System

Abstract

An object of a system according to an embodiment is to improve the efficiency of proofreading work of documents such as securities reports and quarterly reports.SOLUTION: A system includes an analysis part, an error detection part, and a correction proposal part. An analysis part analyzes the contents of a securities report, a quarterly report, a document based on corporate law, and an English disclosed document. The error detection unit detects an error or inconsistency from the content of the document analyzed by the analysis unit. The correction proposal unit makes a correction proposal for the error or inconsistency detected by the error detection unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem that proofreading documents such as securities reports and quarterly reports requires a significant amount of man-hours.

[0005] The system according to the embodiment aims to improve the efficiency of proofreading documents such as securities reports and quarterly reports. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, an error detection unit, and a correction suggestion unit. The analysis unit analyzes the contents of securities reports, quarterly reports, documents based on the Companies Act, and English disclosure documents. The error detection unit detects errors or inconsistencies in the contents of the documents analyzed by the analysis unit. The correction suggestion unit proposes corrections to errors or inconsistencies detected by the error detection unit. [Effects of the Invention]

[0007] The system according to the embodiment can improve the efficiency of proofreading documents such as securities reports and quarterly reports. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The proofreading system according to an embodiment of the present invention utilizes a generative AI to proofread securities reports, quarterly reports, documents required by the Companies Act, and English disclosure documents. This system uses a generative AI to analyze the content of these documents, detect errors and inconsistencies, and propose corrections. This reduces the burden of traditional manual proofreading work, enabling efficient and accurate proofreading.

[0029] A proofreading system according to an embodiment includes an analysis unit, an error detection unit, and a correction suggestion unit. The analysis unit analyzes the content of securities reports, quarterly reports, documents required by the Companies Act, and English disclosure documents. For example, the analysis unit analyzes text data of documents input by a user to detect grammatical errors, numerical inconsistencies, and statutory deficiencies. The error detection unit detects errors or inconsistencies from the content of the documents analyzed by the analysis unit. For example, the error detection unit detects grammatical errors and numerical inconsistencies. The error detection unit can also detect statutory deficiencies. The correction suggestion unit proposes corrections for errors and inconsistencies detected by the error detection unit. For example, the correction suggestion unit proposes correcting grammatical errors to correct grammar. The correction suggestion unit can also propose correct numerical values ​​for numerical inconsistencies. Furthermore, the correction suggestion unit can propose appropriate statutory deficiencies. This allows the proofreading system to streamline document proofreading and significantly reduce work hours. For example, proofreading work that previously took several hours can now be completed in just a few minutes by using generative AI, improving work efficiency and allowing resources to be allocated to other important tasks.

[0030] The error detection unit can improve the accuracy of error detection by learning past error patterns based on a database of similar past documents. For example, when the generation AI analyzes the contents of a document, the error detection unit refers to a database of similar past documents and learns past error patterns to improve the accuracy of error detection. For example, similar errors are detected based on error data from past securities reports and quarterly reports. The generation AI also refers to a database of similar past documents and learns error patterns to detect errors specific to a specific industry or company. For example, it learns errors that frequently appear in reports from a specific company and detects similar errors. The generation AI also refers to a database of similar past documents and learns error patterns to discover new error patterns and improve the accuracy of future error detection. For example, new error patterns can be identified based on past data and used for future error detection. In this way, learning past error patterns improves the accuracy of error detection.

[0031] The error detection unit can understand context and perform error detection based on the context. For example, when the generation AI analyzes the contents of a document, the error detection unit understands the context and performs error detection based on the context. For example, it detects the misuse of specific industry jargon or technical terms. For example, in a report for the financial industry, it detects the misuse of specific financial terminology. Furthermore, when the generation AI understands context and performs error detection based on the context, it becomes possible to detect errors that take into account the flow and meaning of the entire sentence. For example, it detects grammatical errors and unnatural expressions based on the context. Furthermore, when the generation AI understands context and performs error detection based on the context, it becomes possible to detect errors that take into account the context specific to a specific industry or company. For example, in a report for a specific company, it detects errors based on the company's specific context. This makes error detection based on the context possible.

[0032] The analysis unit can accept voice input or handwritten input and convert it into text data for analysis. In the analysis unit, for example, the generation AI accepts voice input and converts the voice data into text data for analysis. For example, it automatically converts what a user has input by voice into text and performs error detection. The generation AI also accepts handwritten input and converts the handwritten data into text data for analysis. For example, it automatically converts what a user has input by hand into text and performs error detection. When converting voice input or handwritten input into text data, the generation AI understands the context and performs error detection based on the context. For example, it identifies errors by taking into account the context of the voice or handwriting. This allows the voice input or handwritten input to be converted into text data for analysis.

