Information processing device and information processing method

Abstract

Provided is an information processing device that is excellent in terms of convenience and usefulness. After a first document and a second document are received, a language model is made to generate a summary sentence of the second document. The language model is made to present a difference in the first document with respect to the summary. If the difference is not valid, the language model is made to present the difference again on the basis of a first instruction document created by a user. If the difference is valid, the language model is made to confirm that no part of the difference is described in the second document. If at least a part of the difference is described in the second document, the language model is made to present the difference again on the basis of a first instruction document created by the user. If no part of the difference is described in the second document, the language model is made to generate a third document on the basis of the second document and the difference. If the third document needs to be revised, the language model is made to revise the third document on the basis of a second instruction document created by the user.

Description

Information processing apparatus and information processing method

[0001] One aspect of the present invention relates to an information processing device. Another aspect of the present invention relates to an information processing method using an information processing device. Furthermore, one aspect of the present invention relates to an information processing system including an information processing device.

[0002] Furthermore, one aspect of the present invention is not limited to the above-mentioned technical field. The technical field of one aspect of the invention disclosed herein relates to a product, a method, or a method of manufacture. Alternatively, one aspect of the present invention relates to a process, a machine, a manufacture, or a composition of matter. More specifically, examples of the technical fields of one aspect of the present invention disclosed herein include information processing devices, semiconductor devices, memory devices, methods for driving them, or methods for manufacturing them.

[0003] Documents related to patent applications, such as patent specifications, must be written in a way that conveys technical ideas while meeting the required description requirements. This requires advanced knowledge and skills regarding intellectual property, making it difficult for those with little experience. Patent Document 1 discloses a method for automatically completing the description of a patent specification.

[0004] In recent years, there has been a surge in the development of language models using artificial neural networks (ANNs, also simply referred to as neural networks), with large-scale language models (LLMs) attracting particular attention. Large-scale language models are natural language processing models trained using large amounts of data. Large-scale language models can be used to realize, for example, dialogue models that respond to user instructions. Non-patent document 1 discloses GPT-4 (registered trademark) (Generative Pre-trained Transformer 4) as a large-scale language model, and also discloses ChatGPT as a dialogue model. In addition to the above, other large-scale language models include LaMDA (Language Model for Dialogue Applications), PaLM (Pathways Language Model), Llama2, and Llama3.

[0005] Japanese Patent Publication No. 2022-24112

[0006] 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>

[0007] For example, a patent specification must meet the description requirements while differentiating it from the invention disclosed in prior art documents. This requires a thorough understanding of the invention in question and the invention disclosed in prior art documents, as well as a deep knowledge of patent law. Furthermore, even slight differences in the description of a patent specification can significantly affect the scope of patent rights. Therefore, utmost care must be taken in writing the patent specification. As a result, drafting a patent specification requires a great deal of time and effort, and it is difficult for someone with little experience to do it quickly. For example, it may be difficult for the inventor themselves to write a patent specification in between other tasks.

[0008] Therefore, one aspect of the present invention aims to provide an information processing device, an information processing method, and an information processing system that assist in the creation of documents relating to intellectual property. Alternatively, one aspect of the present invention aims to provide an information processing device, an information processing method, and an information processing system that can create documents relating to intellectual property in a short amount of time. Alternatively, one aspect of the present invention aims to provide an information processing device, an information processing method, and an information processing system that enable users to create documents relating to intellectual property with minimal effort. Alternatively, one aspect of the present invention aims to provide an information processing device, an information processing method, and an information processing system that can create documents relating to intellectual property with a high degree of completion.

[0009] Alternatively, one aspect of the present invention aims to provide an information processing device, an information processing method, and an information processing system that are excellent in convenience and usefulness. Alternatively, one aspect of the present invention aims to provide a novel information processing device, an information processing method, and an information processing system.

[0010] Furthermore, the description of these problems does not preclude the existence of other problems. Moreover, one aspect of the present invention does not need to solve all of these problems. Other problems will naturally become apparent from the description in the specification, drawings, claims, etc., and it is possible to extract other problems from the description in the specification, drawings, claims, etc.

[0011] One aspect of the present invention comprises steps 1 to 12, in the first step, receiving a first document and a second document; in the second step, creating a first prompt for generating a summary of the second document and sending it to a language model; in the third step, creating a second prompt for presenting differences in the first document to the summary and sending it to the language model; in the fourth step, receiving a judgment on whether the differences are valid or not; if the differences are not valid, in the fifth step, receiving a first instruction document; in the sixth step, based on the first instruction document, creating a third prompt for presenting the differences in the first document again and sending it to the language model, and then performing the fourth step again; and if the differences are valid, in the seventh step, all of the differences are in the second document This information processing method involves creating a fourth prompt to confirm that the differences are not described in the second document and sending it to the language model; if at least some of the differences are described in the second document, performing the fifth step; if all of the differences are not described in the second document, in the eighth step, creating a fifth prompt to generate the second document and a third document based on the differences and sending it to the language model; in the ninth step, receiving a decision on whether the third document needs to be modified; if it needs to be modified, receiving the second instruction document in the tenth step; in the eleventh step, creating a sixth prompt to modify the third document based on the second instruction document and sending it to the language model, then performing the ninth step; and if it does not need to be modified, outputting the third document in the twelfth step.

[0012] Alternatively, in the above embodiment, steps 13 through 15 may be included, and if not all of the differences are described in the second document, then in step 13, before step 8, a seventh prompt may be created and sent to the language model to determine whether there is insufficient information to create the third document. If there is insufficient information, then in step 14, after receiving additional information, in step 15, the seventh prompt may be recreated including the additional information and sent to the language model. If there is no insufficient information, then step 8 may be performed.

[0013] Alternatively, one aspect of the present invention includes a receiving unit, an output unit, and a processing unit, wherein the receiving unit has the function of receiving a first document, a second document, a first instruction document, and a second instruction document; the output unit has the function of supplying a first prompt, a second prompt, a third prompt, a fourth prompt, a fifth prompt, and a sixth prompt to a language model; the output unit has the function of outputting a third document; the processing unit has the function of creating a first prompt for generating a summary of the second document, creating a second prompt for presenting differences in the first document compared to the summary; causing the user to determine whether the differences are valid; and, if the differences are not valid, providing the differences in the first document based on the first instruction document. This information processing device has the following functions: creating a third prompt to present the information again; creating a fourth prompt to confirm that not all of the differences are described in the second document if the differences are valid; creating a third prompt based on the first instruction document if at least some of the differences are described in the second document; creating a fifth prompt to generate the second document and the third document based on the differences if not all of the differences are described in the second document; allowing the user to determine whether the third document needs to be modified; and creating a sixth prompt to modify the third document based on the second instruction document if modifications are necessary.

[0014] Alternatively, in the above aspect, the reception unit has a function of receiving additional information, the output unit has a function of supplying a seventh prompt to the language model, and the processing unit creates a seventh prompt for determining whether there is insufficient information for creating a third document when not all differences are described in the second document, recreates the seventh prompt including the additional information when the information is insufficient, and creates a fifth prompt when the information is sufficient.

[0015] Alternatively, in the above aspect, the first instruction document may include at least one of an instruction to correct the first document and a comment regarding the differences, and the second instruction document may include at least one of an instruction to correct the third document and a comment regarding the third document.

[0016] Alternatively, in the above aspect, the first document and the second document may be documents indicating creation.

[0017] Alternatively, in the above aspect, the second document may be a patent document or a utility model document, and the third document may be a specification belonging to a patent application or a specification belonging to a utility model registration application.

[0018] According to one aspect of the present invention, it is possible to provide an information processing apparatus, an information processing method, and an information processing system for assisting in creating a document related to intellectual property. Alternatively, according to one aspect of the present invention, it is possible to provide an information processing apparatus, an information processing method, and an information processing system capable of creating a document related to intellectual property in a short time. Alternatively, according to one aspect of the present invention, it is possible to provide an information processing apparatus, an information processing method, and an information processing system that enable a user to create a document related to intellectual property with less effort. Alternatively, according to one aspect of the present invention, it is possible to provide an information processing apparatus, an information processing method, and an information processing system capable of creating a document related to intellectual property with a high degree of completion.

[0019] Alternatively, according to one aspect of the present invention, it is possible to provide an information processing apparatus, an information processing method, and an information processing system excellent in convenience and usefulness. Alternatively, according to one aspect of the present invention, it is possible to provide a novel information processing apparatus, an information processing method, and an information processing system.

[0020] Furthermore, the description of these effects does not preclude the existence of other effects. Moreover, one aspect of the present invention does not necessarily have to possess all of these effects. Other effects will become clear from the description in the specification, drawings, claims, etc., and it is possible to extract other effects from the description in the specification, drawings, claims, etc.

[0021] Figure 1 is a schematic diagram showing an example of an information processing system. Figure 2 is a block diagram showing an example of an information processing system. Figure 3 is a flowchart showing an example of an information processing method. Figure 4 is a flowchart showing an example of an information processing method. Figure 5 is a schematic diagram showing an example of an information processing method. Figures 6A and 6B are schematic diagrams showing an example of an information processing method. Figures 7A and 7B are schematic diagrams showing an example of an information processing method. Figures 8A and 8B are schematic diagrams showing an example of an information processing method. Figure 9 is a flowchart showing an example of an information processing method. Figures 10A and 10B are schematic diagrams showing an example of an information processing method. Figure 11 is a flowchart showing an example of an information processing method. Figure 12 is a schematic diagram showing an example of an information processing method.

