Information processing device, information processing method and program

Abstract

To address such a problem that conventionally, it has not been easy to use a generative AI with appropriate prompts according to classes of inquiry information.SOLUTION: An information processing device 1 includes: a template management unit 111 for storing prompt template information in association with one or more class conditions of a character string; an inquiry acquisition unit 131 for acquiring inquiry information, the information used for an inquiry to a generative AI, from reception information; a template acquisition unit 134 for acquiring from the template management unit 111, a prompt template information corresponding to a class condition satisfied by a class of the inquiry information; a prompt creation unit 135 for creating a prompt using the prompt template information and the inquiry information; an answer acquisition unit 136 for passing the prompt to the generative AI and acquiring an answer from the generative AT; an output acquisition unit 137 for acquiring output information; and an output unit 14 for outputting the output information. The information processing device can thus use the generative AI with appropriate prompts according to classes of inquiry information.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an information processing apparatus and the like that acquires and outputs information using generative AI.

Background Art

[0002] Recently, generative AI has been spreading (see Patent Document 1).

Prior Art Documents

Non-Patent Documents

[0003]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, it has not been easy to give an appropriate prompt to generative AI. More specifically, it has not been easy to use generative AI with an appropriate prompt according to the class of inquiry information. Here, the generative AI is an AI that generates text.

Means for Solving the Problems

[0005] The information processing apparatus of this first invention includes a template management unit that stores prompt template information in association with one or more class conditions, which are conditions related to the class of a character string; a reception unit that receives reception information from a user; an inquiry acquisition unit that acquires inquiry information, which is information included in the reception information and used for querying a generation AI; a template acquisition unit that acquires from the template management unit the prompt template information corresponding to the class condition satisfied by the class of the inquiry information acquired by the inquiry acquisition unit; a prompt creation unit that creates a prompt using the prompt template information acquired by the template acquisition unit and the inquiry information acquired by the inquiry acquisition unit; a response acquisition unit that passes the prompt created by the prompt creation unit to the generation AI and acquires a response from the generation AI; an output acquisition unit that acquires output information using the response acquired by the response acquisition unit; and an output unit that outputs the output information.

[0006] With such a configuration, the generation AI can be utilized using an appropriate prompt according to the class of the inquiry information.

[0007] Further, the information processing apparatus of this second invention is an information processing apparatus that, with respect to the first invention, the reception information is information related to the invention, and the output information is information constituting a patent specification or claims or an abstract.

[0008] With such a configuration, the generation AI can be utilized using an appropriate prompt according to the class of the invention information, and the creation of patent documents can be supported.

[0009] Moreover, the information processing apparatus of this third invention is an information processing apparatus that, with respect 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] With such a configuration, the generation AI can be utilized using an appropriate prompt according to the class of the inquiry information.

[0011] Further, for the information processing apparatus of the fourth invention, in relation to any one of the first to third inventions, the output acquisition unit is an information processing apparatus that arranges part or all of the answer in output template information, which is a template for configuring output information, and acquires output information.

[0012] With such a configuration, by using an appropriate prompt according to the class of the inquiry information, the generative AI can be utilized to acquire appropriate output information.

[0013] Further, for the information processing apparatus of the fifth invention, in relation to any one of the first to fourth inventions, the class is the linguistic characteristic of the inquiry information, and it is an information processing apparatus.

[0014] With such a configuration, an appropriate class of the inquiry information can be determined, and the generative AI can be utilized by using an appropriate prompt according to the class.

[0015] Further, for the information processing apparatus of the sixth invention, in relation to the fifth invention, the class can take "question", and when the class determined by the class determination unit is "question", the template acquisition unit does not acquire the prompt template information, and the prompt creation unit is an information processing apparatus that creates a prompt using the inquiry information acquired by the inquiry acquisition unit.

[0016] With such a configuration, an appropriate class of the inquiry information can be determined, and the generative AI can be utilized by using an appropriate prompt according to the class.

[0017] Further, for the information processing apparatus of the seventh invention, in relation to any one of the first to sixth inventions, the class is a tag included in the reception information and is a tag corresponding to the inquiry information, and it is an information processing apparatus.

[0018] With such a configuration, an appropriate class of the inquiry information can be determined, and the generative AI can be utilized by using an appropriate prompt according to the class.

[0019] Further, the information processing apparatus of the eighth invention is an information processing apparatus in which, for any one of the first to seventh inventions, the received information is a document and the class is the type of the document.

[0020] With such a configuration, an appropriate class of the inquiry information can be determined, and the generation AI can be utilized using an appropriate prompt according to the class.

[0021] Further, the information processing apparatus of the ninth invention 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, for any one of the first to eighth inventions, 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. The information processing apparatus according to any one of claims 1 to 8.

[0022] With such a configuration, a generation AI control engine that makes the most of the generation AI can be provided.

Advantages of the Invention

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

Brief Description of the Drawings

[0024]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Mode for Carrying Out the Invention

[0025] Hereinafter, embodiments of an information processing apparatus and the like will be described with reference to the drawings. In the embodiments, components denoted by the same reference numerals perform the same operations, and thus the description may be omitted again.

[0026] (Embodiment 1) In the present embodiment, an information processing apparatus that determines a class of inquiry information, acquires prompt template information corresponding to the class, creates a prompt using the prompt template information, gives the prompt to a generative AI, acquires a response, and outputs output information using the response will be described. In particular, an information processing apparatus that outputs a part of a patent document using inquiry information related to an invention will be described. The class is information based on, for example, the linguistic characteristics of a character string, or tags corresponding to the character string, or the type of received document. Note that the prompt is a question given to the generative AI.

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

[0028] Also, in the present embodiment, an information processing apparatus that gives an answer obtained from a generative AI to output template information and acquires output information will be described.

[0029] Furthermore, in the present embodiment, an information processing apparatus that determines a generative AI according to a class and uses an answer from the generative AI to acquire output information will be described.

[0030] Note that 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 limited. Information X and information Y may be linked, may exist in the same buffer, information X may be included in information Y, information Y may be included in information X, etc.

[0031] Also, 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., as long as information Z can be accessed.

[0032] FIG. 1 is a conceptual diagram of an information system A in the present embodiment. The information system A includes an information processing apparatus 1, one or two or more terminal devices 2, and one or two or more generative AI devices 3.

[0033] The information processing apparatus 1 is an apparatus that receives received information, uses a generative AI to obtain an answer, and outputs output information using the answer. The information processing apparatus 1 is, for example, a cloud server, an ASP server, but its type is not limited. The information processing apparatus 1 may be a terminal. When the information processing apparatus 1 is a terminal, it may be considered that the terminal device 2 is unnecessary for the information system A, or the information processing apparatus 1 also serves as the terminal device 2. The information processing apparatus 1 may include a generative AI.

