System

Abstract

An object of the system according to the embodiment is to perform consistency check of the regulations of a company based on the latest laws and efficiently update the regulations.SOLUTION: A system includes a consistency confirmation part, a draft preparation part, a before-and-after comparison part, a wrong / omitted character detection part, and a version management part. A consistency confirmation part refers to a law database and confirms the consistency of the regulations based on the latest laws of the regulations of the company. A draft preparation part automatically prepares the draft of the rule on the basis of the information confirmed by the matching confirmation part. The before-and-after comparison part compares the before and after of the draft generated by the draft generation part and clarifies a change point. The wrong / missing character detection unit detects a wrong / missing character based on the change point clarified by the before-and-after comparison unit. The version management unit corrects the wrong / missing character detected by the wrong / missing character detection unit and manages the version of the rule.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] With conventional technology, there were issues with verifying whether a company's regulations were based on the latest laws and regulations, and the process of updating regulations was time-consuming and laborious.

[0005] The system according to the embodiment aims to check the consistency of company regulations with the latest laws and regulations and to update them efficiently. [Means for solving the problem]

[0006] The system according to the embodiment includes a consistency checking unit, a draft creation unit, a context comparison unit, a typographical error detection unit, and a version management unit. The consistency checking unit refers to a legal database and checks the consistency of the company's regulations based on the latest laws and regulations. The draft creation unit automatically generates a draft of the regulations based on the information confirmed by the consistency checking unit. The context comparison unit compares the context of the draft created by the draft creation unit to clarify changes. The typographical error detection unit detects typos and omissions based on the changes clarified by the context comparison unit. The version management unit corrects typos and omissions detected by the typographical error detection unit and manages the versions of the regulations. [Effects of the Invention]

[0007] The system according to the embodiment can check whether company regulations are consistent with the latest laws and regulations and can update them efficiently. [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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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) A regulations management system according to an embodiment of the present invention is a system for streamlining company regulations management. This regulations management system includes a consistency check function that references a legal database to check whether the company's regulations comply with the latest laws and regulations, a draft creation function that automatically generates draft regulations, a before-and-after comparison function that compares the before and after of regulations to clarify changes, a typographical error detection function that detects typos, and a version management function that manages versions of regulations. For example, the regulations management system periodically updates the legal database and checks the consistency of regulations based on the latest laws and regulations. Next, the regulations management system learns from past regulations and legal data to generate optimal draft regulations. Furthermore, the regulations management system analyzes document differences and highlights changes. Next, the regulations management system analyzes regulations documents and automatically detects typos and omissions. Finally, the regulations management system automatically records the revision history of regulations, allowing past versions to be referenced as needed. This allows the regulations management system to streamline the regulations management process and support regulations management that require constant review and improvement. For example, compliance with laws and regulations is ensured and the effort required for creating regulations is significantly reduced. It also makes it easier to check revisions, improving document quality and streamlining the management of regulations.

[0029] A regulations management system according to an embodiment includes a consistency check unit, a draft creation unit, a context comparison unit, a typo / misspelling detection unit, and a version management unit. The consistency check unit references a legal database to check whether the company's regulations comply with the latest laws and regulations. For example, the consistency check unit periodically updates the legal database and checks the consistency of the regulations based on the latest laws and regulations. The draft creation unit learns from past regulations and legal data to generate optimal drafts. For example, the draft creation unit uses AI to automatically create drafts of new regulations. The context comparison unit analyzes differences between documents and highlights changes. For example, the context comparison unit displays regulations before and after revision side by side to clarify changes. The typo / misspelling detection unit analyzes regulations documents and automatically detects typos and omissions. For example, the typo / misspelling detection unit uses AI to highlight typos and omissions and prompt corrections. The version management unit automatically records the revision history of regulations, allowing users to refer to past versions as needed. For example, the version management unit automatically records the revision history of rules and organizes past versions. As a result, the rules management system according to the embodiment can streamline the rules management process and support rules management that requires constant review and improvement.

[0030] The consistency checking unit can periodically update the laws and regulations database and check the consistency of the regulations based on the latest laws and regulations. For example, the consistency checking unit can update the laws and regulations database monthly and check the consistency of the regulations based on the latest laws and regulations. The consistency checking unit can also automatically update the laws and regulations database. For example, the consistency checking unit can optimize the update frequency of the laws and regulations database depending on the user's industry or region. This allows the consistency of the regulations to be checked based on the latest laws and regulations.

[0031] The draft sentence creation unit can learn from past regulations and legal data and generate appropriate draft sentences. For example, the draft sentence creation unit uses AI to learn from past regulations and legal data and generate optimal draft sentences. The draft sentence creation unit can also generate draft sentences that reflect terminology and expressions specific to the user's industry. For example, the draft sentence creation unit creates draft sentences using terminology specific to the user's industry. Furthermore, the draft sentence creation unit can improve the accuracy of draft sentences by reflecting the user's past feedback. For example, the draft sentence creation unit improves the accuracy of draft sentences based on the user's past feedback. In this way, optimal draft sentences are generated based on past regulations and legal data.

[0032] The before-and-after comparison unit can analyze the differences between documents and highlight the changes. For example, the before-and-after comparison unit can display regulations before and after revision side by side to clarify the changes. The before-and-after comparison unit can also adjust the level of detail of the changes based on the importance of the document. For example, the before-and-after comparison unit can display detailed changes for documents with high importance and simple changes for documents with low importance. Furthermore, the before-and-after comparison unit can also highlight changes specific to the user's industry. For example, the before-and-after comparison unit can highlight changes specific to the user's industry. This clearly displays the changes in the document.

[0033] The typo / misspelling detection unit can analyze the regulations document and automatically detect typos and omissions. For example, the typo / misspelling detection unit uses AI to analyze the regulations document and highlight typos and omissions. The typo / misspelling detection unit can also detect typos and omissions by reflecting terminology and expressions specific to the user's industry. For example, the typo / misspelling detection unit detects typos and omissions using terminology specific to the user's industry. Furthermore, the typo / misspelling detection unit can select the optimal detection method by reflecting the user's past detection history. For example, the typo / misspelling detection unit selects the optimal typo / misspelling detection method based on the user's past detection history. This allows typos and omissions to be automatically detected.

[0034] The version management unit can automatically record the revision history of regulations and make it possible to refer to past versions as needed. The version management unit, for example, automatically records the revision history of regulations and organizes past versions. The version management unit can also manage regulations by reflecting a version management method specific to the user's industry. For example, the version management unit manages regulations using a version management method specific to the user's industry. Furthermore, the version management unit can also select the optimal management method by reflecting the user's past management history. For example, the version management unit selects the optimal version management method based on the user's past management history. This automatically records the revision history of regulations and makes it possible to refer to past versions.

[0035] The consistency checking unit can adjust the update frequency of the law database according to the user's industry and region. For example, if the user's industry experiences frequent changes in laws and regulations, the consistency checking unit can increase the update frequency of the database. The consistency checking unit can also decrease the update frequency of the database if the user's region experiences infrequent changes in laws and regulations. Furthermore, the consistency checking unit can analyze the patterns of law changes in the user's industry and region and set an optimal update frequency. This optimizes the update frequency of the law database according to the user's industry and region.

