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 apparatus, an information processing method, and an information processing program.

Background Art

[0002] In recent years, technologies for generating information using generative AI (Artificial Intelligence) have been known. For example, Patent Document 1 discloses a technology using large language models (LLMs) that generates a prompt by adding a valid sentence as an additional sentence to an input question sentence within a determined character limit. A prompt is information input to generative AI, and for example, it is information indicating instructions, requests, etc. given to generative AI to execute a specific task.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the above prior art, since the large language model into which the user's question sentence is input generates additional sentences, depending on the learning state of the large 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 an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of providing appropriate prompts more flexibly.

Means for Solving the Problems

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

Effect of the Invention

[0007] According to one aspect of the embodiment, there is an effect that an appropriate prompt can be provided more flexibly.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Mode for Carrying Out the Invention

[0009] Hereinafter, embodiments for implementing an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing apparatus, the information processing method, and the information processing program according to the present application are not limited by this embodiment. Also, in the following embodiments, the same parts are denoted by the same reference numerals, and redundant explanations are omitted.

[0010] 〔1. An example of information processing〕 First, with reference to FIG. 1, an example of information processing according to the embodiment will be described. FIG. 1 is a diagram for explaining the information processing according to the embodiment.

[0011] The information processing apparatus 3 shown in FIG. 1 is an information processing apparatus that cooperates with each terminal device 2 of the user U and provides various types of information to the user U online, and is realized by, for example, one or more servers or a cloud system. The terminal device 2 is, for example, a smartphone, a tablet, or a personal computer.

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

[0013] The generative AI is, for example, a text generation AI, an image generation AI, or a multimodal generation AI. The text generation AI is, for example, a large language model learned to estimate and output the next token from an input token sequence, and is, for example, a transformer-based model or an RNN (Recurrent Neural Network)-based model, but may also be a hybrid model thereof. Also, the text generation AI may be a composite system combined with an identification mechanism for preventing unauthorized use.

[0014] Transformer-based models include, for example, but are not limited to, GPT (Generative Pre-trained Transformer) and PaLM2 (Pathways Language Model Version 2). RNN-based models include, for example, but are not limited to, RWKV (Receptance Weighted Key Value).

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

[0016] Multimodal generation AI is generation AI that generates at least one of text, images, and audio from at least one of text, images, and audio. Multimodal generation AI includes, for example, but is not limited to, GPT-4 Turbo with vision, gemini, CM3Leon (Chameleon Multimodal Model).

[0017] The information processing device 1 is an information processing device that provides a prompt providing service for providing a prompt input to the generation AI operating in 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 cloud systems. In the following, the API provided by the information processing device 1 may be described as a prompt providing API.

[0018] As shown in FIG. 1, the information processing apparatus 3 receives a usage request from the user U (step S1). The usage request includes user-related information including user setting information. For example, the information processing apparatus 3 receives user-related information from the user U by receiving a 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 apparatus 3. The user setting information included in the usage request is, for example, a user prompt that is a prompt input or selected by the user U, or desire information indicating the desire of the user U.

[0020] The user prompt is information indicating a character string that the user U intends to input into the generative AI. For example, it is question information indicating a question sentence, or instruction information indicating an instruction for causing the generative AI to generate, but is not limited to such examples.

[0021] For example, the question information indicating a question sentence is information such as the character string "Please tell me a recommended restaurant where I can have lunch in Roppongi on Saturday this week", or information such as the character string "What will the future of work be like due to the recent progress of AI technology?", and the instruction information is, for example, information such as the character string "Please propose a 3-day travel itinerary in Tokyo.", or information such as the character string "Please summarize the video at the following address", but is not limited to such examples.

[0022] Also, the desire information is, for example, information of a character string indicating the desire of the user U, but is not limited to such examples. For example, the desire information is information such as the character string "A prompt that can ~~~", or information such as the character string "A prompt that ~~~". "~~~" is a character string indicating an operation or process desired by the user U for the generative AI.

[0023] For example, the user setting information is information such as the information of the string "prompt that summarizes the latest information of XXX", the information of the string "prompt that can proofread text", or the information of the string "prompt that functions as a shopping assistant". "XXX" is a specific target (for example, a person). Note that the request information is not limited to the above examples. For example, the request information may be information of a string that more specifically indicates the content of an operation, process, etc. desired by the user U.

[0024] Also, assume that when the generation AI uses the prompt requested by the user U or the user prompt based on the request information, additional information needs to be input to the generation AI. In this case, the user U can input additional information, which is the 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 requested by the user U or the user prompt based on the request information.

[0025] The additional information required prompt, which is a prompt that requires additional information, is, for example, information of a string that defines the content of the task executed by the generation AI based on the input information. The information of the string that defines the task includes, for example, information of a string that indicates the definition of the task, the constraint conditions of the task, the definition of the behavior and tone of the generation AI, the 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 part or all of these information.

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

[0027] For example, when the prompt requested by the user U or the user prompt is an additional information required prompt, the user U can input additional information into the terminal device 2 by operating the terminal device 2. As a result, a usage request including user-related information and 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 obtains a provided prompt provided by the information processing device 1 based on the usage request.

[0028] The additional information required prompt is, for example, information in the character string "You are an experienced travel planner. Propose a 3-day travel plan for specific requests from the user. The plan includes destinations to visit, accommodation facilities, dining places, and activities." In this case, the additional information is, for example, information in the character string "Please create a travel plan for Okinawa. I'm interested in history and gourmet. The budget is 200,000 yen per person."

