Information processing system and information processing method

Abstract

The present invention provides an information processing system that uses a language model to assist in correcting a document. A processing unit of the information processing system is configured to execute: a process for dividing a document into a plurality of first blocks; a process for creating a first prompt including a first target sentence and having a first instruction sentence including a command to make a first determination; a process for acquiring a first response sentence including a first determination result by transmitting the first prompt to the language model; a process for acquiring, on the basis of the first determination result, one or more second blocks including at least one first block; a process for creating a second prompt including a second target sentence and having a second instruction sentence including a command for presenting at least one revised plan for the second blocks; a process for acquiring a second response sentence including the revised plan by transmitting the second prompt to the language model; and a process for updating the document data on the basis of the revised plan.

Description

Information processing system and information processing method

[0001] TECHNICAL FIELD One aspect of the present invention relates to an information processing system and an information processing method, and more particularly, to an information processing system and an information processing method that can utilize processing using a language model.

[0002] One embodiment of the present invention is not limited to the above technical field, and examples of the technical field of one embodiment of the present invention include semiconductor devices, display devices, light-emitting devices, power storage devices, memory devices, electronic devices, lighting devices, input devices (e.g., touch sensors), input / output devices (e.g., touch panels), driving methods thereof, and manufacturing methods thereof.

[0003] In recent years, the development of language models using neural networks has been actively carried out, and large-scale language models (LLMs) in particular have attracted attention. A large-scale language model is a natural language processing model trained using a large amount of data. A large-scale language model can realize a dialogue model that responds to user instructions, for example. Non-Patent Document 1 discloses GPT-4 (Generative Pre-trained Transformer 4) (registered trademark) as a large-scale language model, and also discloses ChatGPT as a dialogue model.

[0004] The use of large-scale language models has significantly increased the capabilities of natural language processing models. However, as language models become larger, it is difficult to incorporate and operate language models in-house due to the equipment and cost involved. Therefore, one way to use language models is to use external services that provide language models.

[0005] Summary of ChatGPT / GPT-4 Research and Perspective Towards the Future of Large Language Models, Yiheng Liu et al. (Submitted on 4 Apr 2023, [online], Internet <URL: https: / / arxiv.org / abs / 2304.01852>

[0006] Due to recent improvements in the performance of language models, there are more opportunities to use language models when correcting documents. However, correcting documents using a language model requires instructing the language model to make corrections, confirming the corrections, and reflecting them in the document, which is time-consuming. Therefore, while system support is effective, it is necessary to optimize corrections using language models.

[0007] Therefore, an object of one embodiment of the present invention is to provide an information processing system or an information processing method that supports document correction by utilizing a language model.An object of one embodiment of the present invention is to provide an information processing system or an information processing method that optimizes document correction work by utilizing a language model.An object of one embodiment of the present invention is to provide a highly convenient information processing system or an information processing method.An object of one embodiment of the present invention is to provide a novel information processing system or an information processing method.

[0008] Note that the description of these problems does not preclude the existence of other problems. One embodiment of the present invention does not necessarily have to solve all of these problems. Problems other than these can be extracted from the description in the specification, drawings, and claims.

[0009] One aspect of the present invention is an information processing system including a receiving unit, a processing unit, and an output unit, wherein the receiving unit receives document data, the output unit updates the document data, and outputs the document data, and the processing unit performs a first process of dividing a document included in the document data into a plurality of first blocks, a second process of creating a first prompt including a first target sentence including at least one of the plurality of first blocks and having a first instruction sentence including an instruction to make a first determination for each of the first blocks included in the first target sentence, and a third process of transmitting the first prompt to a language model via a network to obtain a first response sentence including a first determination result based on the first determination. The system is configured to execute a fourth process of acquiring one or more second blocks each including at least one of the first blocks based on the first determination result; a fifth process of creating a second prompt including a second target sentence including at least one of the second blocks and having a second instruction sentence including an instruction to present at least one revision suggestion for the second block included in the second target sentence; a sixth process of acquiring a second response sentence including the revision suggestion by sending the second prompt to a language model via a network; and a seventh process of updating the document data based on the revision suggestion.

[0010] Alternatively, in the above information processing system, the document data is preferably a specification belonging to a patent application.

[0011] Alternatively, in the above-mentioned information processing system, the first judgment determines whether the configuration and effect are described in each of the first blocks, and if the second block includes multiple first blocks, it is preferable that the multiple first blocks included in the second block have the same configuration described, and the proposed addition is a proposal for the effect corresponding to the configuration described in the second block.

[0012] Alternatively, in the information processing system, it is preferable that the processing unit acquires a second block in which no effect is described in the fourth process.

[0013] Alternatively, in the above information processing system, it is preferable that the processing unit executes, before the seventh process, an eighth process of creating a third prompt including at least one revision suggestion and having a third instruction sentence including an instruction to make a second judgment for each of the revision suggestions, and a ninth process of obtaining a third response sentence including the second judgment result by sending the third prompt to a language model via a network.

[0014] Alternatively, in the information processing system, it is preferable that the second determination determine the consistency of the revision proposal with the description in the document.

[0015] Alternatively, one aspect of the present invention includes a first process of receiving document data, a second process of dividing a document included in the document data into a plurality of first blocks, a third process of creating a first prompt including a first target sentence including at least one of the plurality of first blocks and having a first instruction sentence including an instruction to make a first determination for each of the first blocks included in the first target sentence, a fourth process of transmitting the first prompt to a language model via a network to obtain a first response sentence including a first determination result based on the first determination, and a fourth process of performing a first determination based on the first determination result. This information processing method includes a fifth process of acquiring one or more second blocks each including at least one first block; a sixth process of creating a second prompt including a second target sentence including at least one of the second blocks and having a second instruction sentence including an instruction to present at least one revision suggestion for the second block included in the second target sentence; a seventh process of acquiring a second response sentence including the revision suggestion by sending the second prompt to a language model via a network; an eighth process of updating document data based on the revision suggestion; and a ninth process of outputting the document data.

[0016] Alternatively, in the above information processing method, the document data is preferably a specification belonging to a patent application.

[0017] Alternatively, in the above information processing method, the first judgment determines whether the configuration and effect are described in each of the first blocks, and if the second block includes multiple first blocks, it is preferable that the multiple first blocks included in the second block have the same configuration described, and the proposed addition is a proposal for the effect corresponding to the configuration described in the second block.

[0018] Alternatively, in the above information processing method, it is preferable that the fifth process obtains a second block in which no effect is described.

[0019] Alternatively, in the above information processing method, it is preferable to perform a tenth process of creating a third prompt including at least one revision suggestion and having a third instruction sentence including an instruction to make a second judgment for each of the revision suggestions, and an eleventh process of obtaining a third response sentence including the second judgment result by sending the third prompt to a language model via a network, before the eighth process.

[0020] Alternatively, in the above information processing method, it is preferable that the second determination determine consistency of the revision proposal with a description in the document.

[0021] Alternatively, one aspect of the present invention is an information processing system including a receiving unit, a processing unit, and an output unit. The receiving unit has a function of receiving document data, and the processing unit is configured to execute first to fourth processes, wherein the first process divides a document included in the document data into a plurality of blocks and then transmits the blocks to a language model to divide each block into one of a plurality of classes, the plurality of classes including a first class, the first class including a block including a first description and a second description, the second process extracts a third description corresponding to the first description from a database, the third process creates a first prompt for the block classified into the first class and transmits it to the language model, the first prompt includes the second description and the third description, and if the content of the second description and the third description do not match, the third process includes an instruction to generate a message including a difference between the content of the second description and the third description, and the fourth process is configured to output the message from the output unit.

[0022] Alternatively, in the above information processing system, it is preferable that the receiving unit has a function of receiving a correction command, and the processing unit is configured to perform a fifth process and a sixth process after the fourth process when the correction command is received, the fifth process creating a second prompt and sending it to the language model to obtain a correction suggestion, the second prompt including a second description and a third description and having an instruction to correct the second description using the third description, the sixth process updating the document data based on the correction suggestion, and the output unit has a function of outputting the updated document data.

[0023] Alternatively, in the above information processing system, it is preferable that the multiple classes include a second class, the second class having blocks that include the first description but do not include the second description, the processing unit is configured to perform seventh to ninth processes after the second process, the seventh process creating a third prompt for the blocks classified into the second class and sending it to the language model to obtain a revision suggestion, the third prompt including the block classified into the second class and the third description and having an instruction to correct the third description, the eighth process creating a fourth description corresponding to the first description using the revision suggestion, the ninth process updating the document data based on the fourth description, and the output unit has a function to output the updated document data.

[0024] Alternatively, in the above information processing system, the document data is preferably a specification belonging to a patent application.

[0025] Alternatively, in the above information processing system, it is preferable that the first description represents a description of the configuration included in the block, the second description and the fourth description represent descriptions of the effect corresponding to the first description, and the third description represents a description of the effect corresponding to the first description registered in the database.

[0026] Alternatively, in the above information processing system, it is preferable that a revision suggestion is generated to adapt the appearance of the content of the third description extracted from the database to the appearance of at least one or more blocks classified into the class.

[0027] Alternatively, one aspect of the present invention is an information processing method that executes first to fifth processes, wherein the first process accepts document data, the second process classifies documents included in the document data into one of a plurality of classes, the plurality of classes including a first class, the first class having blocks including a first description and a second description, the third process extracts a third description corresponding to the first description from the database, the fourth process creates a first prompt for the block classified into the first class and sends it to a language model, the first prompt includes a second description and a third description, and if the contents of the second description and the third description do not match, the first prompt has an instruction to create a message, the message including the difference between the contents of the second description and the third description, and the fifth process outputs the message.

[0028] Alternatively, in the above information processing method, when a correction command is received, it is preferable that the sixth and seventh processes are performed after the fifth process, the sixth process creates a second prompt and sends it to the language model to obtain a correction suggestion, the second prompt includes a second description and a third description and has an instruction to correct the second description using the third description, and the seventh process updates the document data based on the correction suggestion and outputs the updated document data.

[0029] Alternatively, in the above information processing method, it is preferable that the multiple classes include a second class, the second class having blocks that include the first description but do not include the second description, and that eighth to tenth processes are performed after the second process, the eighth process creating a third prompt for the blocks classified into the second class and sending it to the language model to obtain a revision suggestion, the third prompt including the blocks classified into the second class and the third description and having an instruction to correct the third description, the ninth process creating a fourth description corresponding to the first description using the revision suggestion, and the tenth process updating the document data based on the fourth description and outputting the updated document data.

[0030] Alternatively, in the above information processing method, the document data is preferably a specification belonging to a patent application.

[0031] Alternatively, in the above information processing method, it is preferable that the first description represents a description of the configuration included in the block, the second description and the fourth description represent descriptions of the effect corresponding to the first description, and the third description represents a description of the effect corresponding to the first description registered in the database.

[0032] Alternatively, in the above information processing method, it is preferable that the revision proposal is generated to adapt the appearance of the content of the third description extracted from the database to the appearance of at least one or more blocks classified into the class.

[0033] One aspect of the present invention is a program having a function of causing a processor to execute any of the above information processing methods.

[0034] According to one aspect of the present invention, an information processing system or an information processing method can be provided that supports document correction using a database or a language model. According to one aspect of the present invention, an information processing system or an information processing method can be provided that optimizes document correction work using a database or a language model. According to one aspect of the present invention, a highly convenient information processing system or an information processing method can be provided. According to one aspect of the present invention, a novel information processing system or an information processing method can be provided.

[0035] Note that the description of these effects does not preclude the existence of other effects. One embodiment of the present invention does not necessarily have all of these effects. Effects other than these can be extracted from the description in the specification, drawings, and claims.

