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

Abstract

To provide an information processing apparatus, an information processing method, and an information processing program capable of supporting information generation using an appropriate prompt in accordance with a request from a user.SOLUTION: An information processing apparatus includes a selection unit, a generation unit, and a provision unit. The selection unit selects a prompt according toa request from a user, from among a plurality of prompts for which details are concealed from a user. The generation unit inputs, to a generative AI, information including the prompt selected by the selection unit, to cause the generative AI to generate information tailored to the prompt selected by the selection unit. The provision unit provides the information generated by the generation unit or information based on the information, as provision information, to the user.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-described conventional technology, since additional sentences are automatically added, there is room for further improvement in terms of supporting the use of more appropriate prompts in response to the user's requests.

[0005] The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can assist in using more appropriate prompts in accordance with the user's requests. [Means for solving the problem]

[0006] The information processing device according to the present application includes a selection unit, a generation unit, and a provision unit. The selection unit selects a prompt in response to a user request from among a plurality of prompts whose details are concealed from the user. The generation unit inputs information including the prompt selected by the selection unit to a generation AI, causing the generation AI to generate information in response to the prompt selected by the selection unit. The provision unit provides the information generated by the generation unit or information based on that information to the user as provided information. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to provide an effect of supporting the use of more appropriate prompts in response to the user's request. [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 user information table stored in the user information storage unit of the information processing device according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a confidential prompt table stored in the confidential prompt storage unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a flowchart showing an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 7] FIG. 7 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[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 device 2 is, for example, a smartphone, a tablet, or a personal computer.

[0012] 1, the information processing device 1 receives a search request from a user U (step S1). For example, the information processing device 1 receives the search request from the user U by receiving the search request transmitted from the terminal device 2 of the user U.

[0013] The search request includes user-related information including user setting information, which is information set by the user U, and user information, which is information about the user U who will be the user of the confidential prompt, which will be described later. The user U who will be the user of the confidential prompt is not limited to the user U of the terminal device 2 that sent the search request, but may be a user U other than the user U of the terminal device 2 that sent the search request. This allows the user U of the terminal device 2 to provide confidential prompts for other users U.

[0014] The user setting information is, for example, the information of the character string "~~~ can prompt" or the information of the character string "~~~ do prompt". "~~~" is a character string that indicates the action or processing that the user U wants the generated AI (Artificial Intelligence) to perform.

[0015] 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 user setting information is not limited to the above-mentioned examples. For example, the user setting information may be information on a string that further details the content of the operation or process desired by the user U.

[0016] The user information includes identification information of the user U. The identification information of the user U is, for example, an ID (identifier) ​​of the user U or a cookie of the browser of the terminal device 2, but is not limited to such examples.

[0017] 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.

[0018] Examples of the transformer-based model include, but are not limited to, GPT (Generative Pre-trained Transformer) (registered trademark) and PaLM2 (Pathways Language Model Version 2). Examples of the RNN-based model include, but are not limited to, RWKV (Receptance Weighted Key Value).

[0019] 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.

[0020] 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).

[0021] It is desirable that the generation AI is trained so as not to include personal information in the generated results. The generation AI is placed in an external information processing device, and the information processing device 1 uses the generation AI via an API (Application Programming Interface), but the generation AI may also be placed within the information processing device 1.

[0022] Next, the information processing device 1 searches for two or more confidential prompts that correspond to the search request from among the multiple confidential prompts (step S2). Details of each confidential prompt are kept secret from the user U, and the user U cannot grasp the details of the confidential prompt. Each confidential prompt is provided, for example, by a prompt provider, which is a business or operator different from the provider of the generation AI described above. Note that the confidential prompt may also be a prompt provided by the user U as a prompt provider.

[0023] The confidential prompt may include, for example, some or all of the information in the string that indicates the definition of the task to be performed by the generation AI, the constraints on the task in the generation AI, the definition of the behavior and tone of the generation AI, the output format of the generation AI, etc., but is not limited to such examples.

[0024] For example, if the generation AI is GPT from OpenAI (registered trademark), the confidential 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 may be system, user, etc. The confidential prompt is a prompt that includes at least one of a system message whose role is system and a user message whose role is user.

[0025] A system message is, for example, a prompt whose role indicates the role of the generation AI, and a user message is, for example, a prompt whose role indicates a message from the user. A system message includes, for example, a definition of the task to be performed by the generation AI, constraints on the task in the generation AI, definitions of the behavior and tone of the generation AI, output format of the generation AI, examples of operation of the generation AI, etc., but is not limited to such examples and may include part of this information.

[0026] 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.

[0027] The user message may include information in the form of a string indicating a definition of the task to be performed by the generation AI, constraints on the task for the generation AI, a definition of the behavior and tone of the generation AI, the output format of the generation AI, an example of the operation of the generation AI, etc., or may include part of this information.

[0028] In addition, if the generating AI is GPT from OpenAI, the confidential 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.

[0029] In step S2, the information processing device 1 has a confidential prompt database containing a plurality of confidential prompts, and identifies the confidential prompt corresponding to the search request by searching and obtaining the confidential prompt corresponding to the search request from the confidential prompt database.

[0030] The confidential prompt database includes, for each confidential prompt, information about the confidential prompt, including, for example, identification information of the confidential prompt, a title of the confidential prompt, header information of the confidential prompt, vector information of the header information of the confidential prompt, information indicating the confidential prompt, etc. The confidential prompt database includes searchable confidential prompts corresponding to a search query.

[0031] The header information of the confidential prompt is information indicating a description of the function of the confidential prompt (e.g., an overview of the function), and the header information of the confidential prompt is vectorized, for example, by embedding using a sentence embedding model (e.g., a transformer-based model). The vector information of the header information of the confidential prompt is represented, for example, by a vector of several hundred dimensions, but is not limited to such an example.

[0032] 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.

[0033] Note that the vectorization of the headline information of the confidential prompt is not limited to embedding using a sentence embedding model, and may be performed using, for example, Doc2Vec, the average of word embeddings, etc. Word2Vec, fastText, etc. are used for word embedding.

[0034] The information processing device 1 vectorizes the user setting information included in the search request using a method similar to that used for vectorizing the headline information of the confidential prompt. Then, the information processing device 1 retrieves, as search results, confidential prompts corresponding to the top m (m is 2 or more) headline information whose vector similarity to the user setting information is equal to or greater than a threshold value or whose similarity is highest from the confidential prompt database.

[0035] The confidential prompt database may include information on each of the multiple keywords included in the confidential prompt or its heading information instead of the vector information of the heading information of the confidential prompt. In this case, the information processing device 1 retrieves, as a search result, from the confidential prompt database, confidential prompts that correspond to confidential prompts or heading information that include one or more terms included in the user setting information included in the search request, for example.

[0036] 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.

[0037] The confidential prompt database may also include information indicating the charge for confidential prompts, information indicating the number of confidential prompts selected, information indicating an evaluation of the confidential prompts, etc. The charge for confidential prompts is the fee paid by user U for using the confidential prompts.

[0038] Next, the information processing device 1 provides the user U with information on the two or more confidential prompts obtained by the search in step S2 by transmitting the information on the two or more confidential prompts obtained by the search in step S2 to the terminal device 2 (step S3).

[0039] The terminal device 2 displays information about two or more confidential prompts sent from the information processing device 1. The information about the confidential prompts displayed on the terminal device 2 includes the titles and header information of the confidential prompts. The user U checks the titles and header information of the two or more confidential prompts and operates the terminal device 2 to select one or more confidential prompts from the two or more confidential prompts displayed on the terminal device 2.

