Information processing device, information processing method, and program

The information processing device addresses the challenge of providing appropriate prompts for generative AI by using a template management system to create tailored prompts based on inquiry class, enhancing the effectiveness of generative AI in tasks like patent document creation.

JP7591212B1Active Publication Date: 2024-11-28IRD

Patent Information

Application Number
JP2023200683
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2023-11-28
Publication Date
2024-11-28
Estimated Expiration
2043-11-28

AI Technical Summary

Technical Problem

Existing systems face challenges in providing appropriate prompts for generative AI, particularly when dealing with different classes of inquiry information, such as text generation tasks.

Method used

An information processing device equipped with a template management unit that stores prompt template information associated with class conditions, an inquiry acquisition unit, a prompt creation unit, and an answer acquisition unit, which work together to create and utilize appropriate prompts for generative AI based on the class of inquiry information.

Benefits of technology

Enables the effective use of generative AI with tailored prompts, supporting tasks like patent document creation by ensuring appropriate responses based on the class of inquiry information.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007591212000001_ABST
    Figure 0007591212000001_ABST
Patent Text Reader

Abstract

Until now, it has not been easy to use generative AI with appropriate prompts depending on the class of inquiry information. [Solution] The information processing device 1 includes a template management unit 111 in which prompt template information is stored in correspondence with one or more class conditions of a string, a query acquisition unit 131 that acquires query information from reception information, which is information used to query the generation AI, a template acquisition unit 134 that acquires from the template management unit 111 prompt template information corresponding to the class conditions satisfied by the class of the query information, a prompt creation unit 135 that creates a prompt using the prompt template information and the query information, an answer acquisition unit 136 that passes the prompt to the generation AI and acquires an answer from the generation AI, an output acquisition unit 137 that acquires output information using the answer, and an output unit 14 that outputs the output information.This allows the generation AI to be used using an appropriate prompt according to the class of the query information.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an information processing device that acquires and outputs information using a generation AI. [Background technology]

[0002] Recently, generative AI has become widespread (see Patent Document 1). [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] “ChatGPT”, [online], [Retrieved November 19, 2023], Internet [URL: https: / / openai.com / chatgpt] Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the prior art, it was not easy to provide an appropriate prompt to the generation AI. More specifically, it was not easy to utilize the generation AI with an appropriate prompt according to the class of inquiry information. Note that the generation AI here is an AI that generates text. [Means for solving the problem]

[0005] The information processing device of the first invention is an information processing device comprising: a template management unit in which prompt template information is stored in correspondence with one or more class conditions, which are conditions related to a class of strings; a reception unit for receiving reception information from a user; a query acquisition unit for acquiring query information, which is information contained in the reception information and is information to be used for querying a generation AI; a template acquisition unit for acquiring from the template management unit prompt template information corresponding to the class conditions satisfied by the class of the query information acquired by the query acquisition unit; a prompt creation unit for creating a prompt using the prompt template information acquired by the template acquisition unit and the query information acquired by the query acquisition unit; an answer acquisition unit for passing the prompt created by the prompt creation unit to the generation AI and acquiring an answer from the generation AI; an output acquisition unit for acquiring output information using the answer acquired by the answer acquisition unit; and an output unit for outputting the output information.

[0006] This configuration allows the generation AI to be utilized with appropriate prompts depending on the class of query information.

[0007] In addition, the information processing device of the second invention is an information processing device in which, compared to the first invention, the received information is information related to the invention and the output information is information constituting a patent specification, claims, or abstract.

[0008] With this configuration, generative AI can be used to assist in the creation of patent documents with appropriate prompts depending on the class of invention information.

[0009] Furthermore, the information processing device of the third invention is an information processing device in which, compared to the first or second invention, the inquiry acquisition unit acquires at least two pieces of inquiry information from the reception information, and the prompt creation unit creates a prompt using each of the two pieces of inquiry information.

[0010] This configuration allows the generation AI to be utilized with appropriate prompts depending on the class of query information.

[0011] In addition, the information processing device of the fourth invention is an information processing device in which, compared to any one of the first to third inventions, the output acquisition unit places a part or all of the answer in output template information, which is a template for constructing output information, and acquires the output information.

[0012] With this configuration, it is possible to utilize the generation AI and obtain appropriate output information using an appropriate prompt according to the class of the inquiry information.

[0013] Further, an information processing device according to a fifth aspect of the present invention is an information processing device according to any one of the first to fourth aspects of the present invention, wherein the class is a linguistic characteristic of the query information.

[0014] With this configuration, an appropriate class of inquiry can be determined and the generation AI can be utilized with appropriate prompts according to that class.

[0015] Furthermore, the information processing device of the sixth invention is an information processing device in which, compared to the fifth invention, the class can be "question", the template acquisition unit does not acquire prompt template information when the class determined by the class determination unit is "question", and the prompt creation unit creates a prompt using the query information acquired by the query acquisition unit.

[0016] With this configuration, an appropriate class of inquiry can be determined and the generation AI can be utilized with appropriate prompts according to that class.

[0017] Further, an information processing device of a seventh aspect of the present invention is an information processing device according to any one of the first to sixth aspects of the present invention, wherein the class is a tag included in the reception information and the inquiry information is a corresponding tag.

[0018] With this configuration, an appropriate class of inquiry can be determined and the generation AI can be utilized with appropriate prompts according to that class.

[0019] An information processing device according to an eighth aspect of the present invention is the information processing device according to any one of the first to seventh aspects of the present invention, wherein the received information is a document and the class is a type of document.

[0020] With this configuration, an appropriate class of inquiry can be determined and the generation AI can be utilized with appropriate prompts according to that class.

[0021] In addition, the information processing device of the ninth invention is any one of the first to eighth inventions, further comprising a generation AI determination unit that determines a generation AI from two or more generation AIs according to the prompt template information acquired by the template acquisition unit, and the answer acquisition unit passes the prompt created by the prompt creation unit to the generation AI determined by the generation AI determination unit and acquires an answer from the generation AI, which is the information processing device described in any one of claims 1 to 8.

[0022] With this configuration, it is possible to provide a generative AI control engine that makes the most of generative AI. Effect of the Invention

[0023] According to the information processing device of the present invention, the generation AI can be utilized by using an appropriate prompt according to the class of the inquiry information. [Brief description of the drawings]

[0024] [Figure 1] Conceptual diagram of information system A in embodiment 1. [Diagram 2] Block diagram of Information System A [Diagram 3] A flowchart illustrating an example of the operation of the information processing device 1. [Figure 4] A flowchart illustrating an example of the reception information process. [Diagram 5] Flowchart for explaining an example of same-class condition processing [Figure 6] 10 is a flowchart illustrating an example of the output acquisition process. [Figure 7] A diagram showing the template management table [Figure 8] A diagram showing an example of the reception information [Figure 9] A diagram showing an example of the answer [Figure 10] A diagram showing an example of the reception information [Figure 11] A diagram showing an example of the answer [Figure 12] A diagram showing an example of the reception information [Figure 13] A diagram showing an example of the answer [Figure 14] Overview of the computer system [Figure 15] Block diagram of the computer system DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0025] Hereinafter, an embodiment of an information processing device and the like will be described with reference to the drawings. Note that, in the embodiments, components with the same reference numerals perform similar operations, and therefore repeated description may be omitted.

