Information management system, information management method, and program

Abstract

To enable presentation of more appropriate response information to a user in response to request information from the user.SOLUTION: An information management system is provided, comprising: a relevant information generation unit configured to input a prompt containing the input information entered by a user to a trained generative model so as to generate one or more pieces of relevant information related to the input information; and a response generation unit configured to generate response information in response to request information from the user. The one or more pieces of relevant information are presented to the user and serve as candidates for the request information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a technique for presenting more appropriate response information in response to request information from a user. [Background technology]

[0002] In recent years, a technology has been proposed that uses large-scale language models capable of natural language processing to output information based on user input. Fine-tuning large-scale language models using dialogue datasets enables dialogue-style interaction. By inputting a question into such a large-scale language model, a user can obtain an answer to the question. Specifically, a prompt containing a question from the user is input into the large-scale language model.

[0003] The answer sentence output by a large-scale language model depends heavily on the content of the question entered by the user. For example, if the vocabulary choice or wording in the question differs, the answer from the large-scale language model may also differ. Therefore, depending on the content of the question, an answer sentence that is not the answer desired by the user may be output. As described above, there is a problem in that the output from a large-scale language model may be inappropriate.

[0004] Therefore, various techniques have been proposed for optimizing the output from a large-scale language model. For example, Patent Document 1 discloses a configuration in which reference information related to a question entered by a user is generated, and a prompt including the question and the reference information is input to a large-scale language model, thereby obtaining an answer to the question. Patent Document 1 certainly appears to be able to generate a more specific answer than a configuration in which a prompt including only a question is generated. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 7313757 Summary of the Invention [Problem to be solved by the invention]

[0006] However, the technology of Patent Document 1 has room for further improvement in terms of presenting a user with an answer that is appropriate to the question. In consideration of the above circumstances, the present invention aims to present a user with more appropriate response information in response to request information from the user. [Means for solving the problem]

[0007] A terminal device according to one example of the present invention includes a reception unit that receives input information entered by a user and an acquisition unit that acquires response information generated in response to request information corresponding to the input information, wherein the response information is information generated in response to one or more first output information generated by a trained first generation model in response to a first prompt including the request information, and one or more second output information generated by a trained second generation model in response to a second prompt including the request information.

[0008] An information providing device according to one example of the present invention includes a response generation unit that generates response information to a first prompt including request information corresponding to input information entered by a user, in accordance with one or more first output information generated by a trained first generation model in response to a first prompt including the request information, and one or more second output information generated by a trained second generation model in response to a second prompt including the request information.

[0009] An information collection system according to one example of the present invention is a system capable of communicating with the terminal device described above, and includes a first acquisition unit that acquires an evaluation of the validity identified for the response information, the request information, and the response information, and a collection unit that stores the evaluation, the request information, and the response information in a storage device.

[0010] An information collection system according to one example of the present invention is a system capable of communicating with the terminal device described above, and includes a first acquisition unit that acquires related information related to the input information generated by a trained fourth generation model in response to a fourth prompt including the input information, a second acquisition unit that acquires answer information generated by a trained fifth generation model in response to a fifth prompt including the related information, and a collection unit that stores the related information and the answer information in a storage device.

[0011] The information processing system of the present invention includes a receiving unit that receives input information entered by a user, a response generation unit that generates response information to the request information in accordance with one or more pieces of first output information generated by a trained first generation model in response to a first prompt including request information corresponding to the input information, and one or more pieces of second output information generated by a trained second generation model in response to a second prompt including the request information, and an acquisition unit that acquires the response information.

[0012] An information acquisition method according to one example of the present invention is realized by a computer system that accepts input information entered by a user and acquires response information generated in response to request information corresponding to the input information, the response information being information generated in response to one or more first output information generated by a trained first generative model in response to a first prompt including the request information and one or more second output information generated by a trained second generative model in response to a second prompt including the request information.

[0013] A program according to one example of the present invention causes a computer system to function as a reception unit that receives input information entered by a user and an acquisition unit that acquires response information generated in response to request information corresponding to the input information, and causes the computer system to function as information generated in response to one or more first output information generated by a trained first generation model in response to a first prompt including the request information and one or more second output information generated by a trained second generation model in response to a second prompt including the request information. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a block diagram illustrating a configuration of an information processing system according to a first embodiment. [Figure 2] 2 is a block diagram illustrating the configuration of a terminal device according to the first embodiment. FIG. [Figure 3] 3 is a block diagram illustrating a functional configuration of a control device in the terminal device according to the first embodiment. FIG. [Figure 4] 1 is a block diagram illustrating a configuration of an information generating system according to a first embodiment. [Figure 5] 2 is a block diagram illustrating an example of the functional configuration of a control device in the information generation system according to the first embodiment. FIG. [Figure 6] 1 is a block diagram illustrating a configuration of an information generating system according to a first embodiment. [Figure 7] 1 is a block diagram illustrating a configuration of an information acquisition device according to a first embodiment. [Figure 8] FIG. 2 is a block diagram illustrating the configuration of a first processing device according to the first embodiment. [Figure 9] 3 is a block diagram illustrating a functional configuration of a control device in a first processing device according to the first embodiment. FIG. [Figure 10] FIG. 2 is a block diagram illustrating the configuration of a second processing device according to the first embodiment. [Figure 11] 4 is a block diagram illustrating a functional configuration of a control device in a second processing device according to the first embodiment. FIG. [Figure 12] 1 is a block diagram illustrating a configuration of an information providing device according to a first embodiment. [Figure 13] 2 is a block diagram illustrating a functional configuration of a control device in the information providing device according to the first embodiment. FIG. [Figure 14] 10 is a flowchart illustrating a procedure of processing executed by the entire information processing system. [Figure 15] FIG. 3 is a diagram showing input information and related information according to the first embodiment. [Figure 16]4 is a flowchart illustrating a procedure of a process executed by the information providing system according to the first embodiment. [Figure 17] 4A and 4B are diagrams showing first output information and second output information according to the first embodiment; [Figure 18] 4 is a flowchart illustrating a procedure of a process executed by a response generation unit of the information providing device according to the first embodiment. [Figure 19] FIG. 10 is a block diagram illustrating the configuration of an information processing system according to a second embodiment. [Figure 20] FIG. 10 is a block diagram illustrating a configuration of an information collection system according to a second embodiment. [Figure 21] FIG. 10 is a block diagram illustrating an example of the functional configuration of a control device in an information collection system according to a second embodiment. [Figure 22] FIG. 11 is a block diagram illustrating a functional configuration of a control device in an information collection system according to a third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0015] First Embodiment 1 is a block diagram illustrating the configuration of an information processing system 100 according to the first embodiment. The information processing system 100 according to the first embodiment is a computer system including a terminal device 10 and an information management system 20. The information management system 20 provides various types of information to a user U of the terminal device 10. The information management system 20 includes an information generation system 30 and an information provision system 40.

[0016] In general terms, the information management system 20 provides information R (hereinafter referred to as "response information") in response to request information from a user U to the user U. Typically, the request information is information for requesting information desired by the user U, and the response information R is information indicating a response to the request information (typically, information requested by the request information). In the following explanation, a case will be exemplified in which the request information is an inquiry regarding a specific target, and the response information R is a reply to the inquiry. The specific target is, for example, various products or services. In the first embodiment, for convenience, a case will be exemplified in which a specific product (hereinafter referred to as "target product") is the specific target. The target product is, for example, software used for a specific purpose.

[0017] The terminal device 10 and the information management system 20 can communicate with each other via a communication network 900 such as a mobile communication network or the Internet.

[0018] The terminal device 10 is realized by, for example, a portable information device such as a smartphone or a tablet terminal, or a portable or stationary information device such as a personal computer. On the other hand, the information generating system 30 and the information providing system 40 are realized by, for example, a server system.

[0019] [Terminal device 10] 2 is a block diagram illustrating the configuration of the terminal device 10. As illustrated in FIG. 2, the terminal device 10 includes a control device 11, a storage device 12, a communication device 13, a display device 14, and an operation device 15.

[0020] The control device 11 is one or more processors that control the operation of the terminal device 10. Specifically, the control device 11 is configured by one or more types of processors, such as a central processing unit (CPU), a graphics processing unit (GPU), a sound processing unit (SPU), a digital signal processor (DSP), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC).

[0021] The storage device 12 is one or more memories that store programs executed by the control device 11 and various data used by the control device 11. For example, a known recording medium such as a semiconductor recording medium or a magnetic recording medium, or a combination of multiple types of recording media, is used as the storage device 12. Note that, for example, a portable recording medium that is detachable from the terminal device 10, or a recording medium that the control device 11 can access via the communication network 900 (for example, cloud storage) may be used as the storage device 12.

[0022] The communication device 13 is a communication device that communicates with the information management system 20 via the communication network 900. Note that the communication device 13, which is separate from the terminal device 10, may be connected to the terminal device 10 by wire or wirelessly.

[0023] The display device 14 displays various types of information under the control of the control device 11. For example, various display panels such as a liquid crystal display panel or an organic EL panel are used as the display device 14. Note that the operation device 15 or the display device 14, which are separate from the information processing system 100, may be connected to the terminal device 10 by wire or wirelessly.

[0024] The operation device 15 is an input device that accepts operations by the user U. For example, an operator operated by the user U or a touch panel that detects contact by the user U is used as the operation device 15. Note that the operation device 15, which is separate from the terminal device 10, may be connected to the terminal device 10 by wire or wirelessly. The operation device 15 accepts various pieces of information that the user U inputs by operating the operation device 15. Note that the operation device 15 may be a sound pickup device (microphone) that accepts input from the user U by voice.

