System

Abstract

An object of a system according to an embodiment is to manage a correction history and reduce a risk of reversion.SOLUTION: A system includes a storage unit, an extraction unit, and a specification unit. The storage unit stores the correction history. The extraction unit extracts changes based on the correction history stored by the storage unit. The specification unit specifies a risk of reversion on the basis of the changes extracted by the extraction unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately manage revision history, which can increase the risk of atavism.

[0005] The system according to the embodiment aims to manage revision history and reduce the risk of atavism. [Means for solving the problem]

[0006] A system according to an embodiment includes a storage unit, an extraction unit, and an identification unit. The storage unit stores a revision history. The extraction unit extracts changes based on the revision history stored by the storage unit. The identification unit identifies a risk of atavism based on the changes extracted by the extraction unit. [Effects of the Invention]

[0007] The system according to the embodiment can manage revision history and reduce the risk of reversion. [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 system according to an embodiment of the present invention utilizes AI to prevent mistakes during revision work on official websites. This system saves revision history, extracts changes, and identifies the risk of atavism. This enables the system to save revision history, extract changes, and identify the risk of atavism. For example, the system saves detailed information such as the revision content, date and time of the revision, and the person who made the revision. Next, the system detects new revisions and compares them with past revision history. Furthermore, the system identifies areas at risk of atavism and issues a warning to the person responsible for revision. This prevents mistakes such as reverting to old information during revision work.

[0029] The revision management system according to the embodiment includes a storage unit, an extraction unit, and an identification unit. The storage unit stores a revision history. The revision history includes detailed information such as the revision content, the revision date and time, and the person who made the revision. The storage unit stores the revision content as text data, for example. The storage unit can also record the revision date and time as a timestamp. The storage unit can also store information about the person who made the revision as a user ID. For example, the storage unit stores the revision content in a database and manages the revision history. The extraction unit extracts changes based on the revision history stored by the storage unit. For example, the extraction unit detects new revision content and compares it with past revision history. The extraction unit extracts differences between the revision content using, for example, a text comparison algorithm. The extraction unit can also highlight changes made in the revision content. For example, the extraction unit displays the changes in the revision content in a list format and provides it to the person responsible for making the revision. The identification unit identifies the risk of atavism based on the changes extracted by the extraction unit. The identification unit, for example, compares past revision history with current revision content to identify areas at risk of atavism. The identification unit, for example, uses a risk identification algorithm to evaluate the risk of atavism. The identification unit can also warn the person in charge of revision of high-risk areas. For example, the identification unit may display high-risk areas in red to alert the person in charge of revision. This enables the revision management system according to the embodiment to store revision history, extract changes, and identify risks of atavism. This improves the accuracy of revision work and reduces the burden on the person in charge of revision.

[0030] The storage unit can store detailed information about the content of the correction, the date and time of the correction, and the person who made the correction. The detailed information includes, for example, the content of the correction, the date and time of the correction, and the person who made the correction. The storage unit, for example, stores the content of the correction as text data. The storage unit can also record the date and time of the correction as a timestamp. The storage unit can also store information about the person who made the correction as a user ID. For example, the storage unit stores the content of the correction in a database and manages the history of the correction. This makes it easier to refer to the history later by storing a detailed history of the correction. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the content of the correction to a generation AI and cause the generation AI to store the content of the correction.

[0031] The extraction unit can detect new modifications and compare them with past modification history. New modifications include, for example, code additions, changes, and deletions. The extraction unit, for example, detects new modifications and compares them with past modification history. The extraction unit, for example, extracts differences between the modifications using a text comparison algorithm. The extraction unit can also highlight changes made to the modifications. For example, the extraction unit may display changes made to the modifications in a list format and provide this to the person responsible for making the modifications. This allows the new modifications to be detected and compared with past modification history to identify the changes. Some or all of the above-described processing by the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit may input new modifications to a generation AI and cause the generation AI to extract changes.

[0032] The identification unit can identify locations at risk of atavism and issue a warning to the person responsible for modification. Locations at risk of atavism include, for example, locations where past bugs occurred and locations where important functions have been changed. The identification unit, for example, compares past modification history with current modification content to identify locations at risk of atavism. The identification unit, for example, uses a risk identification algorithm to evaluate the risk of atavism. The identification unit can also warn the person responsible for modification about high-risk locations. For example, the identification unit displays high-risk locations in red to alert the person responsible for modification. This makes it possible to identify locations at risk of atavism and prevent modification errors from occurring. Some or all of the above-mentioned processing by the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input locations at risk of atavism into a generation AI and have the generation AI perform risk identification.

[0033] When saving the revision history, the storage unit can adjust the level of detail to be saved based on the importance of the revision. The importance of the revision includes, for example, the scope of impact of the revision and the urgency of the revision. For example, in the case of an important revision, the storage unit can have the AI ​​save detailed information to make it easier to refer to later. In addition, in the case of a revision with low importance, the storage unit can have the AI ​​save simplified information to reduce the amount of data. In addition, in the case of a revision with medium importance, the storage unit can have the AI ​​save information with an appropriate level of detail to achieve a balance. In this way, the amount of data can be optimized by adjusting the level of detail to be saved according to the importance of the revision. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, AI. For example, the storage unit can input the importance of the revision to the generation AI and cause the generation AI to adjust the level of detail to be saved.

[0034] When saving the revision history, the storage unit can apply different storage formats depending on the category of the revision. Categories of revisions include, for example, price changes, product descriptions, and image revisions. For example, in the case of a price change revision, the storage unit causes the AI ​​to save the revision in a format dedicated to price changes. Furthermore, in the case of a product description revision, the storage unit can also cause the AI ​​to save the revision in a format dedicated to product descriptions. Furthermore, in the case of an image revision, the storage unit can also cause the AI ​​to save the revision in a format dedicated to images. This makes it easier to organize information by applying a storage format according to the category of revisions. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, AI. For example, the storage unit can input the category of revisions to the generation AI and cause the generation AI to apply a storage format.

