system

Abstract

The system according to the embodiment aims to explain the contents of contracts and terms and conditions in an easy-to-understand manner, so that users can use the service with peace of mind. [Solution] A system according to an embodiment includes an identification unit, an explanation unit, a rating collection unit, a rating publication unit, a list generation unit, and a provision unit. The identification unit identifies the changes. The explanation unit clearly explains the changes identified by the identification unit. The rating collection unit allows users to rate the contract or service content. The rating publication unit publishes the ratings collected by the rating collection unit. The list generation unit generates a recommended service list based on the ratings and risk information published by the rating publication unit. The provision unit provides the list generated by the list generation unit.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult for individuals to fully understand the contracts and terms and conditions, which led to concerns about using the service.

[0005] The system according to the embodiment aims to explain the contents of contracts and terms and conditions in an easy-to-understand manner, so that users can use the service with peace of mind. [Means for solving the problem]

[0006] The system according to the embodiment includes an identification unit, an explanation unit, a rating collection unit, a rating publication unit, a list generation unit, and a provision unit. The identification unit identifies the changes. The explanation unit clearly explains the changes identified by the identification unit. The rating collection unit allows users to rate the contract or service content. The rating publication unit publishes the ratings collected by the rating collection unit. The list generation unit generates a recommended service list based on the ratings and risk information published by the rating publication unit. The provision unit provides the list generated by the list generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can explain the contents of the contract and terms and conditions in an easy-to-understand manner, allowing users to use the service with peace of mind. [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 contract and terms explanation system according to an embodiment of the present invention uses a generation AI to clearly explain and summarize contracts and terms provided by service providers, enabling the system to confirm their safety from a contractual perspective. This system identifies changes to the terms of services provided online and indicates risks. Next, users rate the contracts and service content and publish the results. Finally, a "recommended services / app services" list is created based on this information and provided to users. This list is monetized through performance-based advertising based on customer referrals from the service. For example, changes to the terms of services provided online can be identified and risks indicated. In this case, the generation AI automatically detects changes to the terms and conditions and provides an easy-to-understand explanation of the changes. For example, by clearly indicating important changes to users, such as changes to privacy policies and revisions to terms of use, users can easily understand the risks. Next, users rate the contracts and service content and publish the results. Users can rate the contract content and usability of the services they use and share their ratings with other users. This information can serve as reference information for other users when choosing services. Furthermore, a "recommended services / app services" list is created based on this information and provided to users. This list is generated based on user ratings and risk information on terms and conditions, and recommends services that users can use with confidence. For example, services with strict privacy policies and high user ratings are included on the list. This list is monetized through performance-based advertising based on customer referrals from this service. Specifically, when a service on the list acquires new users, advertising revenue is generated based on their performance. This system ensures the sustainability of the service's operations. In this way, this invention uses generative AI to clearly explain and summarize contracts and terms and conditions, providing an environment in which users can use services with confidence. This is expected to alleviate concerns about personal information protection and accelerate the use of services, especially on smartphones. As a result, the contract and terms and conditions explanation system makes it easier for users to understand the contents of contracts and terms and conditions, providing an environment in which users can use services with confidence.

[0029] A contract and terms explanation system according to an embodiment includes an identification unit, an explanation unit, a rating collection unit, a rating publication unit, a list generation unit, and a provision unit. The identification unit identifies changes to terms of a service provided on the web. The identification unit identifies changes to the terms using, for example, natural language processing technology. Natural language processing technology can accurately identify changes to the terms using techniques such as morphological analysis, grammatical analysis, and semantic analysis. For example, the identification unit automatically detects changes to the terms and conditions and provides an easy-to-understand explanation of the changes. The explanation unit summarizes the changes identified by the identification unit and provides an easy-to-understand explanation to the user. For example, the explanation unit summarizes the identified changes using a generation AI and provides an easy-to-understand explanation to the user. The generation AI can summarize the identified changes using a text generation AI (e.g., LLM) or a multimodal generation AI, and provides an easy-to-understand explanation to the user. The rating collection unit provides an interface for users to evaluate the contract content and usability of the service they have used. For example, the rating collection unit provides an interface for users to evaluate the contract content and usability of the service they have used. The interface includes a method for users to input ratings and a method for displaying rating results, etc. The rating publishing unit provides a platform for sharing collected ratings with other users. The rating publishing unit, for example, provides a platform for sharing collected ratings with other users. The platform includes a method for displaying ratings and a method for sharing between users, etc. The list generation unit has an algorithm for generating a recommended service list by integrating user ratings and risk information. The list generation unit has, for example, an algorithm for generating a recommended service list by integrating user ratings and risk information. The algorithm includes data to be used, a calculation method, etc. The provision unit provides the generated recommended service list to the user. The provision unit provides, for example, the generated recommended service list to the user. The provision method includes the timing of provision, the method of provision, etc. As a result, the contract and terms and conditions explanation system according to the embodiment makes it easier for users to understand the contents of the contract and terms and conditions, and can provide an environment in which services can be used with peace of mind.