[0022] Embodiments will be described in detail with reference to the drawings. However, it will be readily apparent to those skilled in the art that the present invention is not limited to the following description, and that its form and details can be modified in various ways without departing from the spirit and scope of the present invention. Accordingly, the present invention is not to be interpreted as being limited to the contents of the embodiments shown below. In the configuration of the invention described below, the same reference numerals are used in common across different drawings for the same parts or parts having similar functions, and repeated descriptions are omitted.

[0023] In the drawings attached to this specification, the components are classified by function and shown as independent blocks in block diagrams. However, in reality, it is difficult to completely separate the components by function, and one component may be involved in multiple functions.

[0024] In this specification, the terms "first" and "second" may be used for convenience to understand the technical content or to identify each component. Therefore, the terms "first" and "second" do not limit the number of components. Nor do the terms "first" and "second" limit the order of the components. Furthermore, the terms "first" and "second" or the identification codes used in this specification may not correspond to the terms or identification codes in the claims of this patent.

[0025] (Embodiment) This embodiment describes an information processing system according to one aspect of the present invention. This embodiment also describes an information processing device included in the information processing system and an information processing method using the information processing system.

[0026] One aspect of the present invention relates to an information processing system that generates a third document using a language model based on a first document and a second document. The first document and the second document are documents that indicate a creation, for example, a document that indicates an invention or a utility model. Specifically, the first document may be a document that indicates a creation for which an application is filed. The second document may be a prior art document, for example, a patent document or a utility model document. The third document may be a patent application document or a utility model application document, for example, a specification belonging to a patent application or a specification belonging to a utility model registration application. Here, the specification belonging to a patent application and the specification belonging to a utility model registration application are collectively referred to simply as the specification.

[0027] Both inventions and utility models are creations of technical ideas that utilize the laws of nature. Therefore, the term "creation" includes both inventions and utility models. Inventions are protected under patent law, while utility models are protected under utility model law.

[0028] In one aspect of the present invention, an information processing method first generates a summary of a second document from a language model. The language model also presents the differences between the first document and the summary of the second document. Specifically, these differences can be features described in the first document but not in the summary of the second document, such as technical features.

[0029] The user of the information processing system determines whether the above-mentioned differences are valid. If the differences are not valid, the user of the information processing system creates a first instruction document. Based on the first instruction document, the language model presents again the differences in the first document compared to the summary of the second document. The first instruction document may include, for example, instructions to revise the first document and at least one of the above-mentioned differences. Here, the above-mentioned comments on the differences may be, for example, opinions on the above-mentioned differences. For example, if the user of the information processing system believes that there are differences in the first document compared to the second document other than the differences presented, a statement to that effect may be included in the first instruction document. Also, if the user of the information processing system believes that at least a part of the presented differences are described in the second document, a statement to that effect may be included in the first instruction document.

[0030] If the aforementioned differences are valid, the language model will verify that not all of those differences are described in the second document. The verification results will be presented to the user of the information processing system.

[0031] If at least some of the differences are described in the second document, the user of the information processing system creates the first instruction document, as in the case where the differences described above are not valid. If not all of the differences are described in the second document, the language model generates the second document and a third document based on those differences.

[0032] The user of the information processing system reviews the third document. For example, if the third document needs to be modified, the user of the information processing system creates a second instruction document. The language model modifies the third document based on the second instruction document. Here, the second instruction document may include comments regarding the contents of the third document. Such comments may be, for example, questions regarding the contents of the third document. In this case, the language model can generate answers to such comments. Note that the language model may generate only answers to comments and not modify the third document. Also, even if the second instruction document only contains comments and does not include modification instructions, the language model may modify the third document based on those comments. When the third document is completed and no further modifications are needed, the third document is output. For example, the third document is supplied to an information terminal owned by the user of the information processing system.

[0033] As described above, by using the information processing system according to one aspect of the present invention, a third document can be generated, taking into account the differences between the first document and the second document. For example, the specification relating to the creation shown in the first document can be written in a way that emphasizes technical features not disclosed in the prior art documents. As described above, the information processing system according to one aspect of the present invention can assist in the creation of documents related to intellectual property, such as the creation of specifications. Therefore, even a person with little experience in intellectual property work can create documents related to intellectual property, such as specifications, in a short time by using the information processing system according to one aspect of the present invention. Furthermore, users can create documents related to intellectual property, such as specifications, with less effort.

[0034] Furthermore, in one aspect of the information processing system of the present invention, when a user creates a first instruction document, the language model can present the differences between the first document and the second document multiple times. Specifically, the language model can present the aforementioned differences multiple times based on the content of the first instruction document. Moreover, in one aspect of the information processing system of the present invention, when a user creates a second instruction document, the language model can make one or more modifications to the third document. As a result, a user of one aspect of the information processing system of the present invention can create the third document in an interactive manner. This enables, for example, a person with little experience in intellectual property work to create a highly complete specification.

[0035] <Example of Information Processing System Configuration 1> Figure 1 is a schematic diagram showing an example of the configuration of an information processing system according to one aspect of the present invention. The information processing system according to one aspect of the present invention comprises an information processing device 10 and an information processing device 40. The information processing device 10 and the information processing device 40 are connected via a network 30 and can transmit and receive data.

[0036] The information processing device 40 has a function to perform processing using a language model. The language model has a function to generate a response sentence based on a prompt. A prompt can be described as an input sentence that causes the language model to perform a desired action. The prompt is supplied, for example, from the information processing device 10 to the information processing device 40. The response sentence generated by the language model is supplied, for example, from the information processing device 40 to the information processing device 10. The information processing device 10 may also have a function to perform processing using a language model.

[0037] Furthermore, in one embodiment of the present invention, the information processing system may be configured so that a user can input documents, etc., by directly operating the information processing device 10, or, as shown in Figure 1, it may be configured so that a user can input documents, etc., using an information terminal 20 connected to the information processing device 10 via a network 30.

[0038] The following describes an example configuration of the information processing device 10, the information processing device 40, the information terminal 20, and the network 30.

[0039] 《Example Configuration of Information Processing Device 10》 Figure 2 is a block diagram showing an example configuration of the information processing device 10. 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 line 150. Figure 2 also shows an information terminal 20 and an information processing device 40.

[0040] [Reception Unit 110] The reception unit 110 has the function of receiving data from outside the information processing device 10. The reception unit 110 has the function of receiving data from the information terminal 20, for example, a document. The reception unit 110 has the function of receiving data from the information processing device 40, for example, a response message.

[0041] The receiving unit 110 has the function of supplying the received data to one or both of the storage unit 120 and the processing unit 130 via the transmission line 150. For example, a device such as a wired communication port, wireless communication port, or optical communication port can be used as the receiving unit 110.

[0042] [Storage Unit 120] The storage unit 120 has the function of storing the program executed by the processing unit 130. The storage unit 120 may also have the function of storing data created by the processing unit 130 (for example, calculation results, analysis results, and inference results), and data received by the receiving unit 110.

[0043] The storage unit 120 may have a database. The information processing device 10 may also have a database separate from the storage unit 120. The information processing device 10 may have a function to retrieve data from a database located outside the storage unit 120, outside the information processing device 10, or outside the information processing system. The information processing device 10 may also have a function to retrieve data from both its own database and an external database.

[0044] Either or both of the storage and / or file server can be used in the storage unit 120. Furthermore, a database recording the paths of files stored on the file server can also be used in the storage unit 120.

[0045] [Processing Unit 130] The processing unit 130 has the function of performing calculations, analyses, inferences, and other processing using data supplied from either or both of the receiving unit 110 and the storage unit 120. The processing unit 130 can supply the created data (for example, calculation results, analysis results, and inference results) to either or both of the storage unit 120 and the output unit 140. The processing unit 130 also has the function of creating prompts. The processing unit 130 may also have the function of performing processing using a language model.

[0046] The processing unit 130 has the function of acquiring data from the storage unit 120. The processing unit 130 may also have the function of recording or registering data in the storage unit 120.

[0047] [Output Unit 140] The output unit 140 has the function of outputting at least one of the calculation results, analysis results, and inference results from the processing unit 130 to the outside of the information processing device 10. For example, a wired communication port, a wireless communication port, or an optical communication port can be used as the output unit 140.

[0048] For example, the output unit 140 has the function of supplying data indicating prompts, etc., to the information processing device 40. The output unit 140 also has the function of supplying data indicating documents, etc., to the information terminal 20.

[0049] [Transmission Line 150] The transmission line 150 has the function of transmitting data. Data can be transmitted and received between the receiving unit 110, the storage unit 120, the processing unit 130, and the output unit 140 via the transmission line 150. As the transmission line 150, for example, a bus line on the motherboard, a wired communication cable, or an optical communication cable can be used.

[0050] <Example Configuration of Information Processing Device 40> The information processing device 40 can process received data and transmit the processing results. For example, it can perform calculations and other processing using data supplied from the information processing device 10. The information processing device 40 can also supply the processing results to the information processing device 10. This reduces the computational burden on the information processing device 10.