[0035] When saving the revision history, the storage unit can improve the accuracy of the storage by referring to the corrector's past revision history. The corrector's past revision history includes, for example, the content of past revisions and the frequency of revisions. For example, the storage unit improves the accuracy of the storage by using AI by referring to the content of revisions made by the corrector in the past. The storage unit can also identify frequently revised parts from the corrector's past revision history and have the AI ​​prioritize saving them. The storage unit can also analyze the corrector's past revision history and have the AI ​​suggest an optimal saving method. In this way, the accuracy of the storage is improved by referring to the corrector's past revision history. Some or all of the above-mentioned processing in the storage unit may be performed using AI, for example, or may be performed without using AI. For example, the storage unit can input the corrector's past revision history into the generation AI and have the generation AI improve the accuracy of the storage.

[0036] When saving the revision history, the storage unit can prioritize saving highly relevant revision history by taking into account the geographical distribution of the revision content. The geographical distribution of the revision content includes, for example, revision content that is frequently made in a specific region, revision content that is geographically important, etc. The storage unit, for example, prioritizes saving revision content that is frequently made in a specific region. The storage unit can also prioritize saving geographically important revision content. The storage unit can also prioritize saving highly relevant revision history based on the geographical distribution. In this way, by taking the geographical distribution of the revision content into consideration, it is possible to prioritize saving highly relevant revision history. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the geographical distribution of the revision content to the generation AI and cause the generation AI to prioritize saving highly relevant history.

[0037] When saving the revision history, the storage unit can improve the accuracy of the storage by referring to literature related to the revision content. Literature related to the revision content includes, for example, technical literature, patent literature, and research papers. For example, the storage unit can refer to literature related to the revision content, and the AI ​​can improve the accuracy of the storage. The storage unit can also refer to research papers related to the revision content, and the AI ​​can improve the accuracy of the storage. The storage unit can also refer to patent literature related to the revision content, and the AI ​​can improve the accuracy of the storage. By doing so, the accuracy of the storage is improved by referring to literature related to the revision content. Some or all of the above-described processing in the storage unit can be performed, for example, using AI, or can be performed without using AI. For example, the storage unit can input literature related to the revision content into the generation AI, and cause the generation AI to improve the accuracy of the storage.

[0038] The storage unit can store the revision history while taking into consideration the market value of the revision content. The market value of the revision content includes, for example, the impact on sales and the impact on customer satisfaction. The storage unit, for example, prioritizes storing revision content with high market value. The storage unit can also simplify and store revision content with low market value. The storage unit can also adjust the storage method of the revision history based on the market value. In this way, important revision content can be stored preferentially by taking the market value of the revision content into consideration. Some or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or without using AI. For example, the storage unit can input the market value of the revision content into the generation AI and cause the generation AI to store the content based on the market value.

[0039] When extracting changes, the extraction unit can adjust the level of extraction detail based on the importance of the changes. The importance of the changes includes, for example, the scope of impact of the changes and the urgency of the changes. For example, in the case of important changes, the extraction unit uses AI to extract detailed changes. In addition, in the case of low-importance changes, the extraction unit can also use AI to extract simplified changes. In addition, in the case of medium-importance changes, the extraction unit can also use AI to extract changes with an appropriate level of detail. This enables efficient extraction of changes by adjusting the level of extraction detail according to the importance of the changes. Some or all of the above-described processing in the extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the extraction unit can input the importance of the changes to the generation AI and cause the generation AI to adjust the level of extraction detail.

[0040] When extracting changes, the extraction unit can apply different extraction algorithms depending on the category of the correction. Categories of corrections include, for example, price changes, product descriptions, and image corrections. For example, in the case of a price change, the extraction unit can have the AI ​​apply an extraction algorithm dedicated to price changes. Furthermore, in the case of a product description correction, the extraction unit can also have the AI ​​apply an extraction algorithm dedicated to product descriptions. Furthermore, in the case of an image correction, the extraction unit can also have the AI ​​apply an extraction algorithm dedicated to images. This makes it easier to organize information by applying an extraction algorithm according to the category of the correction. Some or all of the above-mentioned processing in the extraction unit can be performed using, for example, AI, or can be performed without using AI. For example, the extraction unit can input the category of the correction to the generation AI and cause the generation AI to apply the extraction algorithm.

[0041] When extracting changes, the extraction unit can improve the accuracy of the extraction by referring to past extraction results. Past extraction results include, for example, past changes and extraction frequency. For example, the extraction unit refers to past extraction results to allow the AI ​​to improve the accuracy of the extraction. The extraction unit can also identify frequently changed parts from past extraction results and have the AI ​​focus on extracting them. The extraction unit can also analyze past extraction results and allow the AI ​​to propose an optimal extraction method. In this way, by referring to past extraction results, the accuracy of the extraction is improved. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input past extraction results into the generation AI and have the generation AI improve the extraction accuracy.

[0042] When extracting changes, the extraction unit can determine the extraction priority based on the submission date of the corrections. The submission date of the corrections includes, for example, the submission date and time, the submission frequency, etc. The extraction unit, for example, prioritizes extraction of corrections that were submitted recently. The extraction unit can also postpone corrections that were submitted earlier. The extraction unit can also adjust the extraction priority based on the submission date. This enables efficient extraction of changes by determining the extraction priority based on the submission date of the corrections. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the submission date of the corrections to the generation AI and have the generation AI determine the extraction priority.

[0043] When extracting changes, the extraction unit can adjust the extraction order based on the relevance of the modifications. The relevance of the modifications includes, for example, interdependence of the modifications, related functions, etc. The extraction unit, for example, prioritizes extraction of highly relevant modifications. The extraction unit can also postpone extraction of less relevant modifications. The extraction unit can also adjust the extraction order based on the relevance. This enables efficient extraction of changes by adjusting the extraction order based on the relevance of the modifications. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the relevance of the modifications to a generation AI and have the generation AI adjust the extraction order.

[0044] When extracting changes, the extraction unit can adjust the level of extraction detail depending on the expertise level of the reviser. The expertise level of the reviser includes, for example, the reviser's years of experience, field of expertise, etc. For example, in the case of a reviser with a high level of expertise, the extraction unit uses AI to extract detailed changes. In addition, in the case of a reviser with a low level of expertise, the extraction unit can also use AI to extract simplified changes. The extraction unit can also adjust the level of extraction detail based on the expertise level. In this way, appropriate information can be provided by adjusting the level of extraction detail depending on the expertise level of the reviser. Some or all of the above-mentioned processing in the extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the extraction unit can input the expertise level of the reviser to the generation AI and cause the generation AI to adjust the level of extraction detail.