[0033] The analysis unit can simultaneously analyze documents in different languages ​​and detect inconsistencies between languages ​​or translation errors. In the analysis unit, for example, the generation AI simultaneously analyzes documents in different languages ​​and detects inconsistencies between languages. For example, it simultaneously analyzes Japanese and English reports to check whether the content matches. The generation AI also analyzes documents in different languages ​​and detects translation errors. For example, it identifies mistranslations and unnatural expressions in translations from English to Japanese. Furthermore, when analyzing documents in different languages, the generation AI understands the context and detects inconsistencies between languages ​​or translation errors based on the context. For example, it suggests an appropriate translation based on the context. This makes it possible to simultaneously analyze documents in different languages ​​and detect inconsistencies between languages ​​or translation errors.

[0034] The error detection unit can detect grammatical errors by taking into account not only grammatical rules but also the style and tone of the sentence. For example, when the generation AI detects grammatical errors, the error detection unit detects errors by taking into account not only grammatical rules but also the style and tone of the sentence. For example, it identifies errors that are intended to maintain an appropriate tone in a formal document. Furthermore, when the generation AI detects grammatical errors, it identifies errors by taking into account the flow and meaning of the entire sentence. For example, it detects grammatical errors and unnatural expressions based on context. Furthermore, when the generation AI detects grammatical errors, it identifies errors by taking into account the style and tone specific to a particular industry or company. For example, in a report for a particular company, it detects errors based on the company's specific style. This allows errors to be detected by taking into account not only grammatical rules but also the style and tone of the sentence.

[0035] When detecting a numerical inconsistency, the error detection unit can determine whether the numerical value is realistic based on past data and the market data. For example, when the generation AI detects a numerical inconsistency, the error detection unit refers to past data to determine whether the numerical value is realistic. For example, the error detection unit checks the consistency of the numerical value based on data from past quarterly reports. The generation AI also refers to market data to detect a numerical inconsistency. For example, the generation AI determines whether the numerical value in the report is realistic based on current market trends and economic indicators. Furthermore, when referring to past data and market data, the generation AI understands the context and detects numerical inconsistencies based on the context. For example, the consistency of the numerical value is checked taking into account the context of a specific industry or company. This makes it possible to detect numerical inconsistencies by referring to past data and market data.

[0036] When detecting deficiencies in the description based on laws and regulations, the error detection unit can respond to changes in the laws and regulations based on the latest laws and regulations database in real time. For example, when the generation AI detects deficiencies in the description based on laws and regulations, the error detection unit refers to the latest laws and regulations database in real time and responds to changes in laws and regulations. For example, the error detection unit checks the contents of the report based on the latest laws and regulations. Furthermore, the generation AI refers to the laws and regulations database in real time and responds to changes in laws and regulations, thereby quickly identifying deficiencies in the description based on laws and regulations. For example, the error detection unit corrects the contents of the report based on the latest laws and regulations. Furthermore, when referring to the latest laws and regulations database, the generation AI understands the context and confirms the application of laws and regulations based on the context. For example, the error detection unit checks the contents of the report based on changes in laws and regulations, taking into account the laws and regulations that apply to a specific industry or company. This makes it possible to refer to the latest laws and regulations database in real time and respond to changes in laws and regulations.

[0037] When detecting grammatical errors and numerical inconsistencies, the error detection unit can detect industry-specific errors based on the standards and guidelines of different industries. For example, the generation AI refers to standards and guidelines of different industries to detect grammatical errors and numerical inconsistencies. For example, the generation AI identifies errors in reports based on financial industry standards. The generation AI also refers to industry-specific guidelines to detect grammatical errors and numerical inconsistencies. For example, the generation AI identifies errors in reports based on medical industry guidelines. When referring to standards and guidelines of different industries, the generation AI understands the context and detects errors based on the context. For example, the generation AI identifies errors taking into account the context of a specific industry. This makes it possible to detect industry-specific errors by referring to standards and guidelines of different industries.

[0038] When analyzing the contents of a document, the analysis unit can also analyze the images and charts, and detect inconsistencies in the text and numbers within the images. For example, when the generation AI analyzes the contents of a document, the analysis unit can also analyze images and charts, and detect inconsistencies in the text and numbers within the images. For example, the analysis unit can analyze the numbers in graphs and tables included in a report and check whether they match the text data. The generation AI can also use image recognition technology to extract text within images and detect grammatical errors and inconsistencies in numbers. For example, the generation AI can extract text from scanned document images and identify errors. The generation AI can also analyze numbers within charts and check whether they match the text data. For example, the analysis unit can check whether the numbers in the body of a report match the text in a chart. This allows the analysis of images and charts to detect inconsistencies in the text and numbers within the images.

[0039] When making correction suggestions, the correction suggestion unit can present multiple correction suggestions and allow the user to select from them. For example, when the generation AI makes correction suggestions, the correction suggestion unit presents multiple correction suggestions and allows the user to select from them. For example, it presents grammatical correction suggestions, stylistic correction suggestions, tone correction suggestions, etc. Furthermore, when the generation AI makes correction suggestions, it presents correction suggestions that match the user's preferences. For example, it refers to past correction history and reflects the user's preferred correction style. Furthermore, when the generation AI makes correction suggestions, it explains the advantages and disadvantages of the correction suggestions and allows the user to select the most appropriate one. For example, it explains the impact of each correction suggestion. In this way, multiple correction suggestions are presented and the user can select from them.