[0034] The terminal device 2 is a terminal used by a user who inputs reception information. The terminal device 2 is, for example, a so-called personal computer, smartphone, or tablet terminal, and its type is not limited.

[0035] The generation AI device 3 is a device having a generation AI that receives a prompt and outputs an answer. When the information processing device 1 includes a generation AI, the generation AI device 3 may not be provided.

[0036] Figure 2 is a block diagram of the information system A in the present 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 an inquiry 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 26.

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

[0039] Two or more pieces of prompt template information are stored in the template management unit 111. Class conditions are associated with each of the two or more pieces of prompt template information.

[0040] The prompt template information is information that serves as a template for creating a prompt. The prompt template information is usually a character string. The prompt template information has one or two or more variables. The variables are variables into which the inquiry information described later is substituted. The prompt template information has, for example, a character string that specifies a question and one or more variables. Note that, for example, the inquiry information is placed at the position of the variable in the prompt template information, and a prompt is created.

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

[0042] The class condition is a condition regarding the class described later. The class condition is a condition regarding one or more classes. The class is related to a character string. The class may be referred to as classification or type. The class may also be a field identifier. The class may be specified by one or more field identifiers. The field identifier is information that identifies a field on an input screen, which is a screen for inputting information. The field identifier is, for example, a field name or a field ID. Note that a field broadly refers to a space or element for a user to input, display, or select information. The field may include, for example, a text box for inputting "name" and "address" on a form screen, a drop-down menu, a checkbox, a radio button, a date field, etc.

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

[0044] Here, reception generally refers to the reception of information transmitted via a wired or wireless communication line, but may also include the reception of information input from input devices such as a keyboard, mouse, touch panel, etc., and the reception of information read from recording media such as optical disks, magnetic disks, semiconductor memories, etc.

[0045] The received information is usually the information input by the user. However, the received information may also be information obtained from a file or database. The received information is, for example, information related to the invention. The received information is, for example, information for identifying the invention. The received information is, for example, the claims, the specification, and the abstract. The received information is, for example, a document. The received information is, for example, a file. The received information is, for example, a sentence, one or more sentences, or a character string. Needless to say, the received information may also be the information input by the user on an input screen having one or more fields. Needless to say, the received information may also be the information input into one or more fields.

[0046] The processing unit 13 performs various processes. The various processes are, for example, the processes performed by 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, or the output acquisition unit 137.

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

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

[0049] One or more pieces of inquiry information acquired by the inquiry acquisition unit 131 from the received information are usually predetermined.

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

[0051] The inquiry acquisition unit 131 may acquire inquiry information based on information input in one or two or more fields. The inquiry information may be part or all of the information input in the fields. The inquiry information may be part or all of the information input in two or more fields.

[0052] The class determination unit 132 determines the class of the inquiry information. The class determination unit 132 may determine the class of the reception information. The class determination unit 132 determines, for example, the class of each one or more pieces of inquiry information acquired by the inquiry acquisition unit 131.

[0053] The class may be referred to as a type, classification, etc. The class is, for example, information based on linguistic characteristics, information based on tags corresponding to the inquiry information, and information based on the type of document in which the inquiry information is included.

[0054] The linguistic characteristics may be referred to as the attribute values of the language for the character string. The class based on the linguistic characteristics is, for example, "question" or "non-question". The class based on the linguistic characteristics is, for example, "sentence" or "word". The class based on the linguistic characteristics is, for example, "sentence", "paragraph", or "word". The class based on the linguistic characteristics is, for example, the part of speech of a word. The class based on the linguistic characteristics is, for example, "component", "technical term" that identifies an invention. "Technical term" may be "specialized term".

[0055] The tags corresponding to the inquiry information are, for example, tags in the specification, tags in the scope of the claims, and tags in the abstract. The class based on the tags is, for example, "problem to be solved by the invention", "means for solving the problem", "effect of the invention", "mode for carrying out the invention", "explanation of reference signs", "claim 1". The tags corresponding to the inquiry information are, for example, HTML tags or XML tags. The tag may be one or two or more field identifiers. That is, it goes without saying that the inquiry information may be information input in a feed identified by one or two or more field identifiers.

[0056] The class based on the document type is a class based on the type of received information that is a file. The classes based on the document type are, for example, "specification", "claims", "abstract", "invention list", "business daily report".

[0057] The class determination unit 132, for example, acquires the linguistic characteristics of the inquiry information and determines the class corresponding to the linguistic characteristics.

[0058] The class determination unit 132, for example, acquires the tag included in the received information, obtains the tag corresponding to the inquiry information from the received information, and determines the class corresponding to the tag.

[0059] The class determination unit 132, for example, acquires the type of the document that is the received information and determines the class corresponding to the type.

[0060] The generation AI determination unit 133, for example, determines the generation AI corresponding to the class from two or more generation AIs. In such a case, class conditions are associated with each of the two or more generation AIs. The generation AI determination unit 133, for example, determines the generation AI that pairs with the class conditions. Determining the generation AI is, for example, acquiring the API for using the generation AI. In such a case, the class conditions are associated with, for example, the API for passing a prompt to the generation AI. Determining the generation AI is, for example, acquiring the identifier (for example, 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 conditions.

[0061] The template acquisition unit 134 acquires the prompt template information corresponding to the class from the template management unit 111. The template acquisition unit 134, for example, acquires the prompt template information corresponding to the class conditions from the template management unit 111.

[0062] When the class of the received received information is "question", it is preferable that the template acquisition unit 134 does not acquire the prompt template information.

[0063] The prompt creation unit 135 creates a prompt using the prompt template information acquired by the template acquisition unit 134 and the inquiry information acquired by the inquiry acquisition unit 131. Usually, the prompt creation unit 135 places the acquired inquiry information at the variable positions of the prompt template information acquired by the template acquisition unit 134 to create a prompt.

[0064] The prompt creation unit 135 may create a prompt using each of the two pieces of inquiry information. The prompt here may be one or two.

[0065] When the class of the inquiry information acquired by the inquiry acquisition unit 131 is "question", the prompt creation unit 135 creates a prompt including the inquiry information. The prompt may be the inquiry information.

[0066] 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 it to the generation AI means, for example, passing it to the generation AI device 3, but it may also be passed to the generation AI possessed by the information processing device 1.

[0067] The answer acquisition unit 136 passes the prompt created by the prompt creation unit 135 to the generation AI, for example, using the API of the generation AI.

[0068] 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.

[0069] The output acquisition unit 137 acquires output information using the response acquired by the response acquisition unit 136. For example, the output acquisition unit 137 acquires output information using the received information and the response acquired by the response acquisition unit 136. For example, the output acquisition unit 137 places the response in the received information and acquires output information. For example, the output acquisition unit 137 replaces part or all of the received information with the response and acquires output information. The output acquisition unit 137 may acquire output information using the response from the generation AI and the type of processing. The output acquisition unit 137 may acquire the output information to be executed by the output unit 14. In such a case, the output information is, for example, a function, a method, or an execution module.