[0040] Furthermore, the information about the confidential prompts displayed on the terminal device 2 may include information indicating the amount charged for the confidential prompts, information indicating the number of selected confidential prompts, information indicating an evaluation of the confidential prompts, etc. In this case, the user U can check the information indicating the amount charged for the confidential prompts, information indicating the number of selected confidential prompts, information indicating an evaluation of the confidential prompts, etc., and select one or more confidential prompts from the two or more confidential prompts displayed on the terminal device 2.

[0041] When the user U specifies one or more confidential prompts from two or more confidential prompts searched by the information processing device 1, the terminal device 2 sends a selection request to the information processing device 1 including information for identifying the one or more confidential prompts specified by the user U (step S4).

[0042] Furthermore, if additional information is required to use the confidential prompt specified by the user U, the user U inputs the additional information by operating the terminal device 2. If the generation AI is a text generation AI, the additional information is an additional prompt, and if the generation AI is a multimodal generation AI, the additional information is at least one of an additional prompt and additional image data.

[0043] For example, if the confidential prompt specified by the user U is a prompt that requires additional information, the user U can input the additional information into the terminal device 2 by operating the terminal device 2. As a result, a selection request including information identifying one or more confidential prompts specified by the user U and the additional information is transmitted from the terminal device 2 to the information processing device 1.

[0044] An example of a prompt that requires additional information is the string "You are an experienced travel planner. Based on the user's specific requests, 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 the string "Please create a plan for a trip to Okinawa. Your interests are history and gourmet food. The budget is 200,000 yen per person."

[0045] Furthermore, a prompt that requires additional information is, for example, the information in the string "You are an excellent proofreader. It will 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 about the string to be proofread.

[0046] When the information processing device 1 receives the selection request transmitted from the terminal device 2, it selects one or more confidential prompts identified in the selection request from among the multiple confidential prompts (step S5). The one or more confidential prompts selected by the information processing device 1 are associated with the user U of the terminal device 2 that transmitted the selection request.

[0047] Next, the information processing device 1 inputs information including the selection prompt, which is the confidential prompt selected in step S5, to the generation AI, and causes the generation AI to generate generation information, which is information according to the selection prompt (step S6).

[0048] For example, if the selection prompt is a prompt that does not require additional information, the information processing device 1 inputs information including the selection prompt to the generation AI and causes the generation AI to generate generation information that is information corresponding to the selection prompt.

[0049] A selection prompt that does not require additional information is, for example, a prompt that instructs the collection of information about a specific object whose status is changing (e.g., a specific disaster, a specific person, or a specific object) and generates current information or summary information about the specific object.

[0050] In this case, the information processing device 1 collects information on a specific object (e.g., a specific disaster, a specific person, or a specific object) whose state changes in accordance with a selection prompt, inputs information including the collected information and instruction information indicating an instruction to execute a specific process on the information as input information, and causes the generation AI to generate generated information that is information in accordance with the selection prompt. The specific process is, for example, a process of compiling the collected information into a specific format, a process of summarizing the collected information, etc., but is not limited to such examples.

[0051] A selection prompt that does not require additional information is a prompt that includes information about a string of characters that instructs a specific process, such as repeating a process of outputting a string of characters according to predetermined conditions or repeating a process of outputting an image according to predetermined conditions.

[0052] In addition, if the selection prompt is a prompt that requires additional information, the information processing device 1 inputs information including the selection prompt and the additional information included in the selection request to the generation AI, and causes the generation AI to generate generation information that is information corresponding to the selection prompt and the additional information.

[0053] Selection prompts requiring additional information may include, but are not limited to, prompts that instruct you to perform a specific task for the additional information, such as summarizing the additional information, analyzing the additional information (e.g., sentiment analysis), translating the additional information, improving or proofreading the additional information, or creating an article or story about the additional information.

[0054] The selection prompt requiring additional information may be, for example, a prompt to execute a specific task in a chat format with the user U. In this case, the specific task is a task to conduct a Q&A (Question and Answer) in a chat format regarding a specific category (e.g., economy, education, etc.), in which the user U inputs information indicating a question as additional information, and the generation AI generates information indicating an answer to the question.

[0055] Furthermore, the specific task may involve having the user U sequentially input the information necessary to create information on a specific subject (e.g., various application forms, novels, cooking recipes, blogs, etc.) as additional information, and then having the generation AI generate information on the specific subject based on this additional information.

[0056] The confidential prompt selected as the selection prompt may be a prompt including 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 input information, and definition information including the intention type and information defining the intention type. When using an API provided by OpenAI, for example, the information processing device 1 can cause the generation AI to generate the intention information by using a function calling function.

[0057] 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.

[0058] 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 1 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.

[0059] Furthermore, when the selection prompt includes a message indicating a scenario, the information processing device 1 can repeat the process of inputting information to the generation AI according to the scenario and obtaining output until the task completion condition is met, and generate generation information based on the results of this process. In this case, the information processing device 1 includes an input / output history, including information previously input to the generation AI and information previously output by the generation AI, in the input information to be input to the generation AI when executing the task.

[0060] For example, the information processing device 1 can cause the generation AI to generate generation information by inputting information including input / output history into the generation AI as input information while changing the content to be generated by the generation AI according to a scenario until the task completion condition is met.

[0061] The information input to the generation AI according to the scenario is information collected from an external information processing device or an internal storage unit, or additional information input by the user U. For example, the information processing device 1 collects information from an external information processing device or an internal storage unit, according to the scenario, and causes the generation AI to generate generation information based on the collected information until the task completion condition is met.

[0062] Furthermore, the information processing device 1 can also have the user U input additional information according to the scenario until the task completion condition is met, and have the generation AI generate generation information based on this additional information.

[0063] If multiple confidential prompts are selected in step S5, the information processing device 1 causes the generation AI to generate generation information for each selected confidential prompt, thereby enabling the information processing device 1 to obtain generation information for each selected prompt.

[0064] Next, the information processing device 1 provides the generated information generated in step S6 or information based on the generated information as provided information to the user U (step S7). The information processing device 1 transmits the generated information generated in step S6 or information based on the generated information as provided information to the terminal device 2, thereby providing the generated information generated in step S6 or information based on the generated information as provided information to the user U. This makes it possible to provide the generated information generated using the confidential prompt or information based on the generated information as provided information to the user U while concealing the detailed content of the confidential prompt.

[0065] When the information generated by the generation AI as generated information is intention information, the information processing device 1 can use such intention information to acquire information from an external information processing device or an internal memory unit, etc., and generate provided information based on the acquired information.

[0066] Furthermore, when the information processing device 1 generates the generated information for each selection prompt using the generation AI, it provides the provided information for each selection prompt to the user U. In this case, the terminal device 2 displays the provided information for each selection prompt, and the user U can compare the provided information for each selection prompt.

[0067] Next, the information processing device 1 receives information indicating the user U's evaluation of the provided information (step S8). The user U can check the provided information displayed on the terminal device 2 and operate the terminal device 2 to input information indicating the evaluation of the provided information.

[0068] The evaluation of the provided information is, for example, a 10-point scale, but may also be a 9-point scale or less, or a 11-point scale or more. The information indicating the evaluation may also be character string information such as a review or comment.

[0069] Next, the information processing device 1 performs a billing process for the user U to whom the provided information was provided in step S7 (step S9). The billing process is, for example, a process in which the user U pays the fee associated with the confidential prompt used to generate the provided information provided to the user U in step S7.