[0051] As described above, the information processing device 40 can perform processing using language models. For example, it can perform processing using language models such as BERT and T5. In addition, the information processing device 40 can perform processing using models that utilize language models (such as text generation models and dialogue models).

[0052] As described above, the language model generates a response sentence based on the prompt. For example, the prompt created by the processing unit 130 is supplied to the language model of the information processing device 40 via the output unit 140. The response sentence generated by the language model is supplied via the receiving unit 110 to, for example, one or both of the storage unit 120 and the output unit 140.

[0053] Furthermore, the information processing device 40 can perform processing using a general-purpose language processing model that can handle various natural language processing tasks.

[0054] The information processing device 40 is a large computer such as a server computer or a supercomputer. Furthermore, it is preferable that the information processing device 40 has the functionality of a parallel computer. By using the information processing device 40 as a parallel computer, for example, large-scale calculations necessary for the learning and inference of artificial intelligence (AI) can be performed.

[0055] Furthermore, the information processing device 40 is a computer with higher processing power compared to the information processing device 10. For example, if both the information processing device 10 and the information processing device 40 have the functionality of parallel computers, the information processing device 40 will have higher processing power than the information processing device 10 and will be able to perform large-scale calculations. Also, for example, if both the information processing device 10 and the information processing device 40 can perform processing using models that utilize language models, the information processing device 40 will be able to perform processing using larger-scale models compared to the information processing device 10.

[0056] Furthermore, service providers are not necessarily required to own the information processing device 40 themselves. For example, a service provider can utilize some of the services provided by other businesses using the information processing device 40.

[0057] <Example Configuration of Information Terminal 20> The information terminal 20 can receive data input by a user of an information processing system according to one aspect of the present invention. The information terminal 20 can also present data output by the information processing system according to one aspect of the present invention to the user by displaying it on the display unit of the information terminal 20. Alternatively, the information terminal 20 can present data output by the information processing system according to one aspect of the present invention to the user by printing it on the printing unit of the information terminal 20.

[0058] Furthermore, the information terminal 20 can supply data received from the user to the information processing device 10. The information terminal 20 can also present data supplied from the information processing device 10 to the user.

[0059] Furthermore, the information terminal 20 can supply data created based on data received from the user to the information processing device 10. The information terminal 20 can also present data created based on data supplied by the information processing device 10 to the user.

[0060] For example, dedicated application software, a web browser, etc., are installed on the information terminal 20. The user can access the information processing device 10 through either of these. As a result, the user can enjoy services using an information processing system according to one embodiment of the present invention, even if the information terminal 20 is, for example, a computer with lower processing power than the information processing device 10.

[0061] The information terminal 20 can also be referred to as a client computer or the like. In any case, the information terminal 20 is an information terminal device used by a user of an information processing system according to one embodiment of the present invention.

[0062] For example, a desktop computer 20a, a notebook computer 20b, a smartphone 20c, or a tablet computer 20d can be used as the information terminal 20. The tablet computer 20d can also be used as a notebook computer by connecting it to a casing 21 with a keyboard.

[0063] Network 30: Network 30 connects the information processing device 10 and the information processing device 40. Network 30 also connects multiple information terminals 20 to the information processing device 10. This enables the transmission and reception of input data and processed data between the two. It also allows for the distribution of the information processing load.

[0064] The following describes an information processing method using the information processing system shown in Figures 1 and 2. Specifically, the operation method of the information processing device 10 will be described.

[0065] <Information Processing Method 1> Figures 3 and 4 are flowcharts showing an example of an information processing method according to one aspect of the present invention, and more specifically, they are flowcharts showing an example of how the information processing device 10 operates.

[0066] An information processing method according to one embodiment of the present invention is "started," and in step S101 of Figure 3, the receiving unit 110 receives a first document and a second document. The first document can be a document showing the creation for which an application is to be filed, specifically an invention, a design, etc. The second document can be a prior art document, as described above, and can be, for example, a patent document or a utility model document. Examples of patent documents include published patent gazettes and patent publications. Examples of utility model documents include utility model gazettes. However, the second document is not limited to patent documents and utility model documents. The second document may be a design document, or a paper, book, magazine, etc. Furthermore, the second document is not limited to published documents, but may be unpublished documents.

[0067] The second document may consist of one or more documents. The second document may, for example, be at least a portion of documents stored in a database. The second document may, for example, be documents retrieved from the database based on the first document.

[0068] In this specification, "search" refers to finding documents that are highly relevant to the search query document from among multiple searchable documents. In the example above, the search query document is the first document.

[0069] When performing a search, the first document and the references may be converted into vector data, and the degree of similarity between the vector data may be determined. Vector data represents multidimensional numerical data composed of integers from 0 to 9, as opposed to text data consisting of strings of characters (natural language) such as sentences. Vector data can also be described as data in a format that can be processed using arithmetic. The conversion of text data to vector data can be performed using AI, and it is preferable to do so using a neural network, for example. A neural network can be implemented by a circuit (hardware) or a program (software). Specific methods for converting text data to vector data include Bag of Words, distributed representation, and embedding representation. Furthermore, cosine similarity can be used as one of the indicators to represent the degree of similarity between vector data.

[0070] In this specification, the term "neural network" refers to any model that mimics the neural network of living organisms, determines the strength of connections between neurons through learning, and possesses problem-solving capabilities. A neural network has an input layer, an intermediate layer (hidden layer), and an output layer.

[0071] In this specification and other documents, when discussing neural networks, the process of determining the connection strength (also called weight coefficient) between neurons from existing information is sometimes referred to as "learning."

[0072] In this specification and other documents, the process of constructing a neural network using connection strengths obtained through learning and deriving new conclusions from it may be referred to as "inference."

[0073] Furthermore, a search may be performed using a search expression. A "search expression" is a string that contains at least one search term. A search expression may contain multiple search terms. A search expression may also contain search conditions, classification codes, etc. Here, for example, a search expression may include at least a portion of the string contained in the first document. Also, the search term may include, for example, the creative field indicated by the first document.

[0074] Figure 5 shows an example of search results. In the example shown in Figure 5, the search results are shown as Table 200. Table 200 can be displayed on the display unit of the information terminal 20. Figure 5 can also be considered an example of a graphical user interface (GUI) related to an information processing system according to one embodiment of the present invention. The forms, icons, tables, etc. in the drawings relating to the GUI exemplified in this embodiment, such as Figure 5, are examples and are not particularly limited. The GUI can be configured as a web page accessed by a user of the information processing system via the network 30. Alternatively, the GUI can be configured as the screen of a program application executed on the information terminal 20.

[0075] Table 200 has columns for "Reference Number" and "Content". The "Reference Number" column shows a number that identifies the searched reference. In Figure 5, "xxx", "yyy", and "zzz" are shown as reference numbers.

[0076] The "Content" column displays at least a portion of the content of the searched document. Examples of document numbers include application numbers, publication numbers, and registration numbers. Alternatively, a company's internal identification number may be used. The content can include, for example, one or both of the text and / or drawings contained in the document. For example, in the case of patent documents or utility model documents, the abstract may be shown in the "Content" column.

[0077] Furthermore, the content of a document may be displayed by selecting a document number, for example. For example, clicking a document number may display the document. For example, clicking a document number may display the specification, drawings, claims, etc., of the document. Note that the document number may be selected using a keyboard, for example. Also, if the information terminal 20 has a touch panel, the document number may be selected by touching it. The selection operations shown below can also be performed in the same manner. Furthermore, in the GUI shown below, when information about a document, such as a document number, is displayed, the content of the document may be displayed by selecting the displayed information.

[0078] Table 200 shows a checkbox 201 for each document. Documents to be designated as the second document can be selected by checking the checkbox 201. Figure 5 shows a button 203 labeled "Select". By selecting button 203, the documents with checkboxes 201 checked can be accepted as the second document by, for example, the reception unit 110. Note that instead of checkboxes 201, radio buttons or text boxes may be displayed.

[0079] In the example shown in Figure 5, the checkboxes 201 for the document with document number "xxx" and the document with document number "zzz" are checked, meaning they are selected. When button 203 is selected in this state, the document with document number "xxx" and the document with document number "zzz" are supplied as second documents to the reception unit 110, for example, from the database.

[0080] Here, not only the searched documents but also documents specified by, for example, the user of the information processing system, can be included in Table 200. The user can specify the documents to be included in Table 200, for example, by specifying the document number. Furthermore, documents found using, for example, a search expression specified by the user can also be included in Table 200.

[0081] Next, in step S102 of Figure 3, the processing unit 130 creates a first prompt and transmits it to the information processing device 40 via the output unit 140. Specifically, the first prompt is transmitted to the language model of the information processing device 40. The first prompt is a prompt for generating a summary of the second document. The first prompt has the second document. The first prompt also has an instruction such as, "Please summarize the following document."

[0082] The information processing device 40 uses a language model to generate a first response statement based on a first prompt and supplies it to the receiving unit 110. As a result, the information processing device 10 obtains the first response statement. The first response statement includes a summary of the second document. If the first prompt includes multiple second documents, the language model can generate a summary for each of the multiple second documents.