[0040] The correction suggestion unit can present the correction suggestion that matches the user's preferences based on the past correction history. For example, when the generation AI makes a correction suggestion, the correction suggestion unit refers to the past correction history and presents a correction suggestion that matches the user's preferences. For example, the suggestion is made based on the correction style selected by the user in the past. Furthermore, the generation AI refers to the past correction history and learns the user's correction tendencies, thereby presenting a more appropriate correction suggestion. For example, the expression and style preferred by the user are reflected. Furthermore, when the generation AI makes a correction suggestion, the suggestion unit preferentially presents a correction suggestion that matches the user's preferences based on the past correction history. For example, the suggestion suggestion that the user frequently selects is preferentially displayed. In this way, the suggestion suggestion can be presented that matches the user's preferences by referring to the past correction history.

[0041] The revision suggestion unit can simultaneously present revision suggestions in the different languages, making revisions from an international perspective. For example, when the generation AI makes revision suggestions, the revision suggestion unit simultaneously presents revision suggestions in different languages, making revisions from an international perspective. For example, revision suggestions in Japanese and English are presented simultaneously. Furthermore, the generation AI presents revision suggestions in different languages, making revisions from an international perspective. For example, it presents appropriate revision suggestions for an English report. Furthermore, when presenting revision suggestions in different languages, the generation AI understands the context and presents revision suggestions based on the context. For example, it presents revision suggestions taking into account the context of a specific industry or company. This makes it possible to simultaneously present revision suggestions in different languages ​​and make revisions from an international perspective.

[0042] The correction suggestion unit can cause the generation AI to automatically apply the correction when making the correction suggestion, so that the user only needs to confirm it. For example, the correction suggestion unit automatically applies the correction when the generation AI makes a correction suggestion, so that the user only needs to confirm it. For example, grammatical errors and numerical inconsistencies are automatically corrected. Furthermore, the generation AI automatically applies corrections, thereby reducing the user's effort. For example, deficiencies in descriptions required by laws and regulations are automatically corrected. Furthermore, when automatically applying corrections, the generation AI understands the context and makes corrections based on the context. For example, corrections are made taking into account the context of a specific industry or company. In this way, the generation AI automatically applies corrections, so that the user only needs to confirm them.

[0043] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0044] When analyzing the contents of a document, the analysis unit also analyzes the document's structure and layout, making it possible to detect layout inconsistencies and visual errors. For example, the generation AI analyzes the document's layout and identifies misaligned paragraphs and font inconsistencies. The generation AI also analyzes the document's structure and detects inconsistencies in headings and bullet points. For example, it identifies cases where the heading hierarchy is incorrect or where bullet points are improperly positioned. The generation AI also analyzes the document's visual elements and detects inconsistencies in the placement of images and charts. For example, it identifies cases where images are not placed in the appropriate position or charts are not displayed correctly. This makes it possible to detect inconsistencies in the document's structure and layout.

[0045] The error detection unit can learn from past user errors based on the user's input history and provide advance warning of similar errors. For example, the generation AI analyzes the user's past input history to identify frequently occurring errors. The generation AI can also provide advance warning of specific grammatical errors or numerical inconsistencies based on the user's input history. For example, it can learn the grammatical or numerical patterns that the user frequently made in the past and display a warning when a similar error is entered. The generation AI can also provide advance warning of errors specific to a particular industry or company based on the user's input history. For example, in a specific company's reports, it can learn the company's specific error patterns and display a warning when a similar error is entered. This allows advance warning of errors based on the user's past input history.

[0046] When analyzing the content of a document, the analysis unit can consider the document's purpose and target audience and suggest an appropriate tone and style. For example, the generation AI analyzes the purpose of a document and suggests an appropriate formal tone for a formal document. The generation AI also analyzes the document's target audience and suggests a style suitable for a specific industry or company. For example, it suggests appropriate technical terms and expressions for financial industry reports. The generation AI also analyzes the content of a document and suggests a tone and style that suits the specific purpose. For example, it suggests an appropriate persuasive tone for marketing materials. This makes it possible to suggest an appropriate tone and style that takes into account the document's purpose and target audience.

[0047] When analyzing the contents of a document, the analysis unit also analyzes the visual elements of the document, making it possible to detect visual errors and inconsistencies. For example, the generation AI analyzes the visual elements of the document to identify inconsistencies in the placement of images and charts. The generation AI also analyzes the visual elements of the document to detect inconsistencies in fonts and colors. For example, it identifies cases where different fonts or colors are used. The generation AI also analyzes the visual elements of the document to detect inconsistencies in layout. For example, it identifies misaligned paragraphs and inconsistent margins. This makes it possible to detect errors and inconsistencies in the visual elements of the document.

[0048] When analyzing the content of a document, the analysis unit can consider the document's purpose and target audience and suggest an appropriate tone and style. For example, the generation AI analyzes the purpose of a document and suggests an appropriate formal tone for a formal document. The generation AI also analyzes the document's target audience and suggests a style suitable for a specific industry or company. For example, it suggests appropriate technical terms and expressions for financial industry reports. The generation AI also analyzes the content of a document and suggests a tone and style that suits the specific purpose. For example, it suggests an appropriate persuasive tone for marketing materials. This makes it possible to suggest an appropriate tone and style that takes into account the document's purpose and target audience.