[0036] FIG. 1 is a diagram illustrating an example of an information processing system. FIG. 2 is a diagram illustrating an example of an information processing system. FIG. 3 is a block diagram illustrating an example of an information processing system. FIG. 4 is a diagram illustrating an example of an information processing method. FIG. 5 is a diagram illustrating an example of an information processing method. FIG. 6 is a diagram illustrating an example of an information processing method. FIGS. 7A to 7C are diagrams illustrating an example of an information processing method. FIGS. 8A and 8B are diagrams illustrating an example of an information processing method. FIGS. 9A and 9B are diagrams illustrating an example of an information processing method. FIGS. 10A to 10D are diagrams illustrating an example of an information processing method. FIGS. 11A and 11B are diagrams illustrating an example of an information processing method. FIGS. 12A and 12B are diagrams illustrating an example of an information processing method. FIG. 13 is a diagram illustrating an example of an information processing method. FIGS. 14A and 14B are diagrams illustrating an example of an information processing method. FIG. 15 is a diagram illustrating an example of an information processing method. FIG. 16 is a diagram illustrating an example of an information processing system. FIG. 17 is a block diagram illustrating an example of an information processing system. FIG. 18 is a diagram illustrating an example of an information processing system. FIG. 19 is a diagram illustrating an example of an information processing system.

[0037] The embodiments will be described in detail with reference to the drawings. However, the present invention is not limited to the following description, and it will be readily understood by those skilled in the art that various changes can be made in form and detail without departing from the spirit and scope of the present invention. Therefore, the present invention should not be interpreted as being limited to the description of the embodiments shown below.

[0038] In the configuration of the invention described below, the same parts or parts having similar functions are denoted by the same reference numerals in different drawings, and repeated explanations thereof will be omitted. Furthermore, when referring to similar functions, the same hatching pattern may be used and no particular reference numeral may be assigned.

[0039] Furthermore, for ease of understanding, the position, size, range, etc. of each component shown in the drawings may not represent the actual position, size, range, etc. Therefore, the disclosed invention is not necessarily limited to the position, size, range, etc. disclosed in the drawings.

[0040] In this specification, the ordinal numbers "first" and "second" are used for convenience and do not limit the number of components or the order of the components (for example, the order of processes or the order of stacking). Furthermore, the ordinal numbers assigned to components in one part of this specification may not match the ordinal numbers assigned to the same components in other parts of this specification or in the claims.

[0041] In this specification, when the same symbol is used for multiple elements, and particularly when it is necessary to distinguish between them, an identification symbol such as “_1”, “[n]”, or “[m, n]” may be added to the symbol.

[0042] Embodiment In this embodiment, an information processing system according to one embodiment of the present invention will be described with reference to FIGS.

[0043] <Configuration Example 1 of Information Processing System> Fig. 1 shows an example of an information processing system according to this embodiment. The information processing system according to this embodiment includes an information processing device 10, an information terminal 20, and an information processing device 40. In the information processing system shown in Fig. 1, the information processing device 10 is connected to the information processing device 40 via a network 30. The information processing device 10 is also connected to a plurality of information terminals 20 via a network 31. Fig. 1 shows information terminals 20a, 20b, 20c, and 20d as examples of the information terminals 20.

[0044] A user of the information processing system can access the information processing device 10 from the information terminals 20a to 20d, etc. The user can then receive a service using the information processing method according to one aspect of the present invention.

[0045] A user can use the information processing device 10, for example, by using dedicated software or an application installed on the information terminal 20. Alternatively, a user can use the information processing device 10, for example, from a web browser on the information terminal 20.

[0046] An organization such as a company that provides a service using an information processing method according to one embodiment of the present invention (hereinafter also referred to as a service provider) can provide the service using the information processing device 10. The service provider does not need to prepare the information processing device 40 on its own, but can use the information processing device 40 via the network 30.

[0047] The information processing device 10 is a device that can execute processing using an information processing method according to one aspect of the present invention. In FIG. 1, a server computer is illustrated as an example.

[0048] The information processing device 10 can perform information processing such as calculations using data input from the information terminal 20a via the network 31. The information processing device 10 can transmit the results of the information processing to the information terminal 20a via the network 31. This can reduce the calculation load on the information terminal 20a. Here, the information terminal 20a has been described as an example, but the same can be said for the information terminals 20b to 20d.

[0049] The information processing device 10 can input data to the information processing device 40 via the network 30. The information processing device 40 can perform information processing such as calculations using the input data. The information processing device 40 can transmit the results of the information processing to the information processing device 10 via the network 30. This can reduce the calculation load on the information processing device 10. The information processing device 10 can then transmit the data received from the information processing device 40 or data created based on the data to the information terminal 20a via the network 31.

[0050] The information terminals 20a to 20d are each an information terminal device such as a computer used by a user, and may also be referred to as a client computer. FIG. 1 illustrates, as an example, the information terminal 20a, which is a desktop computer; the information terminal 20b, which is a notebook computer; the information terminal 20c, which is a smartphone; and the information terminal 20d, which is a tablet computer. The information terminal 20d can also be used as a notebook computer by connecting it to a housing 21 having a keyboard. The number of information terminals connected to the information processing device 10 is not particularly limited. While FIG. 1 shows four information terminals, the number of information terminals may be one, two, three, five, or more. Examples of such information terminals include desktop information terminals, notebook information terminals, tablet information terminals, and mobile information terminals such as smartphones.

[0051] The information terminal 20 is provided with, for example, a display unit. The display unit can display, for example, information indicated by data input to the information terminal 20. This allows the user of the information terminal 20 to recognize the information.

[0052] The display unit of the information terminal 20 may be, for example, a liquid crystal display device, a light-emitting device (for example, a light-emitting device having a light-emitting element such as an organic EL element in each pixel), an electrophoretic display device, a DMD (Digital Micromirror Device), a PDP (Plasma Display Panel), an FED (Field Emission Display), or other display device.

[0053] The information processing device 10 is a large computer such as a server computer or a supercomputer. The information processing device 10 is a computer with higher processing power than the information terminal 20. The information processing device 10 can function as a parallel computer. By using the information processing device 10 as a parallel computer, it is possible to perform large-scale calculations required for learning and inference of artificial intelligence (AI), for example. The information processing device 10 may also be capable of performing processing using a natural language processing model using AI.

[0054] The information processing device 40 is a large computer such as a server computer or a supercomputer. The information processing device 40 is a computer with higher processing power than the information terminal 20. The information processing device 40 is also a computer with higher processing power than the information processing device 10. It is preferable that the information processing device 40 has a function as a parallel computer. By using the information processing device 40 as a parallel computer, it is possible to perform large-scale calculations required for AI learning and inference, for example. Note that when both the information processing device 10 and the information processing device 40 have a function as a parallel computer, the information processing device 40 has a higher processing power and can perform large-scale calculations than the information processing device 10.

[0055] The information processing device 40 can perform processing using a natural language processing model that uses AI. Examples of the natural language processing model that uses AI include BERT (Bidirectional Encoder Representations from Transformers) and T5 (Text-to-Text Transfer Transformer). The information processing device 40 can also perform processing using a large-scale language model. Examples of large-scale language models include GPT-3, GPT-3.5, GPT-4, LaMDA (Language Model for Dialogue Applications), PaLM (Pathways Language Model), PaLM2, Llama2, and Llama3, and it is preferable to use GPT-4.

[0056] The information processing device 40 can execute processing using a general-purpose AI model that can perform various tasks. When the information processing device 10 and the information processing device 40 can each execute processing using a large-scale language model, the information processing device 40 can execute processing using a larger-scale AI model than the information processing device 10.

[0057] Network 31 is a computer network smaller than network 30. Typically, network 30 is a global network, and network 31 is a local network. It is preferable to use the Internet, which is the foundation of the World Wide Web (WWW), as network 30. It is preferable to use an intranet or an extranet as network 31. In this embodiment, an example will be mainly described in which the Internet is used as network 30 and an intranet is used as network 31.

[0058] Other computer networks that can be used as the network 31 include a PAN (Personal Area Network), a LAN (Local Area Network), a CAN (Campus Area Network), a MAN (Metropolitan Area Network), a WAN (Wide Area Network), and a GAN (Global Area Network).

[0059] Furthermore, when wireless communication is performed, communication standards such as the fourth generation mobile communication system (4G), fifth generation mobile communication system (5G), and sixth generation mobile communication system (6G), or specifications standardized by the IEEE such as Wi-Fi (registered trademark) and Bluetooth (registered trademark), can be used as communication protocols or communication technologies.

[0060] Either the network 30 or the network 31 can be applied to transmitting and receiving data between the information terminal 20 and the information processing device 10. Also, either the network 30 or the network 31 can be applied to transmitting and receiving data between the information processing device 10 and the information processing device 40.

[0061] The information processing system shown in FIG. 1 is suitable for a case where a user who uses the information terminal 20 and a service provider belong to the same organization such as a company.

[0062] For example, it is preferable that data is transmitted and received between the information terminal 20 and the information processing device 10 using a network 31 established within an organization such as a company. It is also preferable that data is transmitted and received between the information processing device 10 and the information processing device 40 using the Internet. This allows applications, tools, services, etc. provided outside the organization to be used more safely than when the information terminal 20 is directly connected to the information processing device 40 via the Internet.

[0063] The flow of data in the information processing system shown in Fig. 1 will be described with reference to Fig. 2. In Fig. 2 and other figures, the order of data transmission and reception is indicated by circled numbers.

[0064] First, the user inputs desired data DA1 into the information processing device 10 using the information terminal 20. The data DA1 is transmitted from the information terminal 20 to the information processing device 10 via the network 31.

[0065] The data DA1 is document data corresponding to the document to be corrected. The format of the data DA1 is not particularly important, but it is preferably text data. Details of the data DA1 will be explained later in the section <Information Processing Method>.

[0066] The documents included in the document data accepted by an information processing system according to an embodiment of the present invention are not particularly limited. The information processing system according to an embodiment of the present invention can support the revision of various types of documents. Examples of such documents include patent applications, books, magazines, newspapers, contracts, papers (including academic papers, theses, doctoral dissertations, essays, journal articles, etc.), court decisions, terms and conditions, product manuals, novels, publications, white papers, technical documents, and business documents. More specifically, patent application documents include one or more of the specification, claims, and abstract of a patent application.

[0067] The document data may be, for example, a document relating to an invention. The document data may include, for example, a block describing the configuration of the invention and a block describing information related to the configuration. The document data may include, for example, a block describing the configuration and a block describing at least one of the principles, actions, and effects related to the configuration.

[0068] In this specification, the term "structure of an invention" refers to, for example, each of the constituent elements (which can also be called technical elements) of the invention and the connection between multiple constituent elements. In addition, the means for solving a problem, or part of the means, can also be called the structure of an invention.

[0069] When the data DA1 includes data other than text data, it is preferable to convert the data DA1 into text data in the information processing device 10. When converting various data into text data, it is preferable to use AI technology. The following describes an example in which the data DA1 is text data. Note that when the data DA1 includes data other than text data, the data DA1 can be read as text data generated using the data DA1.

[0070] The information processing device 10 preferably has a function of generating text data using image data. For example, the information processing device 10 can generate text data using image data by performing processing using at least one AI technology such as image recognition, handwritten character recognition, and caption generation. The information processing device 10 may also have an optical character recognition (OCR) function.

[0071] Next, the information processing device 10 creates data DA2 based on the data DA1. The data DA2 corresponds to text data equivalent to a prompt that the user wants to input to the language model. The prompt corresponds to an input sentence that causes the language model to perform a desired operation. When a prompt is given, the language model generates a response content based on the prompt. Details of the data DA2 will be described later in <Information Processing Method 1> and <Information Processing Method 2>.

[0072] The information processing device 10 can create data DA2 by adding second text data to first text data. Here, the first text data is part of the text data included in data DA1, and the second text data is text data corresponding to an instruction sentence in a prompt to be input to a language model. Here, the instruction sentence is part of the prompt to be input to a language model, and can be rephrased as a question sentence, an imperative sentence, or the like.

[0073] The second text data may be a system prompt. In this specification, a system prompt refers to an instruction sentence in a prompt that is preset by a developer or a service provider. Presetting a system prompt makes it easier to obtain a desired answer from a language model.

[0074] An example of the second text data is an instruction sentence including a command to correct a sentence, such as "Please correct target sentence A." Note that the text data corresponding to target sentence A is the first text data.

[0075] The data DA2 obtained through such processing is transmitted from the information processing device 10 to the information processing device 40 via the network 30.