[0083] Furthermore, when the second document is a patent document or a utility model document, it is preferable to generate an abstract using only the specification, for example. That is, it is preferable to generate an abstract without using the claims and abstract included in the patent document or utility model document. In this case, the instruction in the first prompt can be, for example, "Please summarize the specification included in the following document." Furthermore, the claims, abstract, etc. included in the patent document or utility model document do not need to be included in the first prompt. Also, when the second document is a design publication, the language model can generate an abstract using, for example, the description of the article to which the design relates and / or the description of the design.

[0084] Next, in step S103 of Figure 3, the processing unit 130 creates a second prompt and transmits it to the information processing device 40 via the output unit 140. Specifically, the second prompt is transmitted to the language model of the information processing device 40. The second prompt is a prompt for presenting the differences between the first document and the summary of the second document. Specifically, the differences can be features described in the first document that are not described in the summary, such as technical features, as described above.

[0085] The second prompt includes the first document and a summary of the second document. That is, the second prompt includes the first document and, for example, a summary of the document selected in Figure 5. Here, the second prompt can be used to present differences in features not described in any of the summaries when there are multiple summaries of the second document, i.e., when multiple documents are selected in Figure 5. In this case, the second prompt has instructions such as, "Of the features described in the input document, please present the differences from the document that are not described in any of the document summaries. Please present the differences in a bulleted list." Here, the input document refers to the first document. The second prompt may also be used to present differences from the first document for each of the multiple summaries.

[0086] The information processing device 40 uses a language model to generate a second response statement based on the second prompt and supplies it to the receiving unit 110. As a result, the information processing device 10 obtains the second response statement. The second response statement contains the differences between the first document and the summary of the second document.

[0087] Next, in step S104 of Figure 3, the processing unit 130 presents the differences presented by the language model to the user of the information processing system. This allows the processing unit 130 to allow the user to determine whether the differences are valid or not. For example, the processing unit 130 creates data containing the content indicated by the second response statement and supplies it to the information terminal 20 via the output unit 140. As a result, the differences are displayed on the display unit of the information terminal 20.

[0088] Figure 6A is a diagram showing an example of information displayed on the display unit of the information terminal 20 in step S104. Figure 6A can also be considered an example of a GUI related to an information processing system according to one embodiment of the present invention. The following diagrams showing examples of information displayed on the display unit can also be considered examples of a GUI related to an information processing system according to one embodiment of the present invention.

[0089] In the example shown in Figure 6A, the differences between the first document and the summary of the second document are shown as "Differences to the References." The differences shown as "Differences to the References" are denoted as difference 211. In the example shown in Figure 6A, difference 211 includes "aaa.", "bbb.", and "ccc." Here, "aaa." is designated as difference 211[1], "bbb." as difference 211[2], and "ccc." as difference 211[3]. Note that similarities may also be shown in addition to differences to the references. In this case, the second prompt is a prompt to present not only the differences between the first document and the summary of the second document, but also the similarities.

[0090] Furthermore, in the example shown in Figure 6A, Table 212 is shown. Table 212 has a "Document Number" column and a "Summary" column. The "Document Number" column shows a number that identifies the second document, for example, the document number selected in Figure 5. In Figure 6A, "xxx" and "zzz" are shown as the document numbers. The "Summary" column shows the summary generated in step S102 of Figure 3. Although not shown in Figure 6A, the first document may also be displayed on the display unit of the information terminal 20.

[0091] In the example shown in Figure 6A, the question "Is the difference valid?" is presented. A button 213 labeled "Yes" and a button 214 labeled "No" are also shown. The user of the information processing system selects button 213 if they determine that the difference 211 is valid. The user selects button 214 if they determine that the difference 211 is not valid. If button 213 is selected, data indicating that the difference 211 is valid is transmitted from the information terminal 20 to the reception unit 110. In this case, at the branching point in step S105 in Figure 3, the process proceeds to step S108. If button 214 is selected, data indicating that the difference 211 is not valid is transmitted from the information terminal 20 to the reception unit 110. In this case, at the branching point in step S105 in Figure 3, the process proceeds to step S106. Thus, step S105 can be described as the step in which the reception unit 110 receives a judgment on whether the difference 211 is valid or not, specifically the data indicating that judgment.

[0092] In step S106, the reception unit 110 receives the first instruction document. Figure 6B shows an example of the information displayed on the display unit of the information terminal 20 when the button 214 shown in Figure 6A is selected.

[0093] In the example shown in Figure 6B, below the text, "Please write any proposed revisions to the input document, comments on any differences, etc.," is Form 221. Here, the input document refers to the first document. Below Form 221 is a button 223 labeled "Submit."

[0094] A user of the information processing system enters text into form 221, for example. Then, by selecting button 223, the contents of form 221 are supplied from the information terminal 20 to the reception unit 110 as a first instruction document.

[0095] The first instruction document may include, for example, instructions to modify the first document and at least one of the following: comments on the difference 211. Here, comments on the difference 211 may be, for example, opinions on the difference 211. For example, if a user of the information processing system believes that there are differences in the first document from the second document other than the difference 211, a statement to that effect may be included in the first instruction document. Also, if a user of the information processing system believes that at least a part of the difference 211 is described in the second document, a statement to that effect may be included in the first instruction document.

[0096] The user of the information processing system can, for example, write on Form 221: "Please modify the input document as follows," "I believe ddd is not disclosed in any document," and "aaa is paragraph [a] of document number xxx." １ b １ c １ d １ ] ( a １ , b １ , c １ , and d １ The user can input sentences such as, "I believe that these are disclosed to integers between 0 and 9 (each from 0 to 9)." Alternatively, the user of the information processing system may input information into form 221 in bullet points. In step S104 of Figure 3, if the language model determines that there are no differences 211, the processing unit 130 can display, for example, a sentence indicating that there are no differences, table 212, form 221, and button 223 on the display unit of the information terminal 20.

[0097] Alternatively, form 221 and button 223 may be displayed in the GUI shown in Figure 6A. In this case, buttons 213 and 214 do not need to be displayed. In the above case, for example, if button 223 is selected while form 221 is blank, the process can proceed to step S108 at the branching point in step S105 in Figure 3. Also, for example, if button 223 is selected while text is entered in form 221, the process can proceed to step S106 at the branching point in step S105 in Figure 3. Note that the process may proceed to step S108 not only when button 223 is selected while form 221 is blank, but also when button 223 is selected while only predetermined characters are entered in form 221. For example, if button 223 is selected while only blank characters, symbols, and special characters are entered in form 221, the process may proceed to step S108.

[0098] Following step S106 in Figure 3, in step S107, the processing unit 130 creates a third prompt based on the first instruction document and transmits it to the information processing device 40 via the output unit 140. Specifically, the third prompt is transmitted to the language model of the information processing device 40. The third prompt, like the second prompt, is a prompt to present the differences between the first document and the summary of the second document.

[0099] The third prompt includes the first document, a summary of the second document, and the first instruction document. The third prompt includes instructions such as, "Please revise the entered document and answer the questions based on the information below. Also, please identify any features described in the entered document that are not mentioned in the summaries of any of the documents as differences from the documents. Please list the differences in bullet points."

[0100] The information processing device 40 uses a language model to generate a third response statement based on the third prompt and supplies it to the receiving unit 110. As a result, the information processing device 10 obtains the third response statement. The third response statement, like the second response statement, includes the differences between the first document and the summary of the second document. These differences can be based on the content of the first instruction document. Furthermore, the third response statement can include responses to comments included in the first instruction document.

[0101] After step S107 in Figure 3, steps S104 and S105 are repeated. Here, the display unit of the information terminal 20 can display, for example, the answer to the comments included in the first instruction document, in addition to the differences 211, table 212, button 213, and button 214 shown in Figure 6A. Furthermore, if the first document is modified based on the first instruction document, the modified first document can be displayed on the display unit of the information terminal 20.

[0102] In step S108 of Figure 3, the processing unit 130 creates a fourth prompt and transmits it to the information processing device 40 via the output unit 140. Specifically, the fourth prompt is transmitted to the language model of the information processing device 40. The fourth prompt is a prompt to confirm that not all of the differences 211 shown in Figure 6A are described in the second document. In other words, the fourth prompt is a prompt to detect differences 211 that are not described in the summary of the second document but are described in the second document itself.

[0103] The fourth prompt includes Difference 211 and the second document. The fourth prompt also includes instructions such as, "Confirm that the differences to the document are not disclosed in any of the documents. If there are any disclosed differences, please provide those differences."

[0104] The information processing device 40 uses a language model to generate a fourth response statement based on the fourth prompt and supplies it to the receiving unit 110. As a result, the information processing device 10 obtains the fourth response statement. The fourth response statement includes the confirmation result. It also includes whether or not each of the differences 211 is recorded in the second document.

[0105] Next, in step S109 of Figure 3, the processing unit 130 presents the above-mentioned confirmation result to the user of the information processing system. For example, the processing unit 130 creates data including the content indicated by the fourth response statement and supplies it to the information terminal 20 via the output unit 140. As a result, the above-mentioned confirmation result is displayed on the display unit of the information terminal 20.