[0030] The identification unit can identify the changes to the terms and conditions using natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. The identification unit can identify the changes to the terms and conditions using, for example, morphological analysis. Morphological analysis is a technology that divides a sentence into words and analyzes the part of speech of each word. For example, the identification unit can identify the changes to the terms and conditions using morphological analysis and explain the changes in an easy-to-understand manner. The identification unit can also identify the changes to the terms and conditions using grammatical analysis. Grammatical analysis is a technology that analyzes the grammatical structure of a sentence and identifies the subject, predicate, object, etc. of each sentence. For example, the identification unit can identify the changes to the terms and conditions using grammatical analysis and explain the changes in an easy-to-understand manner. The identification unit can also identify the changes to the terms and conditions using semantic analysis. Semantic analysis is a technology that analyzes the meaning of a sentence and identifies the semantic relationship between each sentence. For example, the identification unit can identify the changes to the terms and conditions using semantic analysis and explain the changes in an easy-to-understand manner. This allows the use of natural language processing technology to accurately identify changes to the terms and conditions. Some or all of the above-described processing in the identification unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the identification unit may identify changes using a generation AI model for identifying changes to the terms and conditions.

[0031] The explanation unit can summarize the identified changes and provide an easy-to-understand explanation to the user. The explanation unit can, for example, use a generation AI to summarize the identified changes and provide an easy-to-understand explanation to the user. The generation AI can summarize the identified changes and provide an easy-to-understand explanation to the user using a text generation AI (e.g., LLM) or a multimodal generation AI. For example, to summarize the identified changes, the generation AI can perform summarization based on the length of the sentence and the importance of the information to be summarized. The generation AI can summarize the identified changes based on, for example, the length of the sentence. The length of the sentence is an indicator of the amount of information to be summarized, and the generation AI can perform summarization based on the length of the sentence. The generation AI can also perform summarization based on the importance of the information to be summarized. The importance of the information to be summarized is an indicator of the importance of the information to be summarized, and the generation AI can perform summarization based on the importance of the information to be summarized. For example, the generation AI can evaluate the importance of the information to be summarized and prioritize summarizing important information. This makes it easier for the user to understand by summarizing the identified changes. Some or all of the above-described processing in the explanation unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the explanation unit may perform summarization using a generative AI model for summarizing the identified changes.

[0032] The evaluation collection unit can provide an interface for users to evaluate the contract details or usability of the service they have used. The evaluation collection unit provides, for example, an interface for users to evaluate the contract details or usability of the service they have used. The interface includes a method for users to input information and a method for displaying evaluation results. For example, the evaluation collection unit provides an interface for users to evaluate the contract details of the service they have used. The user can evaluate the contract details of the service they have used through the interface. The evaluation collection unit can also provide an interface for users to evaluate the usability of the service they have used. The user can evaluate the usability of the service they have used through the interface. For example, the evaluation collection unit provides a questionnaire-style interface for users to evaluate the contract details or usability of the service they have used. The user can evaluate the contract details or usability of the service they have used through the questionnaire-style interface. The evaluation collection unit can also provide a feedback-style interface for users to evaluate the contract details or usability of the service they have used. The user can evaluate the contract details or usability of the service they have used through the feedback-style interface. This allows the user to evaluate the contract details or usability of the service. Some or all of the above-described processing in the evaluation collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the evaluation collection unit may perform evaluations using a generation AI model for evaluating the contract details and usability of the service used by the user.