[0045] When identifying a risk of atavism, the identification unit can adjust the level of specific detail based on the importance of the modification content. The importance of the modification content includes, for example, the scope of impact of the modification and the urgency of the modification. For example, in the case of an important modification content, the identification unit may have the AI ​​perform detailed risk identification. In addition, in the case of a modification content with low importance, the identification unit may have the AI ​​perform simplified risk identification. In addition, in the case of a modification content with medium importance, the identification unit may have the AI ​​perform risk identification with an appropriate level of detail. This enables efficient risk identification by adjusting the level of specific detail according to the importance of the modification content. Some or all of the above-described processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit may input the importance of the modification content to the generation AI and cause the generation AI to adjust the level of specific detail.

[0046] When identifying the risk of atavism, the identification unit can apply different identification algorithms depending on the category of the modification. Categories of the modification include, for example, price changes, product descriptions, and image modifications. For example, in the case of a price change modification, the identification unit can have the AI ​​apply an identification algorithm dedicated to price changes. Furthermore, in the case of a product description modification, the identification unit can also have the AI ​​apply an identification algorithm dedicated to product descriptions. Furthermore, in the case of an image modification, the identification unit can also have the AI ​​apply an identification algorithm dedicated to images. This makes it easier to organize information by applying an identification algorithm according to the category of the modification. Some or all of the above-described processing in the identification unit can be performed, for example, using AI, or can be performed without using AI. For example, the identification unit can input the category of the modification to the generation AI and cause the generation AI to apply the identification algorithm.

[0047] When identifying atavism risks, the identification unit can improve the accuracy of the identification by referring to past identification results. Past identification results include, for example, past risk identification results and identification frequency. The identification unit, for example, refers to past identification results to allow the AI ​​to improve the identification accuracy. The identification unit can also identify areas where risks frequently occur from past identification results and have the AI ​​focus on identifying those areas. The identification unit can also analyze past identification results and allow the AI ​​to propose an optimal identification method. In this way, the accuracy of identification is improved by referring to past identification results. Some or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input past identification results into the generation AI and cause the generation AI to improve the identification accuracy.

[0048] When identifying atavism risks, the identification unit can determine a specific priority based on the submission time of the modifications. The submission time of the modifications includes, for example, the submission date and time, the submission frequency, etc. The identification unit, for example, prioritizes identifying risks of modifications submitted recently. The identification unit can also postpone risks of modifications submitted recently. The identification unit can also adjust the priority of risk identification based on the submission time. This enables efficient risk identification by determining the specific priority based on the submission time of the modifications. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the submission time of the modifications to the generation AI and have the generation AI determine the specific priority.

[0049] When identifying atavism risks, the identification unit can adjust the specific order based on the relevance of the modification contents. The relevance of the modification contents includes, for example, interdependence of the modification contents, related functions, etc. The identification unit, for example, prioritizes identifying risks of highly relevant modification contents. The identification unit can also postpone risks of less relevant modification contents. The identification unit can also adjust the order of risk identification based on the relevance. This enables efficient risk identification by adjusting the specific order based on the relevance of the modification contents. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the relevance of the modification contents to the generation AI and cause the generation AI to adjust the specific order.

[0050] When identifying atavism risks, the identification unit can adjust the level of specific detail according to the modifier's level of expertise. The modifier's level of expertise includes, for example, the modifier's years of experience, field of expertise, etc. For example, in the case of a modifier with a high level of expertise, the identification unit may use an AI to perform detailed risk identification. In addition, in the case of a modifier with a low level of expertise, the identification unit may use an AI to perform simplified risk identification. The identification unit can also adjust the level of specific detail based on the level of expertise. In this way, appropriate information can be provided by adjusting the level of specific detail according to the modifier's level of expertise. Some or all of the above-described processing in the identification unit may be performed using, or without, AI. For example, the identification unit may input the modifier's level of expertise to the generation AI and cause the generation AI to adjust the level of specific detail.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The revision management system further includes a notification unit. The notification unit can notify the person in charge of revisions in real time of the results of saving the revision history, extracting changes, and identifying reversion risks. For example, the notification unit can send an email or push notification to the person in charge of revisions when the revision history is saved. The notification unit can also display changes extracted in real time on a dashboard for the person in charge of revisions. Furthermore, the notification unit can issue an alert to the person in charge of revisions when a reversion risk is identified. This allows the person in charge of revisions to understand the progress and risks of the revision work in real time, enabling them to respond quickly.

[0053] The storage unit can manage versions of the revisions when saving the revision history. For example, the storage unit can individually save each version of the revisions and compare past versions with the current version. The storage unit can also display the differences between revision versions, allowing the person in charge of revisions to revert to a past version. Furthermore, the storage unit can display the version history of the revisions in chronological order, allowing the person in charge of revisions to understand the process of the revisions. This facilitates version management of the revisions and improves the efficiency of the revision work.

[0054] When extracting changes in a revision, the extraction unit can evaluate the scope of impact of the revision. For example, the extraction unit can evaluate the extent to which the revision will affect other parts, and if the scope of impact is large, issue a warning to the person responsible for the revision. The extraction unit can also visualize the scope of impact of the revision, allowing the person responsible for the revision to intuitively understand the scope of impact. Furthermore, for revisions with a large scope of impact, the extraction unit can extract detailed changes and provide them to the person responsible for the revision. This makes it possible to extract changes that take the scope of impact of the revision into consideration, improving the accuracy of the revision work.

[0055] The identification unit can take into account the dependency relationships between modifications when identifying the risk of atavism. For example, if a modification is dependent on another modification, the identification unit can evaluate the risk by taking that dependency relationship into account. The identification unit can also determine that modifications with strong dependencies pose a high risk and issue a warning to the person responsible for modification. Furthermore, the identification unit can visualize the dependencies so that the person responsible for modification can intuitively understand them. This makes it possible to identify risks by taking into account the dependency relationships between modifications, improving the accuracy of modification work.

[0056] When saving the revision history, the storage unit can evaluate the security risk of the revisions and adjust the storage method. For example, if the revisions contain confidential information, the storage unit will have AI encrypt and store the data to prevent information leaks. Also, if the revisions are public information, the storage unit can use the AI ​​to apply the normal storage method for efficient storage. Furthermore, the storage unit can evaluate the security risk of the revisions and issue a warning to the person responsible for making the revisions if the risk is high. This realizes a storage method that takes the security risk of the revisions into consideration, improving the safety of information.