[0025] 2 is a block diagram illustrating functions realized by the control device 11 executing a program stored in the storage device 12. The control device 11 realizes a plurality of functions (a reception unit 111, a prompt generation unit 112, an acquisition unit 113, and a presentation unit 114) for providing a response to an inquiry.

[0026] The reception unit 111 receives various pieces of information input by the user U by operating the operation device 15. First, the reception unit 111 receives input information input by the user U. The input information is information for requesting information desired by the user U. The input information in the first embodiment is information indicating an inquiry about the target product. The content of the inquiry (information desired by the user U) is arbitrary, and may be, for example, content regarding how to use the target product, a specific function of the target product, or an error that occurred while using the target product. The user U inputs a sentence (text) indicating the inquiry by operating the operation device 15.

[0027] Second, the receiving unit 111 receives request information input by the user U. The request information in the first embodiment is information selected by the user U from the input information and one or more pieces of related information G. In other words, the input information and one or more pieces of related information G are candidates for the request information.

[0028] Like the input information, the related information G is information for requesting desired information by the user U, and is information related to the input information. The related information G is typically information indicating the same type of content as the input information (e.g., an inquiry). In other words, the content of the input information and the content of the related information G are similar. The requested information, which is information selected by the user U from the input information and one or more pieces of related information G related to the input information, is information corresponding to the input information. Details of the related information G will be described later.

[0029] Third, the receiving unit 111 receives identification information input by the user U. The identification information is, for example, various information such as the name, type, version, and product number of the target product. Note that the identification information may include information for identifying the user U of the target product.

[0030] The prompt generation unit 112 generates a prompt P including various pieces of information input by the user U. The prompt P is a request to the information management system 20. The prompt P generated by the prompt generation unit 112 is transmitted from the communication device 13 to the information management system 20.

[0031] First, the prompt generation unit 112 generates a prompt P1 (an example of a "third prompt") that includes input information. Specifically, the prompt P1 is a prompt for requesting one or more pieces of related information G that are related to the input information. The prompt P1 is transmitted to the information management system 20 (information generation system 30). Note that the prompt P1 that includes input information includes a case where the prompt P1 directly includes the input information and a case where the prompt P1 indirectly includes the input information as information corresponding to the input information (for example, information that has been processed or modified from the input information).

[0032] Second, the prompt generator 112 generates prompts Pz2 and P3 that include request information. Note that prompts Pz2 and P3 that include request information include prompts that directly include the request information and prompts that indirectly include the request information as information corresponding to the request information (for example, information that has been processed or modified from the request information).

[0033] Specifically, each of prompts Pz2 and P3 is a prompt for requesting output information W for requested information. The output information W is information that is a candidate for response information R (i.e., an answer). In other words, prompts Pz2 and P3 are prompts for requesting response information R.

[0034] The prompts Pz2 and P3 are sent to the information management system 20 (information providing system 40). One or more pieces of output information (hereinafter referred to as "first output information") W1 are generated for the prompt Pz2, and one or more pieces of output information (hereinafter referred to as "second output information") W2 are generated for the prompt P3. The multiple pieces of output information W (W1, W2) generated by the information management system 20 are used to generate response information R in response to the request information. Details of the output information W and the response information R will be described later.

[0035] In the first embodiment, one or more pieces of first output information W1 are actually generated for prompt P2 generated from prompt Pz2. The generation of prompt P2 is performed in information providing system 40. In the first embodiment, a configuration is exemplified in which the information included in prompt P2 is different from the information included in prompt P3. Request information and identification information are included in both prompt P2 and prompt P3.

[0036] Meanwhile, the prompt P2 includes, in addition to the request information and the identification information, reference information that is referenced when generating the first output information W1. In the information providing system 40 described below, the prompt P2 is generated by adding the reference information to the prompt Pz2 transmitted from the terminal device 10. The reference information is information that the information processing system 100 references when generating the first output information W1 (candidate for response information). Specifically, the reference information is, for example, information that provides a detailed description of the target product. For example, a document describing the target product's use, purpose, functions, configuration, technical specifications, and usage and setting methods is an example of the reference information. In the first embodiment, the prompt P2 is an example of a "first prompt," and the prompt P3 is an example of a "second prompt."

[0037] The acquisition unit 113 acquires the information generated by the various prompts P1-P3 described above. The acquisition unit 113 of the first embodiment acquires the information generated by the prompts P1-P3 by receiving the information from the information management system 20 via the communication device 13.

[0038] First, the acquisition unit 113 acquires one or more pieces of related information G generated in response to a prompt P1 including input information. Second, the acquisition unit 113 acquires response information R generated in response to request information that is information selected by a user U from the input information and the one or more pieces of related information G.

[0039] The presentation unit 114 presents various types of information (for example, related information G and response information R) to the user U. Specifically, the presentation unit 114 presents various types of information to the user U by displaying them on the display device 14. However, the presentation of information by the presentation unit 114 is not limited to presentation by display, and may be presentation by voice, for example.

[0040] First, the presentation unit 114 presents one or more pieces of related information G generated by the prompt P1 to the user U. Specifically, one or more pieces of related information G are presented to the user U together with the input information.

[0041] [Information Generation System 30] 4 is a block diagram illustrating the configuration of the information generation system 30. The information generation system 30 is a device for generating one or more pieces of related information G related to input information. For example, the information generation system 30 is exemplified by a server system that can communicate with the terminal device 10 via a communication network 900.

[0042] As illustrated in FIG. 4, the information generating system 30 includes, for example, a control device 31, a storage device 32, and a communication device 33.

[0043] The control device 31 is one or more processors that control the operation of the information generation system 30. Specifically, the control device 31 is configured by one or more types of processors, such as a central processing unit (CPU), a graphics processing unit (GPU), a sound processing unit (SPU), a digital signal processor (DSP), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC).

[0044] The storage device 32 is one or more memories that store programs executed by the control device 31 and various data used by the control device 31. For example, a known recording medium such as a semiconductor recording medium or a magnetic recording medium, or a combination of multiple types of recording media, is used as the storage device 32. For example, a portable recording medium that is detachable from the information generation system 30, or a recording medium that the control device 31 can access via the communication network 900 (for example, cloud storage) may be used as the storage device 32.

[0045] The communication device 33 is a communication device that communicates with the terminal device 10 via the communication network 900. Note that the communication device 33, which is separate from the information generation system 30, may be connected to the information generation system 30 by wire or wirelessly.

[0046] 5 is a block diagram illustrating functions realized by the control device 31 executing a program stored in the storage device 32. The control device 31 of the first embodiment realizes a plurality of functions (an acquisition unit 311, a related information generation unit 312) for generating one or more pieces of related information G related to input information.

[0047] The acquiring unit 311 acquires input information transmitted from the terminal device 10 by receiving it via the communication device 33. Specifically, the acquiring unit 311 acquires a prompt P1 including the input information.

[0048] The related information generation unit 312 generates one or more pieces of related information G related to the input information. In the first embodiment, a trained generative model M1 is used to generate the related information G. The related information generation unit 312 generates one or more pieces of related information G by inputting a prompt P1 including the input information to the generative model M1. In other words, the prompt P1 is a prompt that instructs the generative model M1 to generate one or more pieces of related information G related to the input information.

[0049] The one or more pieces of related information G generated by the related information generation unit 312 are transmitted to the terminal device 10 by the communication device 33 and presented to the user U. As described above, the one or more pieces of related information G are presented to the user U together with the input information.

[0050] The generative model M1 is configured, for example, as a Transformer model (sequence transformation model). However, the generative model M1 may be configured as any other type of neural network (for example, a recurrent neural network or a convolutional neural network). The generative model M1 may also be configured by combining multiple types of deep neural networks.

[0051] In the first embodiment, a configuration is exemplified in which a large-scale language model (LLM) that has been trained in advance using a large amount of text data and in which the occurrence probability of words is modeled is used as the generative model M1. The large-scale language model is capable of natural language processing. In particular, it is preferable to use an interactive large-scale language model that has been fine-tuned using a dialogue dataset as the generative model M. The interactive large-scale language model is capable of generating dialogue-style text. As the interactive large-scale language model, any known model such as ChatGPT (manufactured by OpenAI), Bard (manufactured by Google), or Bing AI (manufactured by Microsoft) can be used as the generative model M1. It is preferable that the generative model M1 is fine-tuned using a dataset including multiple combinations of expected input information (prompt P1) and related information G (answers) for the input information. Note that a trained model that has learned the relationship between the input information and the related information G through machine learning may be used as the generative model M1.

[0052] As can be understood from the above explanation, the generative model M1 outputs statistically valid related information G for the input information. Note that the multiple parameters that define the generative model M1 are set by machine learning (particularly deep learning) using multiple training data and are stored in the storage device 32. Note that the generative model M1 can refer to a database D2, which will be described later in the third embodiment, and the information in the database D2 can be used as training data for the generative model M1.

[0053] [Information Provision System 40] 6 is a block diagram illustrating the configuration of an information providing system 40. The information providing system 40 is a device that generates response information R in response to request information corresponding to input information. That is, a response to an inquiry is generated by the information providing system 40. For example, a computer system that can communicate with the terminal device 10 via a communication network 900 is exemplified as the information providing system 40.

[0054] 6, the information providing system 40 includes a first processing device 41, a second processing device 42, an information providing device 43, and an information acquiring device 44. The information providing device 43 can communicate with each of the first processing device 41 and the second processing device 42 via a communication network 900.