[0106] Figure 7A shows an example of the information displayed on the display unit of the information terminal 20 when it is determined that difference 211[2] is described in the second document. In the example shown in Figure 7A, difference 211[1] and difference 211[3] are shown as differences with respect to the document. On the other hand, unlike the example shown in Figure 6A, difference 211[2] is not shown. In addition, the confirmation result shows the sentence, "The following differences are not included in the abstract, but are disclosed in the document," and difference 211[2] is shown as such a difference. Furthermore, the form 221 and button 223 shown in Figure 6B are shown. Note that in the example shown in Figure 7A, the document number of the document in which difference 211[2] is described is not shown, but the document number may be shown.

[0107] Figure 7B shows an example of the information displayed on the display unit of the information terminal 20 when it is determined that all of the differences 211[1], differences 211[2], and differences 211[3] shown in Figure 6A are not described in the second document. In the example shown in Figure 7A, in addition to the differences 211 and table 212 shown in Figure 6A, the confirmation result shows the statement, "None of the differences were disclosed in the document." Furthermore, in the example shown in Figure 7B, a button 217 labeled "Accept" is shown.

[0108] If it is determined that at least some of the differences 211 are described in the second document, that is, if the confirmation result shown in Figure 7A is displayed on the display unit of the information terminal 20, then step S106 is performed at the branch of step S110 in Figure 3. Here, the first instruction document may include comments on the confirmation result shown in Figure 7A, for example. Comments on the confirmation result may be, for example, opinions on the confirmation result. For example, if a user of the information processing system believes that the differences 211[2] are not described in the second document, a statement to that effect may be included in the first instruction document.

[0109] If it is determined that all of the differences 211 are not described in the second document, that is, if the confirmation result shown in Figure 7B is displayed on the display unit of the information terminal 20, then the process proceeds to connector A in the branching step S110 in Figure 3. Specifically, the process proceeds to connector A when the user of the information processing system selects button 217. Note that although Figure 7B does not show, for example, the button for performing the process in step S106, such a button may be shown. For example, by selecting this button, form 221 and button 223 may be displayed on the display unit of the information terminal 20.

[0110] In the process shown in Figure 3, steps S102 and S108 to S110 may be omitted. In this case, in step 103, the processing unit 130 creates a second prompt to present the differences between the first document and the second document itself. If the user of the information processing system determines that the differences 211 are valid, the process proceeds to connector A at the branch in step S105.

[0111] By performing steps S102 and S108 to S110, the processing unit 130 can more easily present the differences 211. For example, it becomes easier to compare the technical features described in the first document with the technical features described in the second document, and to present the differences 211 based on the comparison results. On the other hand, by not performing steps S102 and S108 to S110, the number of processes performed by the information processing system can be reduced.

[0112] Connector A is connected to step S111 shown in Figure 4. In step S111, the processing unit 130 creates a fifth prompt and transmits it to the information processing device 40 via the output unit 140. Specifically, the fifth prompt is transmitted to the language model of the information processing device 40. The fifth prompt is a prompt for generating a third document based on the second document and the differences 211.

[0113] The fifth prompt includes the second document and the differences 211. The fifth prompt also includes instructions such as, "Generate the document based on the references and the differences." The fifth prompt may also include the first document. In this case, it may be possible to prevent the structure shown in the first document from being shown in the third document. On the other hand, if the fifth prompt does not include the first document, it may be possible to prevent the third document from being generated in a format different from, for example, the format of the second document.

[0114] The information processing device 40 uses a language model to generate a fifth response statement based on the fifth prompt and supplies it to the receiving unit 110. As a result, the information processing device 10 obtains the fifth response statement. The fifth response statement includes the third document.

[0115] Since the third document is generated based on the second document, it can be of the same type as the second document. For example, if the second document is a patent application or a utility model application, the third document can also be a patent application or a utility model application. Specifically, if the second document is a specification, the third document can also be a specification.

[0116] Next, in step S112 of FIG. 4, the processing unit 130 presents the third document generated by the language model to the user of the information processing system. Thereby, the processing unit 130 causes the user to confirm the third document. For example, the processing unit 130 creates data including the content indicated by the fifth response sentence and supplies it to the information terminal 20 via the output unit 140. Thereby, the third document is displayed on the display unit included in the information terminal 20.

[0117] FIG. 8A is a diagram showing an example of information displayed on the display unit included in the information terminal 20 in step S112 after step S111. In FIG. 8A, the third document generated by the language model is referred to as document 231. In the following drawings, the third document may be referred to as document 231. Document 231 is also referred to as a generated document.

[0118] In the example shown in FIG. 8A, document 231, button 233 labeled "Accept", form 235, and button 237 labeled "Send" are shown. FIG. 8A shows an example in which form 235 and button 237 are displayed below the sentence "Please enter any amendments, comments, etc.".

[0119] For example, when the second document is a specification, document 231 can be a document conforming to the format of the specification. In FIG. 8A, an example in which paragraph numbers are assigned to each paragraph in document 231 is shown. In the example shown in FIG. 8A, as paragraph numbers,

[0001] ,

[0002] , and [n １ n ２ n ３ n ４ (n １ 、n ２ 、n ３ 、and n ４ are each integers from 0 to 9 inclusive) are shown. Note that, for example, paragraphs including the difference 211 may be emphasized. Examples of methods of emphasis include changing the background color, changing the text color, increasing the text size, changing the font, making the text bold, underlining, etc.

[0120] If a user of the information processing system determines, for example, that document 231 is complete and does not need to be modified, they select button 233. Alternatively, if they determine that document 231 needs to be modified, the user enters instructions for the modification into form 235 and then selects button 237. If button 233 is selected, data indicating that document 231 does not need to be modified is sent from the information terminal 20 to the reception unit 110. In this case, at the branching point in step S113 in Figure 4, the process proceeds to step S116. If button 237 is selected, data indicating that document 231 needs to be modified is sent from the information terminal 20 to the reception unit 110. In this case, at the branching point in step S113 in Figure 4, the process proceeds to step S114. Thus, step S113 can be described as the step in which the reception unit 110 receives a determination on whether or not document 231 needs to be modified, specifically the data indicating that determination.

[0121] For example, instructions regarding revisions include, "Paragraph [p １ p ２ p ３ 1] and [p １ p ２ p ３ 2] (p １ , p ２ , and p ３ Please add a description regarding the structure ddd between each of the integers (0 to 9). "Paragraph [p ４ p ５ q １ q ２ ] (p ４ , p ５ , q １ , and q ２ The structure 'eee' described in (where each is an integer between 0 and 9) should be changed to 'fff'. "After explaining the structure 'fff', please explain the structure 'ddd'. "Add a more detailed explanation of the term 'eee' based on reference xxx. "Add the effect of the 'fff' structure. "Paragraph [q ３ p ６ q ４ p ７ ] (p６ , p ７ , q ３ , and q ４ Examples include: "Please delete integers between 0 and 9 (each between 0 and 9)." Additionally, users of the information processing system may enter information into form 235 in bullet points.

[0122] Users of the information processing system can input information necessary for modifying document 231 into form 235. For example, they can input documents not included in the second document into form 235. Specifically, they can input patent application documents, papers, and other documents that were not selected as the second document into form 235. They can also input related web pages, explanatory texts defining terms, etc. into form 235.

[0123] Form 235 may include comments regarding document 231. Such comments may, for example, be questions regarding document 231. In this case, form 235 does not need to include instructions for correction. That is, even if the user of the information processing system determines that there is no need to correct document 231, if there are matters that the user would like to comment on regarding document 231, the user can proceed to step S114 at the branching point in step S113 in Figure 4. For example, a question regarding document 231 could be, "Paragraph [r １ r ２ r ３ r ４ ] (r １ ,r ２ ,r ３ , and r ４ What does ggg mean in each of the integers (0 to 9)? [paragraph [s] １ s ２ s ３ s ４ ] (s １ s ２ s ３ , and s ４ What effect will be achieved by the configuration shown (where each is an integer between 0 and 9)? Examples include: "..." Furthermore, if a user of the information processing system does not wish to modify document 231, they may write "Please do not modify the document" on form 235.

[0124] Note that button 233 does not need to be displayed in the GUI shown in Figure 8A. In this case, for example, if button 237 is selected while form 235 is blank, the process can proceed to step S116 at the branching point in step S113 in Figure 4. Similarly, if button 223 is selected while only predetermined characters are entered in form 221, the process may also proceed to step S116 if button 237 is selected while only predetermined characters are entered in form 235.

[0125] In step S114 of Figure 4, the reception unit 110 receives the second instruction document. Specifically, the text entered in form 235 can be used as the second instruction document.

[0126] Following step S114 in Figure 4, in step S115, the processing unit 130 creates a sixth prompt based on the second instruction document and transmits it to the information processing device 40 via the output unit 140. Specifically, the sixth prompt is transmitted to the language model of the information processing device 40. The sixth prompt is a prompt for modifying the third document based on the second instruction document.

[0127] The sixth prompt includes the third document and the second instruction document. The sixth prompt also includes instructional statements such as, "Please provide answers and revise the generated document regarding the following. Please provide answers in bullet points." The sixth prompt may also include the second document and difference 211, similar to the fifth prompt. Furthermore, the sixth prompt may include the first document. For example, the sixth prompt may include the first document if the fifth prompt includes the first document.