[0049] When analyzing the contents of a document, the analysis unit also analyzes the visual elements of the document, making it possible to detect visual errors and inconsistencies. For example, the generation AI analyzes the visual elements of the document to identify inconsistencies in the placement of images and charts. The generation AI also analyzes the visual elements of the document to detect inconsistencies in fonts and colors. For example, it identifies cases where different fonts or colors are used. The generation AI also analyzes the visual elements of the document to detect inconsistencies in layout. For example, it identifies misaligned paragraphs and inconsistent margins. This makes it possible to detect errors and inconsistencies in the visual elements of the document.

[0050] The processing flow of the first embodiment will be briefly explained below.

[0051] Step 1: The analysis unit analyzes the contents of securities reports, quarterly reports, documents required by the Companies Act, and English disclosure documents. For example, the analysis unit analyzes the text data of documents entered by the user to detect grammatical errors, numerical inconsistencies, and deficiencies in descriptions required by law. Step 2: The error detection unit detects errors or inconsistencies in the document content analyzed by the analysis unit. For example, the error detection unit detects grammatical errors and numerical inconsistencies. The error detection unit can also detect deficiencies in descriptions required by law. Step 3: The correction suggestion unit makes correction suggestions for errors and inconsistencies detected by the error detection unit. For example, the correction suggestion unit suggests correcting grammatical errors to correct grammar. The correction suggestion unit can also suggest correct numerical values ​​for numerical inconsistencies. Furthermore, the correction suggestion unit can also suggest appropriate legally compliant descriptions for deficiencies in legally compliant descriptions.

[0052] (Example 2) The proofreading system according to an embodiment of the present invention utilizes a generative AI to proofread securities reports, quarterly reports, documents required by the Companies Act, and English disclosure documents. This system uses a generative AI to analyze the content of these documents, detect errors and inconsistencies, and propose corrections. This reduces the burden of traditional manual proofreading work, enabling efficient and accurate proofreading.

[0053] A proofreading system according to an embodiment includes an analysis unit, an error detection unit, and a correction suggestion unit. The analysis unit analyzes the content of securities reports, quarterly reports, documents required by the Companies Act, and English disclosure documents. For example, the analysis unit analyzes text data of documents input by a user to detect grammatical errors, numerical inconsistencies, and statutory deficiencies. The error detection unit detects errors or inconsistencies from the content of the documents analyzed by the analysis unit. For example, the error detection unit detects grammatical errors and numerical inconsistencies. The error detection unit can also detect statutory deficiencies. The correction suggestion unit proposes corrections for errors and inconsistencies detected by the error detection unit. For example, the correction suggestion unit proposes correcting grammatical errors to correct grammar. The correction suggestion unit can also propose correct numerical values ​​for numerical inconsistencies. Furthermore, the correction suggestion unit can propose appropriate statutory deficiencies. This allows the proofreading system to streamline document proofreading and significantly reduce work hours. For example, proofreading work that previously took several hours can now be completed in just a few minutes by using generative AI, improving work efficiency and allowing resources to be allocated to other important tasks.

[0054] The error detection unit can improve the accuracy of error detection by learning past error patterns based on a database of similar past documents. For example, when the generation AI analyzes the contents of a document, the error detection unit refers to a database of similar past documents and learns past error patterns to improve the accuracy of error detection. For example, similar errors are detected based on error data from past securities reports and quarterly reports. The generation AI also refers to a database of similar past documents and learns error patterns to detect errors specific to a specific industry or company. For example, it learns errors that frequently appear in reports from a specific company and detects similar errors. The generation AI also refers to a database of similar past documents and learns error patterns to discover new error patterns and improve the accuracy of future error detection. For example, new error patterns can be identified based on past data and used for future error detection. In this way, learning past error patterns improves the accuracy of error detection.

[0055] The error detection unit can understand context and perform error detection based on the context. For example, when the generation AI analyzes the contents of a document, the error detection unit understands the context and performs error detection based on the context. For example, it detects the misuse of specific industry jargon or technical terms. For example, in a report for the financial industry, it detects the misuse of specific financial terminology. Furthermore, when the generation AI understands context and performs error detection based on the context, it becomes possible to detect errors that take into account the flow and meaning of the entire sentence. For example, it detects grammatical errors and unnatural expressions based on the context. Furthermore, when the generation AI understands context and performs error detection based on the context, it becomes possible to detect errors that take into account the context specific to a specific industry or company. For example, in a report for a specific company, it detects errors based on the company's specific context. This makes error detection based on the context possible.