[0057] When saving the revision history, the storage unit can evaluate the future usability of the revisions and adjust the storage method. For example, if the revisions are likely to be reused in future projects, the storage unit can use AI to store detailed information, facilitating reuse. In addition, if the revisions are temporary, the storage unit can use AI to store simplified information, reducing the amount of data. Furthermore, the storage unit can evaluate the future usability of the revisions and notify the person responsible for making the revisions if there is a high possibility of their use. This realizes a storage method that takes the future usability of the revisions into consideration, enabling efficient data management.

[0058] When saving the revision history, the storage unit can adjust the storage method taking into account the legal requirements of the revisions. For example, if the revisions are legally required to be saved, the storage unit will use AI to save detailed information, thereby meeting the legal requirements. In addition, if the revisions do not legally need to be saved, the storage unit can use AI to save simplified information, thereby reducing the amount of data. Furthermore, the storage unit can evaluate the legal requirements of the revisions and notify the person in charge of making the revisions if the requirements are strict. This allows for a storage method that takes into account the legal requirements of the revisions, thereby reducing legal risks.

[0059] When saving the revision history, the storage unit can prioritize saving highly relevant revisions by taking into account the geographical distribution of the revisions. For example, the storage unit can prioritize saving revisions that are frequently made in a specific region. The storage unit can also prioritize saving geographically important revisions. Furthermore, the storage unit can prioritize saving highly relevant revisions based on the geographical distribution. In this way, highly relevant revisions can be prioritized by taking into account the geographical distribution of the revisions.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The storage unit stores the revision history. The revision history includes detailed information such as the revision content, the revision date and time, and the person who made the revision. The storage unit stores the revision content as text data, for example. The storage unit can also record the revision date and time as a timestamp. The storage unit can also store information about the person who made the revision as a user ID. For example, the storage unit stores the revision content in a database and manages the revision history. Step 2: The extraction unit extracts changes based on the revision history stored by the storage unit. For example, the extraction unit detects new revisions and compares them with past revision history. For example, the extraction unit extracts differences between revisions using a text comparison algorithm. The extraction unit can also highlight changes in the revisions. For example, the extraction unit displays the changes in the revisions in a list format and provides it to the person responsible for making the revisions. Step 3: The identification unit identifies the risk of atavism based on the changes extracted by the extraction unit. For example, the identification unit compares the past revision history with the current revision content to identify areas at risk of atavism. For example, the identification unit evaluates the risk of atavism using a risk identification algorithm. The identification unit can also warn the person responsible for modification of high-risk areas. For example, the identification unit displays high-risk areas in red to alert the person responsible for modification.

[0062] (Example 2) A system according to an embodiment of the present invention utilizes AI to prevent mistakes during revision work on official websites. This system saves revision history, extracts changes, and identifies the risk of atavism. This enables the system to save revision history, extract changes, and identify the risk of atavism. For example, the system saves detailed information such as the revision content, date and time of the revision, and the person who made the revision. Next, the system detects new revisions and compares them with past revision history. Furthermore, the system identifies areas at risk of atavism and issues a warning to the person responsible for revision. This prevents mistakes such as reverting to old information during revision work.

[0063] The revision management system according to the embodiment includes a storage unit, an extraction unit, and an identification unit. The storage unit stores a revision history. The revision history includes detailed information such as the revision content, the revision date and time, and the person who made the revision. The storage unit stores the revision content as text data, for example. The storage unit can also record the revision date and time as a timestamp. The storage unit can also store information about the person who made the revision as a user ID. For example, the storage unit stores the revision content in a database and manages the revision history. The extraction unit extracts changes based on the revision history stored by the storage unit. For example, the extraction unit detects new revision content and compares it with past revision history. The extraction unit extracts differences between the revision content using, for example, a text comparison algorithm. The extraction unit can also highlight changes made in the revision content. For example, the extraction unit displays the changes in the revision content in a list format and provides it to the person responsible for making the revision. The identification unit identifies the risk of atavism based on the changes extracted by the extraction unit. The identification unit, for example, compares past revision history with current revision content to identify areas at risk of atavism. The identification unit, for example, uses a risk identification algorithm to evaluate the risk of atavism. The identification unit can also warn the person in charge of revision of high-risk areas. For example, the identification unit may display high-risk areas in red to alert the person in charge of revision. This enables the revision management system according to the embodiment to store revision history, extract changes, and identify risks of atavism. This improves the accuracy of revision work and reduces the burden on the person in charge of revision.

[0064] The storage unit can store detailed information about the content of the correction, the date and time of the correction, and the person who made the correction. The detailed information includes, for example, the content of the correction, the date and time of the correction, and the person who made the correction. The storage unit, for example, stores the content of the correction as text data. The storage unit can also record the date and time of the correction as a timestamp. The storage unit can also store information about the person who made the correction as a user ID. For example, the storage unit stores the content of the correction in a database and manages the history of the correction. This makes it easier to refer to the history later by storing a detailed history of the correction. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the content of the correction to a generation AI and cause the generation AI to store the content of the correction.

[0065] The extraction unit can detect new modifications and compare them with past modification history. New modifications include, for example, code additions, changes, and deletions. The extraction unit, for example, detects new modifications and compares them with past modification history. The extraction unit, for example, extracts differences between the modifications using a text comparison algorithm. The extraction unit can also highlight changes made to the modifications. For example, the extraction unit may display changes made to the modifications in a list format and provide this to the person responsible for making the modifications. This allows the new modifications to be detected and compared with past modification history to identify the changes. Some or all of the above-described processing by the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit may input new modifications to a generation AI and cause the generation AI to extract changes.

[0066] The identification unit can identify locations at risk of atavism and issue a warning to the person responsible for modification. Locations at risk of atavism include, for example, locations where past bugs occurred and locations where important functions have been changed. The identification unit, for example, compares past modification history with current modification content to identify locations at risk of atavism. The identification unit, for example, uses a risk identification algorithm to evaluate the risk of atavism. The identification unit can also warn the person responsible for modification about high-risk locations. For example, the identification unit displays high-risk locations in red to alert the person responsible for modification. This makes it possible to identify locations at risk of atavism and prevent modification errors from occurring. Some or all of the above-mentioned processing by the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input locations at risk of atavism into a generation AI and have the generation AI perform risk identification.