[0055] The information acquisition device 44 is a server system for generating a prompt P2 from a prompt Pz2 transmitted from the terminal device 10. The information acquisition device 44 of the first embodiment generates the prompt P2 by adding reference information to the prompt Pz2. That is, the prompt P2 is a prompt that includes request information, identification information, and reference information. The information acquisition device 44 can communicate with the terminal device 10 and the first processing device 41 via the communication network 900. For example, the information acquisition device 44 is configured by a control device 441, a storage device 442, and a communication device 443.

[0056] The communication device 443 receives the prompt Pz2 transmitted from the terminal device 10, and transmits to the first processing device 41 a prompt P2 generated from the prompt Pz2.

[0057] The control device 441 generates a prompt P2 from the prompt Pz2. Specifically, the control device 441 acquires reference information corresponding to the request information and identification information included in the prompt Pz2, and adds the reference information to the prompt Pz2 to generate the prompt P2. The method for acquiring the reference information is not particularly limited, but the following description will exemplify a configuration in which the control device 441 acquires the reference information using a data table (hereinafter referred to as a "reference information table") Dq registered in advance in the storage device 442.

[0058] In the reference information table Dq, for example, reference information is registered in association with each combination of identification information and a character string that may be included in the request information (hereinafter referred to as a "target character string"). The target character string that may be included in the request information is, for example, a character string (including a word) that represents a function that may be the subject of an inquiry about the target product. As illustrated in FIG. 7, in the reference information table Dq, different reference information is associated with each combination of identification information and a target character string. Common reference information may be registered for multiple combinations, or multiple pieces of reference information may be registered for one combination. Then, reference information in which the character string in the request information included in the prompt Pz2 matches (or has high similarity to) the identification information is acquired in the reference information table Dq. However, the control device 441 may acquire reference information by inputting the request information and the identification information into a generative model. The generative model may be configured, for example, like the generative model M1, by using a Transformer model or any form of neural network.

[0059] 8 is a block diagram illustrating the configuration of the first processing device 41. The first processing device 41 is a server system that generates one or more pieces of first output information W1 in response to a prompt P2. As described above, the first output information W1 is a candidate for response information R (answer). Specifically, the first processing device 41 includes a control device 411, a storage device 412, and a communication device 413.

[0060] The control device 411 is one or more processors that control the operation of the first processing device 41. Specifically, the control device 411 is configured by one or more types of processors, such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an SPU (Sound Processing Unit), a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array), or an ASIC (Application Specific Integrated Circuit).

[0061] The storage device 412 is one or more memories that store programs executed by the control device 411 and various data used by the control device 411. For example, a well-known recording medium such as a semiconductor recording medium or a magnetic recording medium, or a combination of multiple types of recording media, is used as the storage device 412. For example, a portable recording medium that is detachable from the information providing system 40, or a recording medium that the control device 411 can access via the communication network 900 (for example, cloud storage) may be used as the storage device 412.

[0062] The communication device 413 is a communication device that communicates with the terminal device 10 via the communication network 900. The communication device 413, which is separate from the information providing system 40, may be connected to the first processing device 41 by wire or wirelessly.

[0063] 9 is a block diagram illustrating functions realized by the control device 411 executing a program stored in the storage device 412. The control device 411 of the first embodiment realizes a plurality of functions (an acquisition unit 141, a processing unit 142) for generating one or more pieces of first output information W1 in accordance with request information.

[0064] The acquisition unit 141 acquires the request information transmitted from the information acquisition device 44 by receiving it via the communication device 413. Specifically, the acquisition unit 141 acquires the prompt P2 transmitted from the information acquisition device 44. As described above, the prompt P2 includes reference information in addition to the request information and identification information.

[0065] The processing unit 142 generates one or more pieces of first output information W1 in response to the request information. A trained generation model M2 is used to generate the first output information W1. Specifically, the processing unit 142 generates the one or more pieces of first output information W1 by inputting a prompt P2 acquired by the acquisition unit 141 into the generation model M2. The generation model M2 of the first embodiment generates the first output information W1 in response to the request information by taking into account the identification information and reference information. In other words, the prompt P2 is a prompt that instructs the generation of one or more pieces of first output information W1 in response to the request information based on the identification information and reference information. The generation model M2 will be described in detail later. The first output information W1 generated by the processing unit 142 is transmitted to the information providing device 43 by the communication device 413.

[0066] 10 is a block diagram illustrating the configuration of the second processing device 42. The second processing device 42 is a server system that generates one or more pieces of second output information W2 in response to a prompt P3. As described above, the second output information W2 is a candidate for response information R (answer), similar to the first output information W1. Specifically, the second processing device 42 includes a control device 421, a storage device 422, and a communication device 423.

[0067] The control device 421, storage device 422, and communication device 423 may have the same configuration as that described for the control device 411, storage device 412, and communication device 413 of the first processing device 41, for example.

[0068] 11 is a block diagram illustrating functions realized by the control device 421 executing a program stored in the storage device 422. The control device 421 of the first embodiment realizes a plurality of functions (an acquisition unit 241, a processing unit 242) for generating one or more pieces of second output information W2 in accordance with request information.

[0069] The acquisition unit 241 acquires request information transmitted from the terminal device 10 by receiving it via the communication device 423. Specifically, the acquisition unit 241 acquires a prompt P3 transmitted from the terminal device 10. As described above, the prompt P3 includes request information and identification information. Note that in the first embodiment, reference information is not included in the prompt P3.

[0070] The processing unit 242 generates one or more pieces of second output information W2 in response to the request information. A trained generative model M3 is used to generate the second output information W2. Specifically, the processing unit 242 generates one or more pieces of second output information W2 by inputting a prompt P3 acquired by the acquisition unit 241 into the generative model M3. The generative model M3 of the first embodiment generates one or more pieces of second output information W2 in response to the request information by taking into account the identification information. In other words, the prompt P3 is a prompt that instructs the generation of one or more pieces of second output information W2 in response to the request information based on the identification information. The second output information W2 generated by the processing unit 242 is transmitted to the information providing device 43 by the communication device 423.

[0071] The following describes the generative models M2 and M3. Similar to the generative model M1 described above, the generative models M2 and M3 are configured, for example, as a Transformer model. In the first embodiment, a large-scale language model that has been trained in advance using a large amount of text data (training data) and in which the occurrence probabilities of words are modeled is used as the generative models M2 and M3.

[0072] The large-scale language model is capable of natural language processing. In particular, it is preferable to use an interactive large-scale language model, which is fine-tuned using a dialogue dataset, as the generative models M2 and M3. The interactive large-scale language model is capable of generating dialogue-style text. As the interactive large-scale language model, any known model such as ChatGPT (manufactured by OpenAI), Bard (manufactured by Google), or Bing AI (manufactured by Microsoft) can be used as the generative models M2 and M3. The generative models M2 and M3 may be the same type of model or different types of models. Note that various parameters defining the generative models M2 and M3 are set by machine learning (particularly deep learning) using multiple training data and stored in the storage devices 412 and 422.

[0073] To establish the generative model M2, various data related to the target product are used as training data. In the first embodiment, for example, a data set including multiple combinations of expected request information (prompt P2) and first output information W1 (answer) corresponding to the request information is used as the training data. In particular, highly reliable information related to the target product is preferably used as the training data. Note that the generative model M2 may be established by fine-tuning a generative model previously trained on a large amount of text data using training data related to the target product.

[0074] Highly reliable information about the target product is, for example, information collected by the information collection system 50 (information stored in databases D1 and D2) described below. Also, for example, information made public or collected by the manufacturer or seller of the target product is also highly reliable information about the target product. Note that the generative model M2 can also refer to the information collected by the information collection system 50 when generating the first output information W1.

[0075] To establish the generative model M3 of the first embodiment, various types of publicly available data (e.g., published on websites, in books, academic papers, and newspapers) are primarily used as training data. The training data used to establish the generative model M3 may include publicly available information about the target product, but it is also information covering a wide range of content other than the target product. The generative model M3 of the first embodiment is trained with a wider range of information than the generative model M2, but can also be said to be a model that has not been trained using reliable information about the target product as training data, as the generative model M2 has.

[0076] As can be understood from the above explanation, in the first embodiment, the generative models M2 and M3 have different training data. The generative model M2 uses information specialized in the target product (i.e., information selected as related to a specific target) as training data, while the generative model M3 uses a wide range of publicly available information as training data. In other words, the training data used to train the generative model M2 is more limited (limited in content) than the training data used to train the generative model M3. The generative model M2 can generate an answer (first output information W1) specialized in information about the target product, while the generative model M3 can generate an answer (second output information W2) that takes into account a wide range of information other than the target product. However, in establishing the generative model M2, in addition to various data related to the target product, a wide range of publicly available information may also be used as training data, as with the generative model M3.

[0077] 12 is a block diagram illustrating an example of the configuration of the information providing device 43. The information providing device 43 is a server system that generates response information R in response to request information. Specifically, the information providing device 43 includes a control device 431, a storage device 432, and a communication device 413.

[0078] The control device 431, storage device 432, and communication device 433 may have the same configuration as that described for the control device 411, storage device 412, and communication device 413 of the first processing device 41, for example.

[0079] 13 is a block diagram illustrating functions realized by the control device 431 executing a program stored in the storage device 432. The control device 431 of the first embodiment realizes a plurality of functions (an acquisition unit 341, an index calculation unit 342, and a response generation unit BR43) for generating response information R in response to request information.

[0080] The acquisition unit 341 acquires one or more pieces of first output information W1 transmitted from the first processing device 41 and one or more pieces of second output information W2 transmitted from the second processing device 42 by receiving them via the communication device 433.