[0026] (Embodiment 1) In this embodiment, an information processing device is described that determines a class of inquiry information, obtains prompt template information corresponding to the class, creates a prompt using the prompt template information, provides the prompt to a generation AI, obtains an answer, and outputs output information using the answer. In particular, an information processing device is described that uses inquiry information related to an invention to output a part of a patent document. The class is, for example, information based on the linguistic characteristics of a character string, or a tag corresponding to the character string, or the type of document accepted. Note that a prompt is a question given to the generation AI.

[0027] In the present embodiment, an information processing device will be described that acquires two or more pieces of inquiry information from the reception information and creates a prompt using each of the two or more pieces of inquiry information.

[0028] In addition, in this embodiment, an information processing device that provides an answer acquired from the generation AI to output template information and acquires output information will be described.

[0029] Furthermore, in this embodiment, an information processing device that determines a generation AI according to a class and obtains output information using a response from the generation AI will be described.

[0030] In this specification, information X being associated with information Y means that information Y can be obtained from information X, or information X can be obtained from information Y, and the method of association is not important. Information X and information Y may be linked, may exist in the same buffer, information X may be included in information Y, or information Y may be included in information X, etc.

[0031] Furthermore, in this specification, selecting or determining information Z means obtaining information Z, obtaining a pointer to information Z, obtaining the ID of information Z, setting a flag for information Z, etc., and is sufficient as long as information Z can be accessed.

[0032] 1 is a conceptual diagram of an information system A according to the present embodiment. The information system A includes an information processing device 1, one or more terminal devices 2, and one or more generation AI devices 3.

[0033] The information processing device 1 is a device that receives reception information, acquires an answer using a generation AI, and outputs output information using the answer. The information processing device 1 is, for example, a cloud server or an ASP server, but the type is not important. The information processing device 1 may be a terminal. If the information processing device 1 is a terminal, it may be considered that the terminal device 2 is not necessary in the information system A, or that the information processing device 1 also serves as the terminal device 2. The information processing device 1 may include a generation AI.

[0034] The terminal device 2 is a terminal used by a user to input reception information. The terminal device 2 is, for example, a so-called personal computer, a smartphone, or a tablet terminal, but the type is not important.

[0035] The AI ​​generation device 3 is a device having an AI generation function that receives a prompt and outputs an answer. If the information processing device 1 includes an AI generation function, the AI ​​generation device 3 may be omitted.

[0036] 2 is a block diagram of an information system A in this embodiment. The information processing device 1 includes a storage unit 11, a reception unit 12, a processing unit 13, and an output unit 14. The storage unit 11 includes a template management unit 111. The processing unit 13 includes a query acquisition unit 131, a class determination unit 132, a generation AI determination unit 133, a template acquisition unit 134, a prompt creation unit 135, an answer acquisition unit 136, and an output acquisition unit 137.

[0037] The terminal device 2 includes a terminal storage unit 21, a terminal reception unit 22, a terminal processing unit 23, a terminal transmission unit 24, a terminal reception unit 25, and a terminal output unit .

[0038] Various types of information are stored in the storage unit 11 constituting the information processing device 1. The various types of information are, for example, prompt template information, which will be described later.

[0039] Two or more pieces of prompt template information are stored in the template management unit 111. Each of the two or more pieces of prompt template information is associated with a class condition.

[0040] Prompt template information is information that serves as a template for creating a prompt. Prompt template information is usually a character string. Prompt template information has one or more variables. The variables are variables into which query information, which will be described later, is substituted. Prompt template information has, for example, a character string that specifies a question and one or more variables. For example, the query information is placed in the variable portion of the prompt template information to create a prompt.

[0041] The template management unit 111 may store output template information. The output template information is information that serves as a template for creating output information. The output template information is usually a character string. The output template information has one or more variables. The variables are variables into which part or all of an answer, which will be described later, is substituted. For example, an answer or part of an answer is placed in the place of the variable in the output template information, and output information is created.

[0042] A class condition is a condition related to a class, which will be described later. A class condition is a condition related to one or more classes. A class is related to character strings. A class may also be called a classification or type.

[0043] The reception unit 12 receives reception information. The reception unit 12 normally receives reception information from a user. The reception information from a user is reception information provided by the user. The reception unit 12 normally receives the reception information from the terminal device 2.

[0044] Here, acceptance typically refers to the reception of information transmitted via a wired or wireless communication line, but may also be a concept that includes the acceptance of information input from an input device such as a keyboard, mouse, or touch panel, and the acceptance of information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory.

[0045] The received information is typically information entered by a user. However, the received information may also be information obtained from a file or a database. The received information is, for example, information related to an invention. The received information is, for example, information identifying an invention. The received information is, for example, claims, a specification, or an abstract. The received information is, for example, a document. The received information is, for example, a file. The received information is, for example, a piece of text, one or more sentences, or a character string.

[0046] The processing unit 13 performs various types of processing, such as processing performed by a query acquisition unit 131, a class determination unit 132, a generation AI determination unit 133, a template acquisition unit 134, a prompt creation unit 135, an answer acquisition unit 136, or an output acquisition unit 137.

[0047] The query acquisition unit 131 acquires query information from the reception information received by the reception unit 12. Query information is information used to inquire of the generation AI. Query information is information included in the reception information. Query information may be reception information. Query information is a character string. Query information is, for example, one or more sentences, words, or words of a specific part of speech (e.g., a noun).

[0048] The inquiry acquiring unit 131 acquires, for example, at least two pieces of inquiry information from the reception information received by the receiving unit 12.

[0049] The one or more pieces of inquiry information that the inquiry acquiring unit 131 acquires from the reception information are usually determined in advance.

[0050] The inquiry acquiring unit 131 acquires, for example, one or more pieces of inquiry information classified into a class that matches the class condition from the received information.

[0051] The class determination unit 132 determines a class of the inquiry information. The class determination unit 132 may determine a class of the received information. The class determination unit 132 determines a class of each of the one or more pieces of inquiry information acquired by the inquiry acquisition unit 131, for example.

[0052] The class may be referred to as a type, a classification, etc. The class may be, for example, information based on linguistic characteristics, information based on a tag to which the query information corresponds, or information based on the type of document including the query information.

[0053] The linguistic characteristics may be referred to as linguistic attribute values ​​for a string. An example of a class based on linguistic characteristics is "question" or "non-question". An example of a class based on linguistic characteristics is "sentence" or "word". An example of a class based on linguistic characteristics is "sentence", "paragraph", or "word". An example of a class based on linguistic characteristics is the part of speech of a word. An example of a class based on linguistic characteristics is "component" or "technical term" that identifies the invention. "Technical term" may be "technical term".

[0054] The tags to which the inquiry information corresponds are, for example, tags in the specification, tags in the scope of the claims, and tags in the abstract. Classes based on tags are, for example, "Problem to be solved by the invention," "Means for solving the problem," "Effects of the invention," "Form for carrying out the invention," "Explanation of symbols," and "Claim 1." The tags to which the inquiry information corresponds are, for example, HTML tags or XML tags.