[0029] Also, the additional information required prompt is, for example, information in the character string "You are an excellent corrector. Detect up to 20 misspellings from the input text and propose correction suggestions. The output format is the incorrect text, the correct text, and an explanation of the error." In this case, the additional information is information on the character string to be corrected.

[0030] The user-related information of the usage request further includes user information. The user information is information of the user U who is 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 such examples.

[0031] Subsequently, when the information processing device 3 receives a usage request from the user U, it 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, when the additional information is not included in the usage request, the information processing apparatus 3 transmits a prompt request including user setting information to the information processing apparatus 1 via the prompt providing API based on the information included in the usage request.

[0033] Also, when the additional information is included in the usage request, the information processing apparatus 3 transmits a prompt request including user setting information and additional information to the information processing apparatus 1 via the prompt providing API based on the information included in the usage request.

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

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

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

[0037] Note that the information processing apparatus 3 can also transmit the prompt request to the information processing apparatus 1 via the prompt providing API regardless of whether the user U corresponding to the user information is a predetermined user U.

[0038] Subsequently, the information processing device 1 receives a prompt request including user setting information transmitted from the information processing device 3 via the prompt providing API (step S3). By receiving the prompt request, the information processing device 1 receives the user setting information.

[0039] Also, when additional information is included in the prompt request, the information processing device 1 receives the additional information by receiving the prompt request. Also, when attribute information is included in the prompt request, the information processing device 1 receives the attribute information by receiving the prompt request.

[0040] Subsequently, the information processing device 1 searches for a prompt to be input to the generative 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 including information on a plurality of prompts, and searches for a prompt to be input to the generative AI used in the information processing device 3 from such a prompt database.

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

[0043] For example, when the generative AI is GPT of OpenAI (registered trademark) company, the prompt includes information of a character string included in the input information associated with the information indicating the role and input to the generative AI. The role is a system, a user, or the like. The prompt is a prompt including at least one of a system message with the role being the system and a user message with the role being the user.

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

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

[0046] Also, the system message may be, for example, a message indicating a scenario, and in this case, it may further include, for example, information in the form of a string indicating the end condition of the task in the above-mentioned generative AI.

[0047] The user message is, for example, information in the form of a string indicating a question, inquiry, instruction, etc. to be processed based on the role of the generative AI indicated by the system message, but is not limited to such examples. For example, when the system message is not included in the prompt, the user message may include information in the form of a string that defines the content of the task to be executed by the generative AI and information in the form of a string indicating a question, inquiry, instruction, etc. that is the processing target of the task to be executed by the generative AI.

[0048] Also, when the generative AI is GPT of OpenAI, the prompt may further include an assistant message whose role is an assistant. The assistant message is an output message by the generative AI or a message treated as an output message.

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

[0050] The heading information of the prompt is information indicating a descriptive text (e.g., an outline of the function, etc.) that explains the function of the prompt. The vectorization of the heading information of the prompt is performed, for example, by embedding (Embedding) using a sentence embedding model (e.g., a transformer-based model). The vector information of the heading information of the prompt is represented by a vector of, for example, several hundred dimensions, but is not limited to such an example.

[0051] The embedding by the sentence embedding model is, for example, an embedding by text-embedding-ada provided by OpenAI, BERT (Bidirectional Encoder Representations from Transformers), etc., but is not limited to such an example.

[0052] Note that the vectorization of the heading information of the prompt is not limited to the embedding by the sentence embedding model. For example, the vectorization of the heading information of the prompt may be performed by Doc2Vec, the average of word embeddings (Word Embedding), etc. For word embeddings, for example, Word2Vec, fastText, etc. are used.

[0053] The information processing device 1 vectorizes the user setting information included in the prompt request in the same manner as the vectorization of the heading information of the prompt. Then, the information processing device 1 acquires, from the prompt database, the prompts corresponding to the top m (m is 2 or more) heading information in descending order of the vector similarity with the user setting information being equal to or higher than the threshold value or having a high similarity as prompt candidates.

[0054] Note that the prompt database may contain information on each of a plurality of keywords included in the prompt or its heading information instead of the vector information of the prompt heading information. In this case, the information processing apparatus 1 acquires, as prompt candidates, from the prompt database, for example, a prompt corresponding to a prompt or heading information including one or more terms included in the user setting information included in the search request.

[0055] Further, the prompt database may contain, instead of or in addition to the vector information of the prompt heading information, the vector information of the prompt. In this case, the information processing apparatus 1 acquires, as prompt candidates, from the prompt database, the top m prompts (m is 2 or more) in descending order of the vector similarity with the user setting information being equal to or higher than a threshold value or having a high similarity.

[0056] Further, the prompt database may contain information indicating the provision fee of the prompt, information indicating the number of selections of the prompt, information indicating the evaluation of the prompt, and the like. The provision fee of the prompt is a fee paid by the operator of the information processing apparatus 3 or the user U for the use of the prompt.

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

[0058] Further, the information processing apparatus 1, for example, has a type determination model that is a language model different from the generation AI of the information processing apparatus 3, and can also determine whether the type of the user setting information is a user prompt or a request information using such type determination model.

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

[0060] For example, the model for type determination may be a general large language model. In this case, the information processing apparatus 1 inputs information including instruction information and user setting information into the model for type determination, and causes the model for type determination to determine whether the type of user setting information is a user prompt or a request information. The instruction information is, for example, information instructing whether the type of user setting information is a user prompt or a request information.