[0070] It is preferable that the output acquisition unit 137 places part or all of the response in the variable portion of the output template information to acquire the output information.

[0071] The output information is, for example, information constituting a patent specification, claims, or abstract.

[0072] The output unit 14 outputs the output information acquired by the output acquisition unit 137. For example, the output unit 14 transmits the output information to the terminal device 2. The output unit 14 may perform processing using the output information acquired by the output acquisition unit 137. The output unit 14 may execute a function, a method, or an execution module.

[0073] Here, output generally refers to transmission to the terminal device 2, but may also be a concept including display on a display, projection using a projector, printing by a printer, sound output, transmission to other external devices, storage in a recording medium, delivery of processing results to other processing devices or other programs, etc.

[0074] Various types of information are stored in the terminal storage unit 21 that constitutes the terminal device 2. The various types of information are, for example, received information and user identifiers.

[0075] The terminal reception unit 22 receives various types of information, instructions, etc. The various types of information, instructions, etc. are, for example, received information.

[0076] The input means for various information and instructions can be anything, such as a touch panel, keyboard, mouse, menu screen, etc.

[0077] The terminal processing unit 23 performs various processes. The various processes are, for example, processes of converting the received information, instructions, etc. into information and instructions of a structure to be transmitted. The various processes are, for example, processes of converting the received information into information of a structure for output.

[0078] The terminal transmission unit 24 transmits various information, instructions, etc. to the information processing apparatus 1. The various information, instructions, etc. are, for example, received information.

[0079] The terminal reception unit 25 receives various information from the information processing apparatus 1. The various information is, for example, output information.

[0080] The terminal output unit 26 outputs various information. The various information is, for example, output information.

[0081] The storage unit 11, the template management unit 111, and the terminal storage unit 21 are preferably non-volatile recording media, but can also be realized with volatile recording media.

[0082] The process of storing information in the storage unit 11 or the like is not limited. For example, information may be stored in the storage unit 11 or the like via a recording medium, or information transmitted via a communication line or the like may be stored in the storage unit 11 or the like, or information input via an input device may be stored in the storage unit 11 or the like.

[0083] The reception unit 12 is preferably realized by wireless or wired communication means, but may also be realized by means of receiving broadcasts, device drivers of input means such as touch panels and keyboards, control software of menu screens, etc.

[0084] The processing unit 13, inquiry acquisition unit 131, class determination unit 132, generation AI determination unit 133, template acquisition unit 134, prompt creation unit 135, answer acquisition unit 136, output acquisition unit 137, and terminal processing unit 23 can usually be realized from a processor, memory, etc. The processing procedures of the processing unit 13 etc. are usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may also be realized by hardware (dedicated circuit). Note that the processor is a CPU, MPU, GPU, etc., and its type does not matter.

[0085] The output unit 14 is usually realized by wireless or wired communication means, but may also be realized by broadcasting means. Also, the output unit 14 may be realized by driver software for an output device such as a display or speaker, or by driver software for the output device and the output device etc.

[0086] The terminal reception unit 22 can be realized by a device driver for an input means such as a touch panel or keyboard, control software for a menu screen, etc.

[0087] The terminal transmission unit 24 is usually realized by wireless or wired communication means, but may also be realized by broadcasting means.

[0088] The terminal reception unit 25 is usually realized by wireless or wired communication means, but may also be realized by means for receiving broadcasts.

[0089] The terminal output unit 26 may or may not be considered to include output devices such as a display or speaker. The terminal output unit 26 can be realized by driver software for the output device, or by driver software for the output device and the output device etc.

[0090] Next, an operation example of the information processing apparatus 1 will be described using the flowchart of FIG. 3.

[0091] (Step S301) The reception unit 12 determines whether it has received reception information from the user. If it has received the reception information, it proceeds to step S302; if not, it returns to step S301. Here, for example, the reception unit 12 determines whether it has received reception information from the terminal device 2.

[0092] (Step S302) The inquiry acquisition unit 131 determines whether the class of the reception information received in step S301 is "inquiry" or "non-inquiry". If it is "inquiry", it proceeds to step S303; if not, it proceeds to step S308. Note that the entire reception information being "inquiry" means, for example, consisting of predetermined character strings such as "is ~?" or "is ~?". Also, whether the character string is "inquiry" or "non-inquiry" can be determined by prediction processing of machine learning (a known technique).

[0093] (Step S303) The prompt creation unit 135 constructs a prompt including the reception information received in step S301. Note that the prompt is, for example, the reception information.

[0094] (Step S304) The answer acquisition unit 136 passes the prompt constructed in step S303 to the generation AI. Here, for example, the answer acquisition unit 136 substitutes the prompt into the arguments of the generation AI's API and executes the API.

[0095] (Step S305) The answer acquisition unit 136 determines whether it has obtained an answer from the generation AI. If it has obtained an answer, it proceeds to step S306; if not, it returns to step S305. Here, for example, the answer acquisition unit 136 obtains the answer that is the return value of the executed API.

[0096] (Step S306) The output acquisition unit 137 constructs output information including all or part of the response acquired in Step S305. When the output acquisition unit 137 acquires part of the response, for example, it manages information for determining the part to be acquired (e.g., "information for identifying the written part"), and uses such information to acquire part of the response.

[0097] (Step S307) The output unit 14 outputs the output information configured in Step S306. Return to Step S301.

[0098] (Step S308) The inquiry acquisition unit 131, etc. perform processing on the reception information received in Step S301 and output the output information. Return to Step S301. An example of such reception information processing will be described using the flowchart of FIG. 4.

[0099] In the flowchart of FIG. 3, the processing ends due to a power-off or a processing end interrupt.

[0100] Next, an example of the reception information processing in Step S308 will be described using the flowchart of FIG. 4.

[0101] (Step S401) The class determination unit 132 acquires the type of the document that is the reception information. Here, note that the class determination unit 132 may not be able to acquire the type of the document. The type of the document may be a "class". The class determination unit 132 determines the type of the document from, for example, the file name of the reception information. The class determination unit 132 determines the type of the document from, for example, the character string corresponding to a specific tag (e.g., [document name]) in the reception information.

[0102] The class determination unit 132, for example, provides the reception information and the learning model to the prediction module of machine learning, executes the prediction module, and acquires the type of the document. The learning model is information configured by the learning process of machine learning and is information used for the prediction process of machine learning. The learning model may also be referred to as a learner, a classifier, a classification model, etc. In this specification, the algorithm of machine learning is not limited, such as deep learning, random forest, decision tree, SVM, etc. Also, for machine learning, various functions of machine learning such as the library of TensorFlow (registered trademark), the random forest module of R language, fastText, TinySVM, etc., and various existing libraries can be used.