[0055] A class based on a document type is a class based on the type of reception information, which is a file. Examples of classes based on a document type include "specification," "claims," ​​"abstract," and "list of inventions."

[0056] The class determination unit 132, for example, acquires linguistic characteristics of the inquiry information and determines a class corresponding to the linguistic characteristics.

[0057] The class determination unit 132 acquires a tag, which is included in the reception information and corresponds to the inquiry information, from the reception information, and determines a class corresponding to the tag.

[0058] The class determination unit 132 acquires, for example, the type of document that is the reception information, and determines a class that corresponds to the type.

[0059] The generation AI determination unit 133 determines a generation AI according to a class from, for example, two or more generation AIs. In such a case, each of the two or more generation AIs is associated with a class condition. The generation AI determination unit 133 determines, for example, a generation AI that pairs with a class condition. Determining a generation AI means, for example, obtaining an API for using the generation AI. In such a case, the class condition is associated with, for example, an API for passing a prompt to the generation AI. Determining a generation AI means, for example, obtaining an identifier (for example, an IP address) of the generation AI device 3 that stores the generation AI. In such a case, the identifier of the generation AI device 3 is associated with the class condition.

[0060] The template acquiring unit 134 acquires prompt template information corresponding to a class from the template managing unit 111. The template acquiring unit 134 acquires from the template managing unit 111 prompt template information corresponding to a class condition, for example.

[0061] It is preferable that the template acquiring unit 134 does not acquire prompt template information when the class of the received reception information is a "question."

[0062] The prompt creation unit 135 creates a prompt using the prompt template information acquired by the template acquisition unit 134 and the query information acquired by the query acquisition unit 131. The prompt creation unit 135 normally places the acquired query information in the variable portion of the prompt template information acquired by the template acquisition unit 134 to create a prompt.

[0063] The prompt generator 135 may generate a prompt using each of the two pieces of inquiry information. The number of prompts generated here may be one or two.

[0064] If the class of the inquiry information acquired by the inquiry acquisition unit 131 is a "question," the prompt creation unit 135 creates a prompt including the inquiry information. The prompt may be the inquiry information.

[0065] The answer acquisition unit 136 passes the prompt created by the prompt creation unit 135 to the generation AI and acquires an answer from the generation AI. Passing to the generation AI means, for example, passing to the generation AI device 3, but may also be passing to the generation AI possessed by the information processing device 1.

[0066] The answer acquisition unit 136 passes the prompt created by the prompt creation unit 135 to the generation AI, for example, by using the API of the generation AI.

[0067] It is preferable that the answer acquisition unit 136 passes the prompt created by the prompt creation unit 135 to the generation AI determined by the generation AI determination unit 133, and acquires an answer from the generation AI.

[0068] The output acquisition unit 137 acquires output information using the answer acquired by the answer acquisition unit 136. The output acquisition unit 137 acquires output information using, for example, the reception information and the answer acquired by the answer acquisition unit 136. For example, the output acquisition unit 137 places the answer in the reception information and acquires the output information. For example, the output acquisition unit 137 replaces a part or all of the reception information with the answer and acquires the output information.

[0069] It is preferable that the output acquisition unit 137 acquires the output information by arranging a part or the whole of the answer in the variable portion of the output template information.

[0070] The output information is, for example, information constituting a patent specification or claims or an abstract.

[0071] The output unit 14 outputs the output information acquired by the output acquisition unit 137. The output unit 14 transmits the output information to the terminal device 2, for example.

[0072] Here, output usually means transmission to terminal device 2, but it may also be a concept including display on a display, projection using a projector, printing on a printer, sound output, transmission to other external devices, storage on a recording medium, and handing over the processing results to other processing devices or other programs.

[0073] Various types of information are stored in the terminal storage unit 21 constituting the terminal device 2. The various types of information include, for example, reception information and a user identifier.

[0074] The terminal reception unit 22 receives various types of information, instructions, etc. The various types of information, instructions, etc. are, for example, reception information.

[0075] The means for inputting various information and instructions may be any means, such as a touch panel, a keyboard, a mouse, or a menu screen.

[0076] The terminal processing unit 23 performs various types of processing. For example, the various types of processing are processing for converting received information, instructions, etc. into information or instructions with a structure to be transmitted. For example, the various types of processing are processing for converting received information into information with a structure to be output.

[0077] The terminal transmitting unit 24 transmits various information, instructions, etc. to the information processing device 1. The various information, instructions, etc. are, for example, reception information.

[0078] The terminal receiving unit 25 receives various types of information from the information processing device 1. The various types of information are, for example, output information.

[0079] The terminal output unit 26 outputs various types of information, such as output information.

[0080] The storage unit 11, the template management unit 111, and the terminal storage unit 21 are preferably non-volatile recording media, but may also be realized as volatile recording media.

[0081] There is no restriction on the process by which information is stored in the storage unit 11, etc. For example, information may be stored in the storage unit 11, etc. via a recording medium, information transmitted via a communication line, etc. may be stored in the storage unit 11, etc., or information inputted via an input device may be stored in the storage unit 11, etc.

[0082] The reception unit 12 is preferably realized by a wireless or wired communication means, but may also be realized by a means for receiving broadcasts, a device driver for an input means such as a touch panel or keyboard, or control software for a menu screen.

[0083] The processing unit 13, the inquiry acquisition unit 131, the class determination unit 132, the generation AI determination unit 133, the template acquisition unit 134, the prompt creation unit 135, the answer acquisition unit 136, the output acquisition unit 137, and the terminal processing unit 23 can usually be realized by a processor, a memory, etc. The processing procedure of the processing unit 13, etc. is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may also be realized by hardware (dedicated circuit). The processor may be a CPU, MPU, GPU, etc., and the type is not important.

[0084] The output unit 14 is usually realized by a wireless or wired communication means, but may be realized by a broadcasting means. The output unit 14 may also be realized by driver software for an output device such as a display or a speaker, or by a driver software for an output device and an output device, etc.

[0085] The terminal reception unit 22 can be realized by a device driver for an input means such as a touch panel or a keyboard, or control software for a menu screen.

[0086] The terminal transmitting unit 24 is usually realized by a wireless or wired communication means, but may also be realized by a broadcasting means.

[0087] The terminal receiving unit 25 is usually realized by a wireless or wired communication means, but may be realized by a means for receiving a broadcast.

[0088] The terminal output unit 26 may be considered to include, or may not include, an output device such as a display, a speaker, etc. The terminal output unit 26 may be realized by driver software for an output device, or a combination of driver software for an output device and an output device, etc.

[0089] Next, an example of the operation of the information processing device 1 will be described with reference to the flowchart of FIG.

[0090] (Step S301) The reception unit 12 judges whether or not reception information from a user has been received. If reception information has been received, the process proceeds to step S302, and if reception information has not been received, the process returns to step S301. Here, the reception unit 12 judges whether or not reception information has been received from the terminal device 2, for example.