[0033] The rating publishing unit may provide a platform for sharing collected ratings with other users. The rating publishing unit may, for example, provide a platform for sharing collected ratings with other users. The platform may include a method for displaying ratings and a method for sharing ratings between users. For example, the rating publishing unit may provide a web platform for sharing collected ratings with other users. A user may view the collected ratings and share them with other users through the web platform. The rating publishing unit may also provide a mobile application for sharing collected ratings with other users. A user may view the collected ratings and share them with other users through the mobile application. For example, the rating publishing unit may provide a social media platform for sharing collected ratings with other users. A user may view the collected ratings and share them with other users through the social media platform. The rating publishing unit may also provide an email service for sharing collected ratings with other users. A user may share the collected ratings with other users through the email service. In this way, sharing ratings with other users can provide reference information for selecting a service. Some or all of the above-described processing in the rating publishing unit may be performed using, for example, a generating AI, or may be performed without using a generating AI. For example, the rating publishing unit may publish the ratings using a generating AI model for sharing collected ratings with other users.

[0034] The list generation unit may include an algorithm that integrates user ratings and risk information to generate a recommended service list. The list generation unit may include, for example, an algorithm that integrates user ratings and risk information to generate a recommended service list. The algorithm includes data to be used and a calculation method. For example, the list generation unit generates a recommended service list based on user ratings and risk information. The user ratings are the results of users' evaluations of the contract details and usability of the services they used, and the risk information is information indicating changes to the terms and conditions and high-risk areas. The list generation unit integrates this information to generate a list of recommended services that the user can use with confidence. For example, the list generation unit prioritizes services with high user ratings and low risk information in the list. The list generation unit may also determine the update frequency of the list based on the user ratings and risk information. For example, the list generation unit periodically collects user ratings and risk information and updates the list. This allows the user to always select services based on the latest information. Some or all of the above-described processing in the list generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the list generator can generate the list using a generative AI model for integrating user ratings and risk information to generate a recommended service list.

[0035] The providing unit can provide the generated recommended service list to the user. For example, the providing unit provides the generated recommended service list to the user. The providing method includes the timing of providing, the providing method, etc. For example, the providing unit can provide the generated recommended service list to the user through a web platform. The user can view and use the generated recommended service list through the web platform. The providing unit can also provide the generated recommended service list to the user through a mobile application. The user can view and use the generated recommended service list through the mobile application. For example, the providing unit can provide the generated recommended service list to the user through email. The user can receive and use the generated recommended service list through email. The providing unit can also provide the generated recommended service list to the user through a social media platform. The user can view and use the generated recommended service list through the social media platform. Thus, by providing the recommended service list to the user, the service can be used with peace of mind. Some or all of the above-described processing in the providing unit can be performed, for example, using a generation AI or without using a generation AI. For example, the providing unit can provide the list using a generative AI model for providing the generated recommended service list.

[0036] The identification unit can analyze the history of past changes to the terms and conditions and optimize the algorithm for identifying changes. The identification unit can, for example, use a generation AI to analyze the history of past changes to the terms and conditions and optimize the algorithm for identifying changes. The generation AI can analyze the history of past changes to the terms and conditions and identify parts that are frequently changed. For example, the identification unit allows the generation AI to analyze the history of past changes to the terms and conditions and identify parts that are frequently changed. The identification unit can also allow the generation AI to learn changes that are important to users from the past change history and improve the identification accuracy. Furthermore, the identification unit can allow the generation AI to prioritize high-risk changes based on the past change history. In this way, the accuracy of the identification algorithm can be improved by analyzing the past change history. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the identification unit can analyze the history of past changes to the terms and conditions and optimize the identification algorithm using a generation AI model for optimizing the algorithm for identifying changes.

[0037] When identifying changes to the terms and conditions, the identification unit can determine a specific priority based on the impact of the changes. For example, when identifying changes to the terms and conditions, the identification unit can use a generation AI to determine a specific priority based on the impact of the changes. The generation AI can evaluate the impact of the changes and prioritize identifying changes that are important to the user. For example, the identification unit can use the generation AI to evaluate the impact of the changes and prioritize identifying changes that are important to the user. The identification unit can also prioritize identifying changes with high risk based on the impact of the changes. Furthermore, the identification unit can use the generation AI to analyze the impact of the changes and provide the most important information to the user. In this way, important changes can be prioritized by determining the priority based on the impact of the changes. Some or all of the above-described processing in the identification unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, when identifying changes to the terms and conditions, the identification unit can determine the specific priority using a generation AI model for determining the specific priority based on the impact of the changes.