[0070] The information processing device 1 can perform charging processing, for example, by sending billing information including information indicating the billing amount and information identifying user U to a financial institution's device, or by sending billing information including information indicating the billing amount and information identifying user U's credit card number to a credit card company's device.

[0071] Furthermore, the user U can also pay for the confidential prompt with points instead of or in addition to a specific currency. For example, the information processing device 1 can perform the charging process by transmitting charging information including information indicating the number of points corresponding to the charged amount and information identifying the user U to a device of a point management company.

[0072] Points are rewards given to user U by a points management company, for example, when user U makes a purchase using a credit card or cash, or when user U subscribes to a particular service, but are not limited to such examples.

[0073] Next, the information processing device 1 determines the amount to be charged for using the confidential prompt (step S10). For example, the information processing device 1 determines the amount to be charged based on the evaluation of the provided information by each user U. The information processing device 1 determines a higher amount to be charged for a confidential prompt that has a higher average evaluation of the provided information by each user U.

[0074] The information processing device 1 can determine the charge amount based on the evaluation of the provided information by each user U, using a standard amount set by the provider of the confidential prompt. For example, the information processing device 1 determines a charge amount lower than the standard amount for confidential prompts for which the average evaluation of the provided information by each user U is lower than the standard value. The standard value is 5 when the evaluation is on a 10-point scale.

[0075] The information processing device 1 can also determine the charge amount based on the number of times the confidential prompt is used by the user U. For example, the information processing device 1 determines a higher charge amount for a confidential prompt that is used more frequently by the user U.

[0076] The information processing device 1 can also determine the charge amount based on the evaluation of the provided information by each user U and the number of times the confidential prompt is used by the user U. For example, the information processing device 1 determines a higher charge amount for a confidential prompt with a higher score obtained by weighting the average evaluation of the provided information by each user U and the number of times the confidential prompt is used by the user U.

[0077] The information processing device 1 can also accept a tentative selection request sent from the terminal device 2. The tentative selection request includes information indicating two or more confidential prompts designated by the user U as selection candidates. When the information processing device 1 accepts the tentative selection request, it selects the two or more confidential prompts designated in the tentative selection request as two or more selection prompt candidates.

[0078] In addition, if additional information is required to use a selection prompt candidate, the provisional selection request includes the additional information for each selection prompt candidate in addition to specific information indicating two or more selection prompt candidates.

[0079] The information processing device 1 then inputs information including the selection prompt candidates to the generation AI, and causes the generation AI to generate candidate generation information, which is information corresponding to the selection prompt candidates, for each selection prompt candidate. The method for generating the candidate generation information is the same as the method for generating the generation information described above.

[0080] The information processing device 1 provides the selection information to the user U by transmitting selection information including each of the generated candidate generation information or information based on the candidate generation information to the terminal device 2. The selection information includes the candidate generation information or information based on the candidate generation information for each selection prompt candidate, in association with information about the selection prompt candidate (for example, information indicating the title of the selection prompt candidate or heading information). The candidate generation information and the information based on the candidate generation information are similar to the information provided above, but may also be part of the information provided, and may be referred to as candidate provision information below.

[0081] When the terminal device 2 receives the selection information transmitted from the information processing device 1, the terminal device 2 displays the selection information. This allows the user U to compare the candidate provision information between two or more selection prompt candidates by checking the candidate provision information generated using each of the two or more selection prompt candidates, and to specify and use a more appropriate confidential prompt as the selection prompt.

[0082] The user U checks the candidate provision information corresponding to each selection prompt candidate included in the selection information displayed on the terminal device 2, and specifies one or more selection prompt candidates by operating the terminal device 2. In this case, the terminal device 2 transmits a selection request including information identifying the one or more selection prompt candidates specified by the user U to the information processing device 1, similar to the processing in step S4.

[0083] In this way, the information processing device 1 selects a prompt in response to a request from user U from among multiple prompts whose details are concealed from user U, inputs information including the selected prompt, which is the selection prompt, into the generation AI, and causes the generation AI to generate information in response to the selection prompt. Then, the information processing device 1 provides user U with the information generated by the generation AI or information based on that information as provided information. This allows the information processing device 1 to generate information using a more appropriate prompt in response to user U's request.

[0084] 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.

[0085] [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 a terminal device 3.

[0086] The multiple terminal devices 2 are used by different users U. The terminal device 3 is, for example, a terminal device of a provider O that provides confidential prompts. In the example shown in FIG. 2, one terminal device 3 is shown, but if there are multiple providers O that provide confidential prompts, the information processing system 100 will include multiple terminal devices 3.

[0087] The terminal devices 2 and 3 are, for example, notebook PCs (Personal Computers), desktop PCs, smartphones, tablet PCs, and wearable devices, such as, but not limited to, smart glasses or smart watches.

[0088] The information processing device 1, the terminal device 2, and the terminal device 3 are connected to each other so as to be able to communicate with each other via a network N, either wired or wirelessly. Note that the information processing system 100 shown in FIG. 2 may include a plurality of information processing devices 1 and the like.

[0089] 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).

[0090] The terminal devices 2 and 3 can connect to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or wireless LAN (Local Area Network), and communicate with the information processing device 1 and the like.

[0091] 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.

[0092] [3.1. Communication Unit 10] The communication unit 10 is realized by, for example, a communication module or a network interface card (NIC). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from each of the terminal device 2 and the terminal device 3 via the network N.

[0093] [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 has a user information storage unit 20 and a confidential prompt storage unit 21.

[0094] [3.2.1. User information storage unit 20] The user information storage unit 20 stores user information including information about the user U. Fig. 4 is a diagram showing an example of a user information table stored in the user information storage unit 20 of the information processing device 1 according to the embodiment. As shown in Fig. 4, the user information table stored in the user information storage unit 20 includes items such as "user ID," "attribute information," and "behavioral history."

[0095] The "user ID" is identification information that identifies the user U. The "attribute information" is attribute information of the user U that corresponds to the "user ID," and includes, for example, psychographic attribute information and demographic attribute information. Demographic attributes include, for example, gender, age, place of residence, and occupation, while psychographic attributes include interests such as travel, clothing, cars, and religion, lifestyle, thoughts, and ideological tendencies.

[0096] The "behavioral history" is the behavioral history of the user U corresponding to the "user ID." The behavioral history of the user U includes, for example, identification information of the confidential prompt selected by the processing unit 12 for the user U, identification information of the confidential prompt purchased by the user U, identification information of the confidential prompt used by the user U, and information indicating the number of uses of each confidential prompt used by the user U.

[0097] 3.2.2. Secret Prompt Storage Unit 21 The confidential prompt storage unit 21 stores various types of information related to confidential prompts. Fig. 5 is a diagram showing an example of a confidential prompt table stored in the confidential prompt storage unit 21 of the information processing device 1 according to the embodiment.

[0098] 5, the confidential prompt table stored in the confidential prompt storage unit 21 is an example of the confidential prompt database described above, and includes information on items such as "prompt ID," "confidential prompt," "related information," "number of selections," "number of uses," and "evaluation information." The "prompt ID" is an identifier that identifies a confidential prompt, and is information assigned to each confidential prompt.

[0099] A "confidential prompt" is a confidential prompt associated with a "prompt ID." "Related information" is information about the confidential prompt associated with a "prompt ID," and includes, for example, identification information of the confidential prompt, the title of the confidential prompt, header information of the confidential prompt, vector information of the header information of the confidential prompt, vector information of the confidential prompt, information indicating the confidential prompt, and information indicating the charge for the confidential prompt. The charge for the confidential prompt is the fee paid by user U for using the confidential prompt.