[0056] The error detection unit can use the emotion estimation function to analyze the emotional impact that the document content has on the user and detect statements that evoke negative emotions. For example, the generative AI in the error detection unit uses the emotion estimation function to analyze the emotional impact that the document content has on the user and detect statements that may evoke negative emotions. For example, it identifies negative expressions and statements that incite anxiety. It also uses the emotion estimation function to analyze the emotional impact that the document content has on the user and emphasizes statements that evoke positive emotions. For example, it emphasizes expressions that give a sense of security and positive messages. It also uses the emotion estimation function to analyze the emotional impact that the document content has on the user and makes suggestions for corrections to maintain emotional balance. For example, it suggests replacing negative statements with positive expressions. This enables error detection that takes into account the emotional impact on the user.

[0057] The analysis unit can accept voice input or handwritten input and convert it into text data for analysis. In the analysis unit, for example, the generation AI accepts voice input and converts the voice data into text data for analysis. For example, it automatically converts what a user has input by voice into text and performs error detection. The generation AI also accepts handwritten input and converts the handwritten data into text data for analysis. For example, it automatically converts what a user has input by hand into text and performs error detection. When converting voice input or handwritten input into text data, the generation AI understands the context and performs error detection based on the context. For example, it identifies errors by taking into account the context of the voice or handwriting. This allows the voice input or handwritten input to be converted into text data for analysis.

[0058] The analysis unit can simultaneously analyze documents in different languages ​​and detect inconsistencies between languages ​​or translation errors. In the analysis unit, for example, the generation AI simultaneously analyzes documents in different languages ​​and detects inconsistencies between languages. For example, it simultaneously analyzes Japanese and English reports to check whether the content matches. The generation AI also analyzes documents in different languages ​​and detects translation errors. For example, it identifies mistranslations and unnatural expressions in translations from English to Japanese. Furthermore, when analyzing documents in different languages, the generation AI understands the context and detects inconsistencies between languages ​​or translation errors based on the context. For example, it suggests an appropriate translation based on the context. This makes it possible to simultaneously analyze documents in different languages ​​and detect inconsistencies between languages ​​or translation errors.

[0059] The error detection unit can detect grammatical errors by taking into account not only grammatical rules but also the style and tone of the sentence. For example, when the generation AI detects grammatical errors, the error detection unit detects errors by taking into account not only grammatical rules but also the style and tone of the sentence. For example, it identifies errors that are intended to maintain an appropriate tone in a formal document. Furthermore, when the generation AI detects grammatical errors, it identifies errors by taking into account the flow and meaning of the entire sentence. For example, it detects grammatical errors and unnatural expressions based on context. Furthermore, when the generation AI detects grammatical errors, it identifies errors by taking into account the style and tone specific to a particular industry or company. For example, in a report for a particular company, it detects errors based on the company's specific style. This allows errors to be detected by taking into account not only grammatical rules but also the style and tone of the sentence.

[0060] When detecting a numerical inconsistency, the error detection unit can determine whether the numerical value is realistic based on past data and the market data. For example, when the generation AI detects a numerical inconsistency, the error detection unit refers to past data to determine whether the numerical value is realistic. For example, the error detection unit checks the consistency of the numerical value based on data from past quarterly reports. The generation AI also refers to market data to detect a numerical inconsistency. For example, the generation AI determines whether the numerical value in the report is realistic based on current market trends and economic indicators. Furthermore, when referring to past data and market data, the generation AI understands the context and detects numerical inconsistencies based on the context. For example, the consistency of the numerical value is checked taking into account the context of a specific industry or company. This makes it possible to detect numerical inconsistencies by referring to past data and market data.

[0061] When detecting deficiencies in the description based on laws and regulations, the error detection unit can respond to changes in the laws and regulations based on the latest laws and regulations database in real time. For example, when the generation AI detects deficiencies in the description based on laws and regulations, the error detection unit refers to the latest laws and regulations database in real time and responds to changes in laws and regulations. For example, the error detection unit checks the contents of the report based on the latest laws and regulations. Furthermore, the generation AI refers to the laws and regulations database in real time and responds to changes in laws and regulations, thereby quickly identifying deficiencies in the description based on laws and regulations. For example, the error detection unit corrects the contents of the report based on the latest laws and regulations. Furthermore, when referring to the latest laws and regulations database, the generation AI understands the context and confirms the application of laws and regulations based on the context. For example, the error detection unit checks the contents of the report based on changes in laws and regulations, taking into account the laws and regulations that apply to a specific industry or company. This makes it possible to refer to the latest laws and regulations database in real time and respond to changes in laws and regulations.

[0062] When detecting grammatical errors and numerical inconsistencies, the error detection unit can detect industry-specific errors based on the standards and guidelines of different industries. For example, the generation AI refers to standards and guidelines of different industries to detect grammatical errors and numerical inconsistencies. For example, the generation AI identifies errors in reports based on financial industry standards. The generation AI also refers to industry-specific guidelines to detect grammatical errors and numerical inconsistencies. For example, the generation AI identifies errors in reports based on medical industry guidelines. When referring to standards and guidelines of different industries, the generation AI understands the context and detects errors based on the context. For example, the generation AI identifies errors taking into account the context of a specific industry. This makes it possible to detect industry-specific errors by referring to standards and guidelines of different industries.