[0128] The information processing device 40 uses a language model to generate a sixth response statement based on the sixth prompt and supplies it to the receiving unit 110. As a result, the information processing device 10 obtains the sixth response statement. The sixth response statement may include, for example, a modified third document. The sixth response statement may also include a response to a comment contained in the second instruction document. Furthermore, the language model may modify the third document based on the comment even if the second instruction document only contains a comment and no modification instructions.

[0129] After step S115 in Figure 4, step S112 is performed again. Figure 8B shows an example of the information displayed on the display unit of the information terminal 20 in step S112, following step S115. The following will mainly explain the differences from Figure 8A.

[0130] In the example shown in Figure 8B, the modified parts in document 231 are indicated with a hatching pattern. Specifically, Figure 8B shows an example where "fff" is added and a hatching pattern is applied. Highlighting the modified parts in document 231 in this way is preferable because it allows users of the information processing system to easily recognize the modified parts. Methods of highlighting include changing the background color, changing the font color, increasing the font size, changing the font type, making it bold, and underlining, as mentioned above. Highlighting may be applied to each sentence or to each paragraph. That is, even if only a part of a sentence is modified, the entire sentence may be highlighted. Similarly, even if only a part of a paragraph is modified, the entire paragraph may be highlighted.

[0131] Furthermore, in the example shown in Figure 8B, the answer to the comment included in the second instruction document is shown in area 239. In Figure 8B, an example of an answer to a comment is shown as, "ggg means kkk." For example, if the second instruction document includes the comment, "What does ggg mean?", the answer shown in Figure 8B can be displayed in area 239. Area 239 may also show either or both the modified parts of document 231 and the content of the modifications. Alternatively, either or both the modified parts of document 231 and the content of the modifications may be shown in an area different from area 239.

[0132] In step S116 of Figure 4, the processing unit 130 outputs a third document. The processing unit 130 supplies the third document to, for example, a database via the output unit 140. The processing unit 130 can also supply the third document to, for example, an information terminal 20 via the output unit 140. The third document supplied to the information terminal 20 can be displayed on, for example, a display unit. The third document supplied to the information terminal 20 can also be stored in, for example, the information terminal 20. With this, the information processing method according to one embodiment of the present invention is "completed".

[0133] As described above, by using the information processing system according to one aspect of the present invention, a third document can be generated, taking into account the differences between the first document and the second document. For example, the specification relating to the creation shown in the first document can be written in a way that emphasizes technical features not disclosed in the prior art documents. As described above, the information processing system according to one aspect of the present invention can assist in the creation of documents related to intellectual property, such as the creation of specifications. Therefore, even a person with little experience in intellectual property work can create documents related to intellectual property, such as specifications, in a short time by using the information processing system according to one aspect of the present invention. Furthermore, users can create documents related to intellectual property, such as specifications, with less effort.

[0134] Furthermore, in one aspect of the information processing system of the present invention, when a user creates a first instruction document, the language model can present the differences between the first document and the second document multiple times. Specifically, the language model can present the aforementioned differences multiple times based on the content of the first instruction document. Moreover, in one aspect of the information processing system of the present invention, when a user creates a second instruction document, the language model can make one or more modifications to the third document. As a result, a user of one aspect of the information processing system of the present invention can create the third document in an interactive manner. This enables, for example, a person with little experience in intellectual property work to create a highly complete specification.

[0135] Based on the above, one aspect of the present invention provides an information processing device, an information processing method, and an information processing system that are excellent in convenience and usefulness.

[0136] <Information Processing Method 2> Figure 9 is a flowchart showing a different example from Figure 4 of the processing after connector A. In the example shown in Figure 9, steps S121, S122, S123, S124, and S125 are shown before step S111.

[0137] In step S121, the processing unit 130 creates a seventh prompt and transmits it to the information processing device 40 via the output unit 140. Specifically, the seventh prompt is transmitted to the language model of the information processing device 40. The seventh prompt is a prompt for determining whether or not there is insufficient information to create the third document. The seventh prompt is also a prompt for indicating the type of information that is missing if such information is found to be insufficient.

[0138] The seventh prompt includes the second document and the differences 211. The seventh prompt also includes instructions such as, "When generating a document that satisfies the enablement requirements based on the document and the differences, determine whether there is any missing information. If there is missing information, indicate what information is missing." The seventh prompt may also include the first document. For example, if the processing unit 130 creates the fifth prompt to include the first document in the later step S111, it is preferable that the seventh prompt also includes the first document.

[0139] The information processing device 40 uses a language model to generate a seventh response statement based on the seventh prompt and supplies it to the receiving unit 110. The information processing device 10 then obtains the seventh response statement. The seventh response statement includes a determination result regarding whether or not there is insufficient information to create the third document. If such information is insufficient, the seventh response statement also includes the type of information that is missing.

[0140] For example, if the third document includes examples, and the experimental conditions are not sufficiently described in the first document, the experimental conditions can be considered missing information. Also, if the first document describes the transistor configuration, and the second document describes the transistor configuration and manufacturing method, but the first document does not describe the manufacturing method, the manufacturing method can be considered missing information. Furthermore, if the first document describes the physical properties of a material, such as electrical resistivity, but does not specify the name of the material, the name of the material can be considered missing information. In addition, if an item is not described in either the second document or difference 211, it can be determined that it is not described in the first document either.

[0141] If there is insufficient information to create the third document, the branch in step S122 proceeds to step S123. If there is sufficient information to create the third document, the branch in step S122 proceeds to step S111.

[0142] In step S123, the processing unit 130 presents the user of the information processing system with the information missing to create the third document. For example, the processing unit 130 creates data containing the content indicated by the seventh response statement and supplies it to the information terminal 20 via the output unit 140. As a result, the information missing to create the third document is displayed on the display unit of the information terminal 20.

[0143] Figure 10A is a diagram showing an example of information displayed on the display unit of the information terminal 20 in step S123. In the example shown in Figure 10A, the information that is missing to create the third document is shown as "missing information". The information shown as "missing information" is referred to as information 241. In the example shown in Figure 10A, information 241 is shown as "hhh", "iii", and "jjj". Here, "hhh" is referred to as information 241[1], "iii" as information 241[2], and "jjj" as information 241[3].

[0144] In the example shown in Figure 10A, Form 243 is shown below the text, "Please enter the missing information and select the 'Submit' button." Below Form 243, a button 245 labeled "Submit" is shown.

[0145] The user of the information processing system enters the missing information into form 243, based on information 241, to create the third document. Then, by selecting button 245, the contents of form 243 are supplied as additional information from the information terminal 20 to the reception unit 110.

[0146] For example, if information 241[1] is experimental conditions, the user of the information processing system enters the experimental conditions into form 243. For example, if information 241[2] is a method for fabricating a transistor, the user of the information processing system enters the method for fabricating a transistor into form 243. For example, if information 241[3] is a conductive material with an electrical resistivity of x Ω・cm or less, the user of the information processing system enters the specific name of the conductive material into form 243. In this way, the user of the information processing system can enter additional information corresponding to information 241 into form 243. Note that form 243 may allow input of not only text but also, for example, drawings. Furthermore, form 243 may allow input of additional information in a table format for each piece of information 241.

[0147] In step S124 of Figure 9, the reception unit 110 receives the above-mentioned additional information. Specifically, information such as text entered in form 243 can be used as additional information.

[0148] In step S125, the processing unit 130 creates a seventh prompt again, including additional information, and transmits it to the information processing device 40 via the output unit 140. If, after step S125, there is still insufficient information to create the third document, the process proceeds to step S123 again at the branch in step S122. If the lack of information to create the third document is resolved, the process proceeds to step S111 at the branch in step S122. In step S111, the processing unit 130 creates a fifth prompt that includes additional information. In this case, the fifth prompt includes the second document, the differences 211, and additional information. The instruction text for the fifth prompt can also be, "Generate a document based on the document, the differences, and the additional information," etc.

[0149] As described above, the information processing method shown in Figures 9 and 10A allows for the addition of missing information before the language model generates the third document. This improves the completeness of the third document.

[0150] In step S121, if it is determined that there is no missing information to create the third document, this fact may be presented to the user of the information processing system. After the user of the information processing system confirms that there is no missing information to create the third document, the processing unit 130 may perform the processing in step S111. Figure 10B is a diagram showing an example of the information displayed on the display unit of the information terminal 20 when it is determined in step S121 that there is no missing information to create the third document. In the example shown in Figure 10B, the determination result is shown as, "No missing information was found." Also in the example shown in Figure 10B, a button 242 labeled "Accept" is shown. By selecting the button 242, the processing unit 130 can perform step S111.

[0151] In the example shown in Figure 10B, below the text, "If you have any additional information you would like to add, please enter it in the form below and select the 'Submit' button," a form 243 and a button 246 labeled "Submit" are shown. In this case, even if the user of the information processing system determines in step S121 that there is no missing information to create the third document, the user can still enter additional information in form 243. By selecting button 246, the processing unit 130 can perform step S111 after performing step S124. Alternatively, after button 246 is selected, the processing unit 130 may perform step S125 instead of step S111. Furthermore, form 243 and button 246 do not necessarily have to be displayed in the GUI shown in Figure 10B.