[0103] (Step S402) The class determination unit 132 acquires one or more class conditions that match the type acquired in step S401 from the template management unit 111. If the type of the document could not be acquired in step S401, the class determination unit 132 acquires one or more class conditions that are not associated with any document type from the template management unit 111.

[0104] (Step S403) The class determination unit 132 assigns 1 to the counter i.

[0105] (Step S404) The class determination unit 132 determines whether the i-th class condition exists among the class conditions acquired in step S402. If the i-th class condition exists, it proceeds to step S405; if not, it returns to the upper-level process.

[0106] (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 using the flowchart of FIG. 5.

[0107] (Step S406) The class determination unit 132 increments the counter i by 1. It returns to step S404.

[0108] Next, an example of the class condition processing in step S405 will be described using the flowchart of FIG. 5.

[0109] (Step S501) The template acquisition unit 134 acquires, from the template management unit 111, the prompt template information corresponding to the i-th class condition in step S404.

[0110] (Step S502) The inquiry acquisition unit 131 determines whether a tag exists in the i-th class condition. If a tag exists, it proceeds to step S503; if not, it proceeds to step S505. Note that the existence of a tag in the class condition means that the tag is a condition.

[0111] (Step S503) The inquiry acquisition unit 131 acquires the tag in the i-th class condition.

[0112] (Step S504) The inquiry acquisition unit 131 acquires, from the reception information, the tag content that is the information corresponding to the tag acquired in step S503. The tag content is usually a character string corresponding to the tag.

[0113] (Step S505) The inquiry acquisition unit 131 determines whether a language characteristic exists in the i-th class condition. If a language characteristic exists, it proceeds to step S504; if not, it proceeds to step S508. Note that the existence of a language characteristic in the class condition means that the language characteristic is a condition.

[0114] (Step S506) The inquiry acquisition unit 131 acquires the language characteristic of the i-th class condition.

[0115] (Step S507) When the inquiry acquisition unit 131 has acquired a tag among the i-th class conditions, it acquires one or more inquiry information that is the information in the tag content acquired in Step S504 and matches the linguistic characteristics acquired in Step S506. When the inquiry acquisition unit 131 has not acquired a tag among the i-th class conditions, it acquires one or more inquiry information that is the information in the received reception information and matches the linguistic characteristics acquired in Step S506. Proceed to Step S509.

[0116] (Step S508) When a tag exists in the i-th class condition, the inquiry acquisition unit 131 acquires the tag content acquired in Step S504 as inquiry information. When no tag exists in the i-th class condition, the inquiry acquisition unit 131 acquires the received reception information as inquiry information.

[0117] (Step S509) The prompt creation unit 135 substitutes 1 for the counter i.

[0118] (Step S510) The prompt creation unit 135 determines whether the i-th inquiry information exists among the inquiry information acquired in Step S507 or Step S508. If the i-th inquiry information exists, proceed to Step S510; if not, return to the upper-level process.

[0119] (Step S511) The prompt creation unit 135 acquires the i-th inquiry information among the inquiry information acquired in Step S507 or Step S508. The prompt creation unit 135 arranges the i-th inquiry information in the variable part of the prompt template information acquired in Step S501 to create a prompt.

[0120] (Step S512) The answer acquisition unit 136 passes the prompt created in Step S511 to the generation AI.

[0121] (Step S513) The response acquisition unit 136 determines whether it has acquired a response from the generative AI. If it has acquired a response, it proceeds to step S514. If it has not acquired a response, it returns to step S513.

[0122] (Step S514) The output acquisition unit 137 acquires output information. An example of such output acquisition processing will be described using the flowchart of FIG. 6.

[0123] (Step S515) The prompt creation unit 135 increments the counter i by 1 and returns to step S510.

[0124] Next, an example of the output acquisition processing in step S514 will be described using the flowchart of FIG. 6.

[0125] (Step S601) The output acquisition unit 137 acquires the type of processing paired with the class condition from the template management unit 111.

[0126] (Step S602) The output acquisition unit 137 determines whether the type of processing acquired in step S601 is "addition". If it is "addition", it proceeds to step S603. If it is not "addition", it proceeds to step S604.

[0127] (Step S603) The output acquisition unit 137 places the acquired response or a part of the response at a predetermined position with respect to the inquiry information and returns to the upper-level process.

[0128] (Step S604) The output acquisition unit 137 determines whether the type of processing acquired in step S601 is "modification". If it is "modification", it proceeds to step S605. If it is not "modification", it proceeds to step S606.

[0129] (Step S605) The output acquisition unit 137 updates the inquiry information with the response or a part of the response and returns to the upper-level process.

[0130] (Step S606) The output acquisition unit 137 determines whether the type of process acquired in step S601 is "check". If it is "check", it proceeds to step S607; if it is not "check", it returns to the upper-level process. Note that "check" may also be referred to as "inspection".

[0131] (Step S607) The output acquisition unit 137 associates an answer or a part of the answer with the inquiry information. Then it returns to the upper-level process.

[0132] Hereinafter, a specific operation example of the information system A in the present embodiment will be described.

[0133] Currently, a prototype management table shown in FIG. 7 is stored in the prototype management unit 111 of the information processing apparatus 1. The prototype management table has "ID", "class condition", "prompt prototype information", and "type of process". The "class condition" has "tag" and "linguistic characteristics". Note that an identifier of the generation AI device 3 is associated with the "prompt prototype information", and an answer may be obtained using the generation AI device 3 paired with the prompt prototype information to be used.

[0134] In FIG. 7, "ID" is information for identifying a record. "Tag" is a tag that may be included in the received information. Tags included in the invention list are, for example, [Invention 1]. Tags included in the specification are, for example, [Modes for Carrying Out the Invention]. "Linguistic characteristics" are, for example, "sentence", "paragraph", "component", "technical term". In the "prompt prototype information", <inquiry information> is a variable, and <inquiry information> is replaced with the inquiry information acquired by the inquiry acquisition unit 131.

[0135] "Processing type" refers to information indicating the type of processing when adding an answer. Here, "processing type" refers to information indicating the type of processing when adding an answer to reception information. Here, the "processing type" is "addition", "check", or "change". Also, here, due to the difference in the "processing type", the attribute values of the answer string to be output are different. The attribute values of the string are, for example, font, color, size, presence or absence of underline, etc. The "processing type" may also be information for identifying the processing using the answer. The processing type "insert(travel expenses, expense DB)" means performing the process of registering the travel expenses obtained from the generative AI into the expense DB. The processing type "send(summary, $supervisor address)" means sending the summary (summary of the sales report) obtained from the generative AI by email to the address indicated by "$supervisor address". Note that "$supervisor address" is a variable indicating, for example, the email address of the supervisor of the user paired with the user identifier of the user who input the daily sales report, and is information obtained from an address database (not shown) that manages one or more pairs of user identifiers and supervisor email addresses.