[0091] (Step S302) The inquiry acquisition unit 131 judges whether the class of the reception information received in step S301 is a "question" or a "non-question". If it is a "question", proceed to step S303, and if it is not a "question", proceed to step S308. Note that the entire reception information being a "question" means that it is composed of a predetermined character string such as "Is it...?" or "Is it...?". Also, whether a character string is a "question" or a "non-question" can be determined by machine learning prediction processing (publicly known technology).

[0092] (Step S303) Prompt generator 135 composes a prompt including the reception information received in step S301. Note that the prompt is, for example, the reception information.

[0093] (Step S304) The answer acquisition unit 136 passes the prompt constructed in step S303 to the generation AI. Here, the answer acquisition unit 136, for example, assigns the prompt to an argument of the API of the generation AI and executes the API.

[0094] (Step S305) The answer acquisition unit 136 judges whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S306, and if an answer has not been acquired, the process returns to step S305. Here, the answer acquisition unit 136 acquires the answer, which is, for example, the return value of the executed API.

[0095] (Step S306) The output acquisition unit 137 composes output information including all or part of the answer acquired in step S305. When the output acquisition unit 137 acquires part of the answer, for example, it manages information for determining the part to be acquired (for example, "information for identifying the part of the text") and acquires part of the answer using such information.

[0096] (Step S307) The output unit 14 outputs the output information constructed in step S306. The process returns to step S301.

[0097] (Step S308) The inquiry acquisition unit 131 etc. performs processing on the reception information received in step S301, and outputs output information. Return to step S301. An example of such reception information processing will be described with reference to the flowchart of FIG.

[0098] In the flowchart of FIG. 3, the process ends when the power is turned off or an interrupt occurs to end the process.

[0099] Next, an example of the received information processing in step S308 will be described with reference to the flowchart in FIG.

[0100] (Step S401) The class determination unit 132 acquires the document type, which is the reception information. Note that here, the class determination unit 132 may not be able to acquire the document type. The document type may be a "class." The class determination unit 132 determines the document type, for example, from the file name of the reception information. The class determination unit 132 determines the document type, for example, from a character string corresponding to a specific tag (for example, [document name]) in the reception information.

[0101] The class determination unit 132, for example, provides the reception information and the learning model to a machine learning prediction module, executes the prediction module, and acquires the document type. The learning model is information configured by a machine learning learning process, and is information used in the machine learning prediction process. The learning model may be called a learner, a classifier, a classification model, or the like. In this specification, the machine learning algorithm may be deep learning, random forest, decision tree, SVM, or the like. In addition, for machine learning, for example, various machine learning functions such as the TensorFlow (registered trademark) library, the random forest module of the R language, fastText, TinySVM, and various existing libraries may be used.

[0102] (Step S402) The class determination unit 132 obtains one or more class conditions that match the type obtained in step S401 from the template management unit 111. If the document type cannot be obtained in step S401, the class determination unit 132 obtains one or more class conditions that do not correspond to any document type from the template management unit 111.

[0103] (Step S403) The class determination unit 132 assigns 1 to a counter i.

[0104] (Step S404) The class determination unit 132 judges whether or not the i-th class condition exists among the class conditions acquired in step S402. If the i-th class condition exists, the process proceeds to step S405, and if not, the process returns to the upper process.

[0105] (Step S405) The processing unit 13 performs processing on the reception information using the i-th class condition. An example of such class condition processing will be described with reference to the flowchart of FIG.

[0106] (Step S406) The class determination unit 132 increments the counter i by 1. The process returns to step S404.

[0107] Next, an example of the class condition processing in step S405 will be described with reference to the flowchart in FIG.

[0108] (Step S501) The template acquisition unit 134 acquires, from the template management unit 111, prompt template information that is paired with the i-th class condition of step S404.

[0109] (Step S502) The query acquisition unit 131 judges whether or not a tag exists in the i-th class condition. If the tag exists, the process proceeds to step S503, and if the tag does not exist, the process proceeds to step S505. Note that the presence of a tag in a class condition means that the tag is a condition.

[0110] (Step S503) The query acquiring unit 131 acquires a tag in the i-th class condition.

[0111] (Step S504) The inquiry acquiring unit 131 acquires, from the received information, tag content, which is information corresponding to the tag acquired in step S503. The tag content is usually a character string corresponding to the tag.

[0112] (Step S505) The query acquisition unit 131 judges whether or not a linguistic characteristic is present in the i-th class condition. If the linguistic characteristic is present, the process proceeds to step S504. If the linguistic characteristic is not present, the process proceeds to step S508. Note that the presence of a linguistic characteristic in a class condition means that the linguistic characteristic is a condition.

[0113] (Step S506) The query acquiring unit 131 acquires the linguistic characteristics of the i-th class condition.

[0114] (Step S507) If the query acquisition unit 131 acquires a tag in the i-th class condition, it acquires one or more pieces of query information that are information in the tag content acquired in step S504 and match the linguistic characteristics acquired in step S506. If the query acquisition unit 131 does not acquire a tag in the i-th class condition, it acquires one or more pieces of query information that are information in the received reception information and match the linguistic characteristics acquired in step S506. Go to step S509.

[0115] (Step S508) If a tag exists in the i-th class condition, the query acquisition unit 131 acquires the tag content acquired in step S504 as query information. If a tag does not exist in the i-th class condition, the query acquisition unit 131 acquires the accepted reception information as query information.

[0116] (Step S509) Prompt generator 135 assigns 1 to counter i.

[0117] (Step S510) Prompt generator 135 determines whether the i-th query information is present among the queries acquired in step S507 or step S508. If the i-th query information is present, the process proceeds to step S510; if not, the process returns to the upper level process.

[0118] (Step S511) Prompt creation unit 135 acquires the i-th inquiry information from the inquiry information acquired in step S507 or step S508. Prompt creation unit 135 places the i-th inquiry information in the variable portion of the prompt template information acquired in step S501, and creates a prompt.

[0119] (Step S512) The answer acquisition unit 136 passes the prompt created in step S511 to the generation AI.

[0120] (Step S513) The answer acquisition unit 136 determines whether or not an answer has been acquired from the generation AI. If an answer has been acquired, the process proceeds to step S514; if an answer has not been acquired, the process returns to step S513.

[0121] (Step S514) The output acquisition unit 137 acquires the output information. An example of such output acquisition processing will be described with reference to the flowchart of FIG.

[0122] (Step S515) Prompt generator 135 increments counter i by 1. The process returns to step S510.

[0123] Next, an example of the output acquisition process in step S514 will be described with reference to the flowchart in FIG.

[0124] (Step S601) The output acquisition unit 137 acquires a process type paired with a class condition from the template management unit 111.

[0125] (Step S602) The output acquisition unit 137 judges whether or not the process type acquired in step S601 is “addition.” If it is “addition,” the process proceeds to step S603, and if it is not “addition,” the process proceeds to step S604.

[0126] (Step S603) The output acquisition unit 137 places the acquired answer or part of the answer in a predetermined position for the inquiry information, and then returns to the upper level process.

[0127] (Step S604) The output acquisition unit 137 judges whether or not the process type acquired in step S601 is “change.” If it is “change,” the process proceeds to step S605, and if it is not “change,” the process proceeds to step S606.