[0061] When the type of user setting information is a user prompt, the information processing apparatus 1 can determine, for example, using the model for prompt comparison determination, whether it is possible to obtain information in which the prompt candidate is more appropriate than the user prompt. When it is determined by the model for prompt comparison determination that information in which the prompt candidate is more appropriate than the user prompt can be obtained, the information processing apparatus 1 determines the prompt candidate as a search result corresponding to the prompt request.

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

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

[0064] Also, the model for prompt comparison and determination may be a general large language model. In this case, the information processing apparatus 1 causes the model for prompt comparison and determination to determine whether a prompt candidate is more appropriate than the user prompt by inputting information including, for example, the instruction information, the user prompt, and the prompt candidate into the model for prompt comparison and determination.

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

[0066] Also, the information processing apparatus 1 can also cause the model for prompt comparison and determination to determine whether a prompt candidate is more appropriate than the user prompt by inputting information further including the attribute information of the user U into the model for prompt comparison and determination in addition to the instruction information, the user prompt, and the prompt candidate.

[0067] In this case, the instruction information is, for example, information instructing determination of whether a prompt candidate is more appropriate than the user prompt by the user U having the attribute indicated by the attribute information, and includes, for example, information indicating items for comparing the prompt candidate and the user prompt and scores for each item, and information instructing determination of whether the prompt candidate is more appropriate than the user prompt based on the total score of the scores.

[0068] Also, when the user prompt is a prompt that does not require additional information, the information processing apparatus 1 transmits each of the user prompt and the prompt candidate to the information processing apparatus 3 via, for example, 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 the information including the user prompt as input information to the generative AI, causes the generative AI to generate information corresponding to the user prompt, inputs the information including the prompt candidate as input information to the generative AI, and causes the generative 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 the information including the information corresponding to the user prompt and the information corresponding to the prompt candidate provided from the information processing device 3 to the result comparison and determination model, so that the result comparison and determination model can determine whether the prompt candidate is more appropriate than the user prompt. The information processing device 1 determines the prompt candidate determined by the result comparison and determination model to be more appropriate than the user prompt as the search result corresponding to the prompt request.

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

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

[0073] In this case, the instruction information is, for example, information that instructs a determination as to whether information corresponding to a prompt candidate is more appropriate than information corresponding to a user prompt. Such instruction information includes, for example, information indicating items for comparing information corresponding to a prompt candidate and information corresponding to a user prompt and 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 value of the scores. The items are, for example, clarity of a character string, degree of relevance between character strings, degree of conciseness of a character string, degree of concreteness of a character string, presence or absence of an exemplification, etc., but are not limited to such examples.

[0074] Further, for example, in addition to the instruction information, the information corresponding to the user prompt, and the information corresponding to the prompt candidate, the information processing apparatus 1 can also input information including the attribute information of the user U to the result comparison determination model, and cause the result comparison determination model to 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 determination as to whether a prompt candidate is more appropriate than a user prompt by a user U having an attribute indicated by the attribute information, and includes, for example, information indicating items for comparing information corresponding to the prompt candidate and information corresponding to the user prompt and 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 value of the scores.

[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 apparatus 1 can search for a prompt estimated to be obtained from the generation AI as information more appropriate than such user prompt.

[0077] Further, the information processing apparatus 1 can also search for a prompt estimated to be obtained from the generation AI as information more appropriate than the user prompt based on the user prompt received in step S3 and the attribute of the user U.

[0078] Also, when the user setting information received in step S3 is information indicating the request of user U, the information processing apparatus 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 by the information processing apparatus 1 in step S3 is the request of user U, the information processing apparatus 1 can search for a prompt corresponding to such a request and provided as a provision prompt.

[0080] Subsequently, the information processing apparatus 1 provides the prompt retrieved in step S4 to the information processing apparatus 3 as a provision prompt via the prompt provision API (step S5). The information processing apparatus 3 acquires the provision prompt transmitted from the information processing apparatus 1 via the prompt provision API, inputs the 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.

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

[0082] Subsequently, the information processing apparatus 3 transmits the information generated by the generation AI to the terminal device 2 as provision information, and provides the generation information generated by the generation AI or information based on the generation information to the user U as provision information (step S6).

[0083] Subsequently, the information processing apparatus 1 determines the usage fee of the provision prompt (step S7). For example, the information processing apparatus 1 determines a higher fee as the provision fee for a provision prompt for which it is estimated that there is a high possibility of obtaining appropriate information from the generation AI.

[0084] The information processing apparatus 1 can estimate the degree of possibility of obtaining appropriate information from the generative AI generated by the provision prompt based on, for example, the evaluation of the user U for the provision information obtained using the provision prompt. Information indicating the evaluation of the provision information by each user U is provided from the information processing apparatus 3 to the information processing apparatus 1.

[0085] The information processing apparatus 1 estimates that the higher the average value of the evaluation of the provision information by each user U for the provision prompt, the higher the degree of possibility of obtaining appropriate information from the generative AI, and determines a high amount of fee as the provision fee.

[0086] Also, the information processing apparatus 1 can estimate the degree of possibility of obtaining appropriate information from the generative AI generated by the provision prompt based on the evaluation of the user U for the provision information obtained using the provision prompt and the number of provision prompts provided to the information processing apparatus 3. The number of provision prompts provided can also be said to be the number of times the provision prompt is used by the user U.