[0067] The storage unit can analyze the user's emotions and adjust the frequency of saving the revision history based on the analyzed user's emotions. Examples of user emotions include stress, relaxation, and hurry. For example, when the user is feeling stressed, the storage unit causes the AI ​​to frequently save the revision history, thereby reducing the burden on the user. Furthermore, when the user is relaxed, the storage unit can also cause the AI ​​to reduce the frequency of saving the revision history, thereby reducing the load on the system. Furthermore, when the user is in a hurry, the storage unit can also cause the AI ​​to save the revision history in real time, enabling a quick response. This reduces the burden on the user by adjusting the saving frequency according to the user's emotions. Emotion estimation is realized using an emotion estimation function, 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. Some or all of the above-described processing in the storage unit can be performed using, for example, an AI. For example, the storage unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the saving frequency based on the emotion.

[0068] When saving the revision history, the storage unit can adjust the level of detail to be saved based on the importance of the revision. The importance of the revision includes, for example, the scope of impact of the revision and the urgency of the revision. For example, in the case of an important revision, the storage unit can have the AI ​​save detailed information to make it easier to refer to later. In addition, in the case of a revision with low importance, the storage unit can have the AI ​​save simplified information to reduce the amount of data. In addition, in the case of a revision with medium importance, the storage unit can have the AI ​​save information with an appropriate level of detail to achieve a balance. In this way, the amount of data can be optimized by adjusting the level of detail to be saved according to the importance of the revision. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, AI. For example, the storage unit can input the importance of the revision to the generation AI and cause the generation AI to adjust the level of detail to be saved.

[0069] When saving the revision history, the storage unit can apply different storage formats depending on the category of the revision. Categories of revisions include, for example, price changes, product descriptions, and image revisions. For example, in the case of a price change revision, the storage unit causes the AI ​​to save the revision in a format dedicated to price changes. Furthermore, in the case of a product description revision, the storage unit can also cause the AI ​​to save the revision in a format dedicated to product descriptions. Furthermore, in the case of an image revision, the storage unit can also cause the AI ​​to save the revision in a format dedicated to images. This makes it easier to organize information by applying a storage format according to the category of revisions. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, AI. For example, the storage unit can input the category of revisions to the generation AI and cause the generation AI to apply a storage format.

[0070] When saving the revision history, the storage unit can improve the accuracy of the storage by referring to the corrector's past revision history. The corrector's past revision history includes, for example, the content of past revisions and the frequency of revisions. For example, the storage unit improves the accuracy of the storage by using AI by referring to the content of revisions made by the corrector in the past. The storage unit can also identify frequently revised parts from the corrector's past revision history and have the AI ​​prioritize saving them. The storage unit can also analyze the corrector's past revision history and have the AI ​​suggest an optimal saving method. In this way, the accuracy of the storage is improved by referring to the corrector's past revision history. Some or all of the above-mentioned processing in the storage unit may be performed using AI, for example, or may be performed without using AI. For example, the storage unit can input the corrector's past revision history into the generation AI and have the generation AI improve the accuracy of the storage.

[0071] The storage unit can analyze the user's emotions and determine the priority of the revision history to be saved based on the analyzed user's emotions. Examples of user emotions include stress, relaxation, and hurry. For example, when the user is feeling stressed, the storage unit allows the AI ​​to save important revision history with priority. Furthermore, when the user is relaxed, the storage unit can also allow the AI ​​to save all revision history evenly. Furthermore, when the user is in a hurry, the storage unit can also allow the AI ​​to save the most recent revision history with priority. Thus, by determining the priority of the revision history to be saved according to the user's emotions, important revision history can be saved with priority. Emotion estimation is realized using an emotion estimation function, 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. Some or all of the above-described processing in the storage unit can be performed using, for example, an AI. For example, the storage unit can input the user's emotion data into the generation AI and have the generation AI determine the saving priority based on the emotion.

[0072] When saving the revision history, the storage unit can prioritize saving highly relevant revision history by taking into account the geographical distribution of the revision content. The geographical distribution of the revision content includes, for example, revision content that is frequently made in a specific region, revision content that is geographically important, etc. The storage unit, for example, prioritizes saving revision content that is frequently made in a specific region. The storage unit can also prioritize saving geographically important revision content. The storage unit can also prioritize saving highly relevant revision history based on the geographical distribution. In this way, by taking the geographical distribution of the revision content into consideration, it is possible to prioritize saving highly relevant revision history. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the geographical distribution of the revision content to the generation AI and cause the generation AI to prioritize saving highly relevant history.

[0073] When saving the revision history, the storage unit can improve the accuracy of the storage by referring to literature related to the revision content. Literature related to the revision content includes, for example, technical literature, patent literature, and research papers. For example, the storage unit can refer to literature related to the revision content, and the AI ​​can improve the accuracy of the storage. The storage unit can also refer to research papers related to the revision content, and the AI ​​can improve the accuracy of the storage. The storage unit can also refer to patent literature related to the revision content, and the AI ​​can improve the accuracy of the storage. By doing so, the accuracy of the storage is improved by referring to literature related to the revision content. Some or all of the above-described processing in the storage unit can be performed, for example, using AI, or can be performed without using AI. For example, the storage unit can input literature related to the revision content into the generation AI, and cause the generation AI to improve the accuracy of the storage.

[0074] The storage unit can store the revision history while taking into consideration the market value of the revision content. The market value of the revision content includes, for example, the impact on sales and the impact on customer satisfaction. The storage unit, for example, prioritizes storing revision content with high market value. The storage unit can also simplify and store revision content with low market value. The storage unit can also adjust the storage method of the revision history based on the market value. In this way, important revision content can be stored preferentially by taking the market value of the revision content into consideration. Some or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or without using AI. For example, the storage unit can input the market value of the revision content into the generation AI and cause the generation AI to store the content based on the market value.

[0075] The extraction unit can analyze the user's emotions and adjust the change point extraction method based on the analyzed user's emotions. Examples of user emotions include stress, relaxation, and hurry. For example, if the user is feeling stressed, the extraction unit can provide a simplified extraction method. Furthermore, if the user is relaxed, the extraction unit can provide a detailed extraction method. Furthermore, if the user is in a hurry, the extraction unit can provide a quick extraction method. This reduces the burden on the user by adjusting the change point extraction method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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. Some or all of the above-described processing in the extraction unit can be performed using, for example, an AI. For example, the extraction unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the extraction method based on the emotion.

