] When the processing of step S16 is completed or when it is determined that the timing for determining the provision fee has not come (step S15: No), the processing unit 12 determines whether the timing for ending the operation has come (step S17). The processing unit 12 determines that the timing for ending the operation has come when, for example, the power of the information processing device 1 is turned off.

[0177] If the processing unit 12 determines that the operation end time has not yet arrived (step S17: No), it proceeds to step S10, and if it determines that the operation end time has arrived (step S17: Yes), it terminates the processing shown in Figure 5.

[0178] [5. Modifications] In the above-described example, when the information processing device 3 receives a provision prompt sent from the information processing device 1, it inputs information including the provision prompt to the generation AI as input information, and causes the generation AI to generate information corresponding to the provision prompt, but this example is not limited to this.

[0179] For example, when the information processing device 3 acquires a provision prompt transmitted from the information processing device 1, it can transmit header information of the provision prompt to the terminal device 2 of the user U and inquire of the user U whether or not to use the provision prompt. In this case, the providing unit 33 can transmit a plurality of provision prompts and header information of these plurality of provision prompts to the information processing device 3.

[0180] In addition, if the provision prompt is a prompt requiring additional information and the usage request does not include additional information, the information processing device 3 can input information including the provision prompt as input information to the generation AI when a usage request including additional information is sent from the user U's terminal device 2 after obtaining the provision prompt from the information processing device 1, and have the generation AI generate information corresponding to the provision prompt and the usage information.

[0181] In addition, when the user setting information received by the receiving unit 30 is information indicating the request of user U, the search unit 32 can also determine, from among multiple prompt candidates, the prompt candidate linked to the attribute information of user U as the prompt corresponding to the information indicating the request.

[0182] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by, for example, a computer 80 configured as shown in Fig. 6. Fig. 6 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, an HDD (Hard Disk Drive) 84, a communication interface (I / F) 85, an input / output interface (I / F) 86, and a media interface (I / F) 87.

[0183] The CPU 81 operates and controls each part based on programs stored in the ROM 83 or the HDD 84. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 starts up, programs that depend on the hardware of the computer 80, and the like.

[0184] The HDD 84 stores programs executed by the CPU 81, data used by such programs, etc. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 81, and transmits data generated by the CPU 81 to other devices via the network N.

[0185] The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard or a mouse, via the input / output interface 86. The CPU 81 acquires data from the input devices via the input / output interface 86. The CPU 81 also outputs generated data to the output devices via the input / output interface 86.

[0186] The media interface 87 reads a program or data stored in a recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads the program or data from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0187] For example, when the computer 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 executes programs loaded onto the RAM 82 to realize the functions of the processing unit 12. In addition, the HDD 84 stores data in the storage unit 11. The CPU 81 of the computer 80 reads and executes these programs from a recording medium 88, but as another example, the CPU 81 may obtain these programs from another device via the network N.

[0188] [7. Other] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0189] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0190] For example, the information processing device 1 described above may be realized by a terminal device and a server computer, or may be realized by multiple server computers. Furthermore, depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API or network computing.

[0191] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0192] [8. Effects] As described above, the information processing device 1 according to the embodiment includes a receiving unit 30, a searching unit 32, and a providing unit 33. The receiving unit 30 receives user setting information, which is information set by a user U, and receives the user setting information from the information processing device 3 via a predetermined API. The information processing device 3 is an example of another information processing device. The searching unit 32 searches for a prompt to be input to the generation AI used in the information processing device 3, based on the user setting information received by the receiving unit 30. The providing unit 33 provides the prompt searched by the searching unit 32 to the information processing device 3 via the API as a provided prompt. This allows the information processing device 1 to provide appropriate prompts more flexibly.

[0193] The user setting information is a user prompt that is input or selected by the user U, and the search unit 32 searches for a prompt that is estimated to provide more appropriate information from the generation AI than the user prompt received by the reception unit 30 and that is to be provided as a provision prompt. This allows the information processing device 1 to provide appropriate prompts more flexibly.

[0194] Furthermore, the search unit 32 searches for a prompt to be provided as a delivery prompt based on the user prompt received by the reception unit 30 and the attributes of the user U. This allows the information processing device 1 to provide an appropriate prompt more flexibly.

[0195] Furthermore, the information processing device 1 includes a billing unit 35 that bills the operator of the information processing device 3 for a provision fee for the provision prompt when the provision unit 33 provides the provision prompt. This enables the information processing device 1 to easily operate a service that provides appropriate prompts more flexibly.

[0196] The information processing device 1 also includes a determination unit 34 that determines a higher fee as a provision fee for a provision prompt that is estimated to be more likely to provide appropriate information from the generation AI. This allows the information processing device 1 to easily operate a service that provides appropriate prompts more flexibly.

[0197] Furthermore, when the decision unit 34 provides a prompt based on the attributes of the user U, it sets a higher provision fee compared to when the provision prompt is not based on the attributes of the user U. This enables the information processing device 1 to easily operate a service that provides appropriate prompts more flexibly.

[0198] The user setting information is information indicating a request by the user U, and the search unit 32 searches for a prompt to be provided as a provision prompt that corresponds to the information indicating the request received by the reception unit 30. This allows the information processing device 1 to provide an appropriate prompt more flexibly.

[0199] The above describes the embodiments of the present application in detail based on the drawings, but this is merely an example, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have been modified and improved in various ways based on the knowledge of those skilled in the art.