[0036] The consistency checking unit can add a function to automatically notify the user of the change history of related laws and regulations when the laws and regulations database is updated. For example, when a new law or regulation is enacted, the consistency checking unit notifies the user of the change history of related laws and regulations. The consistency checking unit can also notify the user of the change history of past laws and regulations when a law or regulation is revised. Furthermore, the consistency checking unit can automatically notify the user of the change history of laws and regulations that interest the user. In this way, the change history of laws and regulations is automatically notified.

[0037] When referencing the laws and regulations database, the consistency checking unit can adjust the level of detail of the consistency check based on the importance of the laws and regulations. For example, the consistency checking unit performs a detailed consistency check for laws and regulations with high importance. The consistency checking unit can also perform a simplified consistency check for laws and regulations with low importance. Furthermore, the consistency checking unit can automatically adjust the level of detail of the consistency check according to the importance of the laws and regulations. In this way, the level of detail of the consistency check is adjusted according to the importance of the laws and regulations.

[0038] When referencing the law database, the consistency checking unit can prioritize displaying laws that are highly relevant based on the user's business content. For example, the consistency checking unit prioritizes displaying laws that are relevant to the user's business content. The consistency checking unit can also postpone laws that are less relevant based on the user's business content. Furthermore, the consistency checking unit can analyze the user's business content and suggest the most appropriate laws. As a result, laws that are highly relevant based on the user's business content are prioritized and displayed.

[0039] When referencing the law database, the consistency checking unit can suggest the most appropriate law by reflecting the user's past consistency checking history. The consistency checking unit can, for example, suggest the most appropriate law based on the laws that the user has checked in the past. The consistency checking unit can also preferentially display highly relevant laws from the user's past consistency checking history. Furthermore, the consistency checking unit can analyze the user's past consistency checking history and suggest the most efficient law. In this way, the most appropriate law is suggested based on the user's past consistency checking history.

[0040] When referencing the law database, the consistency checking unit can prioritize displaying laws specific to a region, taking into account the user's geographical location information. For example, the consistency checking unit prioritizes displaying laws specific to a region based on the user's geographical location information. The consistency checking unit can also postpone laws with low relevance, taking into account the user's geographical location information. Furthermore, the consistency checking unit can analyze the user's geographical location information and suggest the most appropriate law. As a result, laws specific to a region are prioritized and displayed based on the user's geographical location information.

[0041] When creating a draft, the draft creation unit can adjust the level of detail of the draft based on the importance of past regulations and legal data. For example, the draft creation unit creates detailed drafts for regulations with high importance. The draft creation unit can also create simple drafts for regulations with low importance. Furthermore, the draft creation unit can analyze the importance of past regulations and legal data and create optimal drafts. In this way, the level of detail of the draft is adjusted based on the importance of past regulations and legal data.

[0042] When creating a draft sentence, the draft sentence creation unit can generate a draft sentence that reflects terminology and expressions specific to the user's industry. The draft sentence creation unit creates a draft sentence, for example, using terminology specific to the user's industry. The draft sentence creation unit can also create a draft sentence that reflects expressions specific to the user's industry. Furthermore, the draft sentence creation unit can learn terminology and expressions specific to the user's industry and create an optimal draft sentence. In this way, a draft sentence that reflects terminology and expressions specific to the user's industry is generated.

[0043] When creating a draft sentence, the draft sentence creation unit can improve the accuracy of the draft sentence by reflecting the user's past feedback. The draft sentence creation unit improves the accuracy of the draft sentence, for example, based on the user's past feedback. The draft sentence creation unit can also create an optimal draft sentence by reflecting the user's past feedback. Furthermore, the draft sentence creation unit can analyze the user's past feedback and improve the accuracy of the draft sentence. This improves the accuracy of the draft sentence based on the user's past feedback.

[0044] When creating a draft sentence, the draft sentence creation unit can propose an optimal draft sentence based on the user's work content. The draft sentence creation unit proposes an optimal draft sentence based on, for example, the user's work content. The draft sentence creation unit can also analyze the user's work content and propose a highly relevant draft sentence. Furthermore, the draft sentence creation unit can automatically generate an optimal draft sentence according to the user's work content. In this way, an optimal draft sentence is proposed based on the user's work content.

[0045] When creating a draft sentence, the draft sentence creation unit can generate an optimal draft sentence by reflecting the user's past draft sentence creation history. The draft sentence creation unit generates an optimal draft sentence, for example, based on the user's past draft sentence creation history. The draft sentence creation unit can also propose an optimal draft sentence by reflecting the user's past draft sentence creation history. Furthermore, the draft sentence creation unit can analyze the user's past draft sentence creation history and generate the most efficient draft sentence. In this way, an optimal draft sentence is generated based on the user's past draft sentence creation history.

[0046] When creating a draft sentence, the draft creation unit can reflect expressions specific to the region by taking into account the user's geographical location information. The draft creation unit creates a draft sentence by reflecting expressions specific to the region, for example, based on the user's geographical location information. The draft creation unit can also propose an optimal draft sentence by taking into account the user's geographical location information. Furthermore, the draft creation unit can analyze the user's geographical location information and create a draft sentence by reflecting expressions specific to the region. In this way, expressions specific to the region are reflected based on the user's geographical location information.

[0047] The context comparison unit can adjust the level of detail of the changes based on the importance of the document when comparing the two. For example, the context comparison unit displays detailed changes for documents with high importance. The context comparison unit can also display simplified changes for documents with low importance. Furthermore, the context comparison unit can analyze the importance of the document and set an optimal level of detail of the changes. This adjusts the level of detail of the changes depending on the importance of the document.

[0048] The before-and-after comparison unit can highlight changes specific to the user's industry during the before-and-after comparison. For example, the before-and-after comparison unit highlights changes specific to the user's industry. The before-and-after comparison unit can also provide an optimal display method that reflects changes specific to the user's industry. Furthermore, the before-and-after comparison unit can learn changes specific to the user's industry and set an optimal display method. This allows changes specific to the user's industry to be highlighted.

[0049] During a before-and-after comparison, the before-and-after comparison unit can select the optimal display method by reflecting the user's past comparison history. The before-and-after comparison unit selects the optimal display method based on, for example, the user's past comparison history. The before-and-after comparison unit can also provide the optimal display method for changes by reflecting the user's past comparison history. Furthermore, the before-and-after comparison unit can analyze the user's past comparison history and select the most efficient display method. In this way, the optimal display method is selected based on the user's past comparison history.

[0050] During the before-and-after comparison, the before-and-after comparison unit can prioritize displaying changes that are highly relevant based on the user's work content. For example, the before-and-after comparison unit prioritizes displaying changes that are relevant to the user's work content. The before-and-after comparison unit can also postpone changes that are less relevant based on the user's work content. Furthermore, the before-and-after comparison unit can analyze the user's work content and suggest optimal changes. This allows changes that are highly relevant based on the user's work content to be prioritized and displayed.