[0076] When extracting changes, the extraction unit can adjust the level of extraction detail based on the importance of the changes. The importance of the changes includes, for example, the scope of impact of the changes and the urgency of the changes. For example, in the case of important changes, the extraction unit uses AI to extract detailed changes. In addition, in the case of low-importance changes, the extraction unit can also use AI to extract simplified changes. In addition, in the case of medium-importance changes, the extraction unit can also use AI to extract changes with an appropriate level of detail. This enables efficient extraction of changes by adjusting the level of extraction detail according to the importance of the changes. Some or all of the above-described processing in the extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the extraction unit can input the importance of the changes to the generation AI and cause the generation AI to adjust the level of extraction detail.

[0077] When extracting changes, the extraction unit can apply different extraction algorithms depending on the category of the correction. Categories of corrections include, for example, price changes, product descriptions, and image corrections. For example, in the case of a price change, the extraction unit can have the AI ​​apply an extraction algorithm dedicated to price changes. Furthermore, in the case of a product description correction, the extraction unit can also have the AI ​​apply an extraction algorithm dedicated to product descriptions. Furthermore, in the case of an image correction, the extraction unit can also have the AI ​​apply an extraction algorithm dedicated to images. This makes it easier to organize information by applying an extraction algorithm according to the category of the correction. Some or all of the above-mentioned processing in the extraction unit can be performed using, for example, AI, or can be performed without using AI. For example, the extraction unit can input the category of the correction to the generation AI and cause the generation AI to apply the extraction algorithm.

[0078] When extracting changes, the extraction unit can improve the accuracy of the extraction by referring to past extraction results. Past extraction results include, for example, past changes and extraction frequency. For example, the extraction unit refers to past extraction results to allow the AI ​​to improve the accuracy of the extraction. The extraction unit can also identify frequently changed parts from past extraction results and have the AI ​​focus on extracting them. The extraction unit can also analyze past extraction results and allow the AI ​​to propose an optimal extraction method. In this way, by referring to past extraction results, the accuracy of the extraction is improved. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input past extraction results into the generation AI and have the generation AI improve the extraction accuracy.

[0079] The extraction unit can analyze the user's emotions and determine the priority of changes to be extracted based on the analyzed user's emotions. Examples of user emotions include stress, relaxation, and hurry. For example, when the user is feeling stressed, the extraction unit causes the AI ​​to prioritize extracting important changes. Furthermore, when the user is relaxed, the extraction unit can also cause the AI ​​to extract all changes equally. Furthermore, when the user is in a hurry, the extraction unit can also cause the AI ​​to prioritize extracting the most recent changes. This allows important changes to be prioritized by determining the priority of changes according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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. Some or all of the above-described processing in the extraction unit can be performed using, for example, an AI, or without an AI. For example, the extraction unit can input user emotion data into the generation AI and cause the generation AI to determine extraction priorities based on emotions.

[0080] When extracting changes, the extraction unit can determine the extraction priority based on the submission date of the corrections. The submission date of the corrections includes, for example, the submission date and time, the submission frequency, etc. The extraction unit, for example, prioritizes extraction of corrections that were submitted recently. The extraction unit can also postpone corrections that were submitted earlier. The extraction unit can also adjust the extraction priority based on the submission date. This enables efficient extraction of changes by determining the extraction priority based on the submission date of the corrections. Some or all of the above-mentioned processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the submission date of the corrections to the generation AI and have the generation AI determine the extraction priority.

[0081] When extracting changes, the extraction unit can adjust the extraction order based on the relevance of the modifications. The relevance of the modifications includes, for example, interdependence of the modifications, related functions, etc. The extraction unit, for example, prioritizes extraction of highly relevant modifications. The extraction unit can also postpone extraction of less relevant modifications. The extraction unit can also adjust the extraction order based on the relevance. This enables efficient extraction of changes by adjusting the extraction order based on the relevance of the modifications. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the relevance of the modifications to a generation AI and have the generation AI adjust the extraction order.

[0082] When extracting changes, the extraction unit can adjust the level of extraction detail depending on the expertise level of the reviser. The expertise level of the reviser includes, for example, the reviser's years of experience, field of expertise, etc. For example, in the case of a reviser with a high level of expertise, the extraction unit uses AI to extract detailed changes. In addition, in the case of a reviser with a low level of expertise, the extraction unit can also use AI to extract simplified changes. The extraction unit can also adjust the level of extraction detail based on the expertise level. In this way, appropriate information can be provided by adjusting the level of extraction detail depending on the expertise level of the reviser. Some or all of the above-mentioned processing in the extraction unit may be performed using AI, for example, or may be performed without using AI. For example, the extraction unit can input the expertise level of the reviser to the generation AI and cause the generation AI to adjust the level of extraction detail.

[0083] The identification unit can analyze the user's emotions and adjust the atavistic risk identification method based on the analyzed user's emotions. Examples of user emotions include stress, relaxation, and hurry. For example, when the user is stressed, the identification unit can provide a simplified risk identification method. Furthermore, when the user is relaxed, the identification unit can provide a detailed risk identification method. Furthermore, when the user is hurrying, the identification unit can provide a quick risk identification method. This reduces the burden on the user by adjusting the risk identification method according to the user's emotions. The emotion estimation is realized using an emotion estimation function, such as 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. Some or all of the above-described processing in the identification unit can be performed using, for example, an AI or without an AI. For example, the identification unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the risk identification method based on the emotion.

[0084] When identifying a risk of atavism, the identification unit can adjust the level of specific detail based on the importance of the modification content. The importance of the modification content includes, for example, the scope of impact of the modification and the urgency of the modification. For example, in the case of an important modification content, the identification unit may have the AI ​​perform detailed risk identification. In addition, in the case of a modification content with low importance, the identification unit may have the AI ​​perform simplified risk identification. In addition, in the case of a modification content with medium importance, the identification unit may have the AI ​​perform risk identification with an appropriate level of detail. This enables efficient risk identification by adjusting the level of specific detail according to the importance of the modification content. Some or all of the above-described processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit may input the importance of the modification content to the generation AI and cause the generation AI to adjust the level of specific detail.