[0128] (Step S605) The output acquisition unit 137 updates the inquiry information to the answer or a part of the answer, and returns to the upper process.

[0129] (Step S606) The output acquisition unit 137 judges whether the process type acquired in step S601 is "check". If it is "check", the process proceeds to step S607, and if it is not "check", the process returns to the upper process. Note that "check" may also be called "inspection".

[0130] (Step S607) The output acquisition unit 137 associates the answer or a part of the answer with the inquiry information, and returns to the upper process.

[0131] A specific example of the operation of the information system A in this embodiment will be described below.

[0132] Currently, the template management table shown in Figure 7 is stored in the template management unit 111 of the information processing device 1. The template management table has "ID," "class condition," "prompt template information," and "processing type." The "class condition" has "tag" and "linguistic characteristic." Note that an identifier of the generation AI device 3 is associated with the "prompt template information," and an answer may be obtained using the generation AI device 3 that is paired with the prompt template information to be used.

[0133] In FIG. 7, "ID" is information that identifies a record. "Tag" is a tag that may be included in the reception information. An example of a tag included in the invention list is [Invention 1]. An example of a tag included in the specification is [Form for implementing the invention]. "Linguistic characteristics" are, for example, "sentence," "paragraph," "component," and "technical term." In the "prompt template information," <query information> is a variable, and <query information> is replaced with the query information acquired by the query acquisition unit 131.

[0134] "Processing type" is information indicating the type of processing when an answer is added. Here, "processing type" is information indicating the type of processing when an answer is added to received information. Here, "processing type" is "add," "check," or "change." Also, here, the attribute values ​​of the character string of the output answer differ depending on the "processing type." The attribute values ​​of the character string are, for example, font, color, size, and the presence or absence of underlining.

[0135] In FIG. 7, when the processing type is "add", it is indicated that the output acquisition unit 137 adds the answer to the received information. When the processing type is "add", it is indicated here that the output acquisition unit 137 adds the answer immediately after the sentence having the inquiry information (including the sentence which is the inquiry information). Also, when the processing type is "check", it is indicated that the output acquisition unit 137 adds the answer to the received information in association with the inquiry information to be checked. When the processing type is "change", it is indicated that the output acquisition unit 137 replaces the inquiry information in the received information with the answer.

[0136] In the above situation, three specific examples will be described. Example 1 is when the document is an invention list. Example 2 is when the document is a specification. Example 3 is when the document is an abstract.

[0137] (Example 1) It is assumed that the user inputs, into the information processing device 1, a file "InventionList20231125.docx" in which the character string shown in FIG.

[0138] Next, the reception unit 12 of the information processing device 1 receives reception information "Invention list 20231125.docx" from the user. Next, the inquiry acquisition unit 131 opens the file "Invention list 20231125.docx", acquires its contents, detects that it does not end with "?", and determines that the received reception information is not a "question" (is a "non-question").

[0139] Next, the inquiry acquisition unit 131 etc. processes the received reception information as follows, and outputs output information.

[0140] First, the class determination unit 132 obtains the document type "invention list" from the file name of the received information "invention list 20231125.docx".

[0141] Next, the class determination unit 132 acquires the class conditions of "ID=1" and "ID=4" that match the type "invention list." Note that the document type "*" of "ID=4" indicates that it matches any document type.

[0142] Next, the class determination unit 132 acquires the class condition "<tag> invention 1 <linguistic property>-" of "ID=1" from the template management table (FIG. 7).

[0143] Moreover, the template acquisition unit 134 acquires the prompt template information "Tell me the subordinate concept of the following invention! Invention "<Inquiry information>"" that is paired with the class condition of "ID=1" from the template management table (FIG. 7).

[0144] Next, the query acquisition unit 131 acquires the tag "Invention 1" in the class condition from the template management table (Figure 7). Next, the query acquisition unit 131 acquires the tag content "electrical device that detects the presence of a person and changes the advertisement output", which is information corresponding to the acquired tag "Invention 1", from the reception information (Figure 8). Next, the query acquisition unit 131 determines that no linguistic characteristics are present in the class condition. Next, the query acquisition unit 131 sets the acquired tag content "electrical device that detects the presence of a person and changes the advertisement output" as query information.

[0145] Next, the prompt creation unit 135 replaces the variable <inquiry information> of the acquired prompt template information with "an electrical device that detects the presence of a person and changes the advertisement output" and acquires the prompt "Please tell me the sub-concept of the following invention! Invention "an electrical device that detects the presence of a person and changes the advertisement output"."

[0146] Next, the answer acquisition unit 136 passes the created prompt to the generation AI. Then, the answer acquisition unit 136 acquires an answer from the generation AI. It is assumed that the answer is, for example, the sentence 901 in FIG.

[0147] Next, the output acquisition unit 137 acquires output information as follows: That is, the output acquisition unit 137 acquires the process type "addition" that is paired with the class condition of "ID=1" from the template management table.

[0148] Next, the output acquisition unit 137 places the acquired response to the inquiry information at a predetermined position (here, immediately after the tag sentence (inquiry information) of invention 1) to obtain the information of FIG.

[0149] Next, the class determination unit 132 acquires the class condition "<tag>-<linguistic property> sentence" of "ID=4" from the template management table (FIG. 7). Then, the information processing device 1 performs the same process as above for the class condition of "ID=4", but here, the output acquisition unit 137 does not acquire output information.

[0150] (Example 2) It is assumed that the user inputs, into the information processing device 1, a file "specification20231125.docx" in which the character string shown in FIG.

[0151] Next, the reception unit 12 of the information processing device 1 receives reception information "specification20231125.docx" from the user. Next, the inquiry acquisition unit 131 determines that the reception information is not a "question" from the contents of the received file "specification20231125.docx".

[0152] Next, the inquiry acquisition unit 131 etc. processes the received reception information as follows, and outputs output information.

[0153] First, the class determination unit 132 obtains the character string "specification" that pairs with the tag [document name] in the file of the reception information "specification20231125.docx", and obtains the document type "specification" from the character string.

[0154] Next, the class determination unit 132 obtains the class conditions for "ID=2" and "ID=4" that match the type "specification".

[0155] Next, the class determination unit 132 obtains the class conditions of "ID=2" "<tag>-<linguistic property> sentence", "<tag>-<linguistic property> paragraph", "<tag> form for carrying out the invention <linguistic property> component", and "<tag> form for carrying out the invention <linguistic property> technical term" from the template management table (FIG. 7). The class determination unit 132 also obtains the class condition of "ID=4" "<tag>-<linguistic property> sentence" from the template management table (FIG. 7).

[0156] Furthermore, the template acquisition unit 134 acquires prompt template information paired with each class condition of "ID=2" from the template management table (FIG. 7) in association with each class condition.

[0157] Next, the query acquisition unit 131 sequentially acquires sentences from the file “specification20231125.docx” based on the class condition “<tag>-<linguistic property> sentence” of “ID=2.” Each sentence is query information.