[0076] Next, data DB1 is transmitted from information processing device 40 to information processing device 10 via network 30. That is, information processing device 10 acquires data DB1 from information processing device 40 via network 30. Data DB1 is text data equivalent to a response sentence corresponding to data DA2 input to information processing device 40. Details of data DB1 will be described later in <Information processing method 1> and <Information processing method 2>.

[0077] Next, the information processing device 10 creates a data DB2 based on the data DB1. The data DB2 is the data DA1 updated based on the data DB1. Details of the data DB2 will be described later in the <Information processing method 1> and <Information processing method 2>.

[0078] Next, the information processing device 10 outputs the data DB2 to the information terminal 20 via the network 31. As a result, the user can obtain the data DB2 created by updating the data DA1.

[0079] For example, data DB2 may be converted into data other than text data and then output to information terminal 20. For example, if data DA1 is data other than text data, data DB2 is preferably data in the same format as data DA1. Information processing device 10 may have a function of generating image data using text data, for example.

[0080] Fig. 3 is a block diagram of the information processing system shown in Fig. 1. In Fig. 3, an example of the configuration of the information processing device 10 will be mainly described.

[0081] The information processing device 10 includes a receiving unit 110 , a storage unit 120 , a processing unit 130 , an output unit 140 , and a transmission path 150 .

[0082] In the drawings accompanying this specification, the components are classified by function and shown as independent blocks in the block diagrams. However, in reality, it is difficult to completely separate the components by function, and one component may be involved in multiple functions. For example, part of the processing unit 130 may function as the reception unit 110. Also, one function may be involved in multiple components. For example, the processing performed by the processing unit 130 may be executed by different servers depending on the processing.

[0083] [Reception Unit 110] The reception unit 110 can receive data from outside the information processing device 10. For example, the reception unit 110 receives data from the information terminal 20 via the network 31. The data received from the information terminal 20 corresponds to the data DA1 described above. Furthermore, for example, the reception unit 110 receives data from the information processing device 40 via the network 30. The data received from the information processing device 40 corresponds to the data DB1 described above.

[0084] As described above, it is preferable that the data accepted by the accepting unit 110 is text data. Furthermore, if the data accepted by the accepting unit 110 is data other than text data, it is preferable that the processing unit 130 generates text data using the data accepted by the accepting unit 110.

[0085] The data supplied to the reception unit 110 is supplied to one or both of the storage unit 120 and the processing unit 130 via the transmission path 150. The reception unit 110 may be, for example, a communication port or an input device such as a personal computer equipped with a communication function.

[0086] [Storage Unit 120] The storage unit 120 has a function of storing a program executed by the processing unit 130. The storage unit 120 may also have a function of storing data created by the processing unit 130 (e.g., calculation results, analysis results, inference results), data input to the reception unit 110, etc.

[0087] The storage unit 120 preferably has a function of storing instruction sentences in the prompts. Details of the instruction sentences in the prompts will be described later in <Information processing method 1> and <Information processing method 2>.

[0088] The storage unit 120 may have a database. Furthermore, the information processing device 10 may have a database separate from the storage unit 120. The information processing device 10 may have a function to retrieve data from a database that exists outside the storage unit 120, outside the information processing device 10, or outside the information processing system. Furthermore, the information processing device 10 may have a function to retrieve data from both its own database and an external database.

[0089] A file server may be used instead of the database. For example, when using files stored in a file server, it is preferable that the database has paths to files stored in the file server.

[0090] The storage unit 120 includes at least one of a volatile memory and a non-volatile memory. Examples of the volatile memory include a dynamic random access memory (DRAM) and a static random access memory (SRAM). Examples of the non-volatile memory include a resistive random access memory (ReRAM), a phase change random access memory (PRAM), a ferroelectric random access memory (FeRAM), a magnetoresistive random access memory (MRAM), and a flash memory. The storage unit 120 may also include at least one of NOSRAM (registered trademark) and DOSRAM (registered trademark). The storage unit 120 may also include a recording media drive. Examples of recording media drives include a hard disk drive (HDD) and a solid state drive (SSD).

[0091] NOSRAM is an abbreviation for "Nonvolatile Oxide Semiconductor Random Access Memory (RAM)." NOSRAM refers to a memory in which memory cells are two-transistor (2T) or three-transistor (3T) gain cells and transistors (also called OS transistors) that use metal oxide in their channel formation regions. OS transistors have an extremely small leakage current, i.e., a current that flows between the source and drain in an off state. NOSRAM can be used as a nonvolatile memory by retaining a charge corresponding to data in the memory cell using its extremely small leakage current characteristic. In particular, NOSRAM can read stored data without destroying it (nondestructive readout), making it suitable for arithmetic processing in which only data read operations are repeated a large number of times. NOSRAM can increase its data capacity by stacking layers, and therefore can be used as a large-scale cache memory, main memory, or storage memory to improve the performance of semiconductor devices.

[0092] DOSRAM is an abbreviation for "Dynamic Oxide Semiconductor RAM" and refers to a RAM having 1T (transistor) 1C (capacitor) type memory cells. DOSRAM is a DRAM formed using OS transistors, and is a memory that temporarily stores information sent from an external device. DOSRAM is a memory that takes advantage of the low off-state current of OS transistors.

[0093] In this specification and the like, a metal oxide refers to an oxide of a metal in a broad sense. Metal oxides are classified into oxide insulators, oxide conductors (including transparent oxide conductors), oxide semiconductors (also referred to as oxide semiconductors or simply as OSs), and the like. For example, when a metal oxide is used for a semiconductor layer of a transistor, the metal oxide may be referred to as an oxide semiconductor.

[0094] The metal oxide included in the channel formation region preferably contains indium (In). When the metal oxide included in the channel formation region contains indium, the carrier mobility (electron mobility) of the OS transistor is increased. Furthermore, the metal oxide included in the channel formation region is preferably an oxide semiconductor containing element M. The element M is preferably at least one of aluminum (Al), gallium (Ga), and tin (Sn). Other elements applicable to element M include boron (B), silicon (Si), titanium (Ti), iron (Fe), nickel (Ni), germanium (Ge), yttrium (Y), zirconium (Zr), molybdenum (Mo), lanthanum (La), cerium (Ce), neodymium (Nd), hafnium (Hf), tantalum (Ta), and tungsten (W). However, a combination of two or more of the above elements may be used as element M. The element M is, for example, an element having a high bond energy with oxygen. For example, it is an element having a higher bond energy with oxygen than indium. The metal oxide contained in the channel formation region is preferably a metal oxide containing zinc (Zn), since zinc-containing metal oxides may be easily crystallized.

[0095] The metal oxide contained in the channel formation region is not limited to a metal oxide containing indium, but may be, for example, a metal oxide containing zinc but not indium, such as zinc tin oxide or gallium tin oxide, a metal oxide containing gallium, or a metal oxide containing tin.

[0096] [Configuration Example 1 of Processing Unit 130] The processing unit 130 has a function of performing processes such as calculation, analysis, and inference using data supplied from one or both of the reception unit 110 and the storage unit 120. The processing unit 130 can supply the created data (e.g., calculation results, analysis results, and inference results) to one or both of the storage unit 120 and the output unit 140.

[0097] The processing unit 130 has a function of acquiring data from the storage unit 120. The processing unit 130 may also have a function of recording or registering data in the storage unit 120.

[0098] The processing unit 130 has a function of dividing a document included in the document data into multiple blocks. For example, the processing unit 130 has a function of dividing a document included in the document data into multiple first blocks. One block includes at least one sentence. For example, a document can be divided into blocks, with one paragraph being one block. The document may also be divided using information such as headings included in the document. Alternatively, blocks may be divided by sentence, i.e., each block may consist of one sentence. The document data is data received by the receiving unit 110 and corresponds to data DA1.

[0099] The processing unit 130 has a function of creating a first prompt including a first object sentence and a first instruction sentence. The first object sentence includes at least one of the plurality of first blocks described above. The first instruction sentence includes an instruction to perform a first determination on each of the first blocks. The created first prompt corresponds to data DA2.

[0100] The processing unit 130 has a function of acquiring a response sentence by transmitting a prompt to the language model via the transmission path 150, the output unit 140, and the network 30. For example, the processing unit 130 has a function of acquiring a first response sentence including a first determination result based on the first determination by transmitting a first prompt to the language model via the transmission path 150, the output unit 140, and the network 30. The first determination includes a determination of the type of content written for each of the above-mentioned multiple first blocks. Examples of the type of content written include the configuration and effects of the invention. From the above, the first prompt can be called a description determination prompt.

[0101] The first determination result may include, for example, information on whether a description regarding the configuration of the invention is included and whether a description regarding the effect is included. Furthermore, the first determination result may include information on first blocks that include descriptions of the same configuration among the above-mentioned multiple first blocks. The language model may also determine the presence or absence of descriptions other than the configuration and the effect. For example, the language model may determine the presence or absence of descriptions of one or both of the principle and the action.

[0102] The processing unit 130 has a function of extracting at least one second block based on the first determination result. The second block can include one or more first blocks. For example, multiple first blocks describing the same configuration can be included in one second block. Furthermore, a first block describing the configuration of the invention and a first block describing the effects associated with the configuration can be included in one second block. Furthermore, a first block describing the configuration of the invention and a first block describing at least one of the effects, principles, and actions associated with the configuration can also be included in one second block.

[0103] The acquired first response sentence corresponds to data DB 1. Hereinafter, the process of acquiring a response sentence corresponding to a prompt by sending a prompt to a language model and extracting at least one block from the response sentence may be referred to as the process of acquiring at least one block by sending a prompt to a language model.

[0104] The processing unit 130 has a function of extracting blocks that satisfy a specific condition from the blocks included in the prompt based on a determination result included in the response sentence obtained from the language model. For example, the processing unit 130 has a function of extracting a second block that satisfies a specific condition based on a first determination result included in a first response sentence obtained from the language model. The processing unit 130 has a function of extracting at least one second block from, for example, a description of the configuration of the invention but not its effects.

[0105] The processing unit 130 has a function of creating a second prompt including a second object sentence and a second instruction sentence. The second object sentence includes at least one of the extracted second blocks. The second instruction sentence includes an instruction to present at least one revision suggestion for each of the second blocks included in the second object sentence. The revision suggestion may be, for example, a proposal for an effect. From the above, the second prompt can be called an revision prompt. The created second prompt corresponds to data DA2.

[0106] The processing unit 130 has a function of acquiring a second response sentence including at least one of the revision suggestions by transmitting a second prompt to the language model via the transmission path 150, the output unit 140, and the network 30. The acquired second response sentence corresponds to the data DB1.

[0107] The processing unit 130 has a function of generating a third prompt including a third object sentence and a third instruction sentence. The third object sentence includes document data and at least one of the revision suggestions. The third instruction sentence includes an instruction to perform a second judgment on each of the revision suggestions. The generated third prompt corresponds to data DA2.

[0108] The processing unit 130 has a function of acquiring a third response sentence including a second determination result based on the second determination by sending a third prompt to the language model. The acquired third response sentence corresponds to data DB1.

[0109] The second determination includes determining whether each of the revision suggestions is consistent with the document data. For example, the second determination can determine whether each of the revision suggestions is consistent with the content of the document data. Therefore, the third prompt can be called a consistency determination prompt.

[0110] The processing unit 130 has a function of updating the document data by adding at least one revision suggestion to at least one of the extracted second blocks. The updated document data corresponds to the data DB2.

[0111] [Configuration Example 2 of Processing Unit 130] The processing unit 130 also has a function of dividing a document included in the document data into a plurality of first blocks, transmitting the first blocks to the language model, and classifying each of the first blocks into one of a plurality of classes. Each of the plurality of classes includes a second block, and each of the second blocks includes at least one first block.

[0112] The processing unit 130 also has a function of creating a second block classified into one of a plurality of classes based on the description for each of the plurality of divided first blocks.

[0113] The above-mentioned multiple classes may include a first class, a second class, a third class, and a fourth class. Here, the first class has, for example, a second block including a description of the configuration and a description of the first effect. The second class has, for example, a second block including a description of the configuration but not including a description of the effect. The third class has, for example, a second block including a description of the first effect but not including a description of the configuration. The fourth class has, for example, a second block including neither a description of the configuration nor a description of the first effect.