[0100] The "number of selections" is information indicating the number of times the confidential prompt associated with the "prompt ID" has been selected and linked to user U. The "number of uses" is the number of times the confidential prompt associated with the "prompt ID" has been used by user U.

[0101] The "rating information" is information indicating each user U's rating of the provided information generated by the processing unit 12 using the confidential 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.

[0102] Although not shown, the confidential prompt table also includes information indicating the number of purchases, which is the number of times the confidential prompt associated with the "prompt ID" has been purchased by the user U.

[0103] [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.

[0104] 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).

[0105] 3, the processing unit 12 has a reception unit 30, an acquisition unit 31, a search unit 32, a selection unit 33, a generation unit 34, a provision unit 35, a billing unit 36, and a determination unit 37, 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.

[0106] 3.3.1. Reception unit 30 The reception unit 30 receives various information and requests. For example, the reception unit 30 receives a prompt list request from the user U. The reception unit 30 receives the prompt list request from the user U, for example, by receiving the prompt list request transmitted from the terminal device 2 of the user U.

[0107] The reception unit 30 also receives a search request from the user U. The reception unit 30 receives a search request from the user U, for example, by receiving a search request transmitted from the terminal device 2 of the user U.

[0108] The search request includes user-related information including user setting information, which is information set by the user U, and user information, which is information about the user U who will be the user of the confidential prompt. The user U who will be the user of the confidential prompt is not limited to the user U of the terminal device 2 that sent the search request, but may be a user U other than the user U of the terminal device 2 that sent the search request. This allows the user U of the terminal device 2 to provide confidential prompts for other users U.

[0109] The user setting information is, for example, the information of the character string "~~~ can prompt" or the information of the character string "~~~ do prompt". "~~~" is a character string that indicates the action or processing that the user U wants the generated AI to perform.

[0110] 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 user setting information is not limited to the above-mentioned examples. For example, the user setting information may be information on a string that further details the content of the operation or process desired by the user U.

[0111] The user information includes identification information of the user U. The identification information of the user U is, for example, the ID of the user U or a cookie in the browser of the terminal device 2, but is not limited to such examples.

[0112] The generative AI may be, for example, a text generation AI, an image generation AI, or a multimodal generation AI. The text generation AI may be, 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-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.

[0113] Examples of the transformer-based model include, but are not limited to, GPT and BARD, and examples of the RNN-based model include, but are not limited to, RWKV.

[0114] Image generation AI is AI that generates images from text, and includes, but is not limited to, StackGAN, AttnGAN, T2I with Transformers, and Diffusion models. Diffusion models include, for example, DALL-E and Stable-Diffusion.

[0115] The multimodal generation AI is, for example, a generation AI that generates at least one of text, image, and audio from at least one of text, image, and audio. Examples of the multimodal generation AI include, but are not limited to, GPT-4V and CM3Leon.

[0116] It is desirable that the generation AI be trained so as not to include personal information in the generated results. The generation AI is placed in an external information processing device, and the information processing device 1 uses the generation AI via an API, but the generation AI may also be placed within the information processing device 1.

[0117] The reception unit 30 also receives a selection request from the user U. The reception unit 30 receives a selection request from the user U, for example, by receiving a selection request transmitted from the terminal device 2 of the user U.

[0118] The selection request includes, for example, specification information that is information that specifies one or more confidential prompts specified by the user U from two or more confidential prompts searched by the search unit 32. In addition, if additional information that is additional information is required to use the confidential prompts specified by the user U, the selection request includes the additional information.

[0119] 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.

[0120] For example, if the confidential prompt specified by the user U is a prompt that requires additional information, the user U can input the additional information into the terminal device 2 by operating the terminal device 2. As a result, a selection request including information identifying one or more confidential prompts specified by the user U and the additional information is transmitted from the terminal device 2 to the information processing device 1.

[0121] The reception unit 30 also receives a tentative selection request from the user U. The reception unit 30 receives the tentative selection request from the user U, for example, by receiving the tentative selection request transmitted from the terminal device 2 of the user U. The tentative selection request includes information indicating two or more selection prompt candidates, which are two or more confidential prompts designated by the user U as selection candidates.

[0122] In addition, if additional information is required to use a selection prompt candidate, the provisional selection request includes the additional information for each selection prompt candidate in addition to specific information indicating two or more selection prompt candidates.

[0123] The reception unit 30 also receives a purchase request from the user U. The reception unit 30 receives a purchase request from the user U, for example, by receiving a purchase request transmitted from the terminal device 2 of the user U. The purchase request includes information indicating one or more confidential prompts that the user U has selected as items to be purchased.

[0124] When the reception unit 30 receives a purchase request from the user U, it stores the identification information of the confidential prompt specified in the purchase request in the user information storage unit 20 as the identification information of the purchase prompt, and updates the user information table.

[0125] The reception unit 30 also receives a usage request from the user U. The reception unit 30 receives a usage request from the user U, for example, by receiving a usage request transmitted from the terminal device 2 of the user U. The reception unit 30 receives a usage request from the user U, for example, when the confidential prompt identified in the usage request from the user U is the purchase prompt of the user U.

[0126] The usage request includes information indicating one or more confidential prompts selected for use by the user U. Furthermore, if additional information is required to use the confidential prompts selected for use by the user U, the usage request includes the additional information for each confidential prompt in addition to specific information indicating one or more confidential prompts.

[0127] The receiving unit 30 also receives evaluation information, which is information indicating the evaluation of the provided information by the user U. The receiving unit 30 receives the evaluation information by, for example, receiving the evaluation information transmitted from the terminal device 2 of the user U.

[0128] [3.3.2. Acquisition part 31] The acquisition unit 31 acquires various pieces of information from external devices or the like via the network N and the communication unit 10, and acquires various pieces of information from the storage unit 11.

[0129] For example, when a search request is accepted by the accepting unit 30, the acquiring unit 31 acquires user-related information included in the search request accepted by the accepting unit 30. The user-related information includes user setting information, which is information set by the user U, and user information, which is information about the user U who will be the user of the confidential prompt. In addition, for example, when a selection request is accepted by the accepting unit 30, the acquiring unit 31 acquires specific information and additional information included in the selection request accepted by the accepting unit 30.

[0130] Furthermore, for example, when the receiving unit 30 receives a tentative selection request, the acquiring unit 31 acquires the specific information and additional information included in the tentative selection request received by the receiving unit 30.

[0131] Furthermore, for example, when a purchase request is accepted by the accepting unit 30, the acquiring unit 31 acquires specific information included in the purchase request accepted by the accepting unit 30. Furthermore, for example, when a usage request is accepted by the accepting unit 30, the acquiring unit 31 acquires specific information and additional information included in the usage request accepted by the accepting unit 30.

[0132] [3.3.3. Search Unit 32] The search unit 32 searches for two or more confidential prompts in response to the search request received by the reception unit 30. For example, the search unit 32 searches for two or more confidential prompts using explanatory text that explains the function of each confidential prompt.

[0133] Each confidential prompt is a prompt whose details are kept secret from the user U, and the user U cannot grasp the detailed content of the confidential prompt. Each confidential prompt is, for example, a prompt provided by a prompt provider that is a business or operator different from the provider of the generation AI described above (for example, the operator of the information processing device 1). Note that the confidential prompt may also be a prompt provided by the user U as a prompt provider.