[0087] For example, the information processing apparatus 1 estimates that the higher the score obtained by weighted addition of the average value of the evaluation of the provision information by each user U and the number of provision prompts provided to the user U, the higher the degree of possibility of the provision prompt of obtaining appropriate information from the generative AI.

[0088] Also, the information processing apparatus 1 can, for example, increase the amount of the provision fee when the prompt based on the attribute of the user U is used as the provision prompt compared to the case where the prompt not based on the attribute of the user U is used as the provision prompt.

[0089] Subsequently, the information processing apparatus 1 performs a billing process on the billing target (step S8). The billing target is, for example, the operator of the information processing apparatus 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 was provided. The billing process is, for example, a process of billing the billing target for the provision fee of the provision prompt provided in step S5.

[0090] The information processing apparatus 1 can perform a billing process, for example, by transmitting billing information including information indicating a fee for a provided prompt and information identifying a person to be billed to an apparatus of a financial institution, or by transmitting billing information including information indicating a fee for a provided prompt and information identifying a credit card number of a person to be billed to an apparatus of a credit card company.

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

[0092] Note that the points are, for example, rewards given to the user U by a point management company or the like when the user U, who is the person to be billed, shops with a credit card or cash, or joins a specific service, but are not limited to such examples.

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

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

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

[0096] The plurality of terminal devices 2 are used by different users U. The terminal device 2 is, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, a tablet PC, or a wearable device. The wearable device is, for example, smart glasses or a smartwatch, but is not limited to such examples.

[0097] Each of the information processing device 1, the terminal device 2, and the information processing device 3 is connected to be communicable with each other by wire or wirelessly via the network N. 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: the 5th generation mobile communication system).

[0099] The terminal device 2 can be connected to the network N via a mobile communication network, short-range wireless communication such as Bluetooth (registered trademark), or wireless LAN (Local Area Network), and communicate with the information processing device 3 and the like. Further, the information processing device 3 can be connected to the network N via a mobile communication network, short-range wireless communication such as Bluetooth, or wireless LAN, and communicate with the information processing device 1 and the like.

[0100] 〔3. Configuration of Information Processing Device 1〕 FIG. 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, a NIC (Network Interface Card), etc. And the communication unit 10 is connected to the network N either wired or wirelessly, and performs information transmission and reception with various other devices. For example, the communication unit 10 performs information transmission and reception with the information processing device 3 via the network N.

[0102] [3.2. Memory Unit 11] The memory unit 11 is realized by, for example, semiconductor memory elements such as RAM (Random Access Memory), flash memory, or storage devices such as hard disks and optical disks. The memory unit 11 has a prompt storage unit 20.

[0103] [3.2.1. Prompt Storage Unit 20] The prompt storage unit 20 stores various 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] In the example shown in FIG. 4, the prompt table stored in the prompt storage unit 20 is an example of the above-described prompt database, and includes information on items such as "prompt ID", "prompt", "related information", "provision count", and "evaluation information". The "prompt ID" is an identifier for identifying a prompt and is information assigned to each prompt.

[0105] The "prompt" is a prompt associated with the "prompt ID". The prompt is, for example, a prompt provided by a prompt provider different from the operator of the information processing device 3, or a prompt provided by, for example, 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, when the generative AI used in the information processing device 3 is GPT of OpenAI, the prompt includes information of a character string included in the input information input to the generative AI in association with information indicating a role. The role is, for example, a system or a user. The prompt is a prompt including at least one of a system message where the role is the system and a user message where the role is the user.

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

[0108] The system message is, for example, information of a character string that defines the content of the task executed by the generative AI used in the information processing device 3. The information of the character string that defines the task includes, for example, information of a character string indicating the definition of the task, the constraint conditions of the task in the generative AI, the definition of the behavior and tone of the generative AI, the output format of the generative AI, the operation example of the generative AI, etc., but is not limited to such examples, and may include a part of such information.

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

[0110] The user message is, for example, information of a character string indicating a question, an inquiry, an instruction, etc. to be processed based on the role of the generative AI indicated by the system message, but is not limited to such examples. For example, when the system message is not included in the prompt, the user message may include information of a character string that defines the content of the task executed by the generative AI and information of a character string indicating a question, an inquiry, an instruction, etc. that are the processing targets of the task executed by the generative AI.

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

[0112] The intention type is, for example, the type of intention for additional information, and the information indicating the intention type is, for example, information specifying a function or function according to the intention type. Also, the intention content is the content of the intention for 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 according to the intention type.

[0113] In this case, intention information including information indicating the intention type and information indicating the intention content is generated by the generative AI. The information processing device 3 uses the intention information generated by the generative AI to acquire information from an external information processing device or an internal storage unit, etc., and inputs information including the acquired information and instruction information indicating an instruction to generate generated information using the information to the generative AI, and can cause the generative AI to generate generated information.

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

[0115] "Related information" is information regarding the prompt associated with the "Prompt ID", and includes, for example, the identification information of the prompt, the title of the prompt, the heading information of the prompt, the vector information of the heading information of the prompt, the vector information of the prompt, the information indicating the prompt, the information indicating the provision fee of the prompt, and the like. The provision fee of the prompt is the fee that the person to be billed pays for the use of the prompt.

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

[0117] The embedding by the sentence embedding model is, for example, an embedding by text-embedding-ada provided by OpenAI, BERT, etc., but is not limited to such an example. Note that the vectorization of the heading information of the prompt and the vectorization of the prompt are not limited to the embedding by the sentence embedding model, and for example, the vectorization of the heading information of the prompt and the vectorization of the prompt may be performed by Doc2Vec, the average of word embeddings, etc. For word embeddings, for example, Word2Vec, fastText, etc. are used.