[0051] The before-and-after comparison unit can select the optimal display method by reflecting the user's past feedback during the before-and-after comparison. The before-and-after comparison unit selects the optimal display method based on, for example, the user's past feedback. The before-and-after comparison unit can also provide the optimal display method for changes by reflecting the user's past feedback. Furthermore, the before-and-after comparison unit can analyze the user's past feedback and select the most efficient display method. In this way, the optimal display method is selected based on the user's past feedback.

[0052] During the before-and-after comparison, the before-and-after comparison unit can highlight region-specific changes taking into account the user's geographical location information. For example, the before-and-after comparison unit highlights region-specific changes based on the user's geographical location information. The before-and-after comparison unit can also postpone less relevant changes taking into account the user's geographical location information. Furthermore, the before-and-after comparison unit can analyze the user's geographical location information and suggest optimal changes. As a result, region-specific changes are highlighted based on the user's geographical location information.

[0053] When detecting typos and omissions, the typo detection unit can adjust the level of detail of detection based on the importance of the document. For example, the typo detection unit performs detailed typo detection for documents with high importance. The typo detection unit can also perform simple typo detection for documents with low importance. Furthermore, the typo detection unit can analyze the importance of the document and set an optimal level of detail for typo detection. In this way, the level of detail of typo detection is adjusted according to the importance of the document.

[0054] The typographical error detection unit can detect typos and omissions by reflecting terms and expressions specific to the user's industry. The typographical error detection unit, for example, detects typos and omissions using terms specific to the user's industry. The typographical error detection unit can also detect typos and omissions by reflecting expressions specific to the user's industry. Furthermore, the typographical error detection unit can learn terms and expressions specific to the user's industry and perform optimal typographical error detection. This allows for typographical error detection that reflects terms and expressions specific to the user's industry.

[0055] When detecting typos and omissions, the typo and omission detection unit can select the optimal detection method by reflecting the user's past detection history. The typo and omission detection unit selects the optimal typo and omission detection method, for example, based on the user's past detection history. The typo and omission detection unit can also provide the optimal typo and omission detection method by reflecting the user's past detection history. Furthermore, the typo and omission detection unit can analyze the user's past detection history and select the most efficient typo and omission detection method. In this way, the optimal typo and omission detection method is selected based on the user's past detection history.

[0056] When detecting typos and omissions, the typo detection unit can prioritize detecting typos and omissions that are highly relevant based on the user's business content. For example, the typo detection unit prioritizes detecting typos and omissions that are relevant to the user's business content. The typo detection unit can also postpone typos and omissions that are less relevant based on the user's business content. Furthermore, the typo detection unit can analyze the user's business content and suggest optimal typos and omissions. This allows typos and omissions that are highly relevant based on the user's business content to be detected preferentially.

[0057] When detecting typos and omissions, the typo and omission detection unit can select an optimal detection method by reflecting the user's past feedback. The typo and omission detection unit selects an optimal typo and omission detection method, for example, based on the user's past feedback. The typo and omission detection unit can also provide an optimal typo and omission detection method by reflecting the user's past feedback. Furthermore, the typo and omission detection unit can analyze the user's past feedback and select the most efficient typo and omission detection method. In this way, an optimal typo and omission detection method is selected based on the user's past feedback.

[0058] When detecting typos and omissions, the typo detection unit can prioritize detecting typos and omissions specific to a region by taking into account the user's geographical location information. The typo detection unit, for example, prioritizes detecting typos and omissions specific to a region based on the user's geographical location information. The typo detection unit can also postpone typos and omissions with low relevance by taking into account the user's geographical location information. Furthermore, the typo detection unit can analyze the user's geographical location information and suggest optimal typos and omissions. In this way, typos and omissions specific to a region are preferentially detected based on the user's geographical location information.

[0059] The version management unit can adjust the level of detail of management based on the importance of the document during version management. For example, the version management unit performs detailed version management for documents with high importance. The version management unit can also perform simplified version management for documents with low importance. Furthermore, the version management unit can analyze the importance of the document and set the optimal level of detail of version management. In this way, the level of detail of management is adjusted according to the importance of the document.

[0060] The version management unit can manage versions by reflecting a version management method specific to the user's industry. For example, the version management unit performs management using a version management method specific to the user's industry. The version management unit can also provide an optimal management method by reflecting the version management method specific to the user's industry. Furthermore, the version management unit can learn the version management method specific to the user's industry and set an optimal management method. This allows the version management method specific to the user's industry to be reflected.

[0061] During version management, the version management unit can select the optimal management method by reflecting the user's past management history. The version management unit selects the optimal version management method based on, for example, the user's past management history. The version management unit can also provide the optimal version management method by reflecting the user's past management history. Furthermore, the version management unit can analyze the user's past management history and select the most efficient version management method. In this way, the optimal management method is selected based on the user's past management history.

[0062] During version management, the version management unit can prioritize managing highly relevant versions based on the user's work content. For example, the version management unit prioritizes managing versions related to the user's work content. The version management unit can also postpone less relevant versions based on the user's work content. Furthermore, the version management unit can analyze the user's work content and suggest the most appropriate version. This allows highly relevant versions to be managed preferentially based on the user's work content.

[0063] The version management unit can select the optimal management method by reflecting the user's past feedback during version management. The version management unit selects the optimal version management method based on, for example, the user's past feedback. The version management unit can also provide the optimal version management method by reflecting the user's past feedback. Furthermore, the version management unit can analyze the user's past feedback and select the most efficient version management method. In this way, the optimal management method is selected based on the user's past feedback.

[0064] During version management, the version management unit can prioritize management of region-specific versions by taking into account the user's geographical location information. For example, the version management unit prioritizes management of region-specific versions based on the user's geographical location information. The version management unit can also postpone less relevant versions by taking into account the user's geographical location information. Furthermore, the version management unit can analyze the user's geographical location information and suggest the most appropriate version. In this way, region-specific versions are prioritized for management based on the user's geographical location information.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The policy management system may further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit analyzes which policies the user has frequently referenced in the past and, based on the results, predicts the policies the user is likely to need next and notifies the provider. For example, if the user frequently references policies related to a specific law, the behavior analysis unit can notify the user through the provider when new policies related to that law are added. Furthermore, if the user tends to reference policies during a specific time period, the behavior analysis unit can provide updated policy information tailored to that time period. Furthermore, the behavior analysis unit can learn patterns of policies that the user has modified in the past and issue an alert when similar modifications are required. This enables more efficient policy management based on user behavior patterns.

[0067] The regulations management system can further include a schedule adjustment unit that adjusts the timing of updating regulations taking into account the user's work schedule. For example, the schedule adjustment unit refrains from updating regulations when the user is busy and updates them when the user has more time. The schedule adjustment unit can also suggest the optimal update timing based on the user's work schedule. Furthermore, the schedule adjustment unit can improve work efficiency by analyzing the user's work schedule and updating regulations before important work. This enables flexible regulations management that suits the user's work schedule.