[0085] When identifying the risk of atavism, the identification unit can apply different identification algorithms depending on the category of the modification. Categories of the modification include, for example, price changes, product descriptions, and image modifications. For example, in the case of a price change modification, the identification unit can have the AI ​​apply an identification algorithm dedicated to price changes. Furthermore, in the case of a product description modification, the identification unit can also have the AI ​​apply an identification algorithm dedicated to product descriptions. Furthermore, in the case of an image modification, the identification unit can also have the AI ​​apply an identification algorithm dedicated to images. This makes it easier to organize information by applying an identification algorithm according to the category of the modification. Some or all of the above-described processing in the identification unit can be performed, for example, using AI, or can be performed without using AI. For example, the identification unit can input the category of the modification to the generation AI and cause the generation AI to apply the identification algorithm.

[0086] When identifying atavism risks, the identification unit can improve the accuracy of the identification by referring to past identification results. Past identification results include, for example, past risk identification results and identification frequency. The identification unit, for example, refers to past identification results to allow the AI ​​to improve the identification accuracy. The identification unit can also identify areas where risks frequently occur from past identification results and have the AI ​​focus on identifying those areas. The identification unit can also analyze past identification results and allow the AI ​​to propose an optimal identification method. In this way, the accuracy of identification is improved by referring to past identification results. Some or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input past identification results into the generation AI and cause the generation AI to improve the identification accuracy.

[0087] The identification unit can analyze the user's emotions and determine the priority of risks to be identified based on the analyzed user's emotions. Examples of user emotions include stress, relaxation, and hurry. For example, when the user is feeling stressed, the identification unit causes the AI ​​to prioritize important risks. Furthermore, when the user is relaxed, the identification unit can cause the AI ​​to identify all risks equally. Furthermore, when the user is in a hurry, the identification unit can cause the AI ​​to prioritize the latest risks. Thus, by determining the priority of risks according to the user's emotions, important risks can be prioritized. The emotion estimation is realized using an emotion estimation function, 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. Some or all of the above-described processing in the identification unit can be performed using, for example, an AI. For example, the identification unit can input the user's emotion data into the generation AI and cause the generation AI to determine risk priorities based on emotions.

[0088] When identifying atavism risks, the identification unit can determine a specific priority based on the submission time of the modifications. The submission time of the modifications includes, for example, the submission date and time, the submission frequency, etc. The identification unit, for example, prioritizes identifying risks of modifications submitted recently. The identification unit can also postpone risks of modifications submitted recently. The identification unit can also adjust the priority of risk identification based on the submission time. This enables efficient risk identification by determining the specific priority based on the submission time of the modifications. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the submission time of the modifications to the generation AI and have the generation AI determine the specific priority.

[0089] When identifying atavism risks, the identification unit can adjust the specific order based on the relevance of the modification contents. The relevance of the modification contents includes, for example, interdependence of the modification contents, related functions, etc. The identification unit, for example, prioritizes identifying risks of highly relevant modification contents. The identification unit can also postpone risks of less relevant modification contents. The identification unit can also adjust the order of risk identification based on the relevance. This enables efficient risk identification by adjusting the specific order based on the relevance of the modification contents. Some or all of the above-described processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the relevance of the modification contents to the generation AI and cause the generation AI to adjust the specific order.

[0090] When identifying atavism risks, the identification unit can adjust the level of specific detail according to the modifier's level of expertise. The modifier's level of expertise includes, for example, the modifier's years of experience, field of expertise, etc. For example, in the case of a modifier with a high level of expertise, the identification unit may use an AI to perform detailed risk identification. In addition, in the case of a modifier with a low level of expertise, the identification unit may use an AI to perform simplified risk identification. The identification unit can also adjust the level of specific detail based on the level of expertise. In this way, appropriate information can be provided by adjusting the level of specific detail according to the modifier's level of expertise. Some or all of the above-described processing in the identification unit may be performed using, or without, AI. For example, the identification unit may input the modifier's level of expertise to the generation AI and cause the generation AI to adjust the level of specific detail. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned storage unit, extraction unit, and identification unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the storage unit is realized by either the smart device 14 or the data processing device 12. For example, the storage unit stores the revision history in the database 24 of the data processing device 12. The extraction unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and extracts changes from the stored revision history. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies a risk of atavism based on the extracted changes. The identification unit is also realized, for example, by the control unit 46A of the smart device 14, and warns a person in charge of revision of high-risk areas. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned storage unit, extraction unit, and identification unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the storage unit is realized in either the smart glasses 214 or the data processing device 12. For example, the storage unit stores the revision history in the database 24 of the data processing device 12. The extraction unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and extracts changes from the stored revision history. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and identifies a risk of atavism based on the extracted changes. The identification unit is also realized, for example, by the control unit 46A of the smart glasses 214 and warns a person in charge of revision of high-risk areas. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned storage unit, extraction unit, and identification unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the storage unit is realized in either the headset type terminal 314 or the data processing device 12. For example, the storage unit stores the revision history in the database 24 of the data processing device 12. The extraction unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and extracts changes from the stored revision history. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies the risk of atavism based on the extracted changes. The identification unit is also realized, for example, by the control unit 46A of the headset type terminal 314, and warns the person in charge of revision of high-risk areas. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned storage unit, extraction unit, and identification unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the storage unit is realized by either the robot 414 or the data processing device 12. For example, the storage unit stores the revision history in the database 24 of the data processing device 12. The extraction unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and extracts changes from the stored revision history. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies a risk of atavism based on the extracted changes. The identification unit is also realized, for example, by the control unit 46A of the robot 414, and warns a person in charge of revision of high-risk areas.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The revision management system further includes a notification unit. The notification unit can notify the person in charge of revisions in real time of the results of saving the revision history, extracting changes, and identifying reversion risks. For example, the notification unit can send an email or push notification to the person in charge of revisions when the revision history is saved. The notification unit can also display changes extracted in real time on a dashboard for the person in charge of revisions. Furthermore, the notification unit can issue an alert to the person in charge of revisions when a reversion risk is identified. This allows the person in charge of revisions to understand the progress and risks of the revision work in real time, enabling them to respond quickly.

[0093] The storage unit can manage versions of the revisions when saving the revision history. For example, the storage unit can individually save each version of the revisions and compare past versions with the current version. The storage unit can also display the differences between revision versions, allowing the person in charge of revisions to revert to a past version. Furthermore, the storage unit can display the version history of the revisions in chronological order, allowing the person in charge of revisions to understand the process of the revisions. This facilitates version management of the revisions and improves the efficiency of the revision work.