[0118] "Number of provisions" is information indicating the number of times the prompt associated with the "Prompt ID" has been provided as a provided prompt to the information processing device 3. "Evaluation information" is information indicating the evaluation of each user U for the provided information generated by the processing unit 12 using the prompt associated with the "Prompt ID". The evaluation of the provided information is, for example, a 10-point evaluation, but may be an evaluation of 9 points or less, or an evaluation of 11 points or more. Also, the information indicating the evaluation may be information in the form of a string such as a review or a comment.

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

[0120] Also, the processing unit 12 is a controller and may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a GPGPU (General Purpose Graphic Processing Unit).

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

[0122] 〔3.3.1. Reception Unit 30〕 The reception unit 30 receives various information and requests via the network N and the communication unit 10. For example, the reception unit 30 receives a prompt request transmitted from the information processing apparatus 3 via a prompt provision API. The prompt provision API is an example of a predetermined API.

[0123] The reception unit 30 receives the user setting information included in the prompt request by receiving the prompt request transmitted from the information processing apparatus 3 via the prompt providing API. The user setting information is information set by the user U, and is, for example, a user prompt which is a prompt input or selected by the user U, or request information indicating a request by the user U. The user prompt is a prompt input or selected by the user U. The request information is information indicating a request by the user U.

[0124] Also, when additional information is included in the prompt request, the reception unit 30 receives the additional information by receiving the prompt request. Further, when the attribute information of the user U is included in the prompt request, the reception unit 30 receives the attribute information by receiving the prompt request.

[0125] Also, the reception unit 30 receives evaluation information indicating the evaluation of the user U with respect to the provided information by receiving the evaluation information transmitted from the information processing apparatus 3. Note that the reception unit 30 can also acquire the evaluation information from a device other than the information processing apparatus 3 (for example, the terminal device 2).

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

[0127] For example, when a prompt request is received by the reception unit 30, the acquisition unit 31 acquires the user setting information included in the prompt request received by the reception unit 30. Also, when additional information is included in the prompt request received by the reception unit 30, the acquisition unit 31 acquires the additional information included in the prompt request.

[0128] In addition, the acquisition unit 31 acquires information regarding the prompts stored in the prompt storage unit 20 of the storage unit 11. The information regarding the prompts includes, for example, prompt identification information, prompt titles, prompt heading information, vector information of the prompt heading information, prompt vector information, information indicating the prompt, information indicating the provision fee of the prompt, and the like.

[0129] [3.3.3. Search Unit 32] The search unit 32 searches for a prompt to be input to the generation AI used in the information processing device 3, which is another information processing device, based on the information included in the prompt request received by the reception 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 the prompt table stored in the prompt storage unit 20 included in the storage unit 11. The prompt table is an example of the above-described prompt database.

[0131] The search unit 32 vectorizes the user setting information included in the prompt request by the same method as the vectorization of the prompt heading information (for example, embedding by a sentence embedding model). Then, the search unit 32 acquires, as prompt candidates, the prompts corresponding to the top m (m is 2 or more) heading information in descending order of the vector similarity with the user setting information being equal to or higher than the threshold value or having a high similarity from the prompt table of the prompt storage unit 20.

[0132] Note that the prompt table in the prompt storage unit 20 may include information on each of a plurality of keywords included in the prompt or its heading information instead of the vector information of the heading information of the prompt. In this case, the search unit 32 acquires, as a prompt candidate, from the prompt table in the prompt storage unit 20, a prompt corresponding to a prompt or heading information including one or more terms included in the user setting information included in the search request, for example.

[0133] The search unit 32 determines whether the type of the user setting information is 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 user prompt or request information based on such type information.

[0134] Also, the search unit 32 has, for example, a type determination model that is a language model different from the generation AI of the information processing apparatus 3, and can also determine whether the type of the user setting information is user prompt or request information using such type determination model.

[0135] The type determination model is, for example, a large language model, and is a model learned to determine whether the type of the user setting information is user prompt or request information by inputting the user setting information, but is not limited to such an example.

[0136] For example, the type determination model may be a general large language model. In this case, the search unit 32 causes the type determination model to determine whether the type of the user setting information is user prompt or request information by inputting information including the instruction information and the user setting information into the type determination model, for example. The instruction information is information for instructing determination as to whether the type of the user setting information is user prompt or request information, for example.

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

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

[0139] The prompt comparison determination model is, for example, a large language model, and is a model learned to determine whether a prompt candidate is more appropriate than a user prompt by inputting the user prompt and the prompt candidate, but is not limited to such an example.

[0140] For example, the prompt comparison determination model may be a model learned to determine whether a prompt candidate is more appropriate than a user prompt by inputting, in addition to the user prompt and the prompt candidate, information further including the attribute information of user U. Thereby, the search unit 32 can search for a prompt provided as a provision prompt based on the user prompt received by the reception unit 30 and the attribute of user U.

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

[0142] In this case, the instruction information is, for example, information that instructs a determination as to whether a prompt candidate is more appropriate than the user prompt. Such instruction information includes, for example, information indicating items for comparing the prompt candidate and the user prompt and scores for each item, and information that instructs a determination as to whether the prompt candidate is more appropriate than the user prompt based on the total value of the scores. The items are, for example, the clarity of the character string, the degree of relevance between character strings, the degree of conciseness of the character string, the degree of specificity of the character string, the presence or absence of exemplification, etc., but are not limited to such examples.