[0081] The index calculation unit 342 identifies an index K indicating the validity of each of the one or more pieces of first output information W1 and one or more pieces of second output information W2 acquired by the acquisition unit 341 with respect to the request information. That is, an index K is identified for each piece of output information W (each piece of first output information W1 and each piece of second output information W2).

[0082] The index K is an index that indicates how appropriate (suitable) the output information W is for the request information, and is, for example, a numerical value (e.g., a score). For example, the higher the score, the more appropriate the output information W is, and the lower the score, the less appropriate the output information W is.

[0083] In the first embodiment, a generative model M4 is used to calculate the index K. Specifically, the index calculation unit 342 inputs, into the generative model M4, the request information and the first output information W1 for each piece of first output information W1, and the request information and the second output information W2 for each piece of second output information W2, thereby identifying the index K for each piece of output information W.

[0084] As with the above-described generation model M1, the generation model M4 is configured as a Transformer model, and may be, for example, a large-scale language model or a trained model that has trained the relationship between the output information W, the request information, and the index K by machine learning. When the generation model M4 is a Transformer model, it is preferable that the generation model M4 has been trained using a dataset that includes, for example, multiple combinations of expected output information W and the index K for the output information W. As can be understood from the above explanation, the generation model M4 outputs an index K that is statistically appropriate for the output information W. Note that multiple parameters that define the generation model M4 are set by machine learning (particularly deep learning) using multiple training data and are stored in the storage device 432.

[0085] The response generation unit 343 generates response information R in response to the request information. Specifically, the response generation unit 343 generates the response information R in response to the request information in accordance with one or more pieces of first output information W1 generated by the generative model M2 in response to the prompt P2 and one or more pieces of second output information W2 generated by the generative model M3 in response to the prompt P3.

[0086] The response generation unit 343 of the first embodiment generates response information R according to the index K identified for each of one or more pieces of first output information W1 and one or more pieces of second output information W2. Specifically, the response generation unit 343 generates response information R according to a result of comparing the index K identified for each of one or more pieces of first output information W1 and one or more pieces of second output information W2 with a threshold. In this embodiment, the method of generating response information R varies depending on the number of pieces of output information W whose index K exceeds the threshold among one or more pieces of first output information W1 and one or more pieces of second output information W2.

[0087] The method of generating the response information R differs depending on whether there is one piece of output information W with an index K exceeding the threshold among one or more pieces of first output information W1 and one or more pieces of second output information W2; whether there are multiple pieces of output information W with an index K exceeding the threshold among one or more pieces of first output information W1 and one or more pieces of second output information W2; or whether there is no piece of output information W with an index K exceeding the threshold among one or more pieces of first output information W1 and one or more pieces of second output information W2. Specific methods by which the response generation unit 343 generates the response information R for these three cases will be described later. The threshold is set arbitrarily by the administrator of the information providing system 40. The response information R identified by the response generation unit 343 is transmitted to the terminal device 10 by the communication device 433.

[0088] As can be understood from the above explanation, the response information R is information generated in response to one or more pieces of first output information W1 generated by a trained generative model M2 in response to a prompt P2 including request information, and one or more pieces of second output information W2 generated by a trained generative model M3 in response to a prompt P3 including request information.

[0089] Fig. 14 is a flowchart illustrating a specific procedure of processing executed by the entire information processing system 100. A user U of the terminal device 10 inputs input information for requesting (inquiring about) desired information about a target product by operating the operation device 15. Fig. 15 illustrates an example of input information input by the user U. Fig. 15 illustrates an example of input information indicating an inquiry about an error that has occurred in function X of the target product.

[0090] The reception unit 111 of the terminal device 10 receives input information entered by the user U (SA1). The prompt generation unit 112 generates a prompt P1 including the input information (SA2) and transmits the prompt P1 from the communication device 13 to the information generation system 30 (SA3). As described above, the prompt P1 is a prompt P for requesting one or more pieces of related information G related to the input information.

[0091] The acquisition unit 311 of the information generation system 30 acquires the prompt P1 transmitted from the terminal device 10 by receiving it via the communication device 33 (SB1). The related information generation unit 312 generates one or more pieces of related information G for the prompt P1 acquired by the acquisition unit 311 (SB2). Statistically valid related information G is generated from the content of the input information (related information G estimated to be highly likely to be related based on the content of the input information). The related information generation unit 312 transmits the generated one or more pieces of related information G from the communication device 33 to the terminal device 10 (SB3).

[0092] 15 also illustrates an example of related information G generated by the related information generation unit 312. FIG. 15 illustrates an example in which three pieces of related information G (G1, G2, G3) are generated. As illustrated in FIG. 15, the related information G is information related to (similar to) the input information, and, like the input information, is information indicating an inquiry about function X. For example, related information G1 may be provided that embodies the content of the input information (e.g., an error that occurred in function X or requested information), and related information G2 and G3 may be provided that contain content related to the content of the input information (e.g., content related to errors that occurred in functions X1 and X2 that are related to function X).

[0093] The acquisition unit 113 of the terminal device 10 receives, via the communication device 13, one or more pieces of related information G transmitted by the information generation system 30 (SA4). The presentation unit 114 presents the input information and one or more pieces of related information G to the user U by displaying them on the display device 14 (SA5). That is, the input information and three pieces of related information G (G1, G2, G3) illustrated in FIG. 15 are displayed on the display device 14. The user U selects, as requested information, the information that is considered most appropriate from the input information and the three pieces of related information G displayed on the display device 14. The selection of requested information is performed by operating the operation device 15. The reception unit 111 receives the requested information input (selected) by the user U by operating the operation device 15 (SA6).

[0094] The user U may modify the input information and the information selected from one or more pieces of related information G before using it as the requested information. The information selected by the user U may also be processed (for example, converted or combined with other information) in the terminal device 10 before using it as the requested information. In other words, the requested information may be the input information or the related information G itself, or may be information corresponding to the input information or the related information G.

[0095] Furthermore, the user U inputs identification information for identifying the subject of the inquiry (target product) by operating the operation device 15. For example, the identification information may be input by selecting it from a plurality of options prepared in advance (such as the version of the target product), or the user U may input any identification information. The plurality of options are displayed on the display device 14. The receiving unit 111 receives the identification information input by the user U by operating the operation device 15 (SA7).

[0096] The prompt generator 112 generates prompts Pz2 and P3 including the request information and the identification information (SA8), and transmits the generated prompts Pz2 and P3 from the communication device 13 to the information providing system 40 (SA9).

[0097] When the information providing system 40 (first processing device 41, second processing device 42, information providing device 43, information acquiring device 44) receives the prompts Pz2 and P3 transmitted from the terminal device 10, it executes a process of generating response information R (SC1). Figure 16 is a flowchart illustrating the detailed procedure of step SC1.

[0098] As illustrated in FIG. 16 , the control device 441 of the information acquisition device 44 acquires a prompt Pz2 transmitted from the terminal device 10 by receiving it via the communication device 443 (SC01). Next, the control device 441 generates a prompt P2 from the prompt Pz2 (SC02). Specifically, the control device 441 generates the prompt P2 including request information, identification information, and reference information by adding reference information to the prompt Pz2. As described above, the reference information is acquired using the reference information table Dq. For example, reference information in which a target string that matches (or is highly similar to) a string included in the reference information of the prompt P2 (hereinafter referred to as a “search string”) is associated with identification information that matches (or is highly similar to) the identification information of the prompt P2 is acquired from the reference information table Dq. For example, if the request information is “I have switched from product A to product B. Please tell me the procedure for activating function X,” the string “procedure for activating function X” may be used as the search string. Note that multiple pieces of reference information may be acquired using multiple different search strings. Then, the control device 441 transmits the prompt P2 to the first processing device 41 (SC03).

[0099] The acquisition unit 141 of the first processing device 41 acquires the prompt P2 transmitted from the information acquisition device 44 by receiving it via the communication device 413 (SC11). The processing unit 142 generates one or more pieces of first output information W1 for the prompt P2 acquired by the acquisition unit 141 (SC12). Specifically, the processing unit 142 generates one or more pieces of first output information W1 by inputting the prompt P2 into the generative model M2. The processing unit 142 transmits the generated one or more pieces of first output information W1 to the information providing device 43 (SC13).

[0100] The acquisition unit 241 of the second processing device 42 acquires the prompt P3 transmitted from the terminal device 10 by receiving it via the communication device 423 (SC21). The processing unit 242 generates one or more pieces of second output information W2 for the prompt P3 acquired by the acquisition unit 241 (SC22). Specifically, the processing unit 242 generates one or more pieces of second output information W2 by inputting the prompt P3 into the generative model M3. The acquisition unit 241 transmits the generated one or more pieces of second output information W2 to the information providing device 43 (SC23). Note that steps SC11-SC13 and steps SC21-SC23 may be performed in parallel or one after the other.

[0101] Fig. 17 illustrates an example of first output information W1 and second output information W2. Fig. 17 illustrates an example in which two pieces of first output information W1 (W11, W12) are generated and one piece of second output information W2 is generated. The output information W1 and W2 are candidates for response information R (answer).

[0102] The acquisition unit 341 of the information providing device 43 acquires one or more pieces of first output information W1 transmitted from the first processing device 41 and one or more pieces of second output information W2 transmitted from the second processing device 42 by receiving them via the communication device 433 (SC31, SC32). Note that the order of steps SC31 and SC32 is arbitrary, and they may be performed in parallel.

[0103] The index calculation unit 342 identifies an index K indicating the validity of each of one or more pieces of first output information W1 and one or more pieces of second output information W2 with respect to the request information (SC33). In the following explanation, a case where the index K is a score (out of 100) is illustrated. The generative model M4 is used to identify the index K. Specifically, the request information and the output information W for each of the multiple pieces of output information W (W11, W12, W2) are input to the generative model M4 to identify the index K. As illustrated in FIG. 17, the index K (score) is identified for each piece of output information W.