[0068] The rules management system can further include a customization unit that customizes rules based on the user's work content. The customization unit, for example, prioritizes displaying rules related to the user's work content. The customization unit can also postpone rules that are less relevant based on the user's work content. Furthermore, the customization unit can analyze the user's work content and propose optimal rules. This provides optimal rules based on the user's work content, improving work efficiency.

[0069] The rules management system may further include a region customization unit that prioritizes displaying region-specific rules based on the user's geographical location information. The region customization unit, for example, prioritizes displaying region-specific rules based on the user's geographical location information. The region customization unit may also prioritize displaying less relevant rules based on the user's geographical location information. Furthermore, the region customization unit may analyze the user's geographical location information and suggest optimal rules. This allows region-specific rules to be prioritized and displayed based on the user's geographical location information.

[0070] The rules management system can further include a feedback reflection unit that reflects the user's past feedback to improve the accuracy of the rules. The feedback reflection unit improves the accuracy of the rules, for example, based on the user's past feedback. The feedback reflection unit can also provide optimal rules by reflecting the user's past feedback. Furthermore, the feedback reflection unit can analyze the user's past feedback to improve the accuracy of the rules. This improves the accuracy of the rules based on the user's past feedback.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The Compliance Check Department refers to the legal database and checks whether the company's regulations comply with the latest laws. For example, the Compliance Check Department periodically updates the legal database and checks whether regulations comply with the latest laws. Step 2: The drafting department studies past regulations and legal data to generate optimal draft texts. For example, the drafting department uses AI to automatically generate draft texts for new regulations. Step 3: The before-and-after comparison section analyzes the differences between the documents and highlights the changes. For example, the before-and-after comparison section displays the regulations before and after the revision side by side to clarify the changes. Step 4: The typo detection unit analyzes the regulations document and automatically detects typos and omissions. For example, the typo detection unit uses AI to highlight typos and omissions and prompt users to correct them. Step 5: The version management department automatically records the revision history of the regulations and makes it possible to refer to past versions as needed. For example, the version management department automatically records the revision history of the regulations and organizes past versions.

[0073] (Example 2) A regulations management system according to an embodiment of the present invention is a system for streamlining company regulations management. This regulations management system includes a consistency check function that references a legal database to check whether the company's regulations comply with the latest laws and regulations, a draft creation function that automatically generates draft regulations, a before-and-after comparison function that compares the before and after of regulations to clarify changes, a typographical error detection function that detects typos, and a version management function that manages versions of regulations. For example, the regulations management system periodically updates the legal database and checks the consistency of regulations based on the latest laws and regulations. Next, the regulations management system learns from past regulations and legal data to generate optimal draft regulations. Furthermore, the regulations management system analyzes document differences and highlights changes. Next, the regulations management system analyzes regulations documents and automatically detects typos and omissions. Finally, the regulations management system automatically records the revision history of regulations, allowing past versions to be referenced as needed. This allows the regulations management system to streamline the regulations management process and support regulations management that require constant review and improvement. For example, compliance with laws and regulations is ensured and the effort required for creating regulations is significantly reduced. It also makes it easier to check revisions, improving document quality and streamlining the management of regulations.

[0074] A regulations management system according to an embodiment includes a consistency check unit, a draft creation unit, a context comparison unit, a typo / misspelling detection unit, and a version management unit. The consistency check unit references a legal database to check whether the company's regulations comply with the latest laws and regulations. For example, the consistency check unit periodically updates the legal database and checks the consistency of the regulations based on the latest laws and regulations. The draft creation unit learns from past regulations and legal data to generate optimal drafts. For example, the draft creation unit uses AI to automatically create drafts of new regulations. The context comparison unit analyzes differences between documents and highlights changes. For example, the context comparison unit displays regulations before and after revision side by side to clarify changes. The typo / misspelling detection unit analyzes regulations documents and automatically detects typos and omissions. For example, the typo / misspelling detection unit uses AI to highlight typos and omissions and prompt corrections. The version management unit automatically records the revision history of regulations, allowing users to refer to past versions as needed. For example, the version management unit automatically records the revision history of rules and organizes past versions. As a result, the rules management system according to the embodiment can streamline the rules management process and support rules management that requires constant review and improvement.

[0075] The consistency checking unit can periodically update the laws and regulations database and check the consistency of the regulations based on the latest laws and regulations. For example, the consistency checking unit can update the laws and regulations database monthly and check the consistency of the regulations based on the latest laws and regulations. The consistency checking unit can also automatically update the laws and regulations database. For example, the consistency checking unit can optimize the update frequency of the laws and regulations database depending on the user's industry or region. This allows the consistency of the regulations to be checked based on the latest laws and regulations.

[0076] The draft sentence creation unit can learn from past regulations and legal data and generate appropriate draft sentences. For example, the draft sentence creation unit uses AI to learn from past regulations and legal data and generate optimal draft sentences. The draft sentence creation unit can also generate draft sentences that reflect terminology and expressions specific to the user's industry. For example, the draft sentence creation unit creates draft sentences using terminology specific to the user's industry. Furthermore, the draft sentence creation unit can improve the accuracy of draft sentences by reflecting the user's past feedback. For example, the draft sentence creation unit improves the accuracy of draft sentences based on the user's past feedback. In this way, optimal draft sentences are generated based on past regulations and legal data.

[0077] The before-and-after comparison unit can analyze the differences between documents and highlight the changes. For example, the before-and-after comparison unit can display regulations before and after revision side by side to clarify the changes. The before-and-after comparison unit can also adjust the level of detail of the changes based on the importance of the document. For example, the before-and-after comparison unit can display detailed changes for documents with high importance and simple changes for documents with low importance. Furthermore, the before-and-after comparison unit can also highlight changes specific to the user's industry. For example, the before-and-after comparison unit can highlight changes specific to the user's industry. This clearly displays the changes in the document.

[0078] The typo / misspelling detection unit can analyze the regulations document and automatically detect typos and omissions. For example, the typo / misspelling detection unit uses AI to analyze the regulations document and highlight typos and omissions. The typo / misspelling detection unit can also detect typos and omissions by reflecting terminology and expressions specific to the user's industry. For example, the typo / misspelling detection unit detects typos and omissions using terminology specific to the user's industry. Furthermore, the typo / misspelling detection unit can select the optimal detection method by reflecting the user's past detection history. For example, the typo / misspelling detection unit selects the optimal typo / misspelling detection method based on the user's past detection history. This allows typos and omissions to be automatically detected.

[0079] The version management unit can automatically record the revision history of regulations and make it possible to refer to past versions as needed. The version management unit, for example, automatically records the revision history of regulations and organizes past versions. The version management unit can also manage regulations by reflecting a version management method specific to the user's industry. For example, the version management unit manages regulations using a version management method specific to the user's industry. Furthermore, the version management unit can also select the optimal management method by reflecting the user's past management history. For example, the version management unit selects the optimal version management method based on the user's past management history. This automatically records the revision history of regulations and makes it possible to refer to past versions.