[0134] The confidential prompt may include, for example, some or all of the information in the string that indicates the definition of the task to be performed by the generation AI, the constraints on the task in the generation AI, the definition of the behavior and tone of the generation AI, the output format of the generation AI, etc., but is not limited to such examples.

[0135] For example, when using an API provided by OpenAI, the confidential prompt includes information about a character string included in the input information input to the generation AI in association with information indicating a role. Roles include system, user, etc. The confidential prompt is a prompt that includes at least one of a system message whose role is system and a user message whose role is user.

[0136] A system message is, for example, a prompt whose role indicates the role of the generation AI, and a user message is, for example, a prompt whose role indicates a message from the user. A system message includes, for example, a definition of the task to be performed by the generation AI, 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, an example of the operation of the generation AI, etc., but is not limited to such examples and may include some of this information.

[0137] 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.

[0138] The user message may include information in the form of a string indicating a definition of the task to be performed by the generation AI, constraints on the task for the generation AI, a definition of the behavior and tone of the generation AI, the output format of the generation AI, an example of the operation of the generation AI, etc., or may include only part of such information.

[0139] Furthermore, when using an API provided by OpenAI, the confidential 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.

[0140] The search unit 32 selects a confidential prompt in response to the search request by searching for and acquiring the confidential prompt in response to the search request from the confidential prompt table stored in the confidential prompt storage unit 21 .

[0141] As described above, the confidential prompt table includes, for each confidential prompt, information about the confidential prompt, including, for example, identification information of the confidential prompt, a title of the confidential prompt, header information of the confidential prompt, vector information of the header information of the confidential prompt, information indicating the confidential prompt, etc. The confidential prompt table includes searchable confidential prompts corresponding to a search query.

[0142] The header information of the confidential prompt is information indicating a description of the function of the confidential prompt (e.g., an overview of the function), and the header information of the confidential prompt is vectorized, for example, by embedding using a sentence embedding model (e.g., a transformer-based model). The vector information of the header information of the confidential prompt is represented, for example, by a vector of several hundred dimensions, but is not limited to such an example.

[0143] Embedding using a sentence embedding model is, for example, embedding using text-embedding-ada provided by OpenAI, BERT, etc., but is not limited to these examples.

[0144] Note that the vectorization of the headline information of the confidential prompt is not limited to embedding using a sentence embedding model, and may be performed using, for example, Doc2Vec, the average of word embeddings, etc. Word2Vec, fastText, etc. are used for word embedding.

[0145] The search unit 32 vectorizes the user setting information included in the search request in the same way as the vectorization of the headline information of the confidential prompt. Then, the search unit 32 retrieves, as search results, confidential prompts corresponding to the top m (m is 2 or more) headline information whose vector similarity to the user setting information is equal to or greater than a threshold value or whose similarity is highest from the confidential prompt table.

[0146] The confidential prompt table may include information on each of the confidential prompts or the keywords included in the header information thereof, instead of the vector information on the header information of the confidential prompt. In this case, the search unit 32 retrieves, as a search result, from the confidential prompt table, a confidential prompt that corresponds to the confidential prompt or header information that includes one or more terms included in the user setting information included in the search request.

[0147] The confidential prompt table may also include vector information of the confidential prompts instead of the vector information of the header information of the confidential prompts. In this case, the search unit 32 retrieves, as search results, from the confidential prompt table, the top m (m is 2 or more) confidential prompts whose vector similarity to the user setting information included in the search request is equal to or greater than a threshold value or whose vector similarity is highest.

[0148] [3.3.4. Selection unit 33] The selection unit 33 selects a confidential prompt in response to a request from the user U from among a plurality of confidential prompts, which are a plurality of prompts whose details are concealed from the user U. For example, the selection unit 33 accepts a confidential prompt specified by the user U as a confidential prompt in response to the request of the user U.

[0149] For example, when the receiving unit 30 receives a selection request including information for identifying one or more confidential prompts specified by the user U, the selecting unit 33 selects one or more confidential prompts identified in the selection request from among the multiple confidential prompts. The one or more confidential prompts identified in the selection request are the one or more confidential prompts specified by the user U. The selecting unit 33 stores identification information of the one or more selected confidential prompts in the storage unit 11.

[0150] In this case, the selection request includes, for example, information for identifying one or more confidential prompts specified by the user U from among a plurality of confidential prompts included in the search results displayed on the terminal device 2. The selection request may also include information for identifying one or more confidential prompts specified by the user U from a plurality of confidential prompts included in a prompt list displayed on the terminal device 2 instead of the search results.

[0151] In addition, when the reception unit 30 receives a selection request including information for identifying one or more selection prompt candidates specified by the user U, the selection unit 33 selects one or more selection prompt candidates identified in the selection request from among the multiple selection prompt candidates.

[0152] The one or more selection prompt candidates specified in the selection request are one or more selection prompt candidates specified by the user U. The selection unit 33 stores identification information of the one or more selected selection prompt candidates in the storage unit 11. In this case, the selection request includes, for example, information for identifying the one or more selection prompt candidates specified by the user U from the multiple selection prompt candidates displayed on the terminal device 2.

[0153] Furthermore, when a provisional selection request is received by the receiving unit 30, the selecting unit 33 provisionally selects a plurality of confidential prompts identified by the provisional selection request from the plurality of confidential prompts. The selecting unit 33 stores identification information of the provisionally selected plurality of confidential prompts in the storage unit 11.

[0154] In addition, the selection unit 33 selects a confidential prompt specified by the user U from among the multiple confidential prompts provisionally selected based on selection information generated by the generation unit 34 based on the multiple provisionally selected confidential prompts as a confidential prompt in response to the user U's request.

[0155] Furthermore, when the receiving unit 30 receives a usage request, the selecting unit 33 selects one or more confidential prompts specified in the usage request from among the multiple confidential prompts.

[0156] [3.3.5. Generation unit 34] The generation unit 34 inputs information including a selection prompt, which is a confidential prompt selected by the selection unit 33, to the generation AI, and causes the generation AI to generate generation information, which is information corresponding to the selection prompt, which is a confidential prompt selected by the selection unit 33.

[0157] For example, if the selection prompt is a prompt that does not require additional information, the generation unit 34 inputs information including the selection prompt to the generation AI and causes the generation AI to generate generation information that is information corresponding to the selection prompt.

[0158] A selection prompt that does not require additional information is, for example, a prompt that instructs the collection of information about a specific object whose status is changing (e.g., a specific disaster, a specific person, or a specific object) and generates current information or summary information about the specific object.

[0159] In this case, the generation unit 34 collects information on a specific object (e.g., a specific disaster, a specific person, or a specific object) whose state changes in response to a selection prompt, inputs the collected information and instruction information indicating an instruction to execute a specific process on the information as input information, and causes the generation AI to generate generated information that is information in response to the selection prompt. The specific process is, for example, a process of compiling the collected information into a specific format, a process of summarizing the collected information, etc., but is not limited to such examples.

[0160] A selection prompt that does not require additional information is a prompt that includes information about a string of characters that instructs a specific process, such as repeating a process of outputting a string of characters according to predetermined conditions or repeating a process of outputting an image according to predetermined conditions.

[0161] In addition, if the selection prompt is a prompt that requires additional information, the generation unit 34 inputs information including the selection prompt and the additional information included in the selection request to the generation AI, and causes the generation AI to generate generation information that is information corresponding to the selection prompt and the additional information.