[0104] The response generation unit 343 executes a process (hereinafter referred to as the "response generation process") to generate response information R according to one or more pieces of first output information W1 and one or more pieces of second output information W2 acquired by the acquisition unit 341 (SC34). In the response generation process of this embodiment, the response information R is generated according to the index K identified for each of the one or more pieces of first output information W1 and each of the one or more pieces of second output information W2. FIG. 18 is a flowchart illustrating a specific procedure of the response generation process.

[0105] First, the response generation unit 343 determines whether or not there is any output information W among the multiple pieces of output information W (W1, W2) whose index K exceeds a threshold value (SC34-1). If there is any output information W among the multiple pieces of output information W whose index K exceeds the threshold value (SC34-1; YES), the response generation unit 343 generates response information R (SC34-2). If there is only one piece of output information W whose index K exceeds the threshold value, response information R is generated in response to that one piece of output information W. The response information R generated in response to the output information W may be the output information W itself, or may be, for example, information that has been processed or corrected, or information in which other information has been added to the output information W.

[0106] When there are multiple pieces of output information W with index K exceeding the threshold, response information R is generated in accordance with the multiple pieces of output information W. The response information R generated in accordance with the multiple pieces of output information W may be, for example, information itself that combines the multiple pieces of output information W, or may be, for example, information that has been processed or corrected from the combined information, or information that has other information added to the multiple pieces of output information W.

[0107] On the other hand, if there is no output information W whose index K exceeds the threshold value among the multiple pieces of output information W (SC34-1; NO), the response generation unit 343 determines whether the process of SC34-1 has been repeated a predetermined number of times (e.g., twice) (SC34-3). If the process of SC34-1 has not been repeated the predetermined number of times (SC34-3; NO), the process returns to step SC02 in FIG. 16 , where a prompt P2 is generated again. Specifically, the information acquisition device 44 generates a prompt P2 by changing the reference information to other reference information. The information acquisition device 44 of the first embodiment uses the reference information table Dq to change the search string and then acquires the reference information again. For example, if the request information contains a content such as "I have switched from product A to product B. Please tell me the procedure for enabling function X," if the string "the procedure for enabling function X" was used as the search string in the previous step SC02, the string "the procedure for enabling function X in product B" may be used as the search string. In other words, the search string may be a string combining multiple words included in the request information. The changed search string may be, for example, a string that combines the previous search string with other words or strings (i.e., a string that partially overlaps before and after the change), or a string that is completely different from the previous search string. The changed prompt P2 may include reference information from the pre-change prompt P2 as well as newly acquired reference information. Meanwhile, the request information and identification information are maintained. The changed prompt P2 is sent to the first processing device 41 (SC03).

[0108] Next, the first processing device 41 performs steps SC11-SC13 of FIG. 16 again. Then, the information providing device 43 acquires one or more pieces of first output information W1 generated for the changed prompt P2 (SC31) and performs steps SC33 and SC34. The process of changing the prompt P2 can also be described as a process of updating the first output information W1. Note that step SC32 of receiving the second output information W2 and the process of calculating the index K for the second output information W2 in step SC33 are omitted because there is no change to the prompt P3. In other words, the second output information W2 is maintained without being updated.

[0109] 18 for the index K identified for each of the one or more pieces of first output information W1 after update and the index K for each of the one or more pieces of second output information W2 that have been maintained (i.e., the index K identified in the previous step SC33). That is, if there is no output information W whose index K exceeds the threshold, the response generation unit 343 generates response information R in accordance with the index K identified for each of the one or more pieces of first output information W1 that have been newly generated by the generative model M2 in response to the prompt P2 whose reference information has been changed to other reference information, and for each of the one or more pieces of second output information W2 that have been maintained.

[0110] In the example of Figure 17, for example, when the threshold is set to 80 points, response information R is generated according to the first output information W11, when the threshold is set to 70 points, response information R is generated according to the first output information W11 and the first output information W12, and when the threshold is set to 95 points, response information R is not generated and prompt P2 is updated.

[0111] 18 is repeated a predetermined number of times (SC34-3; YES), the response generation unit 343 generates response information R (SC34-2). In this case, a response indicating that appropriate information for the request information could not be generated (i.e., a response indicating that the desired information cannot be provided to the user U) is generated as response information R. Note that if there is no output information for which the index K exceeds the threshold, a configuration may be adopted in which the process proceeds to step SC34-2 without performing the process of step SC34-3 and response information R (a response indicating that appropriate information for the request information could not be generated).

[0112] As can be understood from the above explanation, the response generation unit 343 generates response information R according to the result of comparing the index K identified for each of the one or more pieces of first output information W1 and the one or more pieces of second output information W2 with a threshold. The method of generating response information R is then varied depending on the number of pieces of output information W for which the index K exceeds the threshold. Specifically, the method of generating response information R differs depending on whether there is one piece of output information W for which the index K exceeds the threshold among the one or more pieces of first output information W1 and the one or more pieces of second output information W2, whether there is multiple pieces of output information W for which the index K exceeds the threshold, or whether there is no output information W that exceeds the threshold.

[0113] 14, the response information R generated by the response generation unit 343 is transmitted from the communication device 433 to the terminal device 10 (SC2). The acquisition unit 113 of the terminal device 10 acquires the response information R by receiving it via the communication device 13 (SA10). Then, the presentation unit 114 presents the response information R acquired by the acquisition unit 113 to the user U by displaying it on the display device 14 (SA11).

[0114] In the first embodiment, response information R generated in accordance with one or more pieces of first output information W1 generated by the generation model M2 in response to the prompt P2 and one or more pieces of second output information W2 generated by the generation model M3 in response to the prompt P3 can be obtained.Therefore, compared to a configuration in which response information R generated in accordance with output information W generated by one generation model is obtained and provided to the user U, it is possible to present the user U with more appropriate response information R in response to the requested information from the user U.

[0115] Second Embodiment A second embodiment will be described. In the following examples, elements that have the same functions as those in the first embodiment will use the same reference numerals as those in the first embodiment, and detailed descriptions of each element will be omitted as appropriate.

[0116] 19 is a block diagram illustrating the configuration of an information processing system 100 according to the second embodiment. The information processing system 100 according to the second embodiment has a configuration in which an information collection system 50 is added to the information management system 20 according to the first embodiment. The other configurations are the same as those of the first embodiment. The information management system 20 is a computer system for collecting various types of information after response information R is presented to a user U.

[0117] In the second embodiment, after response information R in response to request information is presented, the validity of the response information R is determined. In the second embodiment, for example, a user U determines (inputs) an evaluation of validity (hereinafter referred to as a "feedback evaluation") for the response information R generated in response to the request information by operating the operation device 15. The feedback evaluation includes, for example, an index (hereinafter referred to as an "evaluation index") indicating how appropriate the response information R was for the request information, and a statement (hereinafter referred to as an "evaluation statement") that the user U can arbitrarily input regarding the validity of the response information R. The evaluation index may be, for example, an index selected from options (e.g., "good," "average," and "poor") that classify the evaluation of validity into multiple stages, or may be a score that the user U can arbitrarily input. However, the feedback evaluation may be performed by a processing device (not shown) instead of the user U. The processing device outputs the feedback evaluation for the response information R using, for example, a generative model. For such a generative model, for example, a model in which the relationship between the response information R and the feedback evaluation is learned by machine learning, or a large-scale language model, is used.

[0118] The receiving unit 111 of the terminal device 10 receives the identified feedback evaluation. Then, the terminal device 10 transmits information F including the feedback evaluation (hereinafter referred to as "evaluation information") to the information collection system 50. The evaluation information F includes response information R that was the subject of the evaluation and request information corresponding to the response information R. Furthermore, the evaluation information F of the second embodiment includes identification information. Note that the evaluation information F may also include other information (for example, input information, related information G, reference information, and output information W).

[0119] 20 is a block diagram illustrating an example of the configuration of an information collection system 50. The information collection system 50 is a computer system that collects various pieces of information after presenting response information R to a user U. Specifically, the information collection system 50 includes a control device 51, a storage device 52, and a communication device 53.

[0120] The control device 51 is one or more processors that control the operation of the information collection system 50. The storage device 52 is one or more memories that store programs executed by the control device 51 and various data used by the control device 51. The communication device 53 is a communication device that communicates with the terminal device 10 via the communication network 900. The control device 51, the storage device 52, and the communication device 53 may have the same configuration as that described for the control device 411, the storage device 412, and the communication device 413 of the first processing device 41, for example.

[0121] 21 is a block diagram illustrating functions realized by the control device 51 executing a program stored in the storage device 52. The control device 51 realizes a plurality of functions (an acquisition unit 511, a collection unit 512) for collecting various types of information after presenting response information R to the user U.

[0122] The acquisition unit 511 receives the evaluation information F transmitted from the terminal device 10 via the communication device 53. That is, the acquisition unit 511 (an example of a "first acquisition unit") functions as an element that acquires the evaluation of validity (feedback evaluation) identified for the response information R generated in response to the request information corresponding to the input information entered by the user U, the request information, and the response information R.

[0123] The collection unit 512 stores the evaluation information F acquired by the acquisition unit 511 in the storage device 60. The feedback evaluation, request information, response information R, and identification information included in the evaluation information F are stored in the storage device 60. For example, the feedback evaluation, request information, response information R, and identification information are registered in association with each other in a database D1 stored in the storage device 60.