[0063] When analyzing the contents of a document, the analysis unit can also analyze the images and charts, and detect inconsistencies in the text and numbers within the images. For example, when the generation AI analyzes the contents of a document, the analysis unit can also analyze images and charts, and detect inconsistencies in the text and numbers within the images. For example, the analysis unit can analyze the numbers in graphs and tables included in a report and check whether they match the text data. The generation AI can also use image recognition technology to extract text within images and detect grammatical errors and inconsistencies in numbers. For example, the generation AI can extract text from scanned document images and identify errors. The generation AI can also analyze numbers within charts and check whether they match the text data. For example, the analysis unit can check whether the numbers in the body of a report match the text in a chart. This allows the analysis of images and charts to detect inconsistencies in the text and numbers within the images.

[0064] The analysis unit can analyze the emotions of the user when entering the document and make the suggestion to elicit the positive emotions. For example, the analysis unit uses an emotion estimation function of a generation AI to analyze the emotions of the user when entering the document and make suggestions to elicit positive emotions. For example, it displays an encouraging message so that the user can continue entering the document with a positive attitude. Furthermore, it uses the emotion estimation function to analyze the emotions of the user when entering the document in real time and provides an interface to elicit positive emotions. For example, it displays appropriate encouragement or praise according to the input content. Furthermore, it uses the emotion estimation function to analyze the emotions of the user when entering the document and provides feedback to reduce stress. For example, it provides advice to relax if the user is feeling stressed. In this way, it is possible to make suggestions to elicit positive emotions from the user.

[0065] When making correction suggestions, the correction suggestion unit can present multiple correction suggestions and allow the user to select from them. For example, when the generation AI makes correction suggestions, the correction suggestion unit presents multiple correction suggestions and allows the user to select from them. For example, it presents grammatical correction suggestions, stylistic correction suggestions, tone correction suggestions, etc. Furthermore, when the generation AI makes correction suggestions, it presents correction suggestions that match the user's preferences. For example, it refers to past correction history and reflects the user's preferred correction style. Furthermore, when the generation AI makes correction suggestions, it explains the advantages and disadvantages of the correction suggestions and allows the user to select the most appropriate one. For example, it explains the impact of each correction suggestion. In this way, multiple correction suggestions are presented and the user can select from them.

[0066] The correction suggestion unit can present the correction suggestion that matches the user's preferences based on the past correction history. For example, when the generation AI makes a correction suggestion, the correction suggestion unit refers to the past correction history and presents a correction suggestion that matches the user's preferences. For example, the suggestion is made based on the correction style selected by the user in the past. Furthermore, the generation AI refers to the past correction history and learns the user's correction tendencies, thereby presenting a more appropriate correction suggestion. For example, the expression and style preferred by the user are reflected. Furthermore, when the generation AI makes a correction suggestion, the suggestion unit preferentially presents a correction suggestion that matches the user's preferences based on the past correction history. For example, the suggestion suggestion that the user frequently selects is preferentially displayed. In this way, the suggestion suggestion can be presented that matches the user's preferences by referring to the past correction history.

[0067] The revision suggestion unit can use the emotion estimation function to consider the emotional impact of the revision suggestion on the user and propose a revision suggestion that elicits positive emotions. For example, the generative AI uses the emotion estimation function to consider the emotional impact of the revision suggestion on the user and propose a revision suggestion that elicits positive emotions. For example, the revision suggestion unit enables the user to accept the revision with a positive feeling. Furthermore, the emotion estimation function is used to analyze the emotional impact of the revision suggestion on the user in real time and propose a revision suggestion that elicits positive emotions. For example, a revision suggestion that gives the user a sense of security is proposed. Furthermore, the emotion estimation function is used to consider the emotional impact of the revision suggestion on the user and propose a revision suggestion that reduces negative emotions. For example, a revision suggestion that does not cause the user stress is proposed. In this way, a revision suggestion that elicits positive emotions can be proposed in consideration of the emotional impact of the revision suggestion on the user.

[0068] The revision suggestion unit can simultaneously present revision suggestions in the different languages, making revisions from an international perspective. For example, when the generation AI makes revision suggestions, the revision suggestion unit simultaneously presents revision suggestions in different languages, making revisions from an international perspective. For example, revision suggestions in Japanese and English are presented simultaneously. Furthermore, the generation AI presents revision suggestions in different languages, making revisions from an international perspective. For example, it presents appropriate revision suggestions for an English report. Furthermore, when presenting revision suggestions in different languages, the generation AI understands the context and presents revision suggestions based on the context. For example, it presents revision suggestions taking into account the context of a specific industry or company. This makes it possible to simultaneously present revision suggestions in different languages ​​and make revisions from an international perspective.

[0069] The correction suggestion unit can cause the generation AI to automatically apply the correction when making the correction suggestion, so that the user only needs to confirm it. For example, the correction suggestion unit automatically applies the correction when the generation AI makes a correction suggestion, so that the user only needs to confirm it. For example, grammatical errors and numerical inconsistencies are automatically corrected. Furthermore, the generation AI automatically applies corrections, thereby reducing the user's effort. For example, deficiencies in descriptions required by laws and regulations are automatically corrected. Furthermore, when automatically applying corrections, the generation AI understands the context and makes corrections based on the context. For example, corrections are made taking into account the context of a specific industry or company. In this way, the generation AI automatically applies corrections, so that the user only needs to confirm them.