[0162] Selection prompts requiring additional information may include, but are not limited to, prompts that instruct you to perform a specific task for the additional information, such as summarizing the additional information, analyzing the additional information (e.g., sentiment analysis), translating the additional information, improving or proofreading the additional information, or creating an article or story about the additional information.

[0163] The selection prompt requiring additional information may be, for example, a prompt to execute a specific task in a chat format with the user U. In this case, the specific task is a task to conduct a Q&A (Question and Answer) in a chat format regarding a specific category (e.g., economy, education, etc.), in which the user U inputs information indicating a question as additional information, and the generation AI generates information indicating an answer to the question.

[0164] Furthermore, the specific task may involve having the user U sequentially input the information necessary to create information on a specific subject (e.g., various application forms, novels, cooking recipes, blogs, etc.) as additional information, and then having the generation AI generate information on the specific subject based on this additional information.

[0165] The confidential prompt selected as the selection prompt may include intent definition information for extracting the intent type and the intent content. The intent definition information includes, for example, instruction information including an instruction to extract the intent type and the intent content from the user input information, and definition information including the intent type and information defining the intent type. When using, for example, an API provided by OpenAI, the generation unit 34 can cause the generation AI to generate the intent information by using a function calling function.

[0166] 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.

[0167] In this case, the generation AI generates intention information including information indicating the intention type and information indicating the intention content. The generation unit 34 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.

[0168] Furthermore, if the selection prompt includes a message indicating a scenario, the generation unit 34 can repeat the process of inputting information to the generation AI according to the scenario and obtaining output until the task completion condition is met, and generate generation information based on the results of this process. In this case, the generation unit 34 includes in the input information to be input to the generation AI an input / output history including information previously input to the generation AI when executing the task and information previously output by the generation AI.

[0169] For example, the generation unit 34 can cause the generation AI to generate generation information by inputting information including input / output history into the generation AI as input information while changing the content to be generated by the generation AI according to a scenario until the task completion condition is met.

[0170] The information input to the generation AI according to the scenario is information collected from an external information processing device or an internal storage unit, or additional information input by the user U. For example, the generation unit 34 collects information from an external information processing device or an internal storage unit according to the scenario until the task completion condition is met, and causes the generation AI to generate generation information based on the collected information.

[0171] Furthermore, the generation unit 34 can also have the user U input additional information according to the scenario until the task completion condition is met, and have the generation AI generate generation information based on this additional information.

[0172] When multiple confidential prompts are selected by the selection unit 33, the generation unit 34 causes the generation AI to generate generation information for each confidential prompt selected by the selection unit 33. This allows the generation unit 34 to obtain generation information for each selected prompt.

[0173] Furthermore, the generation unit 34 inputs information including selection prompt candidates, which are prompts provisionally selected by the selection unit 33, to the generation AI, and causes the generation AI to generate, for each selection prompt candidate, candidate generation information, which is information corresponding to the selection prompt candidates, which are prompts provisionally selected by the selection unit 33. The method for generating the candidate generation information is the same as the method for generating the generation information described above.

[0174] [3.3.6.Providing Department 35] The providing unit 35 provides various types of information to the user U. For example, the providing unit 35 provides the various types of information to the user U by transmitting the various types of information to the terminal device 2 via the communication unit 10 and the network N.

[0175] For example, when a prompt list request is accepted by the accepting unit 30, the providing unit 35 provides the prompt list information to the user U by sending the prompt list information, which lists multiple confidential prompts so that each can be selected individually, to the terminal device 2.

[0176] Furthermore, the providing unit 35 provides the user U with a selectable version of each of the two or more confidential prompts searched for by the searching unit 32. For example, the providing unit 35 provides the user U with information on the two or more confidential prompts searched for by the searching unit 32 by transmitting the information on the two or more confidential prompts searched for by the searching unit 32 to the terminal device 2.

[0177] The terminal device 2 displays information about two or more confidential prompts sent from the providing unit 35. The information about the confidential prompts displayed on the terminal device 2 includes the titles and header information of the confidential prompts, but does not include the content of the confidential prompts themselves, and therefore the information processing device 1 can provide the information about the confidential prompts while concealing the detailed content of the confidential prompts. The user U checks the titles and header information of the two or more confidential prompts and operates the terminal device 2 to select one or more confidential prompts from the two or more confidential prompts displayed on the terminal device 2.

[0178] Furthermore, the information about the confidential prompts displayed on the terminal device 2 may include information indicating the amount charged for the confidential prompts, information indicating the number of selected confidential prompts, information indicating an evaluation of the confidential prompts, etc. In this case, the user U can check the information indicating the amount charged for the confidential prompts, information indicating the number of selected confidential prompts, information indicating an evaluation of the confidential prompts, etc., and select one or more confidential prompts from the two or more confidential prompts displayed on the terminal device 2.

[0179] Furthermore, the providing unit 35 transmits the generated information or information based on the generated information generated by the generating unit 34 as provided information to the terminal device 2, thereby providing the generated information or information based on the generated information generated by the generating unit 34 as provided information to the user U. This makes it possible to provide the generated information or information based on the generated information generated using the confidential prompt as provided information to the user U while concealing the detailed content of the confidential prompt.

[0180] When the information that the generation unit 34 has the generation AI generate as generation information is intention information, the providing unit 35 can use such intention information to acquire information from an external information processing device or memory unit 11, etc., and generate the provision information based on the acquired information.

[0181] Furthermore, when the generation unit generates the generation information for each selection prompt, the providing unit 35 provides the provided information for each selection prompt to the user U. In this case, the terminal device 2 displays the provided information for each selection prompt, and the user U can compare the provided information for each selection prompt.

[0182] The user U can check the provided information displayed on the terminal device 2, and operate the terminal device 2 to input information indicating an evaluation of the provided information.

[0183] Furthermore, when candidate generation information for each selection prompt candidate is generated by the generation unit 34 through processing using the generation AI, the providing unit 35 provides selection information including the candidate provision information for each selection prompt candidate to the user U. For example, the providing unit 35 provides the selection information to the user U by transmitting the selection information to the terminal device 2.

[0184] The selection information includes candidate generation information or candidate provision information based on the candidate generation information, which is associated with information about the selection prompt candidate (e.g., information indicating the title of the selection prompt candidate or heading information) for each selection prompt candidate. The candidate provision information is the same information as the provision information described above, but may also be a part of the provision information.

[0185] In this case, the terminal device 2 displays selection information including candidate provision information for each selection prompt candidate, and the user U can compare the candidate provision information for each selection prompt candidate and specify and use a more appropriate confidential prompt.

[0186] The user U checks the candidate provision information corresponding to each selection prompt candidate included in the selection information displayed on the terminal device 2, and specifies one or more selection prompt candidates by operating the terminal device 2. In this case, the terminal device 2 transmits to the information processing device 1 a selection request including information identifying the one or more selection prompt candidates specified by the user U.

[0187] [3.3.7. Billing Unit 36] The billing unit 36 ​​performs a billing process for the user U to whom the provided information has been provided by the providing unit 35. The billing process is, for example, a process in which the user U pays the fee associated with the confidential prompt used to generate the provided information provided to the user U in step S7.

[0188] The billing unit 36 ​​can perform billing processing, for example, by sending billing information including information indicating the billing amount and information identifying user U to a financial institution's device, or by sending billing information including information indicating the billing amount and information identifying user U's credit card number to a credit card company's device.