[0124] The storage device 60 is, for example, a recording medium (e.g., cloud storage) that can be accessed by the information collection system 50 via the communication network 900. As described above in the first embodiment, the storage device 60 is preferably accessible by the processing unit 142 (generative model M2) of the first processing device 41. Note that the storage device 52 of the information collection system 50 may also be used as the storage device 60.

[0125] Before storing the evaluation information F in the storage device 60, a process for confirming the contents of the evaluation information F is performed. First, a confirmation is made as to whether the feedback evaluation is appropriate. For example, based on the request information, identification information, and response information R, a confirmation is made as to whether the feedback evaluation is appropriate (i.e., whether the evaluation is valid or not). The confirmation as to whether the feedback evaluation is appropriate may be performed, for example, by an administrator of the information collection system 50 or by a processing device configured as a computer system. The processing device (not shown) confirms whether the feedback evaluation is appropriate or not using, for example, a generative model. Such a generative model may be, for example, a model in which the relationship between the request information, identification information, response information R, and feedback evaluation and the validity of the feedback evaluation is learned by machine learning, or a large-scale language model.

[0126] If the feedback rating is determined to be inappropriate, the feedback rating is appropriately corrected. The correction of the feedback rating may be performed, for example, by an administrator of the information collection system 50 or by a processing device. The processing device (not shown) corrects the feedback rating using, for example, a generative model. Such a generative model may be, for example, a model in which the relationship between the request information, identification information, response information R, and feedback rating and the corrected feedback rating is learned by machine learning, or a large-scale language model.

[0127] Second, it is confirmed whether the response information R is appropriate for the request information. For example, it is confirmed whether the response information R is appropriate (i.e., whether the response information R is valid) based on the request information, identification information, and feedback evaluation. The confirmation of whether the response information R is appropriate may be performed, for example, by an administrator of the information collection system 50, or by a processing device configured in a computer system. The processing device (not shown) confirms whether the response information R is appropriate using, for example, a generative model. Such a generative model may be, for example, a model in which the relationship between the request information, identification information, and response information R and the validity of the response information R is mechanistically calculated, or a large-scale language model.

[0128] If the response information R is determined to be inappropriate, the response information R is appropriately corrected. The response information R may be corrected, for example, by an administrator of the information collection system 50 or by a processing device. The processing device (not shown) corrects the response information R using, for example, a generative model. Such a generative model may be, for example, a model in which the relationship between the request information, identification information, feedback evaluation, and response information R and the corrected response information R is machine-learned, or a large-scale language model.

[0129] In the present embodiment, when the collection unit 512 determines that the feedback rating is inappropriate, it stores the appropriately corrected feedback rating in the storage device 60, and when it determines that the response information R is inappropriate for the input information, it stores the appropriately corrected response information R in the storage device 60. When the feedback rating and the response information R are appropriate, they are stored in the storage device 60 without being corrected.

[0130] The collection unit 512 may further store whether the feedback evaluation is appropriate or not and the feedback evaluation before correction (when the feedback evaluation is inappropriate) in the storage device 60. Similarly, the collection unit 512 may store whether the response information R is appropriate or not and the response information R before correction (when the response information R is inappropriate) in the storage device 60.

[0131] According to the configuration of the third embodiment, if the feedback evaluation is determined to be inappropriate, the appropriately corrected feedback evaluation is stored in the storage device 60. If the response information R is determined to be inappropriate for the request information, the appropriately corrected response information R is stored in the storage device 60. The information stored in the storage device 60 (database D1) can be used as training data for the generative model M2 of the first processing device 41 or can be referenced by the first processing device 41. This enables the first processing device 41 to generate the first output information W1 with higher accuracy. For example, a combination of the request information and the response information R (i.e., the first output information W1) is used as training data for the generative model M2. Alternatively, the generative model M2 may reference the database D1 to acquire the first output information W1 for the request information.

[0132] Third Embodiment

[0133] FIG. 22 is a block diagram illustrating functions realized by the control device 51 executing a program stored in the storage device 52 of the information collection system 50 according to the third embodiment.

[0134] The control device 51 of the third embodiment realizes a prompt generation unit 513 and an information generation unit 514 in addition to an acquisition unit 511 and a collection unit 512 as multiple functions for collecting various information after presenting response information R to the user U. The function of the information generation unit 514 may be installed in a separate device that can communicate with the information collection system 50.

[0135] First, the acquisition unit 511 (an example of a "first acquisition unit") in the third embodiment acquires input information entered by the user U. The prompt generation unit 513 generates a prompt P4 (an example of a "fourth prompt") that includes the input information. Specifically, the prompt P4 is information that requests the generation of related information related to the input information. Note that the prompt P4 may request the generation of multiple pieces of related information. The related information in the third embodiment is information similar to the related information G described in the first embodiment. In other words, the related information, like the input information, is information for requesting the information desired by the user U.

[0136] The prompt P4 generated by the prompt generation unit 513 is input to the information generation unit 514, which generates related information related to the input information. The information generation unit 514 (an example of a "second acquisition unit") generates (acquires) the related information using a trained generative model M5 (an example of a "fourth generation model").

[0137] Next, the prompt generation unit 513 generates a prompt P5 (an example of a "fifth prompt") that includes the related information. Specifically, the prompt P5 is information for requesting the generation of answer information for the related information. The answer information is information that indicates a response to the related information (typically, information requested by the related information). If the related information is information that indicates a query, the answer information is information that indicates a response to the query. The answer information has the same content (answer to the query) as the first output information W1.

[0138] The prompt P5 generated by the prompt generation unit 513 is input to the information generation unit 514, which generates answer information for the related information. The information generation unit 514 (an example of a "third acquisition unit") generates (acquires) the answer information using a trained generative model M6 (an example of a "fifth generation model").

[0139] In the third embodiment, the information generation unit 514 that generates related information functions as an element (second acquisition unit) that acquires related information related to the input information generated by the generative model M5 in response to a prompt P4 including input information, and the information generation unit 514 that generates answer information functions as an element (third acquisition unit) that acquires answer information generated by the generative model M6 in response to a prompt P5 including related information. However, if the function of the information generation unit 514 is installed in an external device, elements that acquire the related information and answer information generated by the device by receiving the information function as the second acquisition unit and the third acquisition unit, respectively.

[0140] The collection unit 512 stores the input information acquired by the acquisition unit 511 and the related information and answer information generated by the information generation unit 514 in the storage device 60. For example, the input information, the related information, and the answer information are registered in association with each other in a database D2 stored in the storage device 60. However, it is not essential to store the input information in the storage device 60.

[0141] Before storing the input information, related information, and answer information in the storage device 60, it is confirmed whether the answer information is appropriate. For example, it is confirmed whether the answer information is appropriate (i.e., whether the answer information is valid) based on the content of the related information. The confirmation of whether the answer information is appropriate may be performed, for example, by an administrator of the information collection system 50, or by a processing device configured in a computer system. The processing device (not shown) confirms whether the answer information is appropriate using, for example, a generative model. Such a generative model may be, for example, a model in which the relationship between the related information and answer information and the validity of the answer information is mechanistically calculated, or a large-scale language model.

[0142] If the answer information is determined to be inappropriate, the answer information is appropriately corrected. The answer information may be corrected, for example, by an administrator of the information collection system 50 or by a processing device. The processing device (not shown) corrects the answer information using, for example, a generative model. Such a generative model may be, for example, a model in which the relationship between the related information and answer information and the corrected answer information is learned by machine learning, or a large-scale language model.

[0143] When the collection unit 512 of the third embodiment determines that the answer information is inappropriate for the related information, it stores the appropriately corrected answer information in the storage device 60. When the answer information is appropriate, it is stored in the storage device 60 without being corrected. The collection unit 512 may further store in the storage device 60 whether the answer information is appropriate or not, and the answer information before correction (when the answer information is inappropriate).

[0144] According to the configuration of the third embodiment, when answer information is determined to be inappropriate, the answer information is appropriately corrected and stored in the storage device 60. The information stored in the storage device 60 (database D2) can be used as training data for the information generation system 30 (generative model M1) or can be referenced by the information generation system 30. This enables the information generation system 30 to generate related information G with higher accuracy. For example, a combination of input information and related information is used as training data for the generative model M1. Furthermore, since the answer information has the same content as the first output information W1, a combination of related information (i.e., a candidate for request information) and answer information (i.e., the first output information W1) may be used as training data for the generative model M2. Furthermore, the generative model M1 may refer to the database D2 to acquire related information for the input information, or the generative model M2 may refer to the database D2 to acquire the first output information W1 for the request information.

[0145] Note that the generative models M5 and M6 may be a single common generative model. Furthermore, the generative model M5 may be common to the generative model M1, and the generative model M6 may be common to the generative model M2. Furthermore, it may be determined whether the related information generated for the input information is appropriate, and if it is determined that the related information is inappropriate, the related information may be corrected and then stored in the storage device 60.

[0146] <Modification> The above-described embodiments can be modified in various ways. Specific examples of modifications are shown below. Two or more embodiments selected from the following examples can be combined as appropriate.

[0147] (1) In the above-described embodiments, the subject of the inquiry is a specific target product. However, the subject may also be a service. Services include, for example, various services related to water, gas, electricity, banking, medical care, accommodation, education, and transportation. The content of the reference information and identification information may be changed appropriately depending on the type of subject. For example, if the subject of the inquiry is a service (e.g., water, gas, or electricity), examples of the identification information include information identifying the plan subscribed to for that service or the subscriber, and examples of the reference information include information collected by the service provider (such as details of the plan subscribed to by the user or past usage history) or information publicly available from the service provider. Furthermore, the target product is not limited to software, and various products such as home appliances, games, and food are envisioned.