[0136] In FIG. 7, when the processing type is "addition", it indicates that the output acquisition unit 137 adds the answer to the reception information. When the processing type is "addition", here, it indicates that the output acquisition unit 137 adds the answer immediately after the sentence having the inquiry information (including the sentence that is the inquiry information). Also, when the processing type is "check", it indicates that the output acquisition unit 137 adds the answer associated with the inquiry information to be checked to the reception information. When the processing type is "change", it indicates that the output acquisition unit 137 replaces the inquiry information in the reception information with the answer.

[0137] In the above situation, four specific examples will be described. Specific example 1 is the case where the document is an invention list. Specific example 2 is the case where the document is a specification. Specific example 3 is the case where the document is a summary. Specific example 4 is the case where the document is a daily sales report input from the screen.

[0138] (Specific example 1) Suppose that the user inputs the file "invention list 20231125.docx" storing the character string shown in FIG. 8 into the information processing apparatus 1.

[0139] Next, the reception unit 12 of the information processing apparatus 1 receives the reception information "invention list 20231125.docx" from the user. Next, the inquiry acquisition unit 131 opens the file "invention list 20231125.docx", acquires its content, detects that it does not end with "?", and determines that the received reception information is not a "question" (is a "non-question").

[0140] Next, the inquiry acquisition unit 131 and the like perform processing on the received reception information as follows and output output information.

[0141] First, the class determination unit 132 acquires the document type "invention list" from the file name of the reception information "invention list 20231125.docx".

[0142] 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.

[0143] Next, the class determination unit 132 acquires the class condition "<tag> invention 1 <linguistic characteristic> -" of "ID=1" from the prototype management table (FIG. 7).

[0144] Also, the prototype acquisition unit 134 acquires the prompt prototype information "Tell me the subordinate concepts of the following invention! Invention \"<inquiry information>\"" that pairs with the class condition of "ID=1" from the prototype management table (FIG. 7).

[0145] Next, the inquiry acquisition unit 131 acquires the tag "Invention 1" among the class conditions from the prototype management table (Figure 7). Next, the inquiry acquisition unit 131 acquires, from the reception information (Figure 8), the tag content "Electrical equipment that detects the presence of a person and changes the output of an advertisement", which is the information corresponding to the acquired tag "Invention 1". Next, the inquiry acquisition unit 131 determines that there are no linguistic characteristics among the class conditions. Next, the inquiry acquisition unit 131 sets the acquired tag content "Electrical equipment that detects the presence of a person and changes the output of an advertisement" as the inquiry information.

[0146] Next, the prompt creation unit 135 replaces the variable <inquiry information> in the acquired prompt prototype information with "Electrical equipment that detects the presence of a person and changes the output of an advertisement", and obtains the prompt "Teach me the subordinate concepts of the following invention! Invention "Electrical equipment that detects the presence of a person and changes the output of an advertisement"".

[0147] 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. Assume that the answer is, for example, the text of 901 in Figure 9.

[0148] Next, the output acquisition unit 137 acquires output information as follows. That is, the output acquisition unit 137 acquires the processing type "addition", which is paired with the class condition of "ID=1", from the prototype management table.

[0149] Next, the output acquisition unit 137 places the acquired answer at a predetermined position (here, immediately after the sentence of the tag of Invention 1 (inquiry information)) with respect to the inquiry information, and obtains the information of Figure 9.

[0150] Next, the class determination unit 132 acquires the class condition "<tag> - <linguistic characteristic> sentence" of "ID=4" from the prototype management table (Figure 7). Then, the information processing device 1 performs the same processing as above for the class condition of "ID=4", but here, the output acquisition unit 137 does not acquire the output information.

[0151] (Specific Example 2) Assume that the user inputs the file "Specification20231125.docx" with the character string shown in FIG. 10 to the information processing apparatus 1.

[0152] Next, the reception unit 12 of the information processing apparatus 1 receives the reception information "Specification20231125.docx" from the user. Next, the inquiry acquisition unit 131 determines from the content of the received file "Specification20231125.docx" that the reception information is not a "question".

[0153] Next, the inquiry acquisition unit 131 and the like perform processing on the received reception information as follows and output output information.

[0154] First, the class determination unit 132 acquires the character string "Specification" that pairs with the tag [document name] in the file of the reception information "Specification20231125.docx", and acquires the document type "Specification" from the character string.

[0155] Next, the class determination unit 132 acquires the class conditions of "ID=2" and "ID=4" that match the type "Specification".

[0156] Next, the class determination unit 132 acquires the class conditions of "ID=2", "<tag> - <linguistic characteristic> sentence", "<tag> - <linguistic characteristic> paragraph", "<tag> Forms for Carrying Out the Invention <linguistic characteristic> components", "<tag> Forms for Carrying Out the Invention <linguistic characteristic> technical terms" from the prototype management table (FIG. 7). Also, the class determination unit 132 acquires the class condition of "ID=4", "<tag> - <linguistic characteristic> sentence" from the prototype management table (FIG. 7).

[0157] Also, the prototype acquisition unit 134 acquires the prompt prototype information that pairs with each class condition of "ID=2" from the prototype management table (FIG. 7 in association with each class condition.

[0158] Next, the inquiry acquisition unit 131 sequentially acquires sentences from the file "Specification20231125.docx" based on the class condition of "ID=2": "<tag> - <linguistic characteristic> sentence". Each such sentence is inquiry information.

[0159] Next, the prompt creation unit 135 arranges each sentence at the <inquiry information> position in the sentence "Sentence: <inquiry information>" in the prompt template information "Please tell me whether there is a subject in the following sentence, YES / NO. As a result, the prompt creation unit 135 constructs, for example, the prompt "Please tell me whether there is a subject in the following sentence, YES / NO. Sentence: 'The inquiry acquisition unit 131 acquires inquiry information that is information included in the reception information and is used for inquiries to the generative AI.'" and the prompt "Please tell me whether there is a subject in the following sentence, YES / NO. Sentence: 'Acquire at least two pieces of inquiry information from the reception information.'"

[0160] Next, the answer acquisition unit 136 passes each created prompt to the generative AI. Then, for each prompt, the answer acquisition unit 136 acquires an answer ("YES" or "NO") from the generative AI. Note that the answer to the inquiry information "The inquiry acquisition unit 131 acquires inquiry information that is information included in the reception information and is used for inquiries to the generative AI." is "YES", and the answer to the inquiry information "Acquire at least two pieces of inquiry information from the reception information." is "NO".