[0114] The processing unit 130 has a function of extracting from the database, for a second block classified into the first class or the second class, a description of the second effect corresponding to a description of the configuration included in the second block.

[0115] <<When the Second Block is Classified as the First Class>> The processing unit 130 has a function of creating a fourth prompt for a second block classified as the first class. The fourth prompt is created when the description of the first effect described in the document data and the description of the second effect registered in the database do not match. The fourth prompt includes a description of the first effect and a description of the second effect, and has an instruction to generate a message. In other words, the processing unit 130 creates the fourth prompt when the first effect described in the document data differs from the second effect registered in the database.

[0116] The processing unit 130 has a function of sending the fourth prompt to the language model to generate a message. The message includes the difference between the description of the first effect and the description of the second effect. Here, the message may be, for example, text data. Note that the format of the message data is not limited. For example, it may be text data, audio data, image data, etc.

[0117] The processing unit 130 has a function of outputting the above-mentioned message from the output unit 140 and displaying it on the display unit of the information terminal 20. Specifically, the processing unit 130 has a function of displaying, in table format, on the display unit of the information terminal 20, in addition to the second block classified into the first class, for example, a description of the configuration included in the second block, a description of the first effect, a description of the second effect, and a graphical user interface (GUI) including messages, check boxes, etc. The user receives the message and uses the description of the second effect to determine whether or not to modify the document data.

[0118] The processing unit 130 has a function of creating a fifth prompt when it receives a modification command. Here, "receiving the modification command" can refer to, for example, a state in which the receiving unit 110 receives the modification command input by the user using the information terminal 20. The modification command can be executed on a second block classified into the first class, and includes, for example, an instruction to modify the description of the first effect using the description of the second effect. The fifth prompt includes a description of the first effect and a description of the second effect, and has an instruction to modify the description of the first effect using the description of the second effect.

[0119] The processing unit 130 has a function of acquiring a first proposed revision by sending the fifth prompt to the language model. The first proposed revision may be a description obtained by correcting the description of the first effect using the description of the second effect. Furthermore, the first proposed revision may be generated, for example, to adapt the format of the content of the description of the second effect to the format of the first class. Here, the first proposed revision may be a description of an effect corresponding to the description of the configuration included in the second block. For example, if the document data is a specification belonging to a patent application, the first proposed revision may add symbols, etc. included in the first class to the description of the second effect to improve the format of the description.

[0120] The processing unit 130 has a function of updating the document data for the second block classified into the first class for which the above-mentioned correction command has been received, based on the first correction proposal. Specifically, the processing unit 130 updates the first document included in the document data to update the document data.

[0121] <<When the Second Block is Classified into the Second Class>> The processing unit 130 has a function of creating a sixth prompt for a second block classified into the second class. As described above, the second class is a class that has a second block that includes a description of a configuration but does not include a description of an effect. The sixth prompt includes the second block classified into the second class and a description of a second effect, and has an instruction to modify the description of the second effect.

[0122] The processing unit 130 has a function of acquiring a second proposed revision by sending the sixth prompt to the language model. The second proposed revision can be generated, for example, to adapt the format of the content of the description of the second effect to the format of the second class. The second proposed revision can be used to create a description of a third effect corresponding to the description of the configuration included in the second block. Here, the description of the third effect can be a description of an effect corresponding to the description of the configuration included in the second block. For example, if the document data is a specification belonging to a patent application, the second proposed revision adds symbols, etc. included in the second class to the description of the second effect to improve the format of the description.

[0123] The processing unit 130 has a function of updating the document data for the second block classified into the second class based on the third description. Specifically, the document data is updated by the processing unit 130 by updating the first document included in the document data.

[0124] If the second block is classified into the third class or the fourth class, the processing unit 130 does not process the second block.

[0125] The processing unit 130 may include, for example, an arithmetic circuit, a central processing unit (CPU), and a graphics processing unit (GPU).

[0126] The processing unit 130 may have a microprocessor such as a DSP (Digital Signal Processor). The microprocessor may be implemented by a PLD (Programmable Logic Device) such as an FPGA (Field Programmable Gate Array) or an FPAA (Field Programmable Analog Array). The processing unit 130 may also have a quantum processor. The processing unit 130 can perform various data processing and program control by interpreting and executing instructions from various programs using the processor. Programs that can be executed by the processor are stored in at least one of the memory area of ​​the processor and the storage unit 120.

[0127] The processing unit 130 may include a main memory. The main memory may include at least one of a volatile memory such as a random access memory (RAM) and a non-volatile memory such as a read-only memory (ROM). The main memory may also include at least one of the above-mentioned NOSRAM and DOSRAM.

[0128] The RAM may be, for example, a DRAM or an SRAM, and a virtual memory space is allocated and used as a working space for the processing unit 130. The operating system, application programs, program modules, program data, lookup tables, and the like stored in the storage unit 120 are loaded into the RAM for execution. The data, programs, and program modules loaded into the RAM are each directly accessed and operated by the processing unit 130.

[0129] The ROM can store a BIOS (Basic Input / Output System), firmware, etc., which do not require rewriting. Examples of ROM include mask ROM, OTPROM (One Time Programmable Read Only Memory), and EPROM (Erasable Programmable Read Only Memory). Examples of EPROMs include UV-EPROMs (Ultra-Violet Erasable Programmable Read Only Memories), which allow stored data to be erased by exposure to ultraviolet light, EEPROMs (Electrically Erasable Programmable Read Only Memories), and flash memories.

[0130] The processing section 130 can include one or both of an OS transistor and a transistor having silicon in a channel formation region (a Si transistor).

[0131] The processing unit 130 preferably includes an OS transistor. Because an OS transistor has an extremely small off-state current, using the OS transistor as a switch for retaining charge (data) flowing into a capacitor functioning as a memory element can ensure a long data retention period. By using this characteristic in at least one of the register and cache memory of the processing unit, the processing unit can be operated only when necessary, and can be turned off in other cases by saving information from the previous processing in the memory element. In other words, normally-off computing is possible, and the power consumption of the information processing system can be reduced.

[0132] [Output Unit 140] The output unit 140 has a function of outputting data based on the processing result of the processing unit 130. The output unit 140 can supply at least one of the calculation result, analysis result, and inference result of the processing unit 130 to an external device of the information processing device 10.

[0133] The output unit 140 can output data to the outside of the information processing device 10. For example, the output unit 140 outputs data to the information terminal 20 via the network 31. The output unit 140 can output data created by the processing unit 130 based on data received from the information processing device 40 to the information terminal 20. Alternatively, the output unit 140 can output the data itself received from the information processing device 40 to the information terminal 20. The data output to the information terminal 20 corresponds to the data DB 2 described above.

[0134] The data can be presented, for example, by displaying it on the display screen of the information terminal 20, or by outputting a file in a format such as txt, docx, xml, pdf, or csv.

[0135] Furthermore, the output unit 140 outputs data to the information processing device 40 via the network 30. The output unit 140 outputs data created by the processing unit 130 based on data received from the information terminal 20 to the information processing device 40. The data output to the information processing device 40 corresponds to the data DA2 described above. Furthermore, the output unit 140 may be, for example, a communication port or a device such as a personal computer equipped with a communication function.

[0136] [Transmission Path 150] The transmission path 150 has a function of transmitting data. Data can be transmitted and received between the reception unit 110, the storage unit 120, the processing unit 130, and the output unit 140 via the transmission path 150. Specifically, a LAN or the Internet can be used.

[0137] <Information Processing Method 1> The information processing method of this embodiment includes steps S01 to S12 shown in FIG. 4. FIGS. 7A to 13 are diagrams illustrating the information processing method. FIGS. 12A to 13 can be considered examples of GUIs related to the information processing system of this embodiment. Forms, icons, tables, etc. in the drawings related to the GUI illustrated in this embodiment, such as FIG. 12A, are examples and are not particularly limited. The GUI can be configured as a web page accessed by a user via a network. Alternatively, the GUI can be configured as a screen of a program application executed on a terminal used by the user. FIGS. 11A to 13 show an example of a case in which a language model is used to make a judgment on a block (such as a sentence or paragraph) and instructs the user to correct the document based on the judgment result.

[0138] [Step S01] In step S01, the receiving unit 110 receives document data. Specifically, the receiving unit 110 receives the document data via the information terminal 20. The document data corresponds to the above-mentioned data DA1. In the information processing method of this embodiment, a case will be described in which the receiving unit 110 receives document data including the document 301.

[0139] The document 301 may be, for example, a document relating to an invention. The document 301 may include, for example, a block describing the configuration of the invention and a block describing information related to the configuration. The document 301 may include, for example, a block describing the configuration and a block describing at least one of the principles, actions, and effects related to the configuration.

[0140] For example, a user inputs document data including document 301 to information processing device 10 using information terminal 20. Alternatively, for example, the user may specify document data stored in storage unit 120. Then, blocks included in document 301 are output from information processing device 10 to the display unit of information terminal 20.

[0141] [Step S02] In step S02, the processing unit 130 divides the document 301 included in the document data into a plurality of blocks 302. The blocks 302 correspond to the first blocks described above. Each block 302 may be, for example, one or more paragraphs. Also, each block 302 may be, for example, one or more sentences.

[0142] For example, as shown in Fig. 7A, a document 301 is divided into a plurality of blocks 302 by the processing unit 130. Fig. 11A shows an example in which the document 301 is divided into paragraphs. Fig. 11A shows a table including paragraphs 321, determination results 322, and blocks 324. Here, the determination results 322 can be the first determination results described above. Furthermore, the blocks 324 can be the first and second blocks described above. Note that the table items are not limited to these. Furthermore, the determination results 322 will be described later.

[0143] 11A, the paragraph 321 with the paragraph number "0xx1" is set as block 302[1]. Similarly, the paragraphs 321 with the paragraph numbers "0xx2," "0xx3," "0xx4," "0xx5," and "0xx6" are set as block 302[2], block 302[3], block 302[4], block 302[5], and block 302[6], respectively.

[0144] In the information processing method of this embodiment, a case will be described in which a document 301 is divided into n blocks 302 (blocks 302[1] to 302[n]) (n is an integer of 2 or more).

[0145] In addition, if document 301 is the smallest unit to be divided in step S02 (for example, if document 301 consists of one paragraph when dividing by paragraphs, or if document 301 consists of one sentence when dividing by sentences), the processing of step S02 can be omitted.

[0146] [Step S03] In step S03, the processing unit 130 creates a prompt 303. The prompt 303 is a prompt for determining the type of content described in the block 302. For example, if the document 301 is a document relating to an invention, the prompt 303 can be a prompt for determining whether the block 302 describes the configuration or the effect of the invention. Furthermore, if the block 302 describes a configuration, the prompt 303 can be a prompt for determining whether or not there is an effect for the configuration. Furthermore, if the block 302 describes a configuration, the prompt 303 can be a prompt for determining whether or not the document 301 contains a description of the same configuration. Furthermore, if the block 302 describes an effect, it can be determined whether or not the document 301 contains a description of the configuration corresponding to the effect. The prompt 303 corresponds to the first prompt in <Configuration Example 1 of Information Processing System>.

[0147] The processing unit 130 has a function of presenting a first instruction sentence. The first instruction sentence includes a command for making the above-mentioned determination. For example, instructions such as "For each block, determine whether or not a description of the structure and its effect is included," "For each block determined to contain a description of the structure, determine whether or not a description of the effect of the structure is included," "For each block determined to contain a description of the structure, determine whether or not the structure is identical to the structure described from the beginning of the document to the block," and "For each block determined to contain a description of the effect, determine whether or not the document contains a description of the structure corresponding to the effect" are presented. The processing unit 130 can create a prompt 303 using a first object sentence and the first instruction sentence. The first object sentence includes at least one of blocks 302[1] to 302[n], for example, all of blocks 302[1] to 302[n]. The first instruction sentence includes a command for making the above-mentioned determination of the description content for each of the blocks 302 included in the first object sentence.

[0148] [Step S04] In step S04, the processing unit 130 transmits a prompt to the language model via the network 30, thereby acquiring a response sentence 310 including at least one determination result 322. For example, as shown in Fig. 7B, the processing unit 130 transmits a prompt 303 to the language model 210, thereby acquiring a response sentence 310 in response to the prompt 303. The response sentence 310 corresponds to the first response sentence described above.