[0080] The consistency checking unit can estimate the user's emotions and adjust the priority of consistency checking based on the estimated user's emotions. For example, when the user is feeling stressed, the consistency checking unit can prioritize consistency checking of laws and regulations with higher importance. Furthermore, when the user is relaxed, the consistency checking unit can equally check the consistency of all laws and regulations. Furthermore, when the user is in a hurry, the consistency checking unit can check the consistency of laws and regulations with the greatest impact. In this way, the priority of consistency checking is adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0081] The consistency checking unit can adjust the update frequency of the law database according to the user's industry and region. For example, if the user's industry experiences frequent changes in laws and regulations, the consistency checking unit can increase the update frequency of the database. The consistency checking unit can also decrease the update frequency of the database if the user's region experiences infrequent changes in laws and regulations. Furthermore, the consistency checking unit can analyze the patterns of law changes in the user's industry and region and set an optimal update frequency. This optimizes the update frequency of the law database according to the user's industry and region.

[0082] The consistency checking unit can add a function to automatically notify the user of the change history of related laws and regulations when the laws and regulations database is updated. For example, when a new law or regulation is enacted, the consistency checking unit notifies the user of the change history of related laws and regulations. The consistency checking unit can also notify the user of the change history of past laws and regulations when a law or regulation is revised. Furthermore, the consistency checking unit can automatically notify the user of the change history of laws and regulations that interest the user. In this way, the change history of laws and regulations is automatically notified.

[0083] When referencing the laws and regulations database, the consistency checking unit can adjust the level of detail of the consistency check based on the importance of the laws and regulations. For example, the consistency checking unit performs a detailed consistency check for laws and regulations with high importance. The consistency checking unit can also perform a simplified consistency check for laws and regulations with low importance. Furthermore, the consistency checking unit can automatically adjust the level of detail of the consistency check according to the importance of the laws and regulations. In this way, the level of detail of the consistency check is adjusted according to the importance of the laws and regulations.

[0084] The consistency checking unit can estimate the user's emotions and adjust the order in which the consistency checking results are displayed based on the estimated user's emotions. For example, if the user is feeling stressed, the consistency checking unit can display important results first. Also, if the user is relaxed, the consistency checking unit can display all results evenly. Furthermore, if the user is in a hurry, the consistency checking unit can display the most influential results first. In this way, the order in which the consistency checking results are displayed is adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0085] When referencing the law database, the consistency checking unit can prioritize displaying laws that are highly relevant based on the user's business content. For example, the consistency checking unit prioritizes displaying laws that are relevant to the user's business content. The consistency checking unit can also postpone laws that are less relevant based on the user's business content. Furthermore, the consistency checking unit can analyze the user's business content and suggest the most appropriate laws. As a result, laws that are highly relevant based on the user's business content are prioritized and displayed.

[0086] When referencing the law database, the consistency checking unit can suggest the most appropriate law by reflecting the user's past consistency checking history. The consistency checking unit can, for example, suggest the most appropriate law based on the laws that the user has checked in the past. The consistency checking unit can also preferentially display highly relevant laws from the user's past consistency checking history. Furthermore, the consistency checking unit can analyze the user's past consistency checking history and suggest the most efficient law. In this way, the most appropriate law is suggested based on the user's past consistency checking history.

[0087] When referencing the law database, the consistency checking unit can prioritize displaying laws specific to a region, taking into account the user's geographical location information. For example, the consistency checking unit prioritizes displaying laws specific to a region based on the user's geographical location information. The consistency checking unit can also postpone laws with low relevance, taking into account the user's geographical location information. Furthermore, the consistency checking unit can analyze the user's geographical location information and suggest the most appropriate law. As a result, laws specific to a region are prioritized and displayed based on the user's geographical location information.

[0088] The draft sentence creation unit can estimate the user's emotions and adjust the expression style of the draft sentence based on the estimated user emotions. For example, if the user is feeling stressed, the draft sentence creation unit can use concise and clear expressions. Furthermore, if the user is relaxed, the draft sentence creation unit can also use detailed and polite expressions. Furthermore, if the user is in a hurry, the draft sentence creation unit can use short expressions that get to the point. In this way, the expression style of the draft sentence is adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0089] When creating a draft, the draft creation unit can adjust the level of detail of the draft based on the importance of past regulations and legal data. For example, the draft creation unit creates detailed drafts for regulations with high importance. The draft creation unit can also create simple drafts for regulations with low importance. Furthermore, the draft creation unit can analyze the importance of past regulations and legal data and create optimal drafts. In this way, the level of detail of the draft is adjusted based on the importance of past regulations and legal data.

[0090] When creating a draft sentence, the draft sentence creation unit can generate a draft sentence that reflects terminology and expressions specific to the user's industry. The draft sentence creation unit creates a draft sentence, for example, using terminology specific to the user's industry. The draft sentence creation unit can also create a draft sentence that reflects expressions specific to the user's industry. Furthermore, the draft sentence creation unit can learn terminology and expressions specific to the user's industry and create an optimal draft sentence. In this way, a draft sentence that reflects terminology and expressions specific to the user's industry is generated.

[0091] When creating a draft sentence, the draft sentence creation unit can improve the accuracy of the draft sentence by reflecting the user's past feedback. The draft sentence creation unit improves the accuracy of the draft sentence, for example, based on the user's past feedback. The draft sentence creation unit can also create an optimal draft sentence by reflecting the user's past feedback. Furthermore, the draft sentence creation unit can analyze the user's past feedback and improve the accuracy of the draft sentence. This improves the accuracy of the draft sentence based on the user's past feedback.

[0092] The draft sentence creation unit can estimate the user's emotions and adjust the length of the draft sentence based on the estimated user's emotions. For example, if the user is feeling stressed, the draft sentence creation unit creates a short, to-the-point draft sentence. Also, if the user is relaxed, the draft sentence creation unit can create a longer draft sentence including detailed explanations. Furthermore, if the user is in a hurry, the draft sentence creation unit can create a concise, short draft sentence. In this way, the length of the draft sentence is adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0093] When creating a draft sentence, the draft sentence creation unit can propose an optimal draft sentence based on the user's work content. The draft sentence creation unit proposes an optimal draft sentence based on, for example, the user's work content. The draft sentence creation unit can also analyze the user's work content and propose a highly relevant draft sentence. Furthermore, the draft sentence creation unit can automatically generate an optimal draft sentence according to the user's work content. In this way, an optimal draft sentence is proposed based on the user's work content.

[0094] When creating a draft sentence, the draft sentence creation unit can generate an optimal draft sentence by reflecting the user's past draft sentence creation history. The draft sentence creation unit generates an optimal draft sentence, for example, based on the user's past draft sentence creation history. The draft sentence creation unit can also propose an optimal draft sentence by reflecting the user's past draft sentence creation history. Furthermore, the draft sentence creation unit can analyze the user's past draft sentence creation history and generate the most efficient draft sentence. In this way, an optimal draft sentence is generated based on the user's past draft sentence creation history.