[0148] (2) In each of the above-described embodiments, some of the functions of the information generation system 30 or the information provision system 40 may be installed in the terminal device 10. For example, some or all of the related information generation unit 312, the processing unit 142, the processing unit 242, the index calculation unit 342, and the response generation unit 343 may be installed in the terminal device 10. For example, in a configuration in which the response generation unit 343 is installed in the terminal device 10, the acquisition unit 113 that acquires the response information R is an element that generates the response information R (i.e., the response generation unit 343). That is, the acquisition unit 113 may be an element that acquires the response information R by receiving it from an external device (first embodiment to third embodiment), or an element that acquires the response information R by generating it (a configuration in which the response generation unit 343 is installed in the terminal device 10). Similarly, the acquisition unit 113 may be an element that acquires related information G by receiving it from an external device (first embodiment to third embodiment), or an element that acquires related information G by generating it (a configuration in which the related information generation unit 312 is installed in the terminal device 10).

[0149] (3) In each of the above-described embodiments, the configuration for generating one or more pieces of related information G is not essential. In other words, the input information may be used as requested information without presenting the related information G to the user U. Request information corresponding to the input information includes the input information itself (including information obtained by modifying or processing the input information) and related information G related to the input information (including information obtained by modifying or processing the related information G).

[0150] (4) In each of the above-described embodiments, it is also possible that some or all of the functions of the prompt generation unit 112 are installed in a device other than the terminal device 10 (for example, the information generation system 30 or the information provision system 40). For example, if the function for generating prompts Pz2 and P3 is installed in the information provision system 40, information required for generating prompts Pz2 and P3 (for example, request information and identification information) is transmitted from the terminal device 10 to the information provision system 40.

[0151] Furthermore, in the above-described embodiments, the information acquisition device 44 generates the prompt P2 from the prompt Pz2, but the function of generating the prompt P2 may be provided in the terminal device 10 or the first processing device 41, for example.

[0152] (5) In each of the above-described embodiments, it is not essential that the prompt P2 includes identification information and reference information. However, by including identification information and reference information in the prompt P2, the generative model M2 can generate the first output information W1 with high accuracy (i.e., high validity with respect to the requested information). Note that if the prompt P2 does not include reference information, the information acquisition device 44 is omitted from the information providing system 40, and the prompt Pz2 (an example of a "first prompt") is sent directly from the terminal device 10 to the first processing device 41. Similarly, it is not essential that the prompt P3 includes identification information. Furthermore, the prompt P3 may include reference information. Furthermore, the assignment of identification information to the prompt Pz2 and the prompt P3 is not limited to being performed by the terminal device 10, but may also be performed by the information management system 20.

[0153] (6) In each of the above-described embodiments, it is not essential that the response generation unit 343 generate response information R according to the index K. In the above configuration, the index calculation unit 342 is omitted. For example, a configuration may be adopted in which response information R is generated by combining all of the generated multiple pieces of output information W, or a configuration may be adopted in which response information R is generated by combining one piece of first output information W1 and one piece of second output information W2. Alternatively, the similarity (matching rate) between the first output information W1 and the second output information W2 may be calculated, and the response information R may be generated according to the similarity. For example, if the similarity exceeds a predetermined threshold, response information R including the second output information W2 may be generated, and if the similarity is below the predetermined threshold, response information R including the first output information W1 may be generated.

[0154] (7) In the above-described embodiment, the response generator 343 may generate the response information R according to the output information W with the largest index K (or a plurality of output information W with the largest index K in descending order) among the indexes K identified for each of the one or more pieces of first output information W1 and one or more pieces of second output information W2. In other words, it is not essential to generate the response information R according to the result of comparing the index K of each piece of output information W with a threshold value.

[0155] (8) In each of the above-described embodiments, the user U may be able to confirm the flow of processing from inputting input information to obtaining final response information R. For example, the user U may be able to confirm the input information input by the user U, related information G generated from the input information, request information selected by the user U from the input information and related information G, and response information R to the request information. This information is stored in the storage device 12 of the terminal device 10 or in a storage device accessible from the terminal device 10 via the communication network 900.

[0156] (9) In each of the above-mentioned embodiments, each of the information generation system 30, the information management system 20, the first processing device 41, the second processing device 42, the information providing device 43, the information acquisition device 44 and the information collection system 50 may be a single device or a computer system consisting of multiple devices.

[0157] (10) The information processing systems (terminal device, information generation system, information management system, information acquisition device, first processing device, second processing device, information provision device, and information collection system) according to the above-described aspects are realized by cooperation between a computer (specifically, a control device) and a program. The program according to the above-described aspects can be provided in a form stored on a computer-readable recording medium and installed on a computer. The recording medium is, for example, a non-transitory recording medium, such as an optical recording medium (optical disk) such as a CD-ROM, but can also include any known type of recording medium, such as a semiconductor recording medium or a magnetic recording medium. Note that a non-transitory recording medium includes any recording medium other than a transitory, propagating signal, and does not exclude volatile recording media. The program can also be provided to a computer in the form of distribution via a communication network.

[0158] <Additional Notes> From the above-described exemplary embodiments, the following configurations can be understood, for example.

[0159] [1] A terminal device comprising: a reception unit that receives input information entered by a user; and an acquisition unit that acquires response information generated in response to request information corresponding to the input information, wherein the response information is information generated in response to one or more pieces of first output information generated by a trained first generation model in response to a first prompt including the request information, and one or more pieces of second output information generated by a trained second generation model in response to a second prompt including the request information.

[0160] According to the above configuration, it is possible to obtain response information generated in accordance with one or more first output information generated by a trained first generation model in response to a first prompt including request information corresponding to input information entered by a user, and one or more second output information generated by a trained second generation model in response to a second prompt including the request information.Therefore, compared to a configuration in which response information is obtained in accordance with output information generated by one generation model in response to a prompt including request information, it is possible to present the user with more appropriate response information in response to the request information from the user.

[0161] [2] A terminal device according to [1], wherein the request information is information indicating an inquiry regarding a specified object, and the first generative model is a model trained using highly reliable information regarding the object as training data.

[0162] In the above configuration, the first model is a model trained using highly reliable information about a predetermined target as training data, so that the first output information can be generated based on highly reliable information about the target.

[0163] [3] The terminal device of [1], wherein the response information is information generated in accordance with an index identified for each of the one or more first output information and each of the one or more second output information, and the index indicates the validity of the request information.

[0164] According to the above configuration, response information is generated according to an index identified for each of one or more pieces of first output information and one or more pieces of second output information, and the index indicates the validity of the request information, so that the response information generated taking into account the validity of the request information can be presented to the user.

[0165] [4] The terminal device according to [3], wherein the response information is generated according to a result of comparing the index with a threshold value.

[0166] In the above configuration, response information is generated according to the result of comparing the index with a threshold value. For example, response information generated according to one or more pieces of output information whose index exceeds the threshold value (i.e., output information with high validity) can be presented to the user.

[0167] [5] The terminal device of [4], wherein the method for generating the response information differs depending on the number of pieces of output information whose index exceeds the threshold value among each of the one or more pieces of first output information and each of the one or more pieces of second output information.

[0168] In the above configuration, response information can be presented to the user that is generated in different ways depending on the number of pieces of output information whose index exceeds a threshold value among each of the one or more pieces of first output information and each of the one or more pieces of second output information.

[0169] [6] The method of generating the response information differs depending on whether there is one piece of output information among the one or more first output information and the one or more second output information whose index exceeds the threshold, whether there are multiple pieces of output information among the one or more first output information and the one or more second output information whose index exceeds the threshold, or whether there is no piece of output information among the one or more first output information and the one or more second output information whose index exceeds the threshold.

[0170] With the above configuration, response information can be presented to the user in different ways depending on whether there is one output information among the one or more first output information and one or more second output information whose index exceeds the threshold, whether there is multiple output information among the one or more first output information and one or more second output information whose index exceeds the threshold, or whether there is no output information among the one or more first output information and one or more second output information whose index exceeds the threshold.

[0171] [7] A terminal device according to [6], wherein if there is one piece of output information that exceeds the threshold, the response information is generated in response to that one piece of output information, and if there are multiple pieces of output information that exceed the threshold, the response information is generated in response to the multiple pieces of output information.

[0172] In the above configuration, if there is one piece of output information that exceeds the threshold, response information is generated according to that one piece of output information, and if there are multiple pieces of output information that exceed the threshold, response information is generated according to those multiple pieces of output information.Therefore, if there are multiple pieces of output information that are highly valid, response information that takes into account all of those multiple pieces of output information can be presented to the user.

[0173] [8] The terminal device of [7], wherein the first prompt includes reference information that is referenced in generating the first output information, and when there is no output information that exceeds the threshold, the response information is generated according to the indicators identified for each of the one or more pieces of first output information newly generated by the first generative model in response to the first prompt in which the reference information has been changed to other reference information, and for each of the one or more pieces of second output information.

[0174] In the above configuration, if there is no output information exceeding the threshold, response information is generated according to the indexes identified for each of the one or more pieces of first output information newly generated by the first generative model in response to the first prompt in which the reference information has been changed to other reference information and for each of the one or more pieces of second output information. Therefore, if highly valid output information is not obtained, new one or more pieces of first output information (i.e., updated one or more pieces of first output information) can be used to generate response information.

[0175] [9] A terminal device according to any one of [1] to [8], wherein the acquisition unit acquires one or more pieces of related information related to the input information, generated by a trained third generation model in response to a third prompt including the input information, and the requested information is information selected by the user from the input information and the one or more pieces of related information.