[0038] The identification unit can improve the accuracy of identification by taking into account the user's geographical location information when identifying changes to the terms and conditions. For example, the identification unit can improve the accuracy of identification by taking into account the user's geographical location information when identifying changes to the terms and conditions using a generation AI. The generation AI can identify region-specific changes to the terms and conditions based on the user's geographical location information. For example, the identification unit can identify region-specific changes to the terms and conditions based on the user's geographical location information. The identification unit can also indicate risks related to the region by taking into account the user's geographical location information. Furthermore, the identification unit can identify changes by taking into account region-specific legal requirements based on the user's geographical location information. In this way, region-specific changes can be accurately identified by taking into account the geographical location information. Some or all of the above-described processing in the identification unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the identification unit can improve the accuracy of identification by using a generation AI model that takes into account the user's geographical location information when identifying changes to the terms and conditions.

[0039] The identification unit can improve the accuracy of identification by referring to related legal documents when identifying changes to the terms and conditions. For example, the identification unit can improve the accuracy of identification by referring to related legal documents when identifying changes to the terms and conditions using a generation AI. The generation AI can identify changes to the terms and conditions by referring to related legal documents. For example, the identification unit can identify changes to the terms and conditions by having the generation AI refer to related legal documents. The identification unit can also identify high-risk changes based on legal documents. Furthermore, the identification unit can identify changes that are important to the user by having the generation AI refer to legal documents. In this way, the accuracy of identification can be improved by referring to related legal documents. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the identification unit can improve the accuracy of identification by using a generative AI model that improves the accuracy of identification by referring to related legal documents when identifying changes to the terms and conditions.

[0040] When summarizing the identified changes, the explanation unit can adjust the level of detail of the summary based on the importance of the changes. When summarizing the identified changes, the explanation unit can adjust the level of detail of the summary based on the importance of the changes, for example, using a generation AI. The generation AI can evaluate the importance of the changes and summarize important changes in detail. For example, the explanation unit can have the generation AI evaluate the importance of the changes and summarize important changes in detail. The explanation unit can also have the generation AI analyze the importance of the changes and provide important information to the user. In this way, important information can be provided in detail by adjusting the level of detail of the summary based on the importance of the changes. Some or all of the above-described processing in the explanation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, when summarizing the identified changes, the explanation unit can adjust the level of detail of the summary using a generation AI model for adjusting the level of detail of the summary based on the importance of the changes.

[0041] The explanation unit can apply different summarization algorithms depending on the category of changes when summarizing the identified changes. For example, the explanation unit can use a generation AI to apply different summarization algorithms depending on the category of changes when summarizing the identified changes. The generation AI can identify the category of changes and apply an appropriate summarization algorithm. For example, the explanation unit can have the generation AI identify the category of changes and apply an appropriate summarization algorithm. The explanation unit can also have the generation AI summarize high-risk changes in detail depending on the category. Furthermore, the explanation unit can have the generation AI provide information important to the user based on the category. In this way, applying a summarization algorithm depending on the category of changes can provide a more appropriate summary. Some or all of the above-described processing in the explanation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the explanation unit can apply a summarization algorithm using a generation AI model for applying different summarization algorithms depending on the category of changes when summarizing the identified changes.

[0042] When summarizing the identified changes, the explanation unit can determine the priority of summaries based on the time the changes were submitted. When summarizing the identified changes, the explanation unit, for example, uses a generation AI to determine the priority of summaries based on the time the changes were submitted. The generation AI can prioritize summarizing the most recent changes, taking into account the time the changes were submitted. For example, the explanation unit can prioritize summarizing the most recent changes, taking into account the time the changes were submitted. The explanation unit can also prioritize summarizing high-risk changes, taking into account the time the changes were submitted. Furthermore, the explanation unit can provide information important to the user based on the time the changes were submitted. In this way, by determining the priority of summaries based on the time of submission, the most recent information can be provided preferentially. Some or all of the above-described processing in the explanation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, when summarizing the identified changes, the explanation unit can determine the priority of summaries using a generation AI model for determining the priority of summaries based on the time the changes were submitted.