[0158] Next, the prompt creation unit 135 places each sentence in the <inquiry information> section of the prompt template information "Please tell me with YES / NO whether the following sentence has a subject or not. sentence "<inquiry information>". As a result, the prompt creation unit 135 creates, for example, a prompt "Please tell me with YES / NO whether the following sentence has a subject or not. sentence "The inquiry acquisition unit 131 acquires inquiry information, which is information contained in the reception information and is information used to query the generation AI." and a prompt "Please tell me with YES / NO whether the following sentence has a subject or not. sentence "At least two pieces of inquiry information are acquired from the reception information."

[0159] Next, the answer acquisition unit 136 passes each created prompt to the generation AI. Then, the answer acquisition unit 136 acquires an answer ("YES" or "NO") from the generation AI for each prompt. Note that the answer to the inquiry information "Acquire inquiry information that is included in the reception information and is information to be used to inquire of the generation AI" was "YES", and the answer to the inquiry information "Acquire at least two pieces of inquiry information from the reception information" was "NO".

[0160] In addition, the query acquisition unit 131 sequentially acquires all of the sentences in the paragraphs corresponding to each paragraph number from the file "Specification20231125.docx" based on the class condition "<tag>-<linguistic characteristic>paragraph" of "ID=2". All of the sentences in the paragraphs are query information.

[0161] Next, the prompt creation unit 135 places all of the sentences in the paragraph in the <inquiry information> of the prompt template information "Please tell me with YES / NO whether the number of characters in the following sentence group is 500 characters or less. Sentence group "<inquiry information>"" that is paired with the class condition for each paragraph, and creates a prompt. The prompt creation unit 135 creates, for example, "Please tell me with YES / NO whether the number of characters in the following sentence group is 500 characters or less. Sentence group "The information processing device of the first invention is an information processing device that includes .... With this configuration, it is possible to use a generation AI by using an appropriate prompt according to the class of the inquiry information. Furthermore, the information processing device of the second invention is an information processing device that is ... for the first invention. With this configuration, it is possible to support the creation of patent documents by using a generation AI by using an appropriate prompt according to the class of the information of the invention."

[0162] Next, the answer acquisition unit 136 passes each of the created prompts to the generation AI. Then, the answer acquisition unit 136 acquires an answer ("YES" or "NO") from the generation AI for each prompt. Note that the answer to the inquiry information "The information processing device of the first invention is an information processing device comprising... With such a configuration, the generation AI can be utilized by using an appropriate prompt according to the class of the inquiry information. Also, the information processing device of the second invention is an information processing device which, with respect to the first invention, is... With such a configuration, the generation AI can be utilized by using an appropriate prompt according to the class of the information of the invention to assist in the preparation of patent documents." was "NO".

[0163] Furthermore, the query acquisition unit 131 acquires components from a sentence corresponding to the tag [Form for carrying out the invention] in the file "Specification20231125.docx" based on the class condition "<tag>Form for carrying out the invention <linguistic characteristics>Component" of "ID=2". Here, the query acquisition unit 131 acquires a noun phrase (reception unit, query acquisition unit, terminal storage unit, etc.) immediately followed by a code (numeric string) as a component.

[0164] Next, the prompt creation unit 135 places each component in the <inquiry information> of the prompt template information "Please list terms that are subordinate to the <inquiry information>!" that is paired with the class condition, and creates a prompt. For example, the prompt creation unit 135 creates "Please list terms that are subordinate to the reception section!".

[0165] Next, the answer acquisition unit 136 passes each of the created prompts to the generation AI. Then, the answer acquisition unit 136 acquires an answer from the generation AI for each prompt. It should be noted that the answer to the inquiry information "reception department" is "provide information about a general sub-concept of 'reception department'. Sub-concepts of the reception department may include the following functions and elements: reception desk, information counter, guest management, visitor registration, appointment arrangement, security check-in, telephone response, and information service."

[0166] Furthermore, the query acquisition unit 131 acquires technical terms from a sentence corresponding to the tag [Form for carrying out the invention] in the file "Specification20231125.docx" based on the class condition "<tag>Form for carrying out the invention <linguistic characteristics>Technical terminology" of "ID=2". Note that the technology for acquiring technical terms from a sentence can be a publicly known technology such as "termextract" (URL: http: / / gensen.dl.itc.u-tokyo.ac.jp / pytermextract / ), for example. Here, the inquiry acquisition unit 131 acquires, for example, the technical term "generation AI" from the sentence "The inquiry acquisition unit 131 acquires inquiry information, which is information contained in the reception information and is information used to inquire the generation AI," in the tag [Form for implementing the invention].

[0167] Next, the prompt creation unit 135 creates a prompt by placing each technical term in the <inquiry information> of the prompt template information "Please tell me the definition and specific example of <inquiry information>!" that is paired with the class condition for each technical term. For example, the prompt creation unit 135 creates "Please tell me the definition and specific example of generation AI!"

[0168] Next, the answer acquisition unit 136 passes each created prompt to the generation AI. Then, the answer acquisition unit 136 acquires an answer from the generation AI for each prompt. It should be noted that the answer to the inquiry information "generation AI" is "Generation AI is a type of artificial intelligence and refers to a system that generates new content based on input data. Specific examples include the following: Text generation: AIs such as the GPT series can create stories or articles from given prompts. Image generation: DALL-E and this AI system can do... Music generation: AIs such as AIVA can do... Voice synthesis: Can do...."

[0169] Furthermore, the query acquisition unit 131 sequentially acquires sentences from the file “specification20231125.docx” based on the class condition “<tag>-<linguistic property> sentence” of “ID=4.” Each of these sentences is query information.

[0170] Next, the prompt creation unit 135 places each sentence in the <query information> portion of the prompt template information "If the following sentence is a compound sentence, change it to multiple simple sentences with a subject! Sentence "<query information>"". As a result, the prompt creation unit 135 creates, for example, a prompt "If the following sentence is a compound sentence, change it to multiple simple sentences with a subject! Sentence "The terminal storage unit 21 is preferably a non-volatile recording medium, but can also be realized with a volatile recording medium, and the process by which information is stored in the terminal storage unit 21 is not important."

[0171] Next, the answer acquisition unit 136 passes each of the created prompts to the generation AI. Then, the answer acquisition unit 136 acquires an answer from the generation AI for each prompt. Note that the answer to the inquiry information "The terminal storage unit 21 is preferably a non-volatile recording medium, but can also be realized as a volatile recording medium, and the process by which information is stored in the terminal storage unit 21 is not important" was "The terminal storage unit 21 is preferably a non-volatile recording medium, but can also be realized as a volatile recording medium. The process by which information is stored in the terminal storage unit 21 is not important."

[0172] Next, the output acquiring unit 137 acquires output information as follows: That is, the output acquiring unit 137 acquires, from the template management table, the process types paired with the class conditions of "ID=2" and "ID=4" in the template management table.

[0173] Next, the output acquisition unit 137 adds the answer corresponding to the processing type "Check" to the received information "Specification 20231125.docx" as a comment to the inquiry information. If the answer to the prompt template information "Please tell us with YES / NO whether the following sentence has a subject or not. <Inquiry information>" is "NO", the output acquisition unit 137 adds "This sentence does not have a subject" as a comment to the inquiry information (sentence). An example of such a comment is 1101 in FIG. 11.