[0161] Also, the inquiry acquisition unit 131 sequentially acquires all the sentences in the paragraph corresponding to each paragraph number from the file "Specification20231125.docx" based on the class condition of "ID=2": "<tag> - <linguistic characteristic> paragraph". All the sentences in such paragraphs are inquiry information.

[0162] Next, for each paragraph, the prompt creation unit 135 places all the sentences in the paragraph in the <inquiry information> of the prompt template information "Please tell me whether the number of characters in the following text group is within 500 characters or not, YES / NO. Text group "<inquiry information>>" that corresponds to the class condition, and creates a prompt. For example, the prompt creation unit 135 creates "Please tell me whether the number of characters in the following text group is within 500 characters or not, YES / NO. Text group "The information processing apparatus of the first invention of the present invention is an information processing apparatus comprising... Such a configuration enables the use of a generative AI using an appropriate prompt according to the class of the inquiry information. Also, the information processing apparatus of the second invention of the present invention is an information processing apparatus that... with respect to the first invention. Such a configuration enables the use of a generative AI using an appropriate prompt according to the class of the invention information, and can assist in the creation of patent documents."

[0163] Next, the answer acquisition unit 136 passes each created prompt to the generative AI. Then, for each prompt, the answer acquisition unit 136 acquires an answer ("YES" or "NO") from the generative AI. Note that the answer to the inquiry information "The information processing apparatus of the first invention of the present invention is an information processing apparatus comprising... Such a configuration enables the use of a generative AI using an appropriate prompt according to the class of the inquiry information. Also, the information processing apparatus of the second invention of the present invention is an information processing apparatus that... with respect to the first invention. Such a configuration enables the use of a generative AI using an appropriate prompt according to the class of the invention information, and can assist in the creation of patent documents." was "NO".

[0164] Also, based on the class condition of "ID=2", "<tag>Forms for Carrying Out the Invention <linguistic feature>Constituent Elements", the inquiry acquisition unit 131 acquires constituent elements from the text corresponding to the tag [Forms for Carrying Out the Invention] in the file "Specification20231125.docx". Here, the inquiry acquisition unit 131 acquires noun phrases (reception unit, inquiry acquisition unit, terminal storage unit, etc.) with a symbol (numerical sequence) immediately following as constituent elements.

[0165] Next, for each component, the prompt creation unit 135 places each component in the <inquiry information> of the prompt template information "<Answer the terms of the subordinate concept of <inquiry information> in a list!>" that pairs with the class condition, and creates a prompt. For example, the prompt creation unit 135 creates "Answer the terms of the subordinate concept of the reception unit in a list!".

[0166] Next, the answer acquisition unit 136 passes each created prompt to the generation AI. Then, for each prompt, the answer acquisition unit 136 acquires an answer from the generation AI. Suppose the answer to the inquiry information "reception unit" is "Provides information about the general subordinate concepts of the'reception unit'. The subordinate concepts of the reception unit may include the following functions and elements: ·Reception desk ·Information counter ·Guest management ·Visitor registration ·Appointment adjustment ·Security check-in ·Telephone response ·Guided service".

[0167] Also, based on the class condition of "ID=2" "<Form for implementing the invention> <Linguistic characteristic> Technical terms", the inquiry acquisition unit 131 acquires technical terms from the text corresponding to the tag [Form for implementing the invention] in the file "Specification20231125.docx". The technique for acquiring technical terms from text is possible, for example, by a known technique such as "termextract" (URL: http: / / gensen.dl.itc.u-tokyo.ac.jp / pytermextract / ). Here, for example, the inquiry acquisition unit 131 acquires the technical term "generation AI" from the sentence "The inquiry acquisition unit 131 is information included in the reception information and is the inquiry information used for inquiring the generation AI." in the tag [Form for implementing the invention].

[0168] Next, for each technical term, the prompt creation unit 135 places each technical term in the <inquiry information> of the prompt template information "<Teach the definition and specific examples of <inquiry information>!>" that pairs with the class condition, and creates a prompt. For example, the prompt creation unit 135 creates "Teach the definition and specific examples of generation AI!".

[0169] Next, the response acquisition unit 136 passes each of the created prompts to the generation AI. Then, the response acquisition unit 136 acquires a response from the generation AI for each prompt. It is assumed that the response to the inquiry information "generation AI" is "The 'generation AI' is a type of artificial intelligence that refers to a system that generates new content based on input data. Specific examples are as follows: Text generation: An AI such as the GPT series can create a story or article from a given prompt. Image generation: DALL-E and this AI system can... Music generation: An AI such as AIVA can... Voice synthesis:..."

[0170] Also, the inquiry acquisition unit 131 sequentially acquires sentences from the file "Specification20231125.docx" based on the class condition of "ID = 4", "<tag> - <linguistic feature> sentence". Each such sentence is inquiry information.

[0171] Next, the prompt creation unit 135 places each sentence in the <inquiry information> part of the prompt template information "If the following sentence is a complex sentence, change it to multiple simple sentences with a subject! Sentence '<inquiry information>'". As a result, the prompt creation unit 135 constructs, for example, a prompt such as "If the following sentence is a complex sentence, change it to multiple simple sentences with a subject! Sentence 'The terminal storage unit 21 preferably uses a non-volatile recording medium, but a volatile recording medium can also be used, and the process of storing information in the terminal storage unit 21 is not relevant.'"

[0172] Next, the response acquisition unit 136 passes each of the created prompts to the generation AI. Then, the response acquisition unit 136 acquires a response from the generation AI for each prompt. Note that the response to the inquiry information "The terminal storage unit 21 preferably uses a non-volatile recording medium, but a volatile recording medium is also feasible, and the process of storing information in the terminal storage unit 21 is not limited." was "The terminal storage unit 21 preferably uses a non-volatile recording medium, but a volatile recording medium is also feasible. The process of storing information in the terminal storage unit 21 is not limited."

[0173] Next, the output acquisition unit 137 acquires output information as follows. That is, the output acquisition unit 137 acquires from the template management table the processing types corresponding to the class conditions of "ID=2" and "ID=4" in the template management table.

[0174] Next, for the response corresponding to the processing type "Check", the output acquisition unit 137 adds it as a comment on the inquiry information to the reception information "Specification20231125.docx". For the prompt template information "Please tell me whether the following sentence has a subject or not, in YES / NO. If the response to the sentence "<inquiry information>" is "NO", the output acquisition unit 137 adds "This sentence has no subject." as a comment on the said inquiry information (sentence). An example of such a comment is 1101 in Figure 11.

[0175] Also, for the prompt template information "Please tell me whether the number of characters in the following group of sentences is within 500 characters or not, in YES / NO. Group of sentences "<inquiry information>". If the response is "NO", the output acquisition unit 137 adds "This paragraph exceeds 500 characters." as a comment on the said inquiry information (paragraph). An example of such a comment is 1102 in Figure 11.