[0189] Furthermore, the user U can pay for the confidential prompt with points instead of or in addition to a specific currency. For example, the billing unit 36 ​​can perform the billing process by transmitting billing information including information indicating the number of points corresponding to the billing amount and information identifying the user U to a device of the point management company.

[0190] Points are rewards given to user U by a points management company, for example, when user U makes a purchase using a credit card or cash, or when user U subscribes to a particular service, but are not limited to such examples.

[0191] The charging unit 36 can perform charging processing for the user U to whom the provided information is provided by the providing unit 35 at different charging amounts depending on the use and purchase of the confidential prompt. For example, in the case of purchasing a confidential prompt, charging processing is performed at a lump sum or monthly charging amount Ca for the provision of the provided information using the confidential prompt. Also, in the case of using a confidential prompt that the user U has not purchased, charging processing is performed at a per-use charging amount Cb (<Ca) for the provision of the provided information using the confidential prompt.

[0192] [3.3.8. Decision unit 37] The decision unit 37 determines the charging amount for the use of the confidential prompt. For example, the decision unit 37 determines the charging amount based on the evaluation information, which is information indicating the evaluation of the provided information by each user U. The decision unit 37 determines a higher charging amount for a confidential prompt with a higher average value of the evaluation of the provided information by each user U.

[0193] The decision unit 37 can determine the charging amount based on the evaluation of the provided information by each user U with reference to the reference amount set by the provider of the confidential prompt. For example, the decision unit 37 determines a lower charging amount than the reference amount for a confidential prompt with a lower average value of the evaluation of the provided information by each user U than the reference value. The reference value is 5 when the evaluation is a 10-point scale.

[0194] Also, the decision unit 37 can determine the charging amount based on the number of uses of the confidential prompt by the user U. For example, the decision unit 37 determines a higher charging amount for a confidential prompt with a larger number of uses of the confidential prompt by the user U.

[0195] Also, the decision unit 37 can determine the charging amount based on the evaluation of the provided information by each user U and the number of uses of the confidential prompt by the user U. For example, the decision unit 37 determines a higher charging amount for a confidential prompt with a larger score obtained by weighted addition of the average value of the evaluation of the provided information by each user U and the number of uses of the confidential prompt by the user U.

[0196] The determination unit 37 can also determine the charge amount based on the number of purchased confidential prompts. For example, the determination unit 37 determines a higher charge amount for a confidential prompt for which a larger number of confidential prompts have been purchased.

[0197] The determination unit 37 can also determine the charge amount based on the evaluation of the provided information by each user U and the number of confidential prompts purchased. For example, the determination unit 37 determines a higher charge amount for a confidential prompt with a higher score obtained by weighting and adding the average evaluation of the provided information by each user U and the number of confidential prompts purchased.

[0198] The determination unit 37 can also determine the charge amount based on the evaluation of the provided information by each user U, the number of times the confidential prompts are used, and the number of times the confidential prompts are purchased. For example, the determination unit 37 determines a higher charge amount for a confidential prompt that has a higher score obtained by weighting and adding the average evaluation of the provided information by each user U, the number of times the confidential prompts are used, and the number of times the confidential prompts are purchased.

[0199] [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. 6 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0200] 6, the processing unit 12 of the information processing device 1 determines whether a search request has been received (step S20). If the processing unit 12 determines that a search request has been received (step S20: Yes), the processing unit 12 searches for two or more confidential prompts and provides the search results to the user U (step S21).

[0201] When the processing of step S21 is completed or when it is determined that a search request has not been received (step S20: No), the processing unit 12 determines whether a selection request has been received (step S22). When it is determined that a selection request has been received (step S22: Yes), the processing unit 12 selects the confidential prompt identified in the selection request as the selection prompt, and generates generation information, which is information according to the selection prompt, using the generation AI (step S23).

[0202] Then, the processing unit 12 provides the generated information or information based on the generated information as provided information to the user U (step S24). After that, the processing unit 12 performs a billing process for the user U to whom the provided information has been provided (step S25).

[0203] When the processing of step S25 is completed or when it is determined that a selection request has not been received (step S22: No), the processing unit 12 determines whether a tentative selection request has been received (step S26). When it is determined that a tentative selection request has been received (step S26: Yes), the processing unit 12 generates candidate generation information using the generation AI (step S27). Then, the processing unit 12 provides the candidate generation information or information based on the candidate generation information to the user U as candidate provision information (step S28).

[0204] When the processing of step S28 is completed or when it is determined that a tentative selection request has not been received (step S26: No), the processing unit 12 determines whether or not another request has been received (step S29). When it is determined that another request has been received (step S29: Yes), the processing unit 12 performs another process (step S30).

[0205] When the processing of step S30 is completed or when it is determined that no other request has been received (step S29: No), the processing unit 12 determines whether or not the operation end timing has arrived (step S31). The processing unit 12 determines that the operation end timing has arrived when, for example, the power of the information processing device 1 is turned off.

[0206] If the processing unit 12 determines that the operation end time has not yet arrived (step S31: No), it proceeds to step S20, and if it determines that the operation end time has arrived (step S31: Yes), it terminates the processing shown in Figure 6.

[0207] [5. Modifications] In the above example, the user setting information included in the search request includes information indicating a string of characters indicating the actions or processes that user U wants the generated AI to perform, but instead of or in addition to such information, it may also include information indicating the results that user U wants the generated AI to perform.

[0208] In this case, the confidential prompt table may further include, as confidential prompt information, generated information or provided information obtained from the confidential prompt using a generation AI, and its vector information. In this case, the search unit 32 retrieves, as search results, confidential prompts from the confidential prompt table corresponding to the top m (m is 2 or more) generated information or provided information whose vector similarity to the user-set information is equal to or greater than a threshold value or whose similarity is highest.

[0209] The search unit 32 can also calculate a score by weighting and adding the vector similarity between the user-set information and the heading information and the vector similarity between the user-set information and the generated information or provided information, and obtain from the confidential prompt table as search results confidential prompts corresponding to the top m (m is 2 or more) combinations of heading information and generated information or generated information whose scores are above a threshold or whose similarities are highest.

[0210] The search unit 32 can also search for two or more confidential prompts from the confidential prompt table based on attribute information, which is information indicating the attributes of the user U of the terminal device 2 that sent the search request, and user setting information. The attributes of the user U include, for example, the demographic attributes and psychographic attributes of the user U.

[0211] For example, the search unit 32 can provide the user U with, as search results, confidential prompts among multiple confidential prompts according to the user setting information, whose average value of evaluations by other users U who have attributes that are identical to or similar to the attributes of the user U of the terminal device 2 that sent the search request is above a threshold or in the top m (m is 1 or greater) of the multiple confidential prompts according to the user setting information.

[0212] In addition, the search unit 32 can provide the user U with, as search results, confidential prompts that have been used by other users U having attributes that are identical to or similar to the attributes of the user U of the terminal device 2 that sent the search request, above a threshold or in the top m (m is 1 or greater) of the number of times that they have been used by such other users U, among multiple confidential prompts according to the user setting information.

[0213] Furthermore, when the confidential prompt is a prompt that uses a generation AI in a chat format, the determination unit 37 can also determine the amount to be charged for the use of the confidential prompt based on the input / output history performed in the chat format.

[0214] For example, the determination unit 37 can determine a higher fee for the use of such a confidential prompt the more or less the number of inputs and outputs, or can determine a higher fee for the use of such a confidential prompt the more or less the number of tokens input as a string of characters into the generation AI.