[0174] Also, if the answer to the prompt template information "Please tell us with YES / NO whether the number of characters in the following sentence group is 500 characters or less. Sentence group "<Inquiry information>"" is "NO", the output acquisition unit 137 adds "This paragraph exceeds 500 characters" as a comment to the inquiry information (paragraph). An example of such a comment is 1102 in FIG. 11.

[0175] Furthermore, the output acquiring unit 137 places the answer corresponding to the processing type "add" immediately after the sentence which is the inquiry information, the paragraph which is the inquiry information, or the sentence which includes the inquiry information. For example, the answer to the inquiry information "reception unit" is placed immediately after the sentence "The reception unit 12 receives the reception information from the user" which includes the inquiry information "reception unit". Such an answer is 1103 in FIG. 11.

[0176] Also, the output acquisition unit 137 places, for example, a response to the inquiry information "generation AI" immediately after a sentence including the generation AI, "The inquiry acquisition unit 131 acquires the inquiry information, which is information included in the reception information and is information used to inquire the generation AI." Such a response is 1104 in FIG.

[0177] Furthermore, for a response corresponding to the processing type "change", the output acquisition unit 137 replaces the inquiry information with the response. For example, the output acquisition unit 137 replaces the inquiry information, which is a complex sentence, "The terminal storage unit 21 is preferably a non-volatile recording medium, but can also be realized with a volatile recording medium, and the process by which information is stored in the terminal storage unit 21 does not matter" with the response to the inquiry information, "The terminal storage unit 21 is preferably a non-volatile recording medium, but can also be realized with a volatile recording medium. The process by which information is stored in the terminal storage unit 21 does not matter."

[0178] Next, the output unit 14 outputs the "specification 20231125.docx" corrected using the answer of the generation AI. An example of such output is shown in FIG.

[0179] (Example 3) It is assumed that the user inputs, into the information processing device 1, a file "Abstract20231125.docx" in which the character string shown in FIG.

[0180] Next, the reception unit 12 of the information processing device 1 receives reception information "Abstract20231125.docx" from the user. Next, the inquiry acquisition unit 131 determines that the reception information is not a "question" from the contents of the received file "Abstract20231125.docx".

[0181] Next, the inquiry acquisition unit 131 etc. processes the received reception information as follows, and outputs output information.

[0182] First, the class determination unit 132 obtains the character string "abstract" that pairs with the tag [document name] in the file of the reception information "abstract20231125.docx", and obtains the document type "abstract" from the character string.

[0183] Next, the class determination unit 132 acquires the class conditions for "ID=3" and "ID=4" that match the type "abstract." For convenience of explanation, the following will describe the case where only the class condition for "ID=3" is applied.

[0184] Next, the class determination unit 132 obtains the class condition "<tag>-<linguistic property>-" of "ID=3" from the template management table (FIG. 7). The class determination unit 132 also obtains the class condition "<tag>-<linguistic property> sentence" of "ID=4" from the template management table (FIG. 7).

[0185] Furthermore, the template acquisition unit 134 acquires prompt template information paired with the class condition of "ID=3" from the template management table (FIG. 7) in association with each class condition.

[0186] Next, the inquiry acquiring unit 131 acquires the received information (the entire abstract in FIG. 12) as inquiry information from the class condition "<tag>-<linguistic characteristic>-".

[0187] Next, the prompt creation unit 135 creates a prompt by replacing the <inquiry information> in the prompt template information "If the following document is longer than 400 characters, please summarize it in 400 characters or less!" with the entire abstract (Figure 12).

[0188] Next, the answer acquisition unit 136 passes each of the created prompts to the generation AI, and the answer acquisition unit 136 obtains a summary of up to 400 characters.

[0189] Next, the output acquisition unit 137 acquires output information as follows: That is, the output acquisition unit 137 acquires the process type "change" that is paired with the class condition of "ID=3" in the template management table from the template management table.

[0190] Furthermore, for a response corresponding to the processing type "change", the output acquisition unit 137 replaces the inquiry information with the response. That is, the output acquisition unit 137 acquires the acquired response as a summary.

[0191] Next, the output unit 14 outputs the abstract obtained using the answer of the generating AI. An example of such output is shown in FIG.

[0192] As described above, according to this embodiment, an appropriate prompt is created according to the class of inquiry information, and the generation AI can be used using the prompt.

[0193] Furthermore, according to this embodiment, an appropriate prompt can be created according to the class of information of the invention, and the prompt can be used to utilize a generation AI to assist in the creation of patent documents.

[0194] Furthermore, according to this embodiment, it is possible to provide a generative AI control engine that makes the most of generative AI.

[0195] The processing in this embodiment may be realized by software. This software may be distributed by software download or the like. This software may also be recorded on a recording medium such as a CD-ROM and distributed. This also applies to the other embodiments in this specification. The software that realizes information system A in this embodiment is a program such as the following. In other words, this program causes a computer that can access a template management unit in which prompt template information is stored in correspondence with one or more class conditions, which are conditions related to a class of strings, to function as a reception unit that receives reception information from a user, a query acquisition unit that acquires query information, which is information contained in the reception information and is used to query a generation AI, a template acquisition unit that acquires from the template management unit prompt template information corresponding to the class conditions satisfied by the class of the query information acquired by the query acquisition unit, a prompt creation unit that creates a prompt using the prompt template information acquired by the template acquisition unit and the query information acquired by the query acquisition unit, an answer acquisition unit that passes the prompt created by the prompt creation unit to a generation AI and acquires an answer from the generation AI, an output acquisition unit that acquires output information using the answer acquired by the answer acquisition unit, and an output unit that outputs the output information.

[0196] Fig. 14 shows the appearance of a computer that executes the program described in this specification to realize the information processing device 1 and the like of the various embodiments described above. The above-mentioned embodiments can be realized by computer hardware and a computer program executed thereon. Fig. 14 is an overview of this computer system 300, and Fig. 15 is a block diagram of the system 300.

[0197] In FIG. 14, a computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0198] 15, computer 301 includes, in addition to CD-ROM drive 3012, MPU 3013, bus 3014 connected to CD-ROM drive 3012 etc., ROM 3015 for storing programs such as a boot-up program, RAM 3016 connected to MPU 3013 for temporarily storing instructions of application programs and providing temporary storage space, and hard disk 3017 for storing application programs, system programs, and data. Although not shown here, computer 301 may further include a network card for providing connection to a LAN.

[0199] A program for causing computer system 300 to execute the functions of information processing device 1 and the like of the above-mentioned embodiment may be stored on CD-ROM 3101, inserted into CD-ROM drive 3012, and further transferred to hard disk 3017. Alternatively, the program may be transmitted to computer 301 via a network (not shown) and stored on hard disk 3017. The program is loaded into RAM 3016 at the time of execution. The program may be loaded directly from CD-ROM 3101 or the network.

[0200] The program does not necessarily include an operating system (OS) or a third party program that causes the computer 301 to execute the functions of the information processing device 1 of the above-mentioned embodiment. The program only needs to include an instruction portion that calls appropriate functions (modules) in a controlled manner to obtain a desired result. How the computer system 300 operates is well known, and a detailed description will be omitted.