[0070] The revision suggestion unit can use the emotion estimation function to analyze the emotion of the user when accepting the revision suggestion in real time, and make the revision suggestion at the optimal timing. For example, the revision suggestion unit uses the emotion estimation function of a generation AI to analyze the emotion of the user when accepting the revision suggestion in real time, and make the revision suggestion at the optimal timing. For example, it determines the timing when the user can accept the revision with a positive feeling. Furthermore, it uses the emotion estimation function to analyze the emotion of the user when accepting the revision suggestion in real time, and make the revision suggestion at a timing that brings out positive emotions. For example, it makes the revision suggestion at a timing that makes the user feel relieved. Furthermore, it uses the emotion estimation function to analyze the emotion of the user when accepting the revision suggestion in real time, and make the revision suggestion at a timing that reduces negative emotions. For example, it makes the revision suggestion at a timing that the user does not feel stressed. In this way, it is possible to analyze the emotion of the user when accepting the revision suggestion in real time, and make the revision suggestion at the optimal timing.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] When analyzing the contents of a document, the analysis unit also analyzes the document's structure and layout, making it possible to detect layout inconsistencies and visual errors. For example, the generation AI analyzes the document's layout and identifies misaligned paragraphs and font inconsistencies. The generation AI also analyzes the document's structure and detects inconsistencies in headings and bullet points. For example, it identifies cases where the heading hierarchy is incorrect or where bullet points are improperly positioned. The generation AI also analyzes the document's visual elements and detects inconsistencies in the placement of images and charts. For example, it identifies cases where images are not placed in the appropriate position or charts are not displayed correctly. This makes it possible to detect inconsistencies in the document's structure and layout.

[0073] The error detection unit can learn from past user errors based on the user's input history and provide advance warning of similar errors. For example, the generation AI analyzes the user's past input history to identify frequently occurring errors. The generation AI can also provide advance warning of specific grammatical errors or numerical inconsistencies based on the user's input history. For example, it can learn the grammatical or numerical patterns that the user frequently made in the past and display a warning when a similar error is entered. The generation AI can also provide advance warning of errors specific to a particular industry or company based on the user's input history. For example, in a specific company's reports, it can learn the company's specific error patterns and display a warning when a similar error is entered. This allows advance warning of errors based on the user's past input history.

[0074] The error detection unit uses the emotion estimation function to analyze the emotions of the user when entering documents and can provide advance warning of errors that may cause negative emotions. For example, the generation AI uses the emotion estimation function to identify areas where errors are likely to occur when the user is feeling stressed. The emotion estimation function also identifies areas where errors are likely to occur when the user is feeling anxious. For example, the emotion estimation function provides advance warning of numerical or grammatical errors entered when the user is feeling anxious. The emotion estimation function also provides advance warning of areas where errors are likely to occur when the user is tired. For example, the content entered when the user is tired is analyzed and advance warning of areas where errors are likely to occur. This makes it possible to analyze the user's emotions and provide advance warning of errors that may cause negative emotions.

[0075] When analyzing the content of a document, the analysis unit can consider the document's purpose and target audience and suggest an appropriate tone and style. For example, the generation AI analyzes the purpose of a document and suggests an appropriate formal tone for a formal document. The generation AI also analyzes the document's target audience and suggests a style suitable for a specific industry or company. For example, it suggests appropriate technical terms and expressions for financial industry reports. The generation AI also analyzes the content of a document and suggests a tone and style that suits the specific purpose. For example, it suggests an appropriate persuasive tone for marketing materials. This makes it possible to suggest an appropriate tone and style that takes into account the document's purpose and target audience.

[0076] The error detection unit can use the emotion estimation function to analyze the emotions a user has when entering documents and provide feedback to elicit positive emotions. For example, the generation AI can use the emotion estimation function to display an encouraging message so that the user can continue entering documents with a positive attitude. The emotion estimation function can also be used to analyze the emotions a user has when entering documents in real time and provide an interface to elicit positive emotions. For example, appropriate words of encouragement or praise can be displayed according to the input content. The emotion estimation function can also be used to analyze the emotions a user has when entering documents and provide feedback to reduce stress. For example, advice can be given to relax if the user is feeling stressed. This makes it possible to provide feedback to elicit positive emotions from the user.

[0077] When analyzing the contents of a document, the analysis unit also analyzes the visual elements of the document, making it possible to detect visual errors and inconsistencies. For example, the generation AI analyzes the visual elements of the document to identify inconsistencies in the placement of images and charts. The generation AI also analyzes the visual elements of the document to detect inconsistencies in fonts and colors. For example, it identifies cases where different fonts or colors are used. The generation AI also analyzes the visual elements of the document to detect inconsistencies in layout. For example, it identifies misaligned paragraphs and inconsistent margins. This makes it possible to detect errors and inconsistencies in the visual elements of the document.