[0149] 11A also shows the judgment result 322 extracted from the response sentence 310. The judgment result 322 can be assigned to each of blocks 302[1] to 302[n], for example. Specifically, a label indicating the judgment result 322 can be assigned to each of blocks 302[1] to 302[n]. FIG. 11A shows the judgment results assigned to blocks 302[1] to 302[6].

[0150] In the information processing method of this embodiment, an example is shown in which the determination result 322 includes "A", "B", "C", and "D". "A" indicates that it has been determined that both the configuration and the effect are described in the block 302, for example. "B" indicates that it has been determined that the configuration is described in the block 302 but the effect is not described in the block 302, for example. "C" indicates that it has been determined that the effect is described in the block 302 but the configuration is not described in the block 302, for example. "D" indicates that it has been determined that neither the configuration nor the effect is described in the block 302. FIG. 11A shows an example in which the determination results 322 for block 302[1], block 302[2], block 302[3], block 302[4], block 302[5], and block 302[6] are "B", "A", "D", "B", "D", and "C", respectively.

[0151] In the information processing method of this embodiment, in order to make it easier to distinguish the determination results, the determination results "A", "B", "C", and "D" are shown with different hatching.

[0152] When any of blocks 302[1] to 302[n] includes a description of the same configuration, the determination result 322 includes information about the block 302. When any of blocks 302[1] to 302[n] includes a description of an effect, the determination result 322 includes information about the block 302 that has a description of the configuration corresponding to the effect included in the block 302.

[0153] The language model may determine whether or not a description other than the configuration and the effect is included, as described above. For example, the language model may determine whether or not one or both of the principle and the action are included. In this case, for example, the determination result for block 302 in which one or both of the principle and the action are included may be "A" or "C" depending on whether or not the configuration is included. Furthermore, for example, the determination result for block 302 in which one or both of the principle and the action are not included may be "B" or "D" depending on whether or not the configuration is included. Alternatively, a label indicating a determination result other than "A" to "D" may be assigned to block 302 depending on whether or not one or both of the principle and the action are included.

[0154] [Step S05] In step S05, the processing unit 130 acquires at least one block 304 based on the determination result 322. Each block 304 can include one or more blocks 302. For example, multiple blocks 302 describing the same configuration can be included in a single block 304. Also, a block 302 describing the configuration of the invention and a block 302 describing the effects associated with the configuration can be included in a single block 304. Note that a block 302 describing the configuration of the invention and a block 302 describing at least one of the effects, principles, and actions associated with the configuration can also be included in a single block 304. Block 304 corresponds to the second block described above.

[0155] 7C shows a process for acquiring block 304 based on block 302 and determination result 322. FIG. 11B shows an example in which block 302[1] and block 302[2] are included in block 304[1], block 302[3] is included in block 304[2], block 302[4] is included in block 304[3], block 302[5] is included in block 304[4], and block 302[6] is included in block 304[5].

[0156] Furthermore, in step S05, the processing unit 130 assigns a label indicating the determination result 323 to the block 304 based on the determination result 322. The determination result 323 is, for example, the result of determining whether or not the configuration and effect of the block 304 are described, and is indicated by the above-mentioned labels "A" to "D." For example, if the block 304 includes one block 302, the determination result 322 of the block 302 is used as the determination result 323. If the block 304 includes multiple blocks 302 and the determination result 322 of at least one of the multiple blocks 302 is "A," the determination result 323 is set to "A." If the block 304 includes one or more blocks 302 whose determination result 322 is "B" and one or more blocks 302 whose determination result 322 is "C," the determination result 323 is set to "A." Furthermore, if block 304 includes a block 302 whose judgment result 322 is "B" but does not include a block 302 whose judgment result 322 is "A" or "C", judgment result 323 is set to "B". If block 304 includes a block 302 whose judgment result 322 is "C" but does not include a block 302 whose judgment result 322 is "A" or "B", judgment result 323 is set to "C". Furthermore, if block 304 only includes blocks whose judgment result 322 is "D", judgment result 323 is set to "D". Figure 11B shows an example in which judgment result 323 of block 304[1], which includes block 302[1] and block 302[2], is "A". Also, FIG. 11B shows an example in which the judgment results 323 of blocks 304[2] to 304[5] are “D”, “B”, “D”, and “C”, respectively, similar to the judgment results 322 of blocks 302[3] to 302[6].

[0157] In the information processing method of this embodiment, we will explain the case where m blocks 304 (block 304[1] to block 304[m]) (m is an integer greater than or equal to 1 and less than or equal to n) are obtained based on n blocks 302.

[0158] [Step S06] In step S06, the processing unit 130 extracts one or more blocks 304 based on the determination result 323. For example, at least one of the blocks 304 for which the determination result 323 is any one selected from "A", "B", "C", and "D" is extracted. The information processing method of this embodiment shows an example in which at least one of the blocks 304 for which the determination result 323 is "B" is extracted. That is, for example, this shows an example in which at least one of the blocks 304 for which the configuration of the invention is described but the effect is not described is extracted.

[0159] 8A shows examples of block 304[1], block 304[2], block 304[3], block 304[m-1], and block 304[m]. In FIG. 8A, description 201 is, for example, a description about the configuration of the invention. Furthermore, description 202 is, for example, a description about the effects of the invention. Furthermore, description 203 is a description that is not classified as either description 201 or description 202. Note that description 202 may be, for example, a description about the principle of the invention or a description about the operation of the invention.

[0160] In the example shown in FIG. 8A , block 304[1] includes description 201 in paragraph [0xx1] and description 202 in paragraph [0xx2]. Block 304[2] includes description 203 in paragraph [0xx3]. Block 304[3] includes description 201 in paragraph [0xx4]. Block 304[m-1] includes description 202 in paragraph [0yy1]. Block 304[m] includes description 201 in paragraph [0yy2] and description 203 in paragraph [0yy3]. Here, it is assumed that block 304[m-1] does not include description 201. It is also assumed that block 304[3] and block 304[m] do not include description 202. It is also assumed that block 304[2] does not include description 201 or description 202.

[0161] 12A shows an example in which the extracted block 304 is displayed on the display unit of the information terminal 20. In the example shown in FIG. 12A, in addition to the block 304, a check box 330, a paragraph 321, and a judgment result 323 are displayed in a table format. Also shown is an example in which buttons 333 and 335 are displayed above the table. As described above, in step S06, for example, a block 304 whose judgment result 323 is "B" is extracted. Therefore, FIG. 12A shows an example in which, for example, blocks 304[3] and 304[m] shown in FIG. 8A are displayed. Also shown is an example in which block 304[3] includes block 302[4], and block 304[m] includes block 302[n-1] and block 302[n].

[0162] The user selects at least one block 304 that requires additional effects from among the blocks 304 displayed on the display unit of the information terminal 20 and that do not contain effects. For example, suppose the user determines that block 304[3] needs additional effects from among the blocks 304 for which the judgment result 323 is "B." In this case, the user selects block 304[3] by clicking while hovering the mouse pointer 327 over the row containing block 304[3]. At this time, a check mark indicating the selection of block 304[3] is entered in the check box 330. Furthermore, if a check mark has already been entered in block 304[3], selecting the row containing block 304[3] removes the check mark and deselects the block. Furthermore, the display may have a function for selecting or deselecting all blocks 304 at once. For example, the user may select or remove check marks from the check boxes 330 of all blocks 304 by clicking while hovering the mouse pointer 327 over button 333.

[0163] The button 335 can be used as a button for performing the processes from step S07 onwards for the selected block 304. Specifically, by clicking the button 335 with the mouse pointer 327 positioned on it, the processes from step S07 onwards, which will be described later, can be performed using the block 304 with the check mark entered.

[0164] The method of indicating that a block 304 is selected is not limited to a check box. For example, a radio button or a text box may be displayed. Furthermore, buttons and blocks do not have to be selected using a mouse. For example, selection may be performed by pressing a predetermined key or the like while a button, a line, a block, or a check box is focused.

[0165] Note that methods other than hatching may be used to make the judgment results easier to distinguish from one another, such as using different background colors for the judgment results "A," "B," "C," and "D," changing the color of the text, increasing the text size, changing the font, making the text bold, underlining, etc.

[0166] Note that, for example, if no blocks 304 with no effects described therein have been extracted, or if a block 304 with no effects described therein has been extracted but the user determines that no blocks 304 with effects that require modification exist, the user can select button 335 to terminate the update of document 301. Specifically, if no blocks 304 have been selected, selecting button 335 allows the process of step S12 to be performed without performing steps S07 to S11, which will be described later.

[0167] [Step S07] In step S07, the processing unit 130 creates a prompt 305. The prompt 305 corresponds to the second prompt in <Configuration Example 1 of Information Processing System>.

[0168] Prompt 305 is a prompt for amending the description. Prompt 305 includes a second instruction sentence and a second target sentence. For example, if document 301 is a document related to an invention, the second instruction sentence includes an instruction to present an amendment proposal, such as an effect description, for block 304 selected by the user in step S06. The second instruction sentence can be, for example, "Please generate a block describing an effect proposal corresponding to the configuration described in selected block 304."

[0169] Furthermore, the second instruction preferably includes a statement specifying the number of revision suggestions to be output in step S10, which will be described later. That is, the second instruction preferably includes a statement specifying the number of revision suggestions to be generated. For example, if three revision suggestions are to be generated, the second instruction may include a statement such as "Please generate three revision suggestions." In this way, by specifying the number of blocks to be generated in the second instruction, the language model can generate a response sentence including the desired number of revision suggestions.

[0170] The second target sentence includes the block 304 selected by the user in step S06. Note that, for example, all of the blocks 304 extracted in step S06 may be included in the second target sentence. In this case, the user does not select any of the extracted blocks 304 in step S06. For example, the screen shown in FIG. 12A may not be displayed.

[0171] [Step S08] In step S08, the processing unit 130 acquires a response sentence 311 including at least one revision suggestion by sending a prompt to the language model via the network 30. For example, as shown in FIG. 9A , the processing unit 130 acquires a response sentence 311 in response to the prompt 305 by sending the prompt 305 to the language model 220. The response sentence 311 includes a block 306 including a revision suggestion. The block 306 may include, for example, an effect suggestion. The response sentence 311 corresponds to the second response sentence described above.

[0172] In the information processing method of this embodiment, a case will be described in which the language model generates k blocks 306 (block 306[1] to block 306[k]) (k is an integer of 2 or more).

[0173] Furthermore, a plurality of response sentences 311 can also be obtained from the language model. The language model probabilistically calculates subsequent phrases from the arrangement of phrases. At this time, by adding some fluctuation, the language model can generate a plurality of response sentences 311. At this time, revision suggestions may be extracted from each of the plurality of response sentences 311, thereby obtaining a plurality of revision suggestions.

[0174] The language model may also present suggestions for additions other than effects, such as suggestions for additions to principles and actions of the description of the configuration.

[0175] Furthermore, in step S06 described above, the processing unit 130 may extract, for example, block 304 whose determination result 323 is "A" or block 304 whose determination result 323 is "C." That is, for example, as shown in FIG. 8B , block 304 containing a description of effects may be extracted. FIG. 8B shows an example in which block 304[1] containing description 202 about effects in addition to description 201 about the configuration of the invention is extracted. FIG. 8B also shows an example in which block 304[m-1] containing description 202 but not description 201 is extracted. Note that in the example shown in FIG. 8B , blocks 304[3] and 304[m] are extracted, similar to the example shown in FIG. 8A .

[0176] In the above cases, response sentence 311 can include one or more effects related to the effect included in block 304 as block 306. For example, by including in the second instruction sentence an instruction to the effect, "If an effect is described in the selected block 304, please generate one or more blocks describing proposed effects related to that effect," one or more effects related to the effect included in block 304 can be included in response sentence 311.

[0177] As described above, the second directive may specify the number of blocks to be generated more specifically. In this case, the second directive may include, for example, a directive such as "If the selected block 304 contains an effect, generate three blocks containing proposed effects related to that effect." Note that the number of blocks 306 generated may be different for blocks 304 containing an effect and blocks 304 containing no effect. In this case, the second directive may include, for example, a directive such as "If the selected block 304 does not contain an effect, generate five blocks containing proposed effects" and a directive such as "If the selected block 304 contains an effect, generate three blocks containing proposed effects related to that effect."