[0143] In addition, for example, in addition to the instruction information, the user prompt, and the prompt candidate, the search unit 32 can also input information further including the attribute information of the user U to the prompt comparison determination model, and cause the prompt comparison determination model to 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 determination as to whether a prompt candidate is more appropriate than the user prompt by the user U having the attribute indicated by the attribute information, and includes, for example, information indicating items for comparing the prompt candidate and the user prompt and scores for each item, and information that instructs a determination as to whether the prompt candidate is more appropriate than the user prompt based on the total value of the scores.

[0145] In addition, when the user prompt is a no-extra-information-required prompt, for example, the search unit 32 transmits each of the user prompt and the prompt candidate to the information processing device 3 via the generation AI-API. A no-extra-information-required prompt is a prompt that does not require extra information.

[0146] In this case, the information processing device 3 inputs the information including the user prompt into the generative AI as input information, causes the generative AI to generate information corresponding to the user prompt, inputs the information including the prompt candidate into the generative AI as input information, and causes the generative 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 the information including the information corresponding to the user prompt and the information corresponding to the prompt candidate provided from the information processing device 3 into the result comparison and determination model, so that the result comparison and determination model can determine whether the prompt candidate is more appropriate than the user prompt. The search unit 32 determines the prompt candidate determined by the result comparison and determination model to be able to obtain more appropriate information than the user prompt as the search result corresponding to the prompt request.

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

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

[0150] In this case, the instruction information is, for example, information that instructs a determination as to whether information corresponding to a prompt candidate is more appropriate than information corresponding to a user prompt. Such instruction information includes, for example, information indicating items for comparing information corresponding to a prompt candidate and information corresponding to a user prompt and 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 value. The items are, for example, clarity of a character string, degree of relevance between character strings, degree of conciseness of a character string, degree of specificity of a character string, presence or absence of an exemplification, etc., but are not limited to such examples.

[0151] Further, for example, in addition to the instruction information, information corresponding to a user prompt, and information corresponding to a prompt candidate, the search unit 32 can also input information further including attribute information of the user U into the result comparison determination model, thereby causing the result comparison determination 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 determination as to whether a prompt candidate is more appropriate than a user prompt by a user U having an attribute indicated by the attribute information, and includes, for example, information indicating items for comparing information corresponding to the prompt candidate and information corresponding to the user prompt and 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 value. Note that the result comparison determination model can also use information further including the user prompt and the prompt candidate as input information.

[0153] In this way, when the user setting information included in the prompt request received by the reception unit 30 is a user prompt, the search unit 32 can search for a prompt estimated to be obtained from the generation AI as information more appropriate than such user prompt.

[0154] In addition, the information processing apparatus 1 can also search for a prompt that is estimated to be obtained from the generation AI, which is more appropriate than the user prompt, based on the user prompt received by the reception unit 30 and the attributes of the user U.

[0155] Also, when the user setting information received by the reception unit 30 is information indicating the request of the user U, the search unit 32 determines the above-described prompt candidate as a prompt corresponding to the information indicating the request. In this way, when the user setting information received by the reception unit 30 is the request of the user U, the search unit 32 can search for a prompt corresponding to such a request and provided as a provided prompt.

[0156] 〔3.3.4. Providing Unit 33〕 The providing unit 33 provides the prompt searched by the search unit 32 to the information processing apparatus 3 as a provided prompt via the prompt providing API.

[0157] The information processing apparatus 3 acquires the provided prompt transmitted from the information processing apparatus 1 via the prompt providing API, inputs the information including the provided prompt to the generation AI as input information, and causes the generation AI to generate information corresponding to the provided prompt.

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

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

[0160] For example, based on the evaluation of user U for the provided information obtained using the provided prompt, the determination unit 34 can estimate the degree of possibility of obtaining appropriate information from the generation AI by the provided prompt.

[0161] For example, the determination unit 34 estimates the degree of possibility of obtaining appropriate information from the generation AI by the provided prompt based on the evaluation information stored in the prompt storage unit 20 of the storage 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 the provided prompt, the higher the degree of possibility of obtaining appropriate information from the generation AI, and determines a high amount of fee as the provided fee.

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

[0164] For example, the determination unit 34 estimates that the higher the score obtained by weighted addition of the average value of the evaluation of the provided information by each user U and the number of provided prompts for user U, the higher the degree of possibility of the provided prompt of obtaining appropriate information from the generation AI.

[0165] In addition, for example, when the prompt based on the attribute of user U is used as the provided prompt, the determination unit 34 can also increase the amount of the provided fee compared to the case where the prompt not based on the attribute of user U is used as the provided prompt.

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

[0167] [3.3.6. Claim section 35] When the provided prompt is provided to the information processing apparatus 3 by the providing unit 33, the claim section 35 performs a claim process of claiming the provision fee of the provided prompt from the person to be claimed.

[0168] The person to be claimed is, for example, the operator of the information processing apparatus 3 to which the provided prompt is provided by the providing unit 33 or the user U from whom the provided information generated using the provided prompt provided by the providing unit 33 is provided by the information processing apparatus 3. The claim process is, for example, the process of claiming the provision fee of the provided prompt from the person to be claimed.