[0078] The error detection unit uses the emotion estimation function to analyze the emotions of the user when entering documents and can provide advance warning of errors that may cause negative emotions. For example, the generation AI uses the emotion estimation function to identify areas where errors are likely to occur when the user is feeling stressed. The emotion estimation function also identifies areas where errors are likely to occur when the user is feeling anxious. For example, the emotion estimation function provides advance warning of numerical or grammatical errors entered when the user is feeling anxious. The emotion estimation function also provides advance warning of areas where errors are likely to occur when the user is tired. For example, the content entered when the user is tired is analyzed and advance warning of areas where errors are likely to occur. This makes it possible to analyze the user's emotions and provide advance warning of errors that may cause negative emotions.

[0079] When analyzing the content of a document, the analysis unit can consider the document's purpose and target audience and suggest an appropriate tone and style. For example, the generation AI analyzes the purpose of a document and suggests an appropriate formal tone for a formal document. The generation AI also analyzes the document's target audience and suggests a style suitable for a specific industry or company. For example, it suggests appropriate technical terms and expressions for financial industry reports. The generation AI also analyzes the content of a document and suggests a tone and style that suits the specific purpose. For example, it suggests an appropriate persuasive tone for marketing materials. This makes it possible to suggest an appropriate tone and style that takes into account the document's purpose and target audience.

[0080] The error detection unit can use the emotion estimation function to analyze the emotions a user has when entering documents and provide feedback to elicit positive emotions. For example, the generation AI can use the emotion estimation function to display an encouraging message so that the user can continue entering documents with a positive attitude. The emotion estimation function can also be used to analyze the emotions a user has when entering documents in real time and provide an interface to elicit positive emotions. For example, appropriate words of encouragement or praise can be displayed according to the input content. The emotion estimation function can also be used to analyze the emotions a user has when entering documents and provide feedback to reduce stress. For example, advice can be given to relax if the user is feeling stressed. This makes it possible to provide feedback to elicit positive emotions from the user.

[0081] When analyzing the contents of a document, the analysis unit also analyzes the visual elements of the document, making it possible to detect visual errors and inconsistencies. For example, the generation AI analyzes the visual elements of the document to identify inconsistencies in the placement of images and charts. The generation AI also analyzes the visual elements of the document to detect inconsistencies in fonts and colors. For example, it identifies cases where different fonts or colors are used. The generation AI also analyzes the visual elements of the document to detect inconsistencies in layout. For example, it identifies misaligned paragraphs and inconsistent margins. This makes it possible to detect errors and inconsistencies in the visual elements of the document.

[0082] The processing flow of the second embodiment will be briefly explained below.

[0083] Step 1: The analysis unit analyzes the contents of securities reports, quarterly reports, documents required by the Companies Act, and English disclosure documents. For example, the analysis unit analyzes the text data of documents entered by the user to detect grammatical errors, numerical inconsistencies, and deficiencies in descriptions required by law. Step 2: The error detection unit detects errors or inconsistencies in the document content analyzed by the analysis unit. For example, the error detection unit detects grammatical errors and numerical inconsistencies. The error detection unit can also detect deficiencies in descriptions required by law. Step 3: The correction suggestion unit makes correction suggestions for errors and inconsistencies detected by the error detection unit. For example, the correction suggestion unit suggests correcting grammatical errors to correct grammar. The correction suggestion unit can also suggest correct numerical values ​​for numerical inconsistencies. Furthermore, the correction suggestion unit can also suggest appropriate legally compliant descriptions for deficiencies in legally compliant descriptions.

[0084] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0085] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0086] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0087] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0088] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0089] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0090] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0091] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0092] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0093] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0094] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0095] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0096] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0097] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0098] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0099] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0100] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0101] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0102] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0103] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0104] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0105] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0106] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0107] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0108] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0109] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0110] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0111] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0112] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0113] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0114] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0115] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0117] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0118] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0119] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0124] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0125] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0128] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0129] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0130] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0132] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0133] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0134] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0135] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0136] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0137] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0138] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0139] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0140] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0141] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0142] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0143] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0144] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0145] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0146] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0147] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0148] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0149] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0150] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0151] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A system equipped with a generative AI, An analysis department that analyzes the contents of securities reports, quarterly reports, documents based on the Companies Act, and English disclosure documents; an error detection unit that detects errors or inconsistencies in the content of the document analyzed by the analysis unit; a correction suggestion unit that suggests corrections to the errors or inconsistencies detected by the error detection unit. A system characterized by:

2. The error detection unit Based on a database of similar documents from the past, the accuracy of error detection is improved by learning the past error patterns.

2. The system of claim 1.

3. The analysis unit Accepts voice or handwritten input, converts it into text data, and analyzes it 2. The system of claim 1.

4. The modification suggestion unit When making a correction suggestion, multiple correction suggestions are presented and the user can select one.

2. The system of claim 1.

5. The error detection unit Analyzing the emotional impact of the content of the document on the user and detecting statements that evoke negative emotions 2. The system of claim 1.

Images