[0178] [Step S09] In step S09, the processing unit 130 creates a prompt 307. The prompt 307 is a prompt that compares the contents of the generated revision suggestion with the document 301 to make a judgment. The judgment can be, for example, whether there is consistency. Specifically, the prompt 307 can be a prompt that determines whether there is any inconsistency with the contents of the document 301 for each of blocks 306[1] to 306[k] that contain revision suggestions extracted from the response sentence 311. The prompt 307 corresponds to the third prompt in <Configuration Example 1 of Information Processing System>.

[0179] The processing unit 130 has a function of presenting a third instruction sentence. The third instruction sentence includes an instruction to generate a judgment result for each of blocks 306[1] to 306[k]. The judgment result may be, for example, whether or not there is consistency with the description in document 301. For example, an instruction sentence such as "Please judge the consistency of each revision proposal with the description in document 301" is presented. The processing unit 130 can create a prompt 307 using the third target sentence and the third instruction sentence.

[0180] Furthermore, the third directive preferably includes a description specifying a determination method. That is, the directive preferably describes what kind of determination is to be made for, for example, blocks 306[1] to 306[k]. For example, the third directive may include a description such as "Please determine whether there is any contradiction with the contents of document 301 using 'TRUE' or 'FALSE'." In this way, by describing the determination method in the third directive, it becomes easier to obtain highly accurate results from the language model.

[0181] [Step S10] In step S10, the processing unit 130 acquires a response sentence 313 by transmitting a prompt to the language model via the network 30. For example, as shown in FIG. 9B , the processing unit 130 acquires a response sentence 313 in response to the prompt 307 by transmitting a prompt 307 to the language model 230. The response sentence 313 includes, for example, determination results 329 corresponding to each of blocks 306[1] to 306[k]. The response sentence 313 corresponds to the third response sentence described above. The determination result 329 corresponds to the second determination result described above.

[0182] 12B shows an example in which a table including a serial number 325, a determination result 329, and a block 326 is displayed on the display unit of the information terminal 20. Block 326 can be block 306[1] to block 306[k]. In the example shown in FIG. 12B, block 306[1], block 306[2], and block 306[3] are shown as block 326. Note that table items are not limited to these.

[0183] In this embodiment, an example is shown in which the determination result 329 includes "TRUE" and "FALSE." "TRUE" indicates, for example, that it has been determined that the description in block 306 and the description in document 301 are consistent with each other. For example, it indicates that it has been determined that the description in block 306 is not inconsistent with the description in document 301. "FALSE" indicates, for example, that it has been determined that the description in block 306 is not consistent with the description in document 301. For example, it indicates that it has been determined that the description in block 306 is inconsistent with the description in document 301. FIG. 12B shows an example in which the determination results 329 for block 306[1], block 306[2], and block 306[3] are "TRUE," "TRUE," and "FALSE," respectively.

[0184] By determining the blocks 306 as described above, the user can easily select blocks suitable for the document 301. Furthermore, the user can select suggested revisions according to the user's preferences or the classification of the document 301.

[0185] Note that the block 306 with a predetermined determination result 329 may not be displayed on the display unit of the information terminal 20. For example, the block 306 with the determination result 329 being "FALSE" may not be displayed on the display unit of the information terminal 20. This can reduce the number of blocks 306 that the user must check, thereby reducing the workload of the user.

[0186] The user selects, for example, one of blocks 306[1] to 306[k] displayed on the display unit of the information terminal 20. Specifically, as shown in Fig. 12B, the user selects, for example, block 306 including a proposed effect to be added to block 304. In the information processing method of this embodiment, the user selects block 306[2] by clicking the line including block 306[2] with the mouse pointer 327 positioned thereon.

[0187] If block 326 does not contain the proposed effect the user expects, the content of block 326 to be displayed can be changed. For example, by selecting button 336, steps S08 to S10 can be performed again to obtain block 306 and update the displayed content. In step S08, the content of block 306 can be changed by adding some fluctuation when the language model probabilistically calculates the following phrase from the word placement.

[0188] [Step S11] In step S11, the processing unit 130 updates the document data. Specifically, the processing unit 130 updates the document 301 included in the document data.

[0189] Specifically, the processing unit 130 adds block 306 selected by the user to block 304. Fig. 13 shows an example in which block 306[2] is added after block 304[3], and as a result, the determination result 323 of paragraph 321, whose paragraph number is "0xx4," is updated to "A." The updated table can be displayed on the display unit of the information terminal 20. As shown in Fig. 13, the added block 306 is hatched, allowing the user to easily determine that block 306 has been added.

[0190] The user checks whether there are any problems with the content of the revised block 306. If there are any problems, the user can modify or delete the revised block 306. For example, as shown in FIG. 13, the user can repeat the processes of steps S06 to S10 by clicking button 337 with the mouse pointer 327 positioned on it. Specifically, as shown in FIG. 12A, a table in which blocks 304 without effects are extracted is displayed on the information terminal 20. The user can also delete the revised block 306 by clicking button 339 with the mouse pointer 327 positioned on it. The user may also manually modify the block 306.

[0191] 13 shows an example in which the revised block 306 is highlighted by hatching to make it easier to identify it, but the highlighting method is not limited to hatching. For example, the background color of the block 306 may be changed, the color of the text may be changed, the text may be enlarged, the font may be changed, the text may be made bold, or the text may be underlined.

[0192] As a result, the addition of paragraph 321, which includes block 304[3], is completed. The user then performs steps S06 through S10 on the other blocks 304 that the user has determined require addition. Alternatively, if the user selects multiple blocks 304 that require addition in step S06, the selected blocks may be included in prompt 305 and processed collectively in step S07. Specifically, if multiple blocks 304 are selected, steps S07 through S10 may be repeated until all selected blocks 304 have been processed, at which point step S11 may be performed. This completes the update of document 301 included in the document data.

[0193] If none of blocks 304[1] to 304[m] is extracted in step S06, the processes of steps S07 to S11 can be omitted.

[0194] [Step S12] In step S12, the output unit 140 outputs the document data. The document data is the document data of the updated document 301.

[0195] As described above, a document can be corrected using a language model. Furthermore, the document correction work using the language model can be optimized. Note that the language model 210, the language model 220, and the language model 230 may be the same model or different models. For example, when the same model is used, the system can be simplified. Furthermore, when different models are used, the system can be made lighter and optimized. Specifically, by using BERT for the language model 210 and the language model 230 that perform the determination, the generation of a prompt in the processing unit 130 can be omitted.

[0196] <Information Processing Method 2> The information processing method of this embodiment includes the processes of steps S21 to S34 shown in Figures 5 and 6. Figures 10A to 10D and Figures 14A to 15 are diagrams explaining the information processing method. Figures 14B and 15 can also be considered examples of GUIs related to the information processing system of this embodiment. Figure 15 shows a process of generating a suitable revision proposal using a language model for a structural description included in a block (sentence, paragraph, etc.) using a description extracted from a database.

[0197] In the information processing method of this embodiment, steps S21 to S25 can refer to steps S01 to S05, respectively. Specifically, document data is received, and a document 301 included in the document data is divided into a plurality of blocks 302, which are then transmitted to a language model, where each block 302 is classified into one of a plurality of classes. Each of the classes can include a block 304, and each of the blocks 304 can include at least one block 302.

[0198] FIG. 14A shows an example in which, for each of the divided blocks 302, a block 304 is created, classified into one of multiple classes based on the description. Here, description 201 represents a description of the configuration, and description 202 can be a description of the effect. Blocks with a common parenthesized alphabet (e.g., [A]) attached to the reference numeral of the description represent that they contain a description of the same configuration or a description of the effect of the same configuration. Note that description 202 is not limited to a description of the effect, and may be, for example, a description of the principle of the invention or a description of the operation of the invention. For block 304, the explanation in step S05 can be referred to. Description 202 corresponds to the description of the first effect described above.

[0199] The above-mentioned multiple classes include class 340, class 341, class 342, and class 343. Here, for example, class 340 has block 304 that includes description 201 and description 202. For example, class 341 has block 304 that includes description 201 but does not include description 202. For example, class 342 has block 304 that includes description 202 but does not include description 201. For example, class 343 has block 304 that does not include either description 201 or description 202. Class 340 corresponds to the above-mentioned first class, and class 341 corresponds to the above-mentioned second class. For example, class 342 corresponds to the above-mentioned third class, and class 343 corresponds to the above-mentioned fourth class.

[0200] In the example shown in FIG. 14A , blocks 302[1] and 302[7], which do not include a description of the configuration or the effect, are included in blocks 304[1] and 304[6], respectively, and are classified as class 343. Blocks 302[2] and 302[4], which include description 201[A], are both included in block 304[2] and are classified as class 340. Blocks 302[3] and 302[3], which include description 201[B], are both included in block 304[3] and are classified as class 341. Blocks 302[5] and 302[C], and 302[8], which include description 201[C], are both included in block 304[4] and are classified as class 340. Blocks 302[6] and 302[D], which include description 202[D], are included in block 304[5] and are classified as class 342.

[0201] In the following description, the information processing method of this embodiment deals with processing that is executed when the block 304 is classified into class 340 or class 341.

[0202] [Step S26] In step S26, the processing unit 130 extracts the description 205 corresponding to the description 201 from the database 350 for the blocks 304 classified into class 340 or class 341. For example, as shown in FIG. 10A , the description 205 is extracted from the database 350 based on the description 201. The description 205 includes a description of the effect corresponding to the description 201, and may be data registered in the database 350. Note that the type of the database 350 is not limited. For example, a relational database (RDB), an object-oriented database (OODB), a Not Only Structured Query Language (NoSQL) database, or the like may be used for the database 350. In the information processing method of this embodiment, it is assumed that a RDB constructed within the organization is used, and records can be searched for from a pre-registered table using SQL (Structured Query Language). Specifically, description 205 can be extracted by executing a query (SQL statement) including description 201 as a search condition on database 350, in which a table including description 201 and description 205 as items is registered. Furthermore, database 350 is preferably located outside information processing device 10. Description 205 corresponds to the description of the second effect described above.

[0203] [Step S27] In step S27, the processing unit 130 creates a prompt 401 for the block 304 classified into class 340. The prompt 401 is created when the contents of the description 202 and description 205 included in the block 304 do not match, and includes the description 202 and the description 205, and has a command to generate a message 207. In other words, the processing unit 130 creates the prompt 401 when the description 202 included in the document data differs from the description 205 registered in the database. The prompt 401 corresponds to the fourth prompt in <Configuration Example 1 of Information Processing System>.

[0204] [Step S28] In step S28, the processing unit 130 sends the prompt 401 to the language model to generate the message 207. For example, as shown in FIG. 10B , the processing unit 130 sends the prompt 401 to the language model 250 and obtains the generated message 207. The message 207 includes the difference between the content of the description 202 and the description 205. Here, the message 207 may be, for example, text data. Note that the data format of the message 207 is not limited. For example, in addition to text data, it may be audio data, image data, or the like.

[0205] Furthermore, the processing unit 130 can output a message 207 from the output unit 140. Fig. 14B shows an example in which the output message 207 is displayed on the display unit of the information terminal 20. Specifically, Fig. 14B shows an example in which, in addition to the block 304 classified into class 340 shown in Fig. 14A, descriptions 201, 202, 205, message 207, check box 331, and button 355 are displayed. Check box 331 and button 355 will be described later in step S29. The user receives the message and uses description 205 to determine whether or not to modify the document data.

[0206] [Step S29] In step S29, if a correction command is accepted, the processing unit 130 creates a prompt 403. Here, accepting the correction command may refer to, for example, a state in which the accepting unit 110 of the information processing device 10 receives the correction command input by the user using the information terminal 20. The correction command can be executed on the block 304 classified into class 340, and includes, for example, an instruction to correct the description 202 using the description 205. The prompt 403 includes the description 202 and the description 205, and has an instruction to correct the description 202 using the description 205. The prompt 403 corresponds to the fifth prompt in <Configuration Example 1 of Information Processing System>.

[0207] The user can also select a record for which the above-described modification command is to be executed, for example, using a check box 331 shown in FIG. 14B . Alternatively, the user can select a record of a block for which the user wants to execute a process by, for example, clicking with a mouse, pressing the Enter key on a keyboard, or touching a touch panel. A check mark is preferably displayed in the check box 331 of the selected record, indicating that the record has been selected. Note that the method for selecting a record is not limited to using a check box. For example, a radio button or a method such as changing the background color or text color of the selected record may also be used. In the information processing method of this embodiment, as shown in FIG. 14B , a user operates the mouse pointer 327 and clicks on a record containing block 304[2], thereby entering a check mark in the check box 331 of the selected record. Furthermore, an example is shown in which a check mark is not entered in the check box 331 of the record containing block 304[4].

[0208] Furthermore, the user can execute the above-described correction command for the block 304 included in the record for which a check mark has been entered in the check box 331 by, for example, clicking the button 355 shown in FIG. 14B with the mouse pointer 327 over it. The method for executing the correction command is not limited to clicking the button 355 with the mouse pointer 327 over it. For example, input may be performed by pressing a predetermined key, such as the Enter key on a keyboard, with the button 355 focused. Alternatively, the button 355 may be pressed using, for example, touch input on a touch panel. In the information processing method of this embodiment, pressing the button 355 executes the correction command for the block 304 for which a check mark has been entered in the check box 331, as shown in FIG. 14B . That is, the correction command is executed for block 304[2], but not for block 304[4].

[0209] [Step S30] In step S30, the processing unit 130 acquires the proposed revision 308 by sending the prompt 403 to the language model. For example, as shown in FIG. 10C , the proposed revision 308 is acquired by sending the prompt 403 to the language model 260. The proposed revision 308 may be a description obtained by correcting the description 202 included in the block 304 using the description 205. The proposed revision 308 may also be a description of an effect corresponding to the description 201. The proposed revision 308 may not include the first effect but may include the second effect by changing (replacing) the content of the description 202 with the content of the description 205. Alternatively, the proposed revision 308 may include both the first effect and the second effect by adding the content of the description 205 to the content of the description 202. Here, the user may be allowed to select whether to change or add the effect. Furthermore, proposed revision 308 is a proposal to modify the format of the content of description 205 extracted from database 350, for example, so that it conforms to the format of block 304. Note that block 304 is at least one or more blocks 302 classified into class 340. For example, if the document data is a specification belonging to a patent application, proposed revision 308 can add symbols and the like included in block 304 to description 205 to improve the format of the description content. Proposed revision 308 corresponds to the first proposed revision described above.

[0210] [Step S31] In step S31, the processing unit 130 creates a prompt 405 for the block 304 classified into class 341. As described above, class 341 is a class having a block 304 that includes description 201 but does not include description 202. The prompt 405 includes the block 304 classified into class 341 and the description 205, and has a command to modify the description 205. The prompt 405 corresponds to the sixth prompt in <Configuration Example 1 of Information Processing System>.

[0211] [Step S32] In step S32, the processing unit 130 obtains the proposed revision 309 by sending the prompt 405 to the language model. For example, as shown in FIG. 10D , the proposed revision 309 is obtained by sending the prompt 405 to the language model 270. The proposed revision 309 can be a description obtained by correcting the description 205. The proposed revision 309 can be generated, for example, to adapt the format of the content of the description 205 extracted from the database 350 to the format of at least one or more blocks 302 classified into class 341. Here, the at least one or more blocks 302 classified into class 341 are equivalent to block 304. Furthermore, the proposed revision 309 can be used to create a description 208 corresponding to the description 201. Here, the description 208 can be a description of the effect corresponding to the description 201. For example, if the document data is a specification belonging to a patent application, the proposed revision 309 can be generated by adding symbols and the like included in block 304 to the description 205 to improve the format of the description. The statement 208 corresponds to the statement of the third effect described above.

[0212] [Step S33] In step S33, the processing unit 130 updates the document data for the block 304 classified into class 340 for which the above-mentioned correction command was received, based on the proposed revision 308. Also, for the block 304 classified into class 341, the processing unit 130 updates the document data based on the description 208. Fig. 15 shows an example in which a description of the effect to be applied after updating the document data for the block 304 classified into any of classes 340 to 343 shown in Fig. 14A is displayed on the display unit of the information terminal 20. Specifically, the example shows a table displaying the "class," block 304, configuration description 201, and "effect description." Buttons 360 and 361 are also displayed outside the table.

[0213] In addition, in FIG. 15 , updated effect descriptions are indicated by dashed lines. Specifically, the effect description of block 304[2], classified as class 340, has been updated to revision proposal 308[A], and the effect description of block 304[3], classified as class 341, has been updated to description 208[B]. Block 304[4], which is classified as class 340 and to which the above-mentioned revision command was not executed in step S29, shows that its effect description will not be updated. In addition, in FIG. 15 , updated effect descriptions are preferably highlighted so that the update is visually noticeable. Specifically, examples of such highlighting include changing the background color of the updated effect description, changing the text color, increasing the text size, changing the font, making the text bold, or underlining the text. Note that the method of highlighting the updated effect description is not limited to the above-mentioned method.

[0214] The processing unit 130 may update the document data by inputting a button 360 shown in FIG. 15 . Specifically, for example, the user can update the document data by clicking the button 360 with the mouse pointer 327 positioned thereon. Furthermore, the processing unit 130 can cancel the document data update and redo the document 301 from step S29 by inputting a button 361 shown in FIG. 15 . The method of button input is not limited to clicking the button with the mouse pointer positioned thereon. For example, input may be performed by pressing a predetermined key, such as the Enter key on a keyboard, with the button focused. Alternatively, the button may be pressed using touch input on a touch panel, for example. Specifically, the processing unit 130 updates the document 301 included in the document data.

[0215] [Step S34] In step S34, the output unit 140 outputs the updated document data. The updated document data is the document data of the updated document 301.

[0216] As described above, a document can be corrected using the database and the language model. Furthermore, the synergistic effect of the database and the language model can be utilized to optimize the document correction work. Note that the language model 250, the language model 260, and the language model 270 may be the same model or different models.

[0217] <Configuration Example 2 of Information Processing System> Fig. 16 shows another example of the information processing system of this embodiment. The information processing system of this embodiment has an information processing device 11, an information processing device 15, an information terminal 20, and an information processing device 40. In the information processing system shown in Fig. 16, the information processing device 11 is connected to the information processing device 40 via a network 30. The information processing device 11 is also connected to the information processing device 15 and multiple information terminals 20 via a network 31. In Fig. 16, information terminals 20a and 20b are shown as examples of the information terminals 20.

[0218] 16 is mainly used to relay transmission and reception of data between the information terminal 20 and the information processing device 40. Then, in the information processing device 15, data DA2 is created using the data DA1.

[0219] First, the user inputs desired data DA1 into the information processing device 11 using the information terminal 20. The data DA1 is transmitted from the information terminal 20 to the information processing device 11 via the network 31.

[0220] Next, the information processing device 11 transmits the data DA1 to the information processing device 15 via the network 31.

[0221] Next, the information processing device 15 creates data DA2 using the data DA1. The information processing device 15 is configured to execute the various processes performed by the information processing device 10 described above.

[0222] Next, the information processing device 15 transmits the data DA2 to the information processing device 11 via the network 31.

[0223] Next, the information processing device 11 transmits the data DA2 to the information processing device 40 via the network 30.

[0224] Next, the data DB1 is transmitted from the information processing device 40 to the information processing device 11 via the network 30. The data DB1 is text data equivalent to a response sentence corresponding to the data DA2 input to the information processing device 40.

[0225] Next, the information processing device 11 transmits the data DB2 to the information terminal 20 via the network 31. The data DB2 is data based on the data DB1 input to the information processing device 11. As a result, the user can obtain the data DB2, which is the data DA1 updated based on the data DB1.

[0226] The data DB2 can be created by the information processing device 11 or the information processing device 15. For example, the information processing device 11 may input the data DB1 input from the information processing device 40 to the information processing device 15. Then, the information processing device 15 may create the data DB2 based on the data DB1.

[0227] The information processing system shown in FIG. 16 is suitable for a case where a user who uses information terminal 20 and a service provider belong to the same organization such as a company, similar to the information processing system shown in FIG.

[0228] For example, it is preferable that data be transmitted and received between the information terminal 20 and the information processing device 11 using a network 31 established within an organization such as a company. It is also preferable that data be transmitted and received between the information processing device 15 and the information processing device 11 using a network 31 established within an organization such as a company. It is also preferable that data be transmitted and received between the information processing device 11 and the information processing device 40 using the Internet. This allows for more secure use of applications, tools, services, etc. provided outside the organization than when the information terminal 20 is directly connected to the information processing device 40 via the Internet. However, connecting the information processing device 15 to the Internet may raise the risk of external cyberattacks, etc. The information processing system shown in FIG. 16 is preferable from a security perspective because it does not require the information processing device 15 to be directly connected to the information processing device 40 via the Internet.

[0229] Fig. 17 is a block diagram of the information processing system shown in Fig. 16. In Fig. 17, an example of the configuration of the information processing device 11 and the information processing device 15 will be mainly described.

[0230] The information processing device 11 includes a receiving unit 110 , a storage unit 120 , a processing unit 130 , an output unit 140 , and a transmission path 150 .

[0231] For the reception unit 110, storage unit 120, output unit 140, and transmission path 150 of the information processing device 11, the descriptions of the information processing device 10 can be referred to. The following mainly describes the differences from the information processing device 10.

[0232] The information processing device 15 includes a receiving unit 115 , a storage unit 125 , a processing unit 135 , an output unit 145 , and a transmission path 155 .

[0233] The receiving unit 110 receives data from the output unit 145 via the network 31 .

[0234] The receiving unit 115 receives data from the output unit 140 via the network 31 .

[0235] The information supplied to the reception unit 115 is supplied to one or both of the storage unit 125 and the processing unit 135 via the transmission path 155 .

[0236] The storage unit 125 has a function of storing a program executed by the processing unit 135. The storage unit 125 may also have a function of storing data created by the processing unit 135 (e.g., calculation results, analysis results, inference results), data input to the reception unit 115, etc. The storage unit 125 may have various configurations applicable to the storage unit 120.

[0237] The processing unit 135 has a function of performing processes such as calculation, analysis, and inference using data supplied from one or both of the reception unit 115 and the storage unit 125. The processing unit 135 can supply the created data (e.g., calculation results, analysis results, and inference results) to one or both of the storage unit 125 and the output unit 145. The processing unit 135 can use various configurations applicable to the processing unit 130.

[0238] The processing unit 135 has a function of acquiring data from the storage unit 125 .

[0239] The processing unit 135 extracts blocks contained in the target sentence and creates an instruction sentence, etc., using the data received by the receiving unit 115. The processing unit 135 also creates a prompt based on the target sentence and the instruction sentence.

[0240] The output unit 140 outputs the data to the reception unit 115 via the network 31 .

[0241] The output unit 145 outputs information based on the processing result of the processing unit 135. The output unit 145 can supply at least one of the calculation result, analysis result, and inference result of the processing unit 135 to an external device of the information processing device 15.

[0242] The output unit 145 outputs data to the reception unit 110 of the information processing device 10 via the network 31 .

[0243] The transmission path 155 has a function of transmitting data. Data can be transmitted and received between the reception unit 115, the storage unit 125, the processing unit 135, and the output unit 145 via the transmission path 155.

[0244] The processing section 130 and the processing section 135 can each include one or both of a transistor having a metal oxide in a channel formation region (OS transistor) and a transistor having silicon in a channel formation region (Si transistor).

[0245] <Configuration Example 3 of Information Processing System> Fig. 18 shows an example of an information processing system according to this embodiment. In the information processing system shown in Fig. 18, an information processing device 10 is connected to an information processing device 40 and a plurality of information terminals 20 via a network 30. In Fig. 18, the above-mentioned information terminals 20a to 20d are shown as examples of the information terminals 20.

[0246] The flow of data in the information processing system shown in FIG. 18 can be understood by referring to the description of FIG. 2 by replacing the network 31 with the network 30.

[0247] A user of the information processing system can access the information processing device 10 from an information terminal 20. The user can then receive a service using the information processing method according to one aspect of the present invention.

[0248] The information processing system shown in FIG. 18 is suitable for a case where a user who uses the information terminal 20 and a service provider belong to different organizations such as companies.

[0249] The information processing device 10 is connected to an information terminal 20 used by a user who receives a service via a network 30 (typically, the Internet). A service provider can provide the service using the information processing device 10. Data is also transmitted and received between the information processing device 10 and the information processing device 40 using the network 30 (typically, the Internet). This allows applications, tools, services, etc. using the information processing device 40 to be used more safely than when the information terminal 20 is directly connected to the information processing device 40 via the Internet.

[0250] <Configuration Example 4 of Information Processing System> Fig. 19 shows an example of an information processing system according to this embodiment. In the information processing system shown in Fig. 19, an information processing device 11 is connected to an information processing device 40 and a plurality of information terminals 20 via a network 30. In Fig. 19, the above-mentioned information terminals 20a to 20d are shown as examples of the information terminals 20. Furthermore, the information processing device 11 is connected to an information processing device 15 via a network 31.

[0251] A user of the information processing system can access the information processing device 11 from an information terminal 20. The user can then receive services using the information processing method according to one aspect of the present invention.

[0252] The information processing system shown in FIG. 19, like the information processing system shown in FIG. 18, is suitable for a case where a user who uses information terminal 20 and a service provider belong to different organizations such as companies.

[0253] The information processing device 11 is connected to an information terminal 20 used by a user receiving a service via the Internet. Preferably, data is transmitted and received between the information processing device 11 and the information processing device 15 using a network 31 established within an organization such as a company that provides the service. The service provider can provide the service using the information processing device 11 and the information processing device 15. Data is also transmitted and received between the information processing device 11 and the information processing device 40 using the Internet. This allows applications, tools, services, etc. using the information processing device 40 to be used more safely than when the information terminal 20 is directly connected to the information processing device 40 via the Internet. Furthermore, the information processing device 15 does not need to be directly connected to the information processing device 40 via the Internet, which is preferable from the perspective of security.

[0254] 1, data transmission and reception between the information processing device 10 and the information processing device 40 can also be performed using a network 31 established within an organization such as a company. In this case, either the network 30 or the network 31 can be applied to transmission and reception of data between the information terminal 20 used by a user and the information processing device 10.

[0255] According to one aspect of the present invention, it is possible to provide an information processing system or an information processing method that utilizes a language model to support document correction. According to one aspect of the present invention, it is possible to provide a highly convenient information processing system or an information processing method. According to one aspect of the present invention, it is possible to provide a novel information processing system or an information processing method.

[0256] A plurality of configuration examples shown in this embodiment can be combined as appropriate.

[0257] 10: Information processing device, 11: Information processing device, 15: Information processing device, 20: Information terminal, 20a: Information terminal, 20b: Information terminal, 20c: Information terminal, 20d: Information terminal, 21: Housing, 30: Network, 31: Network, 40: Information processing device, 110: Reception unit, 115: Reception unit, 120: Storage unit, 125: Storage unit, 130: Processing unit, 135: Processing unit, 140: Output unit, 145: Output unit, 150: Transmission path, 155: Transmission path, 201[A]: Description, 201[B]: Description, 201[C]: Description, 201: Description, 202[A]: Description, 202[C]: Description ,202[D]: description, 202: description, 203: description, 205: description, 207: message, 208[B]: description, 208: description, 210: language model, 220: language model, 230: language model, 250: language model, 260: language model, 270: language model, 301: document, 302[1]: block, 302[2]: block, 302[3]: block, 302[4]: block, 302[5]: block, 302[6]: block, 302[7]: block, 302[8]: block, 302[n-1]: block, 302[n]: block Block, 302: Block, 303: Prompt, 304[1]: Block, 304[2]: Block, 304[3]: Block, 304[4]: Block, 304[5]: Block, 304[6]: Block, 304[m-1]: Block, 304[m]: Block, 304: Block, 305: Prompt, 306[1]: Block, 306[2]: Block, 306[3]: Block, 306[k]: Block, 306: Block, 307: Prompt, 308[A]: Correction, 308: Correction, 309: Correction, 310: Response, 311: Response Answer, 313: response sentence, 321: paragraph, 322: judgment result, 323: judgment result, 324: block, 325: serial number, 326: block, 327: mouse pointer, 329: judgment result, 330: check box, 331: check box, 333: button, 335: button, 336: button, 337: button, 339: button, 340: class, 341: class, 342: class, 343: class, 350: database, 355: button, 360: button, 361: button, 401: prompt, 403: prompt, 405: prompt

Claims

A receiving unit, a processing unit, and an output unit, the receiving unit has a function of receiving document data, the output unit has a function of updating the document data and then outputting the updated document data; The processing unit a first process of dividing a document included in the document data into a plurality of first blocks; a second process for creating a first prompt including a first object sentence including at least one of the plurality of first blocks, and having a first instruction sentence including an instruction to perform a first determination on each of the first blocks included in the first object sentence; a third process of receiving the first prompt from a language model via a network and acquiring a first response sentence including a first determination result based on the first determination; a fourth process of acquiring one or more second blocks including at least one of the first blocks based on the first determination result; a fifth process of creating a second prompt including a second target sentence including at least one of the second blocks, and having a second instruction sentence including an instruction to present at least one revision suggestion for the second block included in the second target sentence; and a sixth process of receiving the second prompt from the language model via the network to obtain a second response sentence including the suggested revision; a seventh process of updating the document data based on the revision proposal; An information processing system configured to execute the 　 In claim 1, An information processing system, wherein the document data is a specification belonging to a patent application. 　 In claim 1, In the first determination, it is determined whether the first block describes a configuration and an effect, When the second block includes a plurality of the first blocks, the plurality of first blocks included in the second block have the same configuration as each other; An information processing system, wherein the proposed addition is a proposal for an effect corresponding to the configuration described in the second block. 　 In claim 3, The processing unit In the fourth process, the information processing system acquires the second block in which no effect is described. 　 In any one of claims 1 to 4, The processing unit an eighth process for generating a third prompt including at least one of the revision suggestions and having a third directive including an instruction to perform a second determination on each of the revision suggestions; and a ninth process of obtaining a third response sentence including a second determination result by sending the third prompt to the language model via the network, the ninth process being performed before the seventh process. 　 In claim 5, In the second determination, the information processing system determines the consistency of the revision proposal with the description in the document. 　 a first process for receiving document data; a second process of dividing a document included in the document data into a plurality of first blocks; a third process for creating a first prompt including a first object sentence including at least one of the plurality of first blocks, and having a first instruction sentence including an instruction to perform a first determination on each of the first blocks included in the first object sentence; a fourth process of receiving the first prompt from a language model via a network and acquiring a first response sentence including a first determination result based on the first determination; a fifth process of acquiring one or more second blocks including at least one of the first blocks based on the first determination result; a sixth process of creating a second prompt including a second target sentence including at least one of the second blocks, and having a second instruction sentence including an instruction to present at least one revision suggestion for the second block included in the second target sentence; and a seventh process of receiving the second prompt from the language model via the network to obtain a second response sentence including the suggested revision; an eighth process of updating the document data based on the revision proposal; and a ninth process of outputting the document data. 　 In claim 7, An information processing method, wherein the document data is a specification belonging to a patent application. In claim 7, In the first determination, it is determined whether the first block describes a configuration and an effect, When the second block includes a plurality of the first blocks, the plurality of first blocks included in the second block have the same configuration as each other; An information processing method, wherein the proposed addition is a proposal for an effect corresponding to the configuration described in the second block. 　 In claim 9, An information processing method, wherein in the fifth process, the second block in which no effect is described is acquired. 　 In any one of claims 7 to 10, a tenth process for generating a third prompt including at least one of the revision suggestions and having a third instruction statement including an instruction to perform a second determination on each of the revision suggestions; an eleventh process of obtaining a third response sentence including a second determination result by sending the third prompt to the language model via the network, said eleventh process being performed before said eighth process. 　 In claim 11, In the second determination, consistency of the revision proposal with a description in the document is determined. 　 A receiving unit, a processing unit, and an output unit, the receiving unit has a function of receiving document data, the processing unit is configured to execute first to fourth processes; the first processing divides a document included in the document data into a plurality of blocks, and then transmits the blocks to a language model to classify each of the blocks into one of a plurality of classes; the plurality of classes includes a first class; the first class has the block including a first description and a second description; The second process extracts a third description corresponding to the first description from a database; the third process creates a first prompt for the block classified into the first class and sends the first prompt to the language model; the first prompt includes the second description and the third description, and has instructions for generating a message if the second description and the third description do not match; the message includes a difference between the content of the second description and the content of the third description; The fourth process outputs the message from the output unit. 　 In claim 13, the reception unit has a function of receiving a modification command, the processing unit is configured to perform a fifth process and a sixth process after the fourth process when the processing unit receives the modification command; The fifth step creates a second prompt and sends it to the language model to obtain a revision suggestion; the second prompt includes the second description and the third description and has instructions to modify the second description with the third description; the sixth process updates the document data based on the proposed revision; The output unit has a function of outputting the updated document data. 　 In claim 13, the plurality of classes includes a second class; the second class has the blocks that include the first description and do not include the second description; the processing unit is configured to perform seventh to ninth processes after the second process, the seventh process creates a third prompt for the block classified into the second class and sends the third prompt to the language model to obtain a correction suggestion; the third prompt includes the block classified into the second class and the third description, and has an instruction to modify the third description; the eighth process uses the proposed revision to create a fourth description corresponding to the first description; The ninth process updates the document data based on the fourth process; The output unit has a function of outputting the updated document data. In claim 13, An information processing system, wherein the document data is a specification belonging to a patent application. 　 In claim 15, An information processing system, wherein the first description represents a description of a configuration included in the block, the second description and the fourth description represent descriptions of effects corresponding to the first description, and the third description represents a description of effects corresponding to the first description registered in the database. 　 In claim 14 or claim 15, An information processing system in which the revision proposal is generated to adapt the appearance of the content of the third description extracted from the database to the appearance of at least one or more of the blocks classified into the class. 　 Execute the first to fifth processes; The first process includes accepting document data; the second processing divides a document included in the document data into a plurality of blocks, transmits the blocks to a language model, and classifies each of the blocks into one of a plurality of classes; the plurality of classes includes a first class; the first class has the block including a first description and a second description; The third process extracts a third description corresponding to the first description from a database; the fourth process creates a first prompt for the block classified into the first class and sends the first prompt to the language model; the first prompt includes the second description and the third description, and has instructions for generating a message if the second description and the third description do not match; the message includes a difference between the content of the second description and the content of the third description; The information processing method, wherein the fifth process outputs the message. 　 In claim 19, When a correction command is received, the sixth and seventh processes are performed after the fifth process; The sixth step creates a second prompt and sends it to the language model to obtain a revision suggestion; the second prompt includes the second description and the third description and has instructions to modify the second description with the third description; the seventh process updates the document data based on the proposed revision; and outputting the updated document data. 　 In claim 19, the plurality of classes includes a second class; the second class has the blocks that include the first description and do not include the second description; performing eighth to tenth processes after the second process; the eighth process generates a third prompt for the block classified into the second class and sends the third prompt to the language model to obtain a correction suggestion; the third prompt includes the block classified into the second class and the third description, and has an instruction to modify the third description; the ninth process uses the proposed revision to create a fourth description corresponding to the first description; The tenth process updates the document data based on the fourth process; An information processing system that outputs the updated document data. 　 In claim 19, An information processing method, wherein the document data is a specification belonging to a patent application. 　 In claim 21, An information processing method, wherein the first description represents a description of a configuration included in the block, the second description and the fourth description represent descriptions of effects corresponding to the first description, and the third description represents a description of effects corresponding to the first description registered in the database. 　 In claim 20 or claim 21, An information processing method in which the revision proposal is generated to adapt the appearance of the content of the third description extracted from the database to the appearance of at least one or more of the blocks classified into the class.

Images