[0095] When creating a draft sentence, the draft creation unit can reflect expressions specific to the region by taking into account the user's geographical location information. The draft creation unit creates a draft sentence by reflecting expressions specific to the region, for example, based on the user's geographical location information. The draft creation unit can also propose an optimal draft sentence by taking into account the user's geographical location information. Furthermore, the draft creation unit can analyze the user's geographical location information and create a draft sentence by reflecting expressions specific to the region. In this way, expressions specific to the region are reflected based on the user's geographical location information.

[0096] The before-and-after comparison unit can estimate the user's emotions and adjust the display method of the before-and-after comparison based on the estimated user's emotions. For example, when the user is feeling stressed, the before-and-after comparison unit provides a simple, highly visible display method. Furthermore, when the user is relaxed, the before-and-after comparison unit can also provide a display method including detailed information. Furthermore, when the user is in a hurry, the before-and-after comparison unit can also provide a display method that focuses on the main points. In this way, the display method of the before-and-after comparison is adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0097] The context comparison unit can adjust the level of detail of the changes based on the importance of the document when comparing the two. For example, the context comparison unit displays detailed changes for documents with high importance. The context comparison unit can also display simplified changes for documents with low importance. Furthermore, the context comparison unit can analyze the importance of the document and set an optimal level of detail of the changes. This adjusts the level of detail of the changes depending on the importance of the document.

[0098] The before-and-after comparison unit can highlight changes specific to the user's industry during the before-and-after comparison. For example, the before-and-after comparison unit highlights changes specific to the user's industry. The before-and-after comparison unit can also provide an optimal display method that reflects changes specific to the user's industry. Furthermore, the before-and-after comparison unit can learn changes specific to the user's industry and set an optimal display method. This allows changes specific to the user's industry to be highlighted.

[0099] During a before-and-after comparison, the before-and-after comparison unit can select the optimal display method by reflecting the user's past comparison history. The before-and-after comparison unit selects the optimal display method based on, for example, the user's past comparison history. The before-and-after comparison unit can also provide the optimal display method for changes by reflecting the user's past comparison history. Furthermore, the before-and-after comparison unit can analyze the user's past comparison history and select the most efficient display method. In this way, the optimal display method is selected based on the user's past comparison history.

[0100] The before-and-after comparison unit can estimate the user's emotions and adjust the order in which the before-and-after comparison results are displayed based on the estimated user's emotions. For example, if the user is feeling stressed, the before-and-after comparison unit can display important changes first. Also, if the user is relaxed, the before-and-after comparison unit can display all changes evenly. Furthermore, if the user is in a hurry, the before-and-after comparison unit can display the changes with the greatest impact first. In this way, the order in which the before-and-after comparison results are displayed is adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0101] During the before-and-after comparison, the before-and-after comparison unit can prioritize displaying changes that are highly relevant based on the user's work content. For example, the before-and-after comparison unit prioritizes displaying changes that are relevant to the user's work content. The before-and-after comparison unit can also postpone changes that are less relevant based on the user's work content. Furthermore, the before-and-after comparison unit can analyze the user's work content and suggest optimal changes. This allows changes that are highly relevant based on the user's work content to be prioritized and displayed.

[0102] The before-and-after comparison unit can select the optimal display method by reflecting the user's past feedback during the before-and-after comparison. The before-and-after comparison unit selects the optimal display method based on, for example, the user's past feedback. The before-and-after comparison unit can also provide the optimal display method for changes by reflecting the user's past feedback. Furthermore, the before-and-after comparison unit can analyze the user's past feedback and select the most efficient display method. In this way, the optimal display method is selected based on the user's past feedback.

[0103] During the before-and-after comparison, the before-and-after comparison unit can highlight region-specific changes taking into account the user's geographical location information. For example, the before-and-after comparison unit highlights region-specific changes based on the user's geographical location information. The before-and-after comparison unit can also postpone less relevant changes taking into account the user's geographical location information. Furthermore, the before-and-after comparison unit can analyze the user's geographical location information and suggest optimal changes. As a result, region-specific changes are highlighted based on the user's geographical location information.

[0104] The typo / misspelling detection unit can estimate the user's emotions and adjust the typo / misspelling detection method based on the estimated user's emotions. For example, if the user is stressed, the typo / misspelling detection unit can provide a simple and highly visible detection method. Furthermore, if the user is relaxed, the typo / misspelling detection unit can also provide a detection method that includes detailed information. Furthermore, if the user is in a hurry, the typo / misspelling detection unit can also provide a detection method that focuses on the main points. In this way, the typo / misspelling detection method is adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0105] When detecting typos and omissions, the typo detection unit can adjust the level of detail of detection based on the importance of the document. For example, the typo detection unit performs detailed typo detection for documents with high importance. The typo detection unit can also perform simple typo detection for documents with low importance. Furthermore, the typo detection unit can analyze the importance of the document and set an optimal level of detail for typo detection. In this way, the level of detail of typo detection is adjusted according to the importance of the document.

[0106] The typographical error detection unit can detect typos and omissions by reflecting terms and expressions specific to the user's industry. The typographical error detection unit, for example, detects typos and omissions using terms specific to the user's industry. The typographical error detection unit can also detect typos and omissions by reflecting expressions specific to the user's industry. Furthermore, the typographical error detection unit can learn terms and expressions specific to the user's industry and perform optimal typographical error detection. This allows for typographical error detection that reflects terms and expressions specific to the user's industry.

[0107] When detecting typos and omissions, the typo and omission detection unit can select the optimal detection method by reflecting the user's past detection history. The typo and omission detection unit selects the optimal typo and omission detection method, for example, based on the user's past detection history. The typo and omission detection unit can also provide the optimal typo and omission detection method by reflecting the user's past detection history. Furthermore, the typo and omission detection unit can analyze the user's past detection history and select the most efficient typo and omission detection method. In this way, the optimal typo and omission detection method is selected based on the user's past detection history.

[0108] The typo / misspelling detection unit can estimate the user's emotions and adjust the method for correcting typos based on the estimated user's emotions. For example, if the user is feeling stressed, the typo / misspelling detection unit can provide a concise and highly visible correction method. Furthermore, if the user is relaxed, the typo / misspelling detection unit can also provide a correction method that includes detailed information. Furthermore, if the user is in a hurry, the typo / misspelling detection unit can also provide a correction method that focuses on the main points. In this way, the method for correcting typos is adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0109] When detecting typos and omissions, the typo detection unit can prioritize detecting typos and omissions that are highly relevant based on the user's business content. For example, the typo detection unit prioritizes detecting typos and omissions that are relevant to the user's business content. The typo detection unit can also postpone typos and omissions that are less relevant based on the user's business content. Furthermore, the typo detection unit can analyze the user's business content and suggest optimal typos and omissions. This allows typos and omissions that are highly relevant based on the user's business content to be detected preferentially.