[0043] When summarizing the identified changes, the explanation unit can adjust the order of summaries based on the relevance of the changes. When summarizing the identified changes, the explanation unit can adjust the order of summaries based on the relevance of the changes, for example, using a generation AI. The generation AI can evaluate the relevance of the changes and prioritize summarizing important changes. For example, the explanation unit can use the generation AI to evaluate the relevance of the changes and prioritize summarizing important changes. The explanation unit can also use the generation AI to prioritize summarizing high-risk changes based on their relevance. Furthermore, the explanation unit can provide information important to the user based on their relevance. In this way, by adjusting the order of summaries based on the relevance of the changes, important information can be prioritized and provided to the user. Some or all of the above-described processing in the explanation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, when summarizing the identified changes, the explanation unit can adjust the order of summaries using a generation AI model for adjusting the order of summaries based on the relevance of the changes.

[0044] The rating collection unit can analyze the user's past rating history and select the optimal rating collection method. The rating collection unit can analyze the user's past rating history using, for example, a generation AI and select the optimal rating collection method. The generation AI can analyze the user's past rating history and suggest optimal rating items. For example, the rating collection unit can have the generation AI suggest optimal rating items based on the user's past rating history. The rating collection unit can also have the generation AI analyze the user's past rating history and provide an appropriate rating method. Furthermore, the rating collection unit can have the generation AI refer to the user's past rating history to improve the accuracy of the ratings. In this way, the optimal rating collection method can be provided by analyzing the past rating history. Some or all of the above-described processing in the rating collection unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the rating collection unit can analyze the user's past rating history and select the rating collection method using a generation AI model for selecting the optimal rating collection method.

[0045] The rating collection unit can customize rating items based on the user's current usage status when collecting ratings. The rating collection unit, for example, uses a generation AI to customize rating items based on the user's current usage status when collecting ratings. The generation AI can analyze the user's current usage status and provide appropriate rating items. For example, the rating collection unit allows the generation AI to provide appropriate rating items based on the user's current usage status. The rating collection unit can also customize the rating items by taking the user's current usage status into consideration. Furthermore, the rating collection unit can allow the generation AI to improve the accuracy of ratings according to the user's usage status. As a result, more appropriate ratings can be collected by customizing the rating items based on the current usage status. Some or all of the above-described processing in the rating collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the rating collection unit can customize the rating items using a generation AI model for customizing rating items based on the user's current usage status when collecting ratings.

[0046] The evaluation collection unit can select evaluation items taking into account the user's geographical location information when collecting evaluations. The evaluation collection unit, for example, uses a generation AI to select evaluation items taking into account the user's geographical location information when collecting evaluations. The generation AI can provide region-specific evaluation items based on the user's geographical location information. For example, the evaluation collection unit can provide region-specific evaluation items based on the user's geographical location information using the generation AI. The evaluation collection unit can also select appropriate evaluation items by taking into account the user's geographical location information. Furthermore, the evaluation collection unit can improve the accuracy of the evaluations based on the user's geographical location information. In this way, region-specific evaluation items can be provided by taking into account the geographical location information. Some or all of the above-described processing in the evaluation collection unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the evaluation collection unit can select evaluation items using a generation AI model for selecting evaluation items taking into account the user's geographical location information when collecting evaluations.

[0047] The rating publishing unit can select the optimal publishing method by referring to the user's past rating history when publishing a rating. The rating publishing unit can select the optimal publishing method by referring to the user's past rating history, for example, using a generation AI. The generation AI can analyze the user's past rating history and propose the optimal publishing method. For example, the rating publishing unit can propose the optimal publishing method based on the user's past rating history. The rating publishing unit can also analyze rating trends from the user's past rating history and provide an appropriate publishing method. Furthermore, the rating publishing unit can improve the accuracy of the ratings by referring to the user's past rating history. In this way, the optimal publishing method can be provided by referring to the past rating history. Some or all of the above-described processing in the rating publishing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the rating publishing unit can select the publishing method by referring to the user's past rating history when publishing a rating, using a generation AI model for selecting the optimal publishing method.

[0048] The rating disclosure unit can adjust the level of detail of disclosure based on the importance of the rating when disclosing the rating. The rating disclosure unit can adjust the level of detail of disclosure based on the importance of the rating, for example, using a generation AI. The generation AI can evaluate the importance of the rating and disclose important ratings in detail. For example, the rating disclosure unit can evaluate the importance of the rating and disclose important ratings in detail. The rating disclosure unit can also disclose high-risk ratings in detail based on the importance of the rating. Furthermore, the rating disclosure unit can analyze the importance of the rating and provide information that is important to the user. In this way, important information can be provided in detail by adjusting the level of detail of disclosure based on the importance of the rating. Some or all of the above-described processing in the rating disclosure unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the rating disclosure unit can adjust the level of detail when disclosing the rating using a generation AI model for adjusting the level of detail of disclosure based on the importance of the rating.