[0176] In the above configuration, the request information is the information selected by the user from the input information and one or more pieces of related information, so response information is generated with the information desired by the user from multiple options (the input information and one or more pieces of related information) as the request information. Therefore, for example, compared to a configuration in which the input information entered by the user is used as the request information, it is possible to obtain response information that is in line with the user's intention.

[0177]

[10] The terminal device according to [1], wherein the request information is information indicating an inquiry about a predetermined object, and the first prompt includes identification information for identifying the object.

[0178] In the above configuration, the request information is information indicating an inquiry about a predetermined object, and the first prompt includes identification information for identifying the object, so that response information to the request information can be generated with high accuracy.

[0179]

[11] A terminal device according to any one of [1] to [7], wherein the first prompt includes reference information that is referenced in generating the response information.

[0180] In the above configuration, the first prompt includes reference information that is referenced in generating response information, so that response information to request information can be generated with high accuracy.

[0181]

[12] A terminal device comprising: a reception unit that receives input information entered by a user; and an acquisition unit that generates a trained third generation model in response to a third prompt including the input information and acquires one or more related information related to the input information.

[0182] The above configuration includes a receiving unit that receives input information input by a user and an acquiring unit that acquires one or more pieces of related information related to the input information generated by a trained third generative model in response to a third prompt including the input information. This makes it possible to provide the user with one or more pieces of related information related to the input information. Therefore, it is possible to generate a prompt that includes request information, which is information desired by the user from multiple options (the input information and one or more pieces of related information). As a result, it is possible to present the user with more appropriate response information for the request information.

[0183]

[13] An information providing device comprising a response generation unit that generates response information to a first prompt including request information corresponding to input information entered by a user, in accordance with one or more first output information generated by a trained first generation model in response to a first prompt including the request information, and one or more second output information generated by a trained second generation model in response to a second prompt including the request information.

[0184] In the above configuration, response information to the request information is generated based on one or more pieces of first output information generated by a trained first generative model in response to a first prompt including request information corresponding to input information entered by a user, and one or more pieces of second output information generated by a trained second generative model in response to a second prompt including the request information. Therefore, for example, compared to a configuration in which response information corresponding to output information generated by one generative model in response to a prompt including the request information is obtained, it is possible to present the user with more appropriate information for the request information.

[0185]

[14] An information generation system including a related information generation unit that generates one or more related pieces of information related to input information by inputting a third prompt including input information entered by a user into a trained third generation model.

[0186] In the above configuration, by inputting a third prompt including input information entered by a user into the third generation model, one or more pieces of related information are generated, making it possible to provide the user with one or more pieces of related information related to the input information. Therefore, for example, it is possible to generate a prompt including requested information, which is information desired by the user from multiple options (the input information and one or more pieces of related information). As a result, it is possible to present the user with response information that is more appropriate to the requested information.

[0187]

[15] An information collection system comprising: an evaluation of the validity identified for response information generated in response to request information corresponding to input information entered by a user; a first acquisition unit that acquires the request information and the response information; and a collection unit that stores the evaluation, the request information, and the response information in a storage device.

[0188] In the above configuration, the request information and the response information are stored in a storage device along with an assessment of the validity of the response information generated in response to the request information input by the user. Therefore, the assessment, request information, and response information stored in the storage device can be used, for example, as training data for the first generative model, or can be referenced when the first generative model generates the first output information. This allows the first generative model to generate the first output information with high accuracy. Consequently, the user can be presented with more appropriate response information for the request information.

[0189]

[16] The information collection system of

[14] , wherein if the collection unit determines that the evaluation is inappropriate, the collection unit stores an appropriately corrected evaluation in the storage device, and if the response information is determined to be inappropriate for the request information, the collection unit stores an appropriately corrected response information in the storage device.

[0190] In the above configuration, if the evaluation is determined to be inappropriate, the evaluation is appropriately corrected and stored in the storage device, and if the response information is determined to be inappropriate for the request information, the response information is appropriately corrected and stored in the storage device. Therefore, the effect of enabling the first generative model to generate the first output information with high accuracy is remarkable.

[0191]

[17] An information collection system comprising: a first acquisition unit that acquires related information related to a fourth prompt that includes input information entered by a user and that is generated by a trained fourth generation model; a second acquisition unit that acquires answer information that is generated by a trained fifth generation model in response to a fifth prompt that includes the related information; and a collection unit that stores the related information and the answer information in a storage device.

[0192] In the above configuration, the trained fourth generative model generates information in response to a fourth prompt including input information entered by a user, and related information related to the input information and answer information generated by the trained fifth generative model in response to a fifth prompt including the related information are stored in a storage device. Therefore, the related information and answer information stored in the storage device can be used, for example, as training data for a third generative model or can be referenced when the third generative model generates related information. This enables the third generative model to generate related information with high accuracy.

[0193]

[18] The information collection system of

[16] , wherein if the collection unit determines that the answer information is not appropriate for the related information, the collection unit stores appropriately corrected answer information in the storage device.

[0194] In the above configuration, if it is determined that the answer information is inappropriate for the related information, the answer information is appropriately corrected and stored in the storage device, which has the notable effect of enabling the third generation model to generate related information with high accuracy.

[0195]

[19] An information processing system comprising: a receiving unit that receives input information entered by a user; a response generation unit that generates response information to the request information in accordance with one or more pieces of first output information generated by a trained first generation model in response to a first prompt including request information corresponding to the input information, and one or more pieces of second output information generated by a trained second generation model in response to a second prompt including the request information; and an acquisition unit that acquires the response information generated in response to the request information corresponding to the input information.

[0196] In the above configuration, response information can be obtained that is generated based on one or more first output information generated by a trained first generation model in response to a first prompt that includes request information corresponding to input information entered by a user, and one or more second output information generated by a trained second generation model in response to a second prompt that includes the request information.Therefore, compared to a configuration in which response information is obtained based on output information generated by one generation model in response to a prompt that includes request information, it is possible to present the user with more appropriate response information in response to the request information from the user.

[0197]

[20] An information acquisition method realized by a computer system that accepts input information entered by a user and acquires response information generated in response to request information corresponding to the input information, the response information being information generated in response to one or more first output information generated by a trained first generative model in response to a first prompt including the request information and one or more second output information generated by a trained second generative model in response to a second prompt including the request information.

[0198] In the above configuration, response information can be obtained that is generated based on one or more first output information generated by a trained first generation model in response to a first prompt that includes request information corresponding to input information entered by a user, and one or more second output information generated by a trained second generation model in response to a second prompt that includes the request information.Therefore, compared to a configuration in which response information is obtained based on output information generated by one generation model in response to a prompt that includes request information, it is possible to present the user with more appropriate response information in response to the request information from the user.

[0199]

[21] A program that causes a computer system to function as a reception unit that receives input information entered by a user and an acquisition unit that acquires response information generated in response to request information corresponding to the input information, wherein the response information is information generated in response to one or more first output information generated by a trained first generation model in response to a first prompt including the request information, and one or more second output information generated by a trained second generation model in response to a second prompt including the request information.

[0200] In the above configuration, response information can be obtained that is generated based on one or more first output information generated by a trained first generation model in response to a first prompt that includes request information corresponding to input information entered by a user, and one or more second output information generated by a trained second generation model in response to a second prompt that includes the request information.Therefore, compared to a configuration in which response information is obtained based on output information generated by one generation model in response to a prompt that includes request information, it is possible to present the user with more appropriate response information in response to the request information from the user.

[0201] This invention is also specified as an invention of a method executed by the information providing device

[12] , the information providing device

[13] , the information generating system

[14] , and the information collecting system

[15] and

[17] . It is also specified as an invention of a program that causes the information providing device

[12] , the information generating system

[13] , the information collecting system

[15] and

[17] , and the information processing system

[19] to function. [Explanation of symbols]

[0202] 10: Terminal device 11: Control device 12:Storage device 13: Communication equipment 14:Display device 15: Operating device 20: Information Management System 30: Information Generation System 31: Control device 32: Storage device 33: Communication equipment 40: Information provision system 41: First processing device 42: Second processing device 43: Information provision device 44: Information acquisition device 50: Information gathering system 51: Control device 52: Storage device 53: Communication equipment 60:Storage device 100: Information Processing Systems 111: Reception 112: Prompt generation unit 113: Acquisition Department 114: Presentation part 141: Acquisition Department 142: Processing section 241: Acquisition Department 242: Processing section 311: Acquisition Department 312: Related information generation unit 341: Acquisition Department 342: Indicator calculation department 343: Response generation unit 411: Control device 412 :Storage device 413: Communication equipment 421: Control device 422 :Storage device 423: Communication equipment 431: Control device 432 :Storage device 433: Communication equipment 511: Acquisition Department 512: Collection Department 513: Prompt generation unit 514: Information generation section 900:Communication network F: Feedback rating G: Related information K: indicator M1-M6: Generative models P1-P6: Prompt W1, W2: Output information

Claims

1. a related information generation unit that generates one or more related information items related to the input information by inputting a prompt including the input information input by a user into a trained generative model; a response generation unit that generates response information in response to the request information from the user, The one or more pieces of related information are presented to the user and are candidates for the requested information. Information management system.

2. a related information generation unit that generates one or more related information items related to the input information by inputting a prompt including the input information input by a user into a trained generative model; and causing the computer system to function as a response generation unit that generates response information in response to the request information from the user; The one or more pieces of related information are presented to the user and are candidates for the requested information. program.

3. generating one or more pieces of related information related to the input information by inputting a prompt including the input information entered by the user into a trained generative model; generating response information in response to the request information from the user; The one or more pieces of related information are presented to the user and are candidates for the requested information. An information management method implemented by a computer system.

Images