[0110] When detecting typos and omissions, the typo and omission detection unit can select an optimal detection method by reflecting the user's past feedback. The typo and omission detection unit selects an optimal typo and omission detection method, for example, based on the user's past feedback. The typo and omission detection unit can also provide an optimal typo and omission detection method by reflecting the user's past feedback. Furthermore, the typo and omission detection unit can analyze the user's past feedback and select the most efficient typo and omission detection method. In this way, an optimal typo and omission detection method is selected based on the user's past feedback.

[0111] When detecting typos and omissions, the typo detection unit can prioritize detecting typos and omissions specific to a region by taking into account the user's geographical location information. The typo detection unit, for example, prioritizes detecting typos and omissions specific to a region based on the user's geographical location information. The typo detection unit can also postpone typos and omissions with low relevance by taking into account the user's geographical location information. Furthermore, the typo detection unit can analyze the user's geographical location information and suggest optimal typos and omissions. In this way, typos and omissions specific to a region are preferentially detected based on the user's geographical location information.

[0112] The version management unit can estimate the user's emotions and adjust the version management method based on the estimated user's emotions. For example, if the user is feeling stressed, the version management unit can provide a concise and highly visible version management method. If the user is relaxed, the version management unit can also provide a version management method that includes detailed information. If the user is in a hurry, the version management unit can also provide a version management method that focuses on the main points. In this way, the version management method is adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0113] The version management unit can adjust the level of detail of management based on the importance of the document during version management. For example, the version management unit performs detailed version management for documents with high importance. The version management unit can also perform simplified version management for documents with low importance. Furthermore, the version management unit can analyze the importance of the document and set the optimal level of detail of version management. In this way, the level of detail of management is adjusted according to the importance of the document.

[0114] The version management unit can manage versions by reflecting a version management method specific to the user's industry. For example, the version management unit performs management using a version management method specific to the user's industry. The version management unit can also provide an optimal management method by reflecting the version management method specific to the user's industry. Furthermore, the version management unit can learn the version management method specific to the user's industry and set an optimal management method. This allows the version management method specific to the user's industry to be reflected.

[0115] During version management, the version management unit can select the optimal management method by reflecting the user's past management history. The version management unit selects the optimal version management method based on, for example, the user's past management history. The version management unit can also provide the optimal version management method by reflecting the user's past management history. Furthermore, the version management unit can analyze the user's past management history and select the most efficient version management method. In this way, the optimal management method is selected based on the user's past management history.

[0116] The version management unit can estimate the user's emotions and determine the priority of version management based on the estimated user's emotions. For example, if the user is feeling stressed, the version management unit prioritizes managing important versions. The version management unit can also manage all versions equally if the user is relaxed. Furthermore, if the user is in a hurry, the version management unit can prioritize managing the most influential version. In this way, the priority of version management is determined according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0117] During version management, the version management unit can prioritize managing highly relevant versions based on the user's work content. For example, the version management unit prioritizes managing versions related to the user's work content. The version management unit can also postpone less relevant versions based on the user's work content. Furthermore, the version management unit can analyze the user's work content and suggest the most appropriate version. This allows highly relevant versions to be managed preferentially based on the user's work content.

[0118] The version management unit can select the optimal management method by reflecting the user's past feedback during version management. The version management unit selects the optimal version management method based on, for example, the user's past feedback. The version management unit can also provide the optimal version management method by reflecting the user's past feedback. Furthermore, the version management unit can analyze the user's past feedback and select the most efficient version management method. In this way, the optimal management method is selected based on the user's past feedback.

[0119] During version management, the version management unit can prioritize management of region-specific versions by taking into account the user's geographical location information. For example, the version management unit prioritizes management of region-specific versions based on the user's geographical location information. The version management unit can also postpone less relevant versions by taking into account the user's geographical location information. Furthermore, the version management unit can analyze the user's geographical location information and suggest the most appropriate version. In this way, region-specific versions are prioritized for management based on the user's geographical location information. === Hard Collateral 1-1 === Each of the multiple elements, including the consistency checker, draft creator, context comparer, typographical error detector, and version manager, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the consistency checker is implemented by the specific processing unit 290 of the data processing device 12, which refers to the legal database 24 and checks the consistency of regulations based on the latest laws and regulations. The draft creator is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, which learns from past regulations and legal data and generates an optimal draft. The context comparer is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, which analyzes differences in documents and highlights changes. The typographical error detector is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, which analyzes the regulations document and automatically detects typos and omissions. The version management unit is realized by, for example, the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and automatically records the revision history of the regulations so that past versions can be referenced as needed. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned consistency checker, draft creation unit, context comparison unit, typographical error detection unit, and version management unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the consistency checker is implemented by the specific processing unit 290 of the data processing device 12, which refers to the laws and regulations database 24 and checks the consistency of regulations based on the latest laws and regulations. The draft creation unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, which learns from past regulations and legal data and generates an optimal draft. The context comparison unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, which analyzes differences between documents and highlights changes. The typographical error detection unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, which analyzes documents containing regulations and automatically detects typos and omissions. The version management unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and automatically records the revision history of the regulations so that past versions can be referenced as needed. === Hard Collateral 1-3 === Each of the multiple elements, including the consistency checker, draft creation unit, context comparison unit, typographical error detection unit, and version management unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the consistency checker is implemented by the specific processing unit 290 of the data processing device 12, which refers to the laws and regulations database 24 and checks the consistency of regulations based on the latest laws and regulations. The draft creation unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12, which learns from past regulations and legal data and generates an optimal draft. The context comparison unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12, which analyzes differences in the document and highlights changes. The typographical error detection unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12, which analyzes the document of regulations and automatically detects typos and omissions. The version management unit is realized, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12, and automatically records the revision history of the regulations so that past versions can be referenced as needed. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned consistency checker, draft creation unit, context comparison unit, typographical error detection unit, and version management unit, is implemented, for example, by at least one of the robot 414 and the data processing device 12. For example, the consistency checker is implemented by the specific processing unit 290 of the data processing device 12, and refers to the laws and regulations database 24 to check the consistency of the regulations based on the latest laws and regulations. The draft creation unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and learns from past regulations and legal data to generate an optimal draft. The context comparison unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and analyzes differences in the document and highlights changes. The typographical error detection unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and analyzes the document of the regulations and automatically detects typos and omissions. The version management unit is realized by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and automatically records the revision history of the regulations, making it possible to refer to past versions as needed.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] The policy management system may further include a behavior analysis unit that analyzes the user's behavioral history. The behavior analysis unit analyzes which policies the user has frequently referenced in the past and, based on the results, predicts the policies the user is likely to need next and notifies the provider. For example, if the user frequently references policies related to a specific law, the behavior analysis unit can notify the user through the provider when new policies related to that law are added. Furthermore, if the user tends to reference policies during a specific time period, the behavior analysis unit can provide updated policy information tailored to that time period. Furthermore, the behavior analysis unit can learn patterns of policies that the user has modified in the past and issue an alert when similar modifications are required. This enables more efficient policy management based on user behavior patterns.