[0049] The rating publishing unit can select the optimal display method by taking into consideration the user's device information when publishing the rating. The rating publishing unit can select the optimal display method by taking into consideration the user's device information, for example, using a generation AI. The generation AI can provide an appropriate display method based on the user's device information. For example, the rating publishing unit can provide an appropriate display method by using the generation AI based on the user's device information. The rating publishing unit can also select the optimal display method by taking into consideration the user's device information. Furthermore, the rating publishing unit can also improve the accuracy of the display based on the user's device information. This makes it possible to provide the optimal display method by taking into consideration the device information. Some or all of the above-described processing in the rating publishing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the rating publishing unit can select the display method by using a generation AI model for selecting the optimal display method by taking into consideration the user's device information when publishing the rating.

[0050] When generating a list, the list generation unit can select an optimal list generation method by referring to the user's past rating history. When generating a list, the list generation unit can, for example, use a generation AI to select an optimal list generation method by referring to the user's past rating history. The generation AI can analyze the user's past rating history and include optimal services in the list. For example, the list generation unit can include optimal services in the list based on the user's past rating history. The list generation unit can also prioritize highly rated services in the list based on the user's past rating history. Furthermore, the list generation unit can improve the accuracy of the list by referring to the user's past rating history. In this way, an optimal list generation method can be provided by referring to the past rating history. Some or all of the above-described processing in the list generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, when generating a list, the list generation unit can select a generation method using a generation AI model that selects an optimal list generation method by referring to the user's past rating history.

[0051] The list generation unit can adjust the level of detail of the list based on the importance of the evaluation when generating the list. The list generation unit can adjust the level of detail of the list based on the importance of the evaluation when generating the list, for example, using a generation AI. The generation AI can evaluate the importance of the evaluation and include important services in the list in detail. For example, the list generation unit can evaluate the importance of the evaluation and include important services in the list in detail. The list generation unit can also include high-risk services in the list in detail based on the importance of the evaluation. Furthermore, the list generation unit can analyze the importance of the evaluation and provide information that is important to the user. As a result, important information can be provided in detail by adjusting the level of detail of the list based on the importance of the evaluation. Some or all of the above-mentioned processing in the list generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the list generation unit can adjust the level of detail of the list based on the importance of the evaluation when generating the list, using a generation AI model for adjusting the level of detail of the list based on the importance of the evaluation.

[0052] The list generation unit can select the optimal list generation method by taking into account the user's geographical location information when generating the list. The list generation unit can select the optimal list generation method by taking into account the user's geographical location information when generating the list, for example, using a generation AI. The generation AI can include region-specific services in the list based on the user's geographical location information. For example, the list generation unit can include region-specific services in the list by taking into account the user's geographical location information. The list generation unit can also include appropriate services in the list by taking into account the user's geographical location information. Furthermore, the list generation unit can improve the accuracy of the list by taking into account the user's geographical location information. In this way, region-specific services can be included in the list by taking into account the geographical location information. Some or all of the above-described processing in the list generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the list generation unit can select the generation method by using a generation AI model for selecting the optimal list generation method by taking into account the user's geographical location information when generating the list.

[0053] The list generation unit can improve the accuracy of the list by referring to related market data when generating the list. The list generation unit can improve the accuracy of the list by referring to related market data when generating the list, for example, using a generation AI. The generation AI can refer to market data and include popular services in the list. For example, the list generation unit can refer to market data and include popular services in the list. The list generation unit can also include highly rated services in the list based on the market data. Furthermore, the list generation unit can refer to market data and provide information important to users. In this way, the accuracy of the list can be improved by referring to market data. Some or all of the above-mentioned processing in the list generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the list generation unit can improve the accuracy by using a generation AI model for improving the accuracy of the list by referring to related market data when generating the list.

[0054] When providing the list, the providing unit can select the optimal provision method by referring to the user's past usage history. When providing the list, the providing unit can, for example, use a generation AI to select the optimal provision method by referring to the user's past usage history. The generation AI can analyze the user's past usage history and provide the optimal list. For example, the providing unit can provide the optimal list based on the user's past usage history. The providing unit can also cause the generation AI to prioritize highly rated services in the user's past usage history. Furthermore, the providing unit can also cause the generation AI to improve the accuracy of the list by referring to the user's past usage history. In this way, the optimal list provision method can be provided by referring to the past usage history. Some or all of the above-described processing in the providing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, when providing the list, the providing unit can select the provision method using a generation AI model that refers to the user's past usage history to select the optimal provision method.