[0176] In addition, the output acquisition unit 137 places the response corresponding to the processing type "addition" immediately after the sentence that is the inquiry information, the paragraph that is the inquiry information, or the sentence that includes the inquiry information. For example, the response to the inquiry information "reception unit" is placed immediately after the sentence "The reception unit 12 receives reception information from the user" that includes the inquiry information "reception unit". Such a response is 1103 in FIG. 11.

[0177] In addition, the output acquisition unit 137, for example, places the response to the inquiry information "generative AI" immediately after the sentence that includes generative AI, "The inquiry acquisition unit 131 acquires inquiry information that is information included in the reception information and is used for an inquiry to generative AI." Such a response is 1104 in FIG. 11.

[0178] In addition, the output acquisition unit 137 replaces the inquiry information with the response for the processing type "modification". For example, the output acquisition unit 137 replaces the inquiry information, which is a complex sentence, "The terminal storage unit 21 preferably uses a non-volatile recording medium, but a volatile recording medium is also feasible, and the process of storing information in the terminal storage unit 21 is not questioned." with the response to the said inquiry information, "The terminal storage unit 21 preferably uses a non-volatile recording medium, but a volatile recording medium is also feasible. The process of storing information in the terminal storage unit 21 is not questioned."

[0179] Next, the output unit 14 outputs "Specification 20231125.docx" corrected using the response of the generative AI. Such an output example is shown in FIG. 11.

[0180] (Specific Example 3) Suppose the user inputs the file "Summary 20231125.docx" in which the character string shown in FIG. 11 is stored into the information processing apparatus 1.

[0181] Next, the reception unit 12 of the information processing apparatus 1 receives the reception information "Summary 20231125.docx" from the user. Next, the inquiry acquisition unit 131 determines from the content of the received file "Summary 20231125.docx" that the reception information is not a "question".

[0182] Next, the inquiry acquisition unit 131 and the like perform processing on the received reception information as follows and output output information.

[0183] 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 "abstract_20231125.docx", and obtains the document type "abstract" from the character string.

[0184] Next, the class determination unit 132 obtains the class conditions of "ID=3" and "ID=4" that match the type "abstract". For convenience of explanation, the case where only the class condition of "ID=3" is applied is described below.

[0185] Next, the class determination unit 132 obtains the class condition "<tag> - <language characteristic> -" of "ID=3" from the prototype management table (Figure 7). Also, the class determination unit 132 obtains the class condition "<tag> - <language characteristic> sentence" of "ID=4" from the prototype management table (Figure 7).

[0186] Also, the prototype acquisition unit 134 obtains the prompt prototype information corresponding to the class condition of "ID=3" from the prototype management table (Figure 7) in association with each class condition.

[0187] Next, the inquiry acquisition unit 131 obtains the reception information (the entire abstract in Figure 12) as inquiry information from the class condition "<tag> - <language characteristic> -".

[0188] Next, the prompt creation unit 135 creates a prompt by replacing the <inquiry information> in the prompt prototype information "If the following document exceeds 400 words, summarize it within 400 words! Document "<inquiry information>" with the entire abstract (Figure 12).

[0189] Next, the answer acquisition unit 136 passes each created prompt to the generation AI. Then, the answer acquisition unit 136 obtains a summary within 400 words.

[0190] Next, the output acquisition unit 137 acquires output information as follows. That is, the output acquisition unit 137 acquires the processing type "modification" that pairs with the class condition of "ID=3" in the template management table from the template management table.

[0191] Also, for the answer corresponding to the processing type "modification", the output acquisition unit 137 replaces the inquiry information with the answer. That is, the output acquisition unit 137 acquires the obtained answer as a summary.

[0192] Next, the output unit 14 outputs the summary obtained using the answer of the generation AI. Such an output example is shown in FIG. 13.

[0193] (Specific Example 4) Assume that the user (Atsuo Yamada) inputs information for the business report into each field of the input screen (FIG. 14) displayed on the terminal device 2 and presses the "Register" button.

[0194] Next, the terminal device 2 accepts the input of Atsuo Yamada and constructs information to be transmitted to the information processing device using the set of information input in each field. Such information is shown in FIG. 15, for example. Next, the terminal device 2 transmits the information (FIG. 15) to the information processing device 1.

[0195] Next, the reception unit 12 of the information processing device 1 receives the reception information in FIG. 15.

[0196] Next, the class determination unit 132 acquires the document type "business daily report" from the "<document> business daily report" included in the reception information received by the reception unit 12.

[0197] Next, the class determination unit 132 acquires the class condition of "ID=51" that matches the type "business daily report". Here, usually, the class condition of "ID=4" is adopted, but since it has been described above, the processing for the class condition of "ID=4" is not described.

[0198] Next, the class determination unit 132 acquires the class conditions of "ID=51", namely, "<tag>departure station, arrival seat <language characteristic>-" and "<tag>business report <language characteristic>-", from the prototype management table (Figure 7).

[0199] Also, the prototype acquisition unit 134 acquires the prompt prototype information "Tell me the transportation fee from <departure station> to <arrival station>!" that corresponds to the class conditions of "ID=51" from the prototype management table (Figure 7).

[0200] Also, the prototype acquisition unit 134 acquires the other prompt prototype information "Summarize the following business report within 400 words! [Business report]<Business report>" that corresponds to the class conditions of "ID=51" from the prototype management table (Figure 7).

[0201] Next, the inquiry acquisition unit 131 acquires the inquiry information "<departure station> Osaka, <arrival station> Tokyo" corresponding to the tags <departure station> and <arrival station> in the class conditions from the received information (Figure 15).

[0202] Also, the inquiry acquisition unit 131 acquires the inquiry information "<Business report>Today, I visited Mr. XXX of XX Co., Ltd. in Tokyo. ···" corresponding to the tag <Business report> in the class conditions from the received information (Figure 15).

[0203] Next, the prompt creation unit 135 substitutes each of the inquiry information "<departure station> Osaka, <arrival station> Tokyo" into the variable part of the prompt prototype information "Tell me the transportation fee from <departure station> to <arrival station>!" to construct the first prompt "Tell me the transportation fee from Osaka to Tokyo!".

[0204] Also, the prompt creation unit 135 substitutes the inquiry information "<Business report>Today, I visited Mr. XXX of XX Co., Ltd. in Tokyo. ···" into the variable part of the prompt prototype information "Summarize the following business report within 400 words! [Business report]<Business report>" to construct the second prompt "Summarize the following business report within 400 words! [Business report]Today, I visited Mr. XXX of XX Co., Ltd. in Tokyo. ···".

[0205] Next, the response acquisition unit 136 passes the created first prompt to the generation AI. Then, the response acquisition unit 136 acquires the response "14,720 yen" from the generation AI.