[0122] The rules management system may further include an emotion adjustment unit that estimates the user's emotions and adjusts the display method of the rules based on the estimated emotions. For example, if the user is feeling stressed, the emotion adjustment unit may simplify the display of the rules and emphasize only the important points. Also, if the user is relaxed, the emotion adjustment unit may provide a display method that includes detailed explanations. Furthermore, if the user is in a hurry, the emotion adjustment unit may provide a short display method that focuses on the main points. This adjusts the display method of the rules according to the user's emotions, reducing the burden on the user. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0123] The regulations management system can further include a schedule adjustment unit that adjusts the timing of updating regulations taking into account the user's work schedule. For example, the schedule adjustment unit refrains from updating regulations when the user is busy and updates them when the user has more time. The schedule adjustment unit can also suggest the optimal update timing based on the user's work schedule. Furthermore, the schedule adjustment unit can improve work efficiency by analyzing the user's work schedule and updating regulations before important work. This enables flexible regulations management that suits the user's work schedule.

[0124] The rule management system may further include an emotion suggestion unit that estimates the user's emotion and proposes rule revisions based on the estimated emotion. For example, if the user is stressed, the emotion suggestion unit may provide concise and clear revision suggestions. Furthermore, if the user is relaxed, the emotion suggestion unit may provide detailed revision suggestions. Furthermore, if the user is in a hurry, the emotion suggestion unit may provide short, concise revision suggestions that focus on the main points. This allows optimal revision suggestions to be made according to the user's emotion, improving the efficiency of revision work. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0125] The rules management system can further include a customization unit that customizes rules based on the user's work content. The customization unit, for example, prioritizes displaying rules related to the user's work content. The customization unit can also postpone rules that are less relevant based on the user's work content. Furthermore, the customization unit can analyze the user's work content and propose optimal rules. This provides optimal rules based on the user's work content, improving work efficiency.

[0126] The rules management system may further include an emotion prioritization unit that estimates the user's emotions and adjusts the priority of rules based on the estimated emotions. For example, if the user is feeling stressed, the emotion prioritization unit may prioritize displaying important rules. Also, if the user is relaxed, the emotion prioritization unit may prioritize displaying all rules equally. Furthermore, if the user is in a hurry, the emotion prioritization unit may prioritize displaying the most influential rules. This allows the priority of rules to be adjusted according to the user's emotions, enabling efficient rule management. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0127] The rules management system may further include a region customization unit that prioritizes displaying region-specific rules based on the user's geographical location information. The region customization unit, for example, prioritizes displaying region-specific rules based on the user's geographical location information. The region customization unit may also prioritize displaying less relevant rules based on the user's geographical location information. Furthermore, the region customization unit may analyze the user's geographical location information and suggest optimal rules. This allows region-specific rules to be prioritized and displayed based on the user's geographical location information.

[0128] The rules management system may further include an emotion notification unit that estimates the user's emotions and adjusts the notification method for rules based on the estimated emotions. For example, the emotion notification unit may provide a concise notification when the user is stressed. It may also provide a detailed notification when the user is relaxed. Furthermore, the emotion notification unit may provide a short notification that focuses on the main points when the user is in a hurry. This provides an optimal notification method according to the user's emotions, reducing the burden on the user. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0129] The rules management system can further include a feedback reflection unit that reflects the user's past feedback to improve the accuracy of the rules. The feedback reflection unit improves the accuracy of the rules, for example, based on the user's past feedback. The feedback reflection unit can also provide optimal rules by reflecting the user's past feedback. Furthermore, the feedback reflection unit can analyze the user's past feedback to improve the accuracy of the rules. This improves the accuracy of the rules based on the user's past feedback.

[0130] The rules management system may further include an emotion history unit that estimates the user's emotions and displays a rule revision history based on the estimated emotions. For example, the emotion history unit may display a concise revision history when the user is stressed. Alternatively, it may display a detailed revision history when the user is relaxed. Furthermore, the emotion history unit may display a short revision history that focuses on the main points when the user is in a hurry. This allows the display of an optimal revision history according to the user's emotions, reducing the burden on the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0131] The processing flow of the second embodiment will be briefly explained below.

[0132] Step 1: The Compliance Check Department refers to the legal database and checks whether the company's regulations comply with the latest laws. For example, the Compliance Check Department periodically updates the legal database and checks whether regulations comply with the latest laws. Step 2: The drafting department studies past regulations and legal data to generate optimal draft texts. For example, the drafting department uses AI to automatically generate draft texts for new regulations. Step 3: The before-and-after comparison section analyzes the differences between the documents and highlights the changes. For example, the before-and-after comparison section displays the regulations before and after the revision side by side to clarify the changes. Step 4: The typo detection unit analyzes the regulations document and automatically detects typos and omissions. For example, the typo detection unit uses AI to highlight typos and omissions and prompt users to correct them. Step 5: The version management department automatically records the revision history of the regulations and makes it possible to refer to past versions as needed. For example, the version management department automatically records the revision history of the regulations and organizes past versions.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] 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.

[0149] 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.

[0150] 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 AI 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.

[0151] 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.

[0152] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0161] 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.

[0162] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0163] 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0164] 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.

[0165] 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.

[0166] 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 AI 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.

[0167] 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.

[0168] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0180] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. 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 the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0181] 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.

[0182] 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.

[0183] 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 AI 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.

[0184] 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.

[0185] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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).

[0190] 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.

[0191] 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."

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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, in order to avoid confusion and to 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.

[0203] 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.

[0204] [Explanation of symbols]

[0205] 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 consistency confirmation department that refers to a database of laws and regulations and checks whether the company's regulations are consistent with the latest laws and regulations; a draft creation unit that automatically creates draft regulations based on the information confirmed by the consistency confirmation unit; a context comparison unit that compares the context of the draft text generated by the draft text generation unit to clarify changes; a typographical error detection unit that detects typographical errors and omissions based on the changes identified by the context comparison unit; a version management unit that corrects the typographical errors detected by the typographical error detection unit and manages the version of the regulations. A system characterized by:

2. The consistency checking unit Regularly update the legal database and check the consistency of regulations with the latest laws and regulations 2. The system of claim 1.

3. The drafting department Learn from past regulations and legal data to generate appropriate drafts 2. The system of claim 1.

4. The front-rear comparison unit Analyze document differences and highlight changes 2. The system of claim 1.

5. The typographical error / omission detection unit Analyzes regulations documents and automatically detects typos and omissions 2. The system of claim 1.

6. The version management unit Automatically record revision history of regulations, allowing past versions to be referenced as needed 2. The system of claim 1.

7. The consistency checking unit Inferring user sentiment and adjusting reconciliation priorities based on the inferred user sentiment 2. The system of claim 1.

8. The consistency checking unit Adjust the frequency of updates to the legal database based on the user's industry and region 2. The system of claim 1.

Images