[0055] The providing unit can adjust the level of detail of the list provided based on the importance of the list when providing the list. The providing unit can adjust the level of detail of the list provided based on the importance of the list, for example, using a generation AI. The generation AI can evaluate the importance of the list and include important services in the list in detail. For example, the providing unit can evaluate the importance of the list using the generation AI and include important services in the list in detail. The providing unit can also include high-risk services in the list in detail based on the importance of the list. Furthermore, the providing unit can analyze the importance of the list using the generation AI to provide information that is important to the user. As a result, important information can be provided in detail by adjusting the level of detail of the list based on the importance of the list. Some or all of the above-described processing in the providing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the providing unit can adjust the level of detail of the list provided based on the importance of the list when providing the list, using a generation AI model for adjusting the level of detail of the list.

[0056] The providing unit can select the optimal display method by taking into account the user's device information when providing the list. The providing unit can select the optimal display method by taking into account the user's device information, for example, using a generation AI when providing the list. The generation AI can provide an appropriate display method based on the user's device information. For example, the providing unit can provide an appropriate display method by having the generation AI provide the appropriate display method based on the user's device information. The providing unit can also select the optimal display method by having the generation AI take into account the user's device information. Furthermore, the providing unit can also improve the accuracy of the display based on the user's device information. This makes it possible to provide the optimal display method by taking into account the device information. Some or all of the above-described processing in the providing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the providing unit can select the display method by using a generation AI model for selecting the optimal display method by taking into account the user's device information when providing the list.

[0057] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0058] The contract and clause explanation system can further include a history analysis unit that analyzes the user's past contract history. The history analysis unit can identify changes that are important to the user by analyzing services that the user has previously subscribed to and their ratings, and comparing them with the current contract content. For example, the history analysis unit can extract characteristics of services that the user has previously rated highly and check whether there are similarities with the current contract content. The history analysis unit can also identify contract items that the user is particularly interested in from the past contract history and prioritize notifying the user of changes related to those items. Furthermore, the history analysis unit can identify high-risk changes based on contract content in which the user has previously reported problems, and issue a warning to the user. This makes it possible to provide more personalized information by utilizing the user's past contract history.

[0059] When summarizing the identified changes, the explanation unit can apply different summarization algorithms depending on the category of the change. For example, the explanation unit allows the generation AI to identify the category of the change and apply an appropriate summarization algorithm. The explanation unit can also allow the generation AI to summarize high-risk changes in detail depending on the category. Furthermore, the explanation unit allows the generation AI to provide important information to the user based on the category. This allows the generation AI to provide a more appropriate summary by applying a summarization algorithm depending on the category of the change.

[0060] The rating publishing unit may provide a platform for sharing collected ratings with other users. For example, the rating publishing unit may provide a web platform for sharing collected ratings with other users. Users may view the collected ratings and share them with other users through the web platform. The rating publishing unit may also provide a mobile application for sharing collected ratings with other users. Users may view the collected ratings and share them with other users through the mobile application. For example, the rating publishing unit may provide a social media platform for sharing collected ratings with other users. Users may view the collected ratings and share them with other users through the social media platform. The rating publishing unit may also provide an email service for sharing collected ratings with other users. Users may share the collected ratings with other users through the email service. In this way, sharing ratings with other users can provide reference information for selecting a service.

[0061] The providing unit may provide the generated recommended service list to a user. For example, the providing unit may provide the generated recommended service list to a user through a web platform. The user may view and use the generated recommended service list through the web platform. The providing unit may also provide the generated recommended service list to a user through a mobile application. The user may view and use the generated recommended service list through the mobile application. For example, the providing unit may provide the generated recommended service list to a user through email. The user may receive and use the generated recommended service list through email. The providing unit may also provide the generated recommended service list to a user through a social media platform. The user may view and use the generated recommended service list through the social media platform. Thus, providing the recommended service list to a user allows the user to use the service with peace of mind.

[0062] The identification unit can analyze the history of past changes to the terms and conditions and optimize the algorithm for identifying changes. For example, the identification unit allows the generation AI to analyze the history of past