[0094] When extracting changes in a revision, the extraction unit can evaluate the scope of impact of the revision. For example, the extraction unit can evaluate the extent to which the revision will affect other parts, and if the scope of impact is large, issue a warning to the person responsible for the revision. The extraction unit can also visualize the scope of impact of the revision, allowing the person responsible for the revision to intuitively understand the scope of impact. Furthermore, for revisions with a large scope of impact, the extraction unit can extract detailed changes and provide them to the person responsible for the revision. This makes it possible to extract changes that take the scope of impact of the revision into consideration, improving the accuracy of the revision work.

[0095] The identification unit can take into account the dependency relationships between modifications when identifying the risk of atavism. For example, if a modification is dependent on another modification, the identification unit can evaluate the risk by taking that dependency relationship into account. The identification unit can also determine that modifications with strong dependencies pose a high risk and issue a warning to the person responsible for modification. Furthermore, the identification unit can visualize the dependencies so that the person responsible for modification can intuitively understand them. This makes it possible to identify risks by taking into account the dependency relationships between modifications, improving the accuracy of modification work.

[0096] The storage unit can analyze the user's emotions and adjust the method of saving the revision history based on the analyzed user's emotions. For example, if the user is feeling stressed, the AI ​​in the storage unit can automatically save the revision history, reducing the burden on the user. Also, if the user is relaxed, the AI ​​in the storage unit can confirm with the user whether to save the revision history and save according to the user's intention. Furthermore, if the user is in a hurry, the AI ​​in the storage unit can quickly save the revision history to support the user's work. This realizes a flexible saving method that corresponds to the user's emotions and reduces the burden on the user.

[0097] When saving the revision history, the storage unit can evaluate the security risk of the revisions and adjust the storage method. For example, if the revisions contain confidential information, the storage unit will have AI encrypt and store the data to prevent information leaks. Also, if the revisions are public information, the storage unit can use the AI ​​to apply the normal storage method for efficient storage. Furthermore, the storage unit can evaluate the security risk of the revisions and issue a warning to the person responsible for making the revisions if the risk is high. This realizes a storage method that takes the security risk of the revisions into consideration, improving the safety of information.

[0098] When saving the revision history, the storage unit can evaluate the future usability of the revisions and adjust the storage method. For example, if the revisions are likely to be reused in future projects, the storage unit can use AI to store detailed information, facilitating reuse. In addition, if the revisions are temporary, the storage unit can use AI to store simplified information, reducing the amount of data. Furthermore, the storage unit can evaluate the future usability of the revisions and notify the person responsible for making the revisions if there is a high possibility of their use. This realizes a storage method that takes the future usability of the revisions into consideration, enabling efficient data management.

[0099] When saving the revision history, the storage unit can adjust the storage method taking into account the legal requirements of the revisions. For example, if the revisions are legally required to be saved, the storage unit will use AI to save detailed information, thereby meeting the legal requirements. In addition, if the revisions do not legally need to be saved, the storage unit can use AI to save simplified information, thereby reducing the amount of data. Furthermore, the storage unit can evaluate the legal requirements of the revisions and notify the person in charge of making the revisions if the requirements are strict. This allows for a storage method that takes into account the legal requirements of the revisions, thereby reducing legal risks.

[0100] The storage unit can analyze the user's emotions and determine the priority of the revision history to be saved based on the analyzed user's emotions. For example, if the user is feeling stressed, the storage unit allows the AI ​​to save important revision history with priority. Also, if the user is relaxed, the storage unit can allow the AI ​​to save all revision history evenly. Furthermore, if the user is in a hurry, the storage unit can allow the AI ​​to save the most recent revision history with priority. In this way, by determining the priority of the revision history to be saved according to the user's emotions, important revision history can be saved with priority.

[0101] When saving the revision history, the storage unit can prioritize saving highly relevant revisions by taking into account the geographical distribution of the revisions. For example, the storage unit can prioritize saving revisions that are frequently made in a specific region. The storage unit can also prioritize saving geographically important revisions. Furthermore, the storage unit can prioritize saving highly relevant revisions based on the geographical distribution. In this way, highly relevant revisions can be prioritized by taking into account the geographical distribution of the revisions.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The storage unit stores the revision history. The revision history includes detailed information such as the revision content, the revision date and time, and the person who made the revision. The storage unit stores the revision content as text data, for example. The storage unit can also record the revision date and time as a timestamp. The storage unit can also store information about the person who made the revision as a user ID. For example, the storage unit stores the revision content in a database and manages the revision history. Step 2: The extraction unit extracts changes based on the revision history stored by the storage unit. For example, the extraction unit detects new revisions and compares them with past revision history. For example, the extraction unit extracts differences between revisions using a text comparison algorithm. The extraction unit can also highlight changes in the revisions. For example, the extraction unit displays the changes in the revisions in a list format and provides it to the person responsible for making the revisions. Step 3: The identification unit identifies the risk of atavism based on the changes extracted by the extraction unit. For example, the identification unit compares the past revision history with the current revision content to identify areas at risk of atavism. For example, the identification unit evaluates the risk of atavism using a risk identification algorithm. The identification unit can also warn the person responsible for modification of high-risk areas. For example, the identification unit displays high-risk areas in red to alert the person responsible for modification.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0108] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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).

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0124] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0140] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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."

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] [Explanation of symbols]

[0176] 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 storage unit for storing the revision history; an extracting unit that extracts changes based on the revision history stored by the storing unit; an identification unit that identifies a risk of atavism based on the changes extracted by the extraction unit; A system characterized by:

2. The storage unit Save detailed information about the revision, revision date and time, and the person who made the revision 2. The system of claim 1.

3. The extraction unit Detect new modifications and compare them with previous modifications 2. The system of claim 1.

4. The identification unit Identify areas at risk of regression and alert fixers 2. The system of claim 1.

5. The storage unit Analyze user sentiment and adjust the frequency of saving revision history based on the analyzed user sentiment.

2. The system of claim 1.

6. The storage unit When saving revision history, adjust the level of detail saved based on the importance of the revisions 2. The system of claim 1.

7. The storage unit When saving revision history, apply different saving formats depending on the category of revisions 2. The system of claim 1.

8. The storage unit When saving revision history, improve the accuracy of saving by referring to the revision history of the person who made the revision.

2. The system of claim 1.

Images