[0206] Also, the response acquisition unit 136 passes the created second prompt to the generation AI. Then, the response acquisition unit 136 acquires the response "Today, I visited Mr. XXX of ○○ Co., Ltd. in Tokyo and introduced our company's business daily report system using AI. In particular, Mr. XXX showed interest in the generation AI function, ···" from the generation AI.

[0207] Next, the output acquisition unit 137 uses the response "14,720 yen" from the generation AI and the processing type (insert (transportation expenses, expense DB)) to construct the output information "insert (14,720 yen, expense DB)". Next, the output unit 14 executes "insert (14,720 yen, expense DB)" to input the transportation expenses "14,720 yen" into the expense DB (not shown).

[0208] Also, the output acquisition unit 137 uses the response "Today, I visited Mr. XXX of ○○ Co., Ltd. in Tokyo and introduced our company's business daily report system using AI. In particular, Mr. XXX showed interest in the generation AI function, ···" from the generation AI and the processing type (send ("Today, I visited Mr. XXX of ○○ Co., Ltd. in Tokyo and introduced our company's business daily report system using AI. In particular, Mr. XXX showed interest in the generation AI function, ···", $supervisor address)) to acquire the output information "send ("Today, I visited Mr. XXX of ○○ Co., Ltd. in Tokyo and introduced our company's business daily report system using AI. In particular, Mr. XXX showed interest in the generation AI function, ···", the address of Mr. A Yamada's supervisor)". Next, the output unit 14 executes the said output information. As a result, the summary of Mr. A Yamada's business report is sent to Mr. A Yamada's superior.

[0209] As described above, according to the present embodiment, an appropriate prompt corresponding to the class of inquiry information can be created, and the generation AI can be utilized using the said prompt.

[0210] In addition, according to the present embodiment, an appropriate prompt can be created according to the class of invention information, and using the prompt, a generative AI can be utilized to assist in the creation of patent documents.

[0211] In addition, according to the present embodiment, a generative AI control engine that makes use of the generative AI can be provided.

[0212] Note that the processing in this embodiment may be realized by software. And this software may be distributed by software download or the like. Also, this software may be recorded on a recording medium such as a CD-ROM and distributed. Note that this also applies to other embodiments in this specification. The software that realizes the information system A in this embodiment is the following program. That is, this program causes a computer that can access a template management unit in which prompt template information is stored in association with one or more class conditions that are conditions regarding the class of character strings to function as a reception unit that receives reception information from a user, an inquiry acquisition unit that acquires inquiry information that is information included in the reception information and is used for an inquiry to a generative AI, a template acquisition unit that acquires, from the template management unit, prompt template information corresponding to the class condition satisfied by the class of the inquiry information acquired by the inquiry acquisition unit, a prompt creation unit that creates a prompt using the prompt template information acquired by the template acquisition unit and the inquiry information acquired by the inquiry acquisition unit, a response acquisition unit that passes the prompt created by the prompt creation unit to the generative AI and acquires a response from the generative AI, an output acquisition unit that acquires output information using the response acquired by the response acquisition unit, and an output unit that outputs the output information.

[0213] FIG. 16 shows the appearance of a computer that executes the programs described in this specification to realize the information processing apparatus 1 and the like of the various embodiments described above. The above-described embodiments can be realized by computer hardware and a computer program executed thereon. FIG. 16 is an overview diagram of this computer system 300, and FIG. 17 is a block diagram of the system 300.

[0214] In FIG. 16, the computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0215] In FIG. 17, in addition to the CD-ROM drive 3012, the computer 301 includes an MPU 3013, a bus 3014 connected to the CD-ROM drive 3012 and the like, a ROM 3015 for storing programs such as a boot-up program, and is connected to the MPU 3013 and temporarily stores instructions of an application program and provides a temporary storage space. And a RAM 3016, and a hard disk 3017 for storing application programs, system programs, and data. Here, although not shown, the computer 301 may further include a network card that provides a connection to a LAN.

[0216] A program for causing the computer system 300 to execute the functions of the information processing apparatus 1 and the like of the above-described embodiments may be stored in the CD-ROM 3101, inserted into the CD-ROM drive 3012, and further transferred to the hard disk 3017. Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored in the hard disk 3017. The program is loaded into the RAM 3016 during execution. The program may be loaded directly from the CD-ROM 3101 or the network.

[0217] The program does not necessarily include an operating system (OS) that causes the computer 301 to execute the functions of the information processing apparatus 1 or the like in the above-described embodiments, or a third-party program or the like. The program only needs to include only the part of the instructions that calls appropriate functions (modules) in a controlled manner so as to obtain a desired result. How the computer system 300 operates is well known, and a detailed description thereof will be omitted.

[0218] In the above program, in steps such as transmitting information and receiving information, processing performed by hardware, for example, processing performed by a modem or an interface card in the transmission step (processing that can only be performed by hardware) is not included.

[0219] Also, the computer that executes the above program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

[0220] Also, in each of the above embodiments, it goes without saying that two or more communication means existing in one device may be physically realized by one medium.

[0221] Also, in each of the above embodiments, each process may be realized by being centrally processed by a single device, or may be realized by being distributedly processed by a plurality of devices.

[0222] Needless to say, the present invention is not limited to the above embodiments, and various modifications are possible, and those are also included in the scope of the present invention.

Industrial Applicability

[0223] As described above, the information processing apparatus 1 according to the present invention has an effect that the generative AI can be used by using an appropriate prompt according to the class of the inquiry information, and is useful as a specification creation support apparatus, a document creation support apparatus, or the like.

Description of Symbols

[0224] 1 Information processing device 2 Terminal device 3 Generation AI device 11 Storage unit 12 Reception unit 13 Processing unit 14 Output unit 21 Terminal storage unit 22 Terminal reception unit 23 Terminal processing unit 24 Terminal transmission unit 25 Terminal reception unit 26 Terminal output unit 111 Template management unit 131 Inquiry acquisition unit 132 Class determination unit 133 Generation AI determination unit 134 Template acquisition unit 135 Prompt creation unit 136 Answer acquisition unit 137 Output acquisition unit

Claims

1. a template management unit in which prompt template information is stored in association with one or more class conditions which are conditions related to a class of a character string; A reception unit that receives reception information; An inquiry acquisition unit that acquires inquiry information, which is information included in the reception information and is information used for making 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; and an output unit that performs processing using the output information.

2. The class is identified by a field identifier that identifies one or more fields on a screen; The class condition is a condition on one or more field identifiers, The reception unit is accepting the reception information entered into one or more screen fields; The inquiry acquisition unit, 2. The information processing apparatus according to claim 1, wherein the inquiry information is obtained based on information entered in one or more fields.

3. 3. An information processing method for executing all the processes performed by the information processing device according to claim 1.

4. Computer, A program for causing the information processing device according to claim 1 to function as the information processing device.

Images