[0169] The claim section 35 can perform the claim process, for example, by transmitting claim information including information indicating the provision fee of the provided prompt and information identifying the person to be claimed to the apparatus of a financial institution, or by transmitting claim information including information indicating the provision fee of the provided prompt and information identifying the credit card number of the person to be claimed to the apparatus of a credit card company.

[0170] Also, when the person to be claimed is user U, the claim section 35 can also claim the provision fee of the provided prompt in points instead of or in addition to a specific currency. For example, the claim section 35 can perform the claim process by transmitting claim information including information indicating the number of points corresponding to the provision fee of the provided prompt and information identifying the person to be claimed to the apparatus of a point management company.

[0171] Note that the points are, for example, rewards given to the user U, who is the person to be billed, by a point management company or the like when the user U, who is the person to be billed, shops using a credit card or cash, or joins a specific service, but are not limited to such examples.

[0172] [4. Processing Procedure] Next, the information processing procedure by the processing unit 12 of the information processing apparatus 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 apparatus 1 according to the embodiment.

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

[0174] When the processing in step S12 is completed, or when the processing unit 12 determines that a prompt request has not been received via the prompt providing API (step S10: No), it determines whether it is the timing to bill for the provision (step S13). When the processing unit 12 determines that it is the timing to bill for the provision (step S13: Yes), it bills for the provision (step S14).

[0175] When the processing in step S14 is completed, or when the processing unit 12 determines that it is not the timing to bill for the provision (step S13: No), it determines whether it is the timing to determine the provision fee (step S15). When the processing unit 12 determines that it is the timing to determine the provision fee (step S15: Yes), it determines the provision fee (step S16).

[0176] When the process in step S16 ends, or when it is determined that it is not the timing for determining the offering fee (step S15: No), the processing unit 12 determines whether it is the timing to end the operation (step S17). The processing unit 12 determines that it is the timing to end the operation, for example, when the power of the information processing apparatus 1 is turned off.

[0177] When the processing unit 12 determines that it is not the timing to end the operation (step S17: No), the process proceeds to step S10. When the processing unit 12 determines that it is the timing to end the operation (step S17: Yes), the process shown in FIG. 5 ends.

[0178] [5. Modification Example] In the example described above, when the information processing apparatus 3 acquires the offering prompt transmitted from the information processing apparatus 1, the information including the offering prompt is input to the generation AI as input information, and the generation AI is caused to generate information corresponding to the offering prompt. However, the example is not limited thereto.

[0179] For example, when the information processing apparatus 3 acquires the offering prompt transmitted from the information processing apparatus 1, the information processing apparatus 3 can transmit the heading information of the offering prompt or the like to the terminal device 2 of the user U and inquire whether the user U uses the offering prompt. In this case, the providing unit 33 can transmit a plurality of offering prompts and the heading information of these plurality of offering prompts to the information processing apparatus 3.

[0180] Further, when the offering prompt is an additional information required prompt and the usage request does not include additional information, after the information processing apparatus 3 acquires the offering prompt from the information processing apparatus 1, when a usage request including additional information is transmitted from the terminal device 2 of the user U, the information processing apparatus 3 can input the information including the offering prompt to the generation AI as input information and cause the generation AI to generate information corresponding to the offering prompt and the usage information.

[0181] Further, when the user setting information received by the reception unit 30 is information indicating the request of the user U, the search unit 32 can also determine, as a prompt corresponding to the information indicating the request, a prompt candidate associated with the attribute information of the user U among a plurality of prompt candidates.

[0182] 6. Hardware Configuration The information processing apparatus 1 according to the above-described embodiment is realized by a computer 80 having a configuration as shown in FIG. 6, for example. FIG. 6 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing apparatus 1 according to the embodiment. The computer 80 includes 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 based on a program stored in the ROM 83 or the HDD 84 and controls each unit. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 is started up, and programs dependent on the hardware of the computer 80.

[0184] The HDD 84 stores programs executed by the CPU 81 and data used by such programs. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 81, and sends 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 device via the input / output interface 86. Further, the CPU 81 outputs data generated via the input / output interface 86 to the output device.

[0186] The media interface 87 reads a program or data stored in the recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads such a program 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), a PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0187] For example, when the computer 80 functions as the information processing apparatus 1 according to the embodiment, the CPU 81 of the computer 80 realizes the functions of the processing unit 12 by executing the program loaded onto the RAM 82. Further, the HDD 84 stores the data in the storage unit 11. The CPU 81 of the computer 80 reads and executes these programs from the recording medium 88. As another example, these programs may be acquired from another device via the network N.

[0188] 〔7. Others〕 In addition, among the respective processes described in the above embodiment, all or part of the processes described as being automatically performed can also be performed manually, or all or part of the processes described as being manually performed can be automatically performed by a known method. In addition, regarding the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings, they can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

[0189] In addition, each component of each of the illustrated devices is a functional concept and does not necessarily have to be physically configured as shown in the drawings. That is, the specific form of distribution and integration of each device is not limited to that shown in the drawings, and all or part of it can be functionally or physically distributed and integrated in any unit according to various loads, usage situations, 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 a plurality of server computers. Also, depending on the function, the configuration can be flexibly changed, such as by calling an external platform or the like through an API or network computing.

[0191] In addition, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not conflict.