[0152] <Information Processing Method 3> Figure 11 is a flowchart showing an example of an information processing method according to one aspect of the present invention, different from that shown in Figures 3 and 4. In Figure 11, steps that are not performed in the information processing methods shown in Figures 3 and 4 are indicated by thick borders.

[0153] An information processing method according to one embodiment of the present invention is "started," and in step S131, the receiving unit 110 receives a base document in addition to the first document and the second document. The base document is the document that serves as the basis when generating the third document.

[0154] The base document shall be a document that describes a creation related to the first document. Preferably, the base document shall be a pre-publication document. The base document may be, for example, a specification belonging to a pre-publication patent application or a specification belonging to a utility model registration application of the company. Alternatively, the base document may be an application form belonging to a pre-publication design registration application of the company. Furthermore, the base document may be a paper, book, journal, etc. The base document may be, for example, a document stored in a database.

[0155] The receiving unit 110 may accept multiple base documents. In this case, in a later step, a third document can be generated based on parts common to multiple base documents. This makes it possible to suppress the inclusion of a description of the main feature of the invention related to the patent application in the third document, for example, when the base document is a specification belonging to a patent application.

[0156] Next, step S102 is performed. Then, in step S132, the processing unit 130 creates a second prompt and transmits it to the information processing device 40 via the output unit 140. Specifically, the second prompt is transmitted to the language model of the information processing device 40, similar to step S103 in Figure 3. In step S132, the second prompt is a prompt to present the differences between the first document and the summary of the second document, as well as the differences between the first document and the base document.

[0157] The second prompt in step S132 includes the first document, a summary of the second document, and the base document. The second prompt in step S132 also includes instructions such as, "Please list the features described in the input document that are not described in the base document as differences from the base document. Also, please list the features that are not described in the summary of any of the documents as differences from the documents. Please list the differences in bullet points."

[0158] The information processing device 40 uses a language model to generate a second response statement based on a second prompt and supplies it to the receiving unit 110. As a result, the information processing device 10 obtains the second response statement. The second response statement includes differences between the first document and the summary of the second document, as well as differences from the base document. Here, if there are multiple base documents, the second prompt in step S132 can be a prompt to present features not described in any of the base documents as differences. In one embodiment of the present invention, the information processing system may perform step S103 instead of step S132. That is, even in the information processing method shown in Figure 11, the information processing system does not need to present differences between the first document and the base document.

[0159] Next, in step S133, the processing unit 130 presents the differences presented by the language model to the user of the information processing system. Specifically, the processing unit 130 presents to the user of the information processing system the differences 215 between the first document and the base document, in addition to the differences 211 between the first document and the summary of the second document. This allows the user to determine whether these differences are valid or not. For example, the processing unit 130 creates data containing the content indicated by the second response statement, similar to step S104 in Figure 3, and supplies it to the information terminal 20 via the output unit 140. As a result, the differences are displayed on the display unit of the information terminal 20.

[0160] Figure 12 is a diagram showing an example of the information displayed on the display unit of the information terminal 20 in step S133. In Figure 12, in addition to the differences 211 with respect to the document (second document) shown in Figure 6A, a table 212 which is a list of the second documents, a button 213 which is selected when the differences are valid, and a button 214 which is selected when the differences are not valid, an example is shown in which differences 215 with respect to the base document are displayed. In the example shown in Figure 12, the differences 215 are shown as "kkk." and "lll.". Here, "kkk." is referred to as difference 215[1] and "lll." is referred to as difference 215[2]. Note that not only differences with respect to the base document but also similarities may be shown. In this case, the second prompt is a prompt that presents not only the differences in the first document with respect to the base document but also the similarities.

[0161] Next, steps S105 to S110 are performed. Here, the first instruction document may include comments regarding the differences 215. The third prompt may be a prompt to present the differences in the first document to the base document, in addition to the differences in the summary of the second document.

[0162] In step S108, if it is determined that at least some of the differences 211 are described in the second document, the branch in step S110 proceeds to step S106, similar to the example shown in Figure 3. In step S108, if it is determined that not all of the differences 211 are described in the second document, the branch in step S110 proceeds to step S134. In step S134, the processing unit 130 creates a fifth prompt and transmits it to the information processing device 40 via the output unit 140. Specifically, the fifth prompt is transmitted to the language model of the information processing device 40, similar to step S111 in Figure 4. The fifth prompt in step S134 is a prompt for generating a third document, which includes the differences 211 and 215, based on the base document.

[0163] Here, difference 211 is a difference in the first document with respect to, for example, publicly available literature. On the other hand, difference 215 is a difference in the first document with respect to, for example, unpublished literature. Therefore, it is preferable that the fifth prompt in step S134 be a prompt to generate the third document such that difference 211 is emphasized more than difference 215.

[0164] The fifth prompt in step S134 includes the second document and the difference 211, as well as the base document and the difference 215. The fifth prompt in step S134 also includes instructions such as, "Generate a new document based on the base document so that it includes the differences in the input document to the references and the differences to the base document. The differences to the references should be expressed in a more emphatic way than the differences to the base document." The fifth prompt does not necessarily have to include the difference 215. For example, if step S103 is performed instead of step S132 as described above, the fifth prompt will not include the difference 215.

[0165] The information processing device 40 uses a language model to generate a fifth response statement based on the fifth prompt and supplies it to the receiving unit 110. As a result, the information processing device 10 obtains the fifth response statement. The fifth response statement includes the third document as described above.

[0166] Here, if the fifth prompt has multiple base documents, the language model can generate a third document based on, for example, parts common to the multiple base documents, as described above. This makes it possible to suppress the inclusion of a description of the essential structure of the invention related to the patent application in the third document, for example, if the base document is a specification belonging to a patent application.

[0167] Since the third document in step S134 is generated based on the base document, it can be of the same type as the base document. For example, if the base document is a patent application or a utility model application, the base document can also be a patent application or a utility model application. Specifically, if the base document is a specification, the third document can also be a specification.

[0168] Before step S134, steps S121 to S125 shown in Figure 9 may be performed. That is, the language model may add any missing information necessary to create the third document before generating the third document in step S134.

[0169] Next, steps S112 to S116 in Figure 4 are performed. With this, the information processing method according to one embodiment of the present invention is "completed".

[0170] As described above, the information processing method shown in Figures 11 and 12 can generate a third document based on a base document. This allows for the generation of a third document that includes, for example, information commonly found in a company's patent applications. Furthermore, it can prevent the wording and phrasing of the third document from becoming too similar to those of other companies' documents. As a result, the quality of the third document can be improved.

[0171] Furthermore, a third document of a different type from the second document can be generated. For example, by using a patent document or utility model document as the base document, even if at least a part of the second document consists of a paper, book, journal, etc., a specification belonging to a patent application or utility model registration application can be generated as the third document. Moreover, by generating the third document to include the differences between the first document and the base document, it becomes possible to cover, for example, more configurations in one of the company's applications. Thus, a comprehensive network of rights, such as a patent network, can be easily created.

[0172] Based on the above, we can provide an information processing device, an information processing method, and an information processing system that are excellent in terms of convenience and usefulness.

[0173] <Example of Information Processing System Configuration 2> Below, a detailed example of the configuration of an information processing system according to one embodiment of the present invention will be described. Specifically, a configuration example of the storage unit 120, the processing unit 130, and the network 30 that is not shown in <Example of Information Processing System Configuration 1> will be described.

[0174] The memory unit 120 has at least one of volatile memory and non-volatile memory. Examples of volatile memory include DRAM (Dynamic Random Access Memory) and SRAM (Static Random Access Memory). Examples of non-volatile memory include ReRAM (Resistive Random Access Memory), PRAM (Phase Change Random Access Memory), FeRAM (Ferroelectric Random Access Memory), MRAM (Magnetoresistive Random Access Memory), and flash memory. Furthermore, the storage unit 120 may have at least one of NOSRAM (registered trademark) and DOSRAM (registered trademark). The storage unit 120 may also have a recording media drive. Examples of recording media drives include hard disk drives (HDD) and solid state drives (SSD).

[0175] NOSRAM is an abbreviation for "Nonvolatile Oxide Semiconductor Random Access Memory." NOSRAM is a memory in which the memory cell is a 2-transistor type (2T) or 3-transistor type (3T) gain cell, and the transistors are transistors that use metal oxide in the channel formation region (also called OS transistors). OS transistors have an extremely small current flowing between the source and drain when off, i.e., a leakage current. By utilizing the characteristic of extremely low leakage current, NOSRAM can be used as a non-volatile memory by holding a charge corresponding to the data within the memory cell. In particular, NOSRAM can read the stored data without destroying it (non-destructive read), making it suitable for computational processing that repeatedly performs a large number of data read operations. Because the data capacity of NOSRAM can be increased by stacking them, it can be used as a large-scale cache memory, main memory, storage memory, etc., to improve the performance of semiconductor devices.

[0176] DOSRAM is an abbreviation for "Dynamic Oxide Semiconductor RAM," and refers to RAM with a 1T (transistor) 1C (capacitance) type memory cell. DOSRAM is a DRAM formed using OS transistors and is a memory that temporarily stores information sent from the outside. DOSRAM is a memory that takes advantage of the small off-current of OS transistors.