[0200] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0201] 1,3 Information processing equipment 2. Terminal Device 10. Communications Department 11 Storage section 12 Processing section 20 Prompt storage section 30 Reception 31 Acquisition Department 32 Search Section 33 Providing Department 34 Decision Section 35 Billing Department 100 Information Processing Systems N Network

Claims

1. a receiving unit that receives user setting information, which is information set by a user, from another information processing device that has received the user setting information via a predetermined API; a search unit that searches for a prompt to be input to a generation AI used in the other information processing device based on the user setting information received by the reception unit; a providing unit that provides the prompt searched by the searching unit as a provision prompt to the other information processing device via the API, The user setting information is Information indicating a request by the user, The search unit A prompt corresponding to the information indicating the request received by the receiving unit and linked to attribute information of the user is searched for as the prompt to be provided.

1. An information processing device comprising:

2. A reception unit that receives user setting information, which is information set by a user, from another information processing device that has received the user setting information via a predetermined API; a search unit that searches for a prompt to be input to a generation AI used in the other information processing device based on the user setting information received by the reception unit; a providing unit that provides the prompt searched by the searching unit as a provision prompt to the other information processing device via the API, The user setting information is a user prompt, which is a prompt entered or selected by the user; The search unit A prompt is searched for that is estimated to provide more appropriate information than the user prompt received by the reception unit from the generation AI and is to be provided as the provision prompt.

1. An information processing device comprising:

3. The search unit A prompt to be provided as the provision prompt is searched for based on the user prompt and the attribute of the user received by the reception unit.

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

4. a billing unit that bills an operator of the other information processing device for a provision fee for the provision prompt when the provision unit provides the provision prompt; 4. The information processing device according to claim 1, wherein the information processing device is a computer.

5. A reception unit that receives user setting information, which is information set by a user, from another information processing device that has received the user setting information via a predetermined API; a search unit that searches for a prompt to be input to a generation AI used in the other information processing device based on the user setting information received by the reception unit; a providing unit that provides the prompt searched by the searching unit as a provision prompt to the other information processing device via the API; a billing unit that bills an operator of the other information processing device for a provision fee for the provision prompt when the provision unit provides the provision prompt; a determination unit that determines a higher fee as the provision fee for a provision prompt that is estimated to have a higher possibility of obtaining appropriate information from the generation AI.

1. An information processing device comprising:

6. The determination unit When the prompt based on the attributes of the user is used as the provision prompt, the amount of the provision fee is made higher than when the prompt not based on the attributes of the user is used as the provision prompt.

6. The information processing apparatus according to claim 5,

7. 1. A computer-implemented information processing method, comprising: a receiving step of receiving user setting information, which is information set by a user, from another information processing device that has received the user setting information via a predetermined API; a search step of searching for a prompt to be input to a generation AI used in the other information processing device based on the user setting information received in the receiving step; a providing step of providing the prompt searched for by the searching step to the other information processing device via the API as a provided prompt, The user setting information is Information indicating a request by the user, The searching step includes: A prompt corresponding to the information indicating the request received in the receiving step and linked to the attribute information of the user is searched for as the prompt to be provided.

1. An information processing method comprising:

8. A computer-implemented information processing method, comprising: a receiving step of receiving user setting information, which is information set by a user, from another information processing device that has received the user setting information via a predetermined API; a search step of searching for a prompt to be input to a generation AI used in the other information processing device based on the user setting information received in the receiving step; a providing step of providing the prompt searched for by the searching step to the other information processing device via the API as a provided prompt, The user setting information is a user prompt, which is a prompt entered or selected by the user; The searching step includes: A prompt is searched for that is estimated to provide more appropriate information from the generation AI than the user prompt received by the receiving step and is to be provided as the provision prompt.

1. An information processing method comprising:

9. A computer-implemented information processing method, comprising: a receiving step of receiving user setting information, which is information set by a user, from another information processing device that has received the user setting information via a predetermined API; a search step of searching for a prompt to be input to a generation AI used in the other information processing device based on the user setting information received in the receiving step; a providing step of providing the prompt searched for in the searching step as a provision prompt to the other information processing device via the API; a billing step of billing an operator of the other information processing device for a provision fee for the provision prompt when the provision prompt is provided by the providing step; A determination step of determining a higher fee as the provision fee for a provision prompt that is estimated to be more likely to obtain appropriate information from the generation AI.

1. An information processing method comprising:

10. a receiving step of receiving user setting information, which is information set by a user, from another information processing device that has received the user setting information via a predetermined API; a search procedure for searching for a prompt to be input to a generation AI used in the other information processing device based on the user setting information received by the reception procedure; a provision step of providing the prompt searched for by the search step to the other information processing device via the API as a provision prompt; The user setting information is Information indicating a request by the user, The search procedure includes: A prompt corresponding to the information indicating the request received by the receiving procedure and linked to attribute information of the user is searched for as the prompt to be provided. An information processing program characterized by:

11. A reception procedure for receiving user setting information, which is information set by a user, from another information processing device that has received the user setting information via a predetermined API; a search procedure for searching for a prompt to be input to a generation AI used in the other information processing device based on the user setting information received by the reception procedure; a provision step of providing the prompt searched for by the search step to the other information processing device via the API as a provision prompt; The user setting information is a user prompt, which is a prompt entered or selected by the user; The search procedure includes: A prompt is searched for that is estimated to provide more appropriate information from the generation AI than the user prompt received by the reception procedure and is to be provided as the provision prompt. An information processing program characterized by:

12. A reception procedure for receiving user setting information, which is information set by a user, from another information processing device that has received the user setting information via a predetermined API; a search procedure for searching for a prompt to be input to a generation AI used in the other information processing device based on the user setting information received by the reception procedure; a providing step of providing the prompt searched for by the searching step to the other information processing device via the API as a provided prompt; a billing step of billing an operator of the other information processing device for a provision fee for the provision prompt when the provision prompt is provided by the provision step; a determination step of determining a higher fee as the provision fee for a provision prompt that is estimated to be more likely to obtain appropriate information from the generation AI; An information processing program characterized by:

Images