[0215] The determination unit 37 can also input information including the input / output history and instruction information, which is character string information indicating instructions for determining the accuracy and value of the confidential prompt from the input / output history, as input information to the generation AI, and cause the generation AI to output information indicating the accuracy and value of the confidential prompt. In this case, the determination unit 37 can determine a higher fee for the use of a confidential prompt with higher accuracy and value.

[0216] Furthermore, if an upper limit on the charge amount is set for each user U at the request of the user U, the determination unit 37 can also search for a confidential prompt with a charge amount that does not exceed the upper limit.

[0217] [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. 7. Fig. 7 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] [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.

[0224] 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.

[0225] 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.

[0226] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0227] [8. Effects] As described above, the information processing device 1 according to the embodiment includes a selection unit 33, a generation unit 34, and a provision unit 35. The selection unit 33 selects a prompt in response to a request from the user U from among a plurality of prompts whose details are concealed from the user U. The generation unit 34 inputs information including the prompt selected by the selection unit 33 to the generation AI, causing the generation AI to generate information in response to the prompt selected by the selection unit 33. The provision unit 35 provides the information generated by the generation unit 34 or information based on that information to the user U as provided information. This allows the information processing device 1 to generate information using a more appropriate prompt in response to the request of the user U.

[0228] The information processing device 1 also includes a billing unit 36 ​​that performs billing processing for the user U to whom the provided information is provided by the providing unit 35. This enables the information processing device 1 to promote the provision of prompts in response to the request of the user U, and to generate information using more appropriate prompts in response to the request of the user U.

[0229] The information processing device 1 also includes a determination unit 37 that determines the amount of money charged for the use of the prompt. This allows the information processing device 1 to promote the provision of prompts in response to the user U's requests.

[0230] Furthermore, the determination unit 37 determines the charge amount based on the evaluation of the provided information by the user U. This enables the information processing device 1 to promote the provision of more appropriate prompts in response to the user U's request.

[0231] Furthermore, the generation unit 34 causes the generation AI to generate information corresponding to each of the plurality of prompts, the provision unit 35 provides the user U with selection information including information corresponding to each of the plurality of prompts generated by the generation unit 34 or information based on each of the information, and the selection unit 33 selects a prompt specified by the user U from the plurality of prompts based on the selection information generated by the generation unit 34 as a prompt corresponding to the request of the user U. This allows the information processing device 1 to more appropriately generate information using a more appropriate prompt corresponding to the request of the user U.

[0232] The information processing device 1 also includes a reception unit 30 that receives a search request from a user U, and a search unit 32 that searches for two or more prompts as multiple prompts in response to the search request received by the reception unit 30. The provision unit 35 provides the user U with each of the multiple prompts searched for by the search unit 32 in a selectable manner. This allows the information processing device 1 to more appropriately generate information using a more appropriate prompt in response to the user U's request.

[0233] Furthermore, the selection unit 33 selects the prompt specified by the user U as the prompt in response to the request of the user U. This allows the information processing device 1 to more appropriately generate information using a more appropriate prompt in response to the request of the user U.

[0234] Furthermore, the search unit 32 searches for a plurality of prompts using explanatory text that explains the function of each prompt, which allows the information processing device 1 to more appropriately generate information using more appropriate prompts that meet the request of the user U.

[0235] 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.

[0236] 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]

[0237] 1. Information processing equipment 2,3 Terminal equipment 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 21 Secret prompt memory unit 30 Reception 31 Acquisition Department 32 Search Section 33 Selection section 34 Generation part 35 Providing Department 36 Billing Department 37 Decision Section 100 Information Processing Systems N Network

Claims

1. a selection unit that selects a prompt designated by a user as a prompt in response to a request from the user from among a plurality of prompts that present an outline of a function while the details are concealed from the user; a generation unit that inputs information including the prompt selected by the selection unit to a generation AI and causes the generation AI to generate information according to the prompt selected by the selection unit; a providing unit that provides the information generated by the generating unit or information based on the information to the user as provided information.

1. An information processing device comprising:

2. A selection unit that selects a prompt according to a request from a user from among a plurality of prompts whose details are concealed from the user; a generation unit that inputs information including the prompt selected by the selection unit to a generation AI and causes the generation AI to generate information according to the prompt selected by the selection unit; a providing unit that provides the information generated by the generating unit or information based on the information to the user as provided information, The generation unit causing the generation AI to generate information in response to each of the plurality of prompts; The providing unit providing the user with selection information including information corresponding to each of the plurality of prompts generated by the generation unit or information based on each of the information; The selection unit a prompt designated by the user from among the plurality of prompts based on the selection information generated by the generating unit, as a prompt in response to a request from the user; 1. An information processing device comprising:

3. a charging unit that performs charging processing for the user to whom the provision information is provided by the provision unit; 3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

4. a determination unit for determining a charge for using the prompt; 4. The information processing apparatus according to claim 3,

5. The determination unit The amount of charge is determined based on the user's evaluation of the provided information.

5. The information processing apparatus according to claim 4,

6. a reception unit that receives a search request from the user; a search unit configured to search for two or more prompts corresponding to the search request received by the reception unit as the plurality of prompts, The providing unit and providing the user with a selectable version of each of the plurality of prompts retrieved by the search unit.

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

7. The search unit Searching the plurality of prompts using a description that explains the function of each prompt 7. The information processing apparatus according to claim 6,

8. 1. A computer-implemented information processing method, comprising: a selection step of selecting a prompt designated by the user as a prompt in response to a request from the user from among a plurality of prompts in which an outline of a function is presented while details are concealed from the user; a generating step of inputting information including the prompt selected by the selection step into a generating AI and causing the generating AI to generate information according to the prompt selected by the selection step; a providing step of providing the information generated by the generating step or information based on the information to the user as provided information. An information processing method comprising:

9. A computer-implemented information processing method, comprising: a selection step of selecting a prompt according to a request from the user from among a plurality of prompts whose details are concealed from the user; a generating step of inputting information including the prompt selected by the selection step into a generating AI and causing the generating AI to generate information according to the prompt selected by the selection step; a providing step of providing the information generated by the generating step or information based on the information to the user as provided information, The generating step includes: causing the generation AI to generate information in response to each of the plurality of prompts; The providing step includes: providing the user with selection information including information corresponding to each of the plurality of prompts generated by the generating step or information based on each of the information; The selection step includes: A prompt designated by the user is selected from the plurality of prompts based on the selection information generated in the generating step as a prompt in response to the user's request. An information processing method comprising:

10. a selection step of selecting a prompt designated by the user as a prompt in response to a request from the user from among a plurality of prompts in which an outline of a function is presented while details are concealed from the user; a generation step of inputting information including the prompt selected by the selection step into a generation AI and causing the generation AI to generate information according to the prompt selected by the selection step; a provision procedure for providing the information generated by the generation procedure or information based on the information to the user as provision information; An information processing program characterized by:

11. A selection step of selecting a prompt according to a request from a plurality of prompts whose details are concealed from the user; a generation step of inputting information including the prompt selected by the selection step into a generation AI and causing the generation AI to generate information according to the prompt selected by the selection step; a provision step of providing the information generated by the generation step or information based on the information generated by the generation step to the user as provision information; The generating procedure includes: causing the generation AI to generate information in response to each of the plurality of prompts; The providing step comprises: providing the user with selection information including information corresponding to each of the plurality of prompts generated by the generating procedure or information based on each of the information; The selection procedure comprises: A prompt designated by the user is selected from the plurality of prompts based on the selection information generated by the generation procedure as a prompt in response to a request from the user. An information processing program characterized by:

Images