[0192] 〔8. Effects〕 As described above, the information processing device 1 according to the embodiment includes a reception unit 30, a search unit 32, and a provision unit 33. The reception unit 30 receives user setting information, which is information set by the user U, from the information processing device 3 via a predetermined API. The information processing device 3 is an example of another information processing device. The search unit 32 searches for a prompt to be input to the generative AI used in the information processing device 3 based on the user setting information received by the reception unit 30. The provision unit 33 provides the prompt searched by the search unit 32 to the information processing device 3 as a provision prompt via the API. Thereby, the information processing device 1 can provide an appropriate prompt more flexibly.

[0193] Also, the user setting information is a user prompt, which is a prompt input or selected by the user U, and the search unit 32 searches for a prompt that is estimated to be obtained from the generative AI as more appropriate information than the user prompt received by the reception unit 30 and is provided as a provision prompt. Thereby, the information processing device 1 can provide an appropriate prompt more flexibly.

[0194] In addition, the search unit 32 searches for a prompt to be provided as a provision prompt based on the user prompt received by the reception unit 30 and the attributes of the user U. As a result, the information processing apparatus 1 can provide an appropriate prompt more flexibly.

[0195] Further, when a provision prompt is provided by the provision unit 33, the information processing apparatus 1 includes a billing unit 35 that bills the operator of the information processing apparatus 3 for the provision fee of the provision prompt. As a result, the information processing apparatus 1 can facilitate the operation of a service that provides an appropriate prompt more flexibly.

[0196] Furthermore, the information processing apparatus 1 includes a determination unit 34 that determines a higher amount of fee as the provision fee for a provision prompt for which it is estimated that there is a high possibility of obtaining appropriate information from the generation AI. As a result, the information processing apparatus 1 can facilitate the operation of a service that provides an appropriate prompt more flexibly.

[0197] In addition, when the prompt based on the attributes of the user U is used as the provision prompt, the determination unit 34 increases the amount of the provision fee compared to the case where the prompt not based on the attributes of the user U is used as the provision prompt. As a result, the information processing apparatus 1 can facilitate the operation of a service that provides an appropriate prompt more flexibly.

[0198] Also, the user setting information is information indicating the requests of the user U, and the search unit 32 searches for a prompt that corresponds to the information indicating the requests received by the reception unit 30 and that is provided as the provision prompt. As a result, the information processing apparatus 1 can provide an appropriate prompt more flexibly.

[0199] As described above, the embodiments of the present application have been described in detail with reference to the drawings. However, this is an example, and the present invention can be implemented in other forms with various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the column of the disclosure of the invention.

[0200] Also, the "section (section, module, unit)" described above can be read as "means", "circuit", etc. For example, the acquisition section can be read as an acquisition means or an acquisition circuit.

Explanation of Reference Signs

[0201] 1,3 Information processing apparatus 2 Terminal device 10 Communication section 11 Storage section 12 Processing section 20 Prompt storage section 30 Reception section 31 Acquisition section 32 Search section 33 Provision section 34 Decision section 35 Claim section 100 Information processing system N Network

Claims

1. A receiving unit that receives the user setting information from another information processing device that has received the user setting information, which is information set by the user, via a predetermined API; A search unit that searches for a prompt to be input to the generation AI used in the other information processing device based on the user setting information received by the receiving unit; A providing unit that provides the prompt searched by the search unit as a provided prompt to the other information processing device via the API, and an information processing apparatus comprising: An information processing apparatus characterized by the above.

2. The user setting information is A user prompt that is a prompt input or selected by the user, and the search unit Searches for a prompt that is estimated to obtain more appropriate information from the generation AI than the user prompt received by the receiving unit and is provided as the provided prompt. The information processing apparatus according to claim 1, characterized by the above.

3. The search unit Searches for a prompt to be provided as the provided prompt based on the user prompt received by the receiving unit and the attributes of the user. The information processing apparatus according to claim 2, characterized by the above.

4. When the provided prompt is provided by the providing unit, a billing unit that bills the operator of the other information processing device for the provision fee of the provided prompt is provided. The information processing apparatus according to any one of claims 1 to 3, characterized by the above.

5. A determination unit that determines a higher amount of the provision fee as the provision fee for a provided prompt that is estimated to have a high possibility of obtaining appropriate information from the generation AI. The information processing apparatus according to claim 4, characterized by the above.

6. The determination unit When a prompt based on the attributes of the user is used as the provided prompt, the amount of the provision fee is made higher than when a prompt not based on the attributes of the user is used as the provided prompt. The information processing apparatus according to claim 5, characterized by the above.

7. The user setting information is Information indicating the user's request, and the search unit Searches for a prompt corresponding to the information indicating the request received by the receiving unit and provided as the provided prompt. The information processing apparatus according to any one of claims 1 to 3, characterized by the above.

8. An information processing method executed by a computer, comprising: ​ ​ A receiving step of receiving the user setting information, which is information set by a user, from another information processing apparatus that has received the user setting information via a predetermined API; A searching step of searching for a prompt to be input to a generative AI used in the other information processing apparatus based on the user setting information received in the receiving step; A providing step of providing the prompt searched in the searching step to the other information processing apparatus as a provided prompt via the API, and An information processing method characterized by the above.

9. A receiving procedure of receiving the user setting information, which is information set by a user, from another information processing apparatus that has received the user setting information via a predetermined API; A searching procedure of searching for a prompt to be input to a generative AI used in the other information processing apparatus based on the user setting information received in the receiving procedure; Causing a computer to execute a providing procedure of providing the prompt searched in the searching procedure to the other information processing apparatus as a provided prompt via the API, and An information processing program characterized by the above.

Images