[0201] In addition, in the above program, the steps of transmitting information and receiving information do not include processing performed by hardware, such as processing performed by a modem or interface card in the transmitting step (processing that is performed only by hardware).

[0202] The program may be executed by a single computer or a plurality of computers, that is, centralized processing or distributed processing may be performed.

[0203] Furthermore, in each of the above embodiments, it goes without saying that two or more communication means present in one device may be physically realized by one medium.

[0204] Furthermore, in each of the above embodiments, each process may be realized by centralized processing in a single device, or may be realized by distributed processing in a plurality of devices.

[0205] The present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these modifications are also included within the scope of the present invention. [Industrial Applicability]

[0206] As described above, the information processing device 1 of the present invention has the effect of being able to utilize a generation AI by using an appropriate prompt according to the class of inquiry information, and is useful as a specification creation support device, a document creation support device, etc. [Explanation of symbols]

[0207] 1. Information processing device 2 Terminal Device 3 Generation AI device 11 Storage area 12 Reception 13 Processing section 14 Output section 21 Terminal storage section 22 Terminal Reception 23 Terminal Processing Section 24 Terminal transmitter 25 Terminal receiving section 26 Terminal Output Section 111 Template Management Department 131 Inquiry Acquisition Department 132 Class Decision Section 133 Generation AI decision unit 134 Template acquisition part 135 Prompt Creation Department 136 Answer acquisition part 137 Output Acquisition Unit

Claims

1. a template management unit in which prompt template information is stored in association with two or more class conditions, the class conditions being related to a class of character strings, the class conditions including one or two types of conditions of a tag in the reception information or a linguistic characteristic condition of a character string in the reception information; A reception unit that receives reception information; An inquiry acquisition unit that acquires inquiry information, which is information included in the reception information, is a character string that matches each of the two or more class conditions, and is a character string used to make an inquiry to the generation AI; a template acquisition unit that acquires, from the template management unit, prompt template information that is paired with a class condition that matches the inquiry information acquired by the inquiry acquisition unit; a prompt creating unit that creates a prompt using the prompt template information acquired by the template acquiring unit and the inquiry information acquired by the inquiry acquiring unit; an answer acquisition unit that transfers the prompt created by the prompt creation unit to a generation AI and acquires an answer from the generation AI; an output acquisition unit that acquires output information using the answer acquired by the answer acquisition unit; and an output unit that outputs the output information.

2. The received information is information related to an invention, 2. An information processing apparatus according to claim 1, wherein the output information is information constituting a patent specification, claims, or abstract.

3. The inquiry acquisition unit, acquiring two or more pieces of inquiry information from the reception information for at least one class condition; The prompt creation unit is 2 . The information processing apparatus according to claim 1 , further comprising: a prompt generating unit that generates a prompt for the one class condition by arranging each of the two or more pieces of inquiry information in prompt template information acquired for the one class condition.

4. The output acquisition unit is 2. The information processing apparatus according to claim 1, wherein a part or all of the answers are arranged in output template information that is a template for configuring output information, and the output information is acquired.

5. 2. The information processing apparatus according to claim 1, wherein the linguistic characteristics are "sentences," "paragraphs," "words," "constituent elements" that specify an invention, or "technical terms."

6. Further comprising a class determination unit that determines whether the reception information is a "question", The template acquisition unit is If the class determination unit determines that the received information is a "question", the prompt template information is not acquired, The prompt creation unit is The information processing apparatus according to claim 1 , wherein a prompt including the reception information is generated.

7. The reception information is a document, The information processing apparatus according to claim 1 , wherein the class includes a type of the document.

8. The method further includes a generation AI determination unit that determines a generation AI according to the prompt template information acquired by the template acquisition unit from two or more generation AIs, The answer acquisition unit, The information processing apparatus according to claim 1 , wherein the prompt created by the prompt creating unit is passed to the generation AI determined by the generation AI determination unit, and an answer is obtained from the generation AI.

9. Each of the two or more pieces of prompt template information in the template management unit is associated with a processing type that specifies a type of processing for the output information, The process type includes "add" and "change", The output acquisition unit is when the process type paired with the prompt template information used to obtain the answer obtained by the answer obtaining unit is “add”, the answer or a part of the answer is placed at a predetermined position with respect to the inquiry information on which the answer is based, 2. The information processing device according to claim 1, wherein, when the processing type paired with the prompt template information used to obtain the answer obtained by the answer obtaining unit is "change," the answer or a part of the answer is updated to the inquiry information on which the answer is based with the answer or a part of the answer.

10. An information processing method is implemented by a template management unit in which prompt template information is stored in association with two or more class conditions, the class conditions being conditions related to a class of character strings, the class conditions including one or two types of conditions of a tag in received information or a linguistic characteristic condition of a character string in the received information, a reception unit, a query acquisition unit, a template acquisition unit, a prompt creation unit, a response acquisition unit, an output acquisition unit, and an output unit, a receiving step in which the receiving unit receives reception information; An inquiry acquisition step in which the inquiry acquisition unit acquires inquiry information, which is information included in the reception information, is a character string that matches each of the two or more class conditions, and is a character string used to make an inquiry to a generation AI; a template acquisition step in which the template acquisition unit acquires, from the template management unit, prompt template information corresponding to a class condition satisfied by a class of the inquiry information acquired by the inquiry acquisition unit; a prompt creating step in which the prompt creating unit creates a prompt using the prompt template information acquired by the template acquiring unit and the query information acquired by the query acquiring unit; an answer acquisition step in which the answer acquisition unit passes the prompt created by the prompt creation unit to a generation AI and acquires an answer from the generation AI; an output information acquisition step in which the output acquisition unit acquires output information by using the answer acquired by the answer acquisition unit; and an output step in which the output unit outputs the output information.

11. a computer that can access a template management unit in which prompt template information is stored in association with two or more class conditions, the class conditions being related to a class of character strings, the class conditions including one or two of a tag condition in the reception information or a linguistic characteristic condition of a character string in the reception information; A reception unit that receives reception information; An inquiry acquisition unit that acquires inquiry information, which is information included in the reception information, is a character string that matches each of the two or more class conditions, and is a character string used to make an inquiry to the generation AI; a template acquisition unit that acquires, from the template management unit, prompt template information corresponding to a class condition satisfied by a class of the inquiry information acquired by the inquiry acquisition unit; a prompt creating unit that creates a prompt using the prompt template information acquired by the template acquiring unit and the inquiry information acquired by the inquiry acquiring unit; an answer acquisition unit that transfers the prompt created by the prompt creation unit to a generation AI and acquires an answer from the generation AI; an output acquisition unit that acquires output information using the answer acquired by the answer acquisition unit; A program for causing the output unit to function as an output unit that outputs the output information.

Citation Information

Patent Citations

  • Manuscript generation method and device, equipment and storage medium

    CN116741178A

  • Guide rail structure of hydraulic drilling rig and multifunctional full-hydraulic drilling rig thereof

    CN116856855A

  • Language model-based image report generation method and system

    CN116884559A

  • JPP7370118B

Cited By

  • Information processing systems, computers, information processing methods, and programs

    JP2026142462A

  • Information processing device and information processing method

    WO2026196417A1