[0177] In this specification, "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 called oxide semiconductors or simply OS), etc. For example, when a metal oxide is used in the semiconductor layer of a transistor, that metal oxide may be called an oxide semiconductor.

[0178] The metal oxide in the channel-forming region preferably contains indium (In), and for example, indium oxide is preferred. When the metal oxide in the channel-forming region is an indium-containing metal oxide, the carrier mobility (electron mobility) of the OS transistor is increased. Furthermore, the metal oxide in the channel-forming region is preferably an oxide semiconductor containing element M. 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, multiple elements mentioned above may be combined as element M. Element M is, for example, an element with a high bond energy with oxygen. For example, it is an element whose bonding energy with oxygen is higher than that of indium. Furthermore, the metal oxide containing the channel-forming region is preferably a metal oxide containing zinc (Zn). Zinc-containing metal oxides may be more prone to crystallization.

[0179] The metal oxides present in the channel-forming regions are not limited to indium-containing metal oxides. For example, the metal oxides present in the channel-forming regions may be zinc-tin oxides, gallium-tin oxides, or other metal oxides that do not contain indium but contain zinc, gallium, or tin.

[0180] The processing unit 130 may, for example, have an arithmetic circuit. The processing unit 130 may, for example, have a central processing unit (CPU). Furthermore, the processing unit 130 may have a graphics processing unit (GPU).

[0181] The processing unit 130 may have a microprocessor such as a DSP (Digital Signal Processor). The microprocessor may be implemented using a PLD (Programmable Logic Device) such as an FPGA (Field Programmable Gate Array) or 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 processor's memory area and the storage unit 120.

[0182] The processing unit 130 may have main memory. The main memory includes at least one of volatile memory such as RAM (Random Access Memory) and non-volatile memory such as ROM (Read Only Memory). The main memory may also include at least one of the above-mentioned NOSRAM and DOSRAM.

[0183] For RAM, for example, DRAM or SRAM is used, and a memory space is virtually allocated and used as a workspace for the processing unit 130. The operating system, application programs, program modules, program data, lookup tables, etc., stored in the storage unit 120 are loaded into RAM for execution. These data, programs, and program modules loaded into RAM are directly accessed and manipulated by the processing unit 130.

[0184] ROM can store BIOS (Basic Input / Output System), firmware, and other data that does 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-EPROM (Ultra-Violet Erasable Programmable Read Only Memory), which allows data to be erased by ultraviolet irradiation, EEPROM (Electrically Erasable Programmable Read Only Memory), and flash memory.

[0185] The processing unit 130 may have either or both an OS transistor and a transistor having silicon in its channel formation region (Si transistor).

[0186] The processing unit 130 preferably has an OS transistor. Because the OS transistor has an extremely small off-current, using the OS transistor as a switch to hold the charge (data) that has flowed into a capacitive element that functions as a memory element ensures that the data can be retained for a long period of time. If at least one of the registers and cache memory of the processing unit 130 has this characteristic, the processing unit 130 can be operated only when necessary, and in other cases the information of the previous processing is saved to the memory element and the processing unit 130 can be turned off. In other words, normally-off computing becomes possible, and the power consumption of the information processing system can be reduced.

[0187] Network 30 can, for example, use the Internet, which is the foundation of the World Wide Web (WWW), as a global network. Network 30 can also use a local network. Furthermore, an intranet or extranet can be used as network 30. In addition, PAN (Personal Area Network), LAN (Local Area Network), CAN (Campus Area Network), MAN (Metropolitan Area Network), WAN (Wide Area Network), GAN (Global Area Network), etc., can be used as network 30.

[0188] When a service provider using an information processing method according to one aspect of the present invention and a user enjoying the service belong to the same organization, such as a company, it is preferable that data transmission and reception between the information terminal 20 and the information processing device 10 be performed, for example, using a network established within that organization. This allows for more secure data transmission and reception between the information terminal 20 and the information processing device 40 compared to transmission via the Internet. Furthermore, it prevents the leakage of confidential information within the organization to the outside.

[0189] When performing wireless communication, communication protocols or technologies that can be used include communication standards such as the 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), and 6th generation mobile communication system (6G), or specifications standardized by the IEEE (Institute of Electrical and Electronics Engineers), such as Wi-Fi® and Bluetooth®.

[0190] 10: Information processing device, 20: Information terminal, 20a: Desktop computer, 20b: Notebook computer, 20c: Smartphone, 20d: Tablet computer, 21: Enclosure, 30: Network, 40: Information processing device, 110: Reception unit, 120: Storage unit, 130: Processing unit, 140: Output unit, 150: Transmission line, 201: Check box, 203: Button, 211[1]: Differences, 211[2]: Differences, 211[ 3]: Differences, 211: Differences, 213: Button, 214: Button, 215[1]: Differences, 215[2]: Differences, 215: Differences, 217: Button, 221: Form, 223: Button, 231: Document, 233: Button, 235: Form, 237: Button, 239: Area, 241[1]: Information, 241[2]: Information, 241[3]: Information, 241: Information, 242: Button, 243: Form, 245: Button, 246: Button

Claims

The process comprises a first to a twelfth step, In the first step described above, the first document and the second document are received, In the second step, a first prompt for generating a summary of the second document is created and sent to the language model. In the third step, a second prompt is created to present the differences in the first document compared to the summary and sent to the language model. In the fourth step described above, a judgment is made as to whether the differences are valid or not. If the aforementioned differences are not valid, in the fifth step, the first instruction document is received, and in the sixth step, a third prompt is created based on the first instruction document to re-present the aforementioned differences in the first document and sent to the language model, and then the fourth step is performed. If the differences are valid, in the seventh step, a fourth prompt is generated and sent to the language model to confirm that all of the differences are not described in the second document. If at least some of the differences are described in the second document, then proceed to step 5. If all of the aforementioned differences are not described in the second document, in the eighth step, create the second document and a fifth prompt for generating a third document based on the aforementioned differences and send it to the language model. In step 9 above, the third document accepts a determination as to whether or not it needs to be modified. If the aforementioned modification is necessary, in step 10, a second instruction document is received, and in step 11, a sixth prompt for modifying the third document based on the second instruction document is created and sent to the language model, and then step 9 is performed. If the aforementioned modification is not necessary, the information processing method outputs the third document in the twelfth step. 　 In claim 1, The first instruction document includes at least one of instructions for modifying the first document and comments regarding the differences, The second instruction document is an information processing method comprising at least one of instructions for modifying the third document and comments relating to the third document. 　 In claim 1, The process comprises steps 13 through 15, If all of the aforementioned differences are not described in the second document, in the 13th step, before the 8th step, a 7th prompt is created and sent to the language model to determine whether there is insufficient information to create the third document. If the aforementioned information is insufficient, in step 14, after receiving additional information, in step 15, the prompt in step 7 is recreated including the additional information and sent to the language model. If the aforementioned information is not lacking, the information processing method proceeds to the eighth step. 　 In any one of claims 1 to 3, The first document and the second document are information processing methods that are documents indicating creation. 　 In claim 4, The second document mentioned above is a patent document or a utility model document. The third document is an information processing method which is a specification belonging to a patent application or a specification belonging to a utility model registration application. 　 It has a reception unit, an output unit, and a processing unit. The reception unit has the function of receiving the first document, the second document, the first instruction document, and the second instruction document. The output unit has the function of supplying a first prompt, a second prompt, a third prompt, a fourth prompt, a fifth prompt, and a sixth prompt to the language model. The output unit has the function of outputting a third document, The aforementioned processing unit, A process for creating the first prompt for generating a summary of the second document, A process for creating a second prompt to present the differences in the first document compared to the summary, A process to allow the user to determine whether the aforementioned differences are valid or not, If the aforementioned differences are not valid, the process of creating a third prompt to re-present the aforementioned differences in the first document based on the first instruction document, If the aforementioned differences are valid, the process of creating a fourth prompt to confirm that not all of the aforementioned differences are described in the second document, If at least some of the differences are described in the second document, the process of creating the third prompt based on the first instruction document, If all of the aforementioned differences are not described in the second document, the process of creating the second document and the fifth prompt for generating the third document based on the aforementioned differences, The process involves allowing the user to determine whether the third document needs to be modified, An information processing device having the function of creating a sixth prompt for modifying the third document based on the second instruction document when such modification is necessary. 　 In claim 6, The first instruction document includes at least one of instructions for modifying the first document and comments regarding the differences, The second instruction document includes at least one of instructions for modifying the third document and comments relating to the third document. 　 In claim 6, The aforementioned reception unit has a function to receive additional information, The output unit has the function of supplying a seventh prompt to the language model. The processing unit includes a process for creating a seventh prompt to determine whether there is insufficient information to create the third document if not all of the differences are described in the second document, If the aforementioned information is insufficient, the process involves creating the seventh prompt again, including the aforementioned additional information. An information processing device having the function of creating the fifth prompt if the aforementioned information is not lacking. 　 In any one of claims 6 to 8, The first document and the second document are information processing devices that are documents indicating creation. 　 In claim 9, The second document mentioned above is a patent document or a utility model document. The third document is an information processing device, which is a specification belonging to a patent application or a specification belonging to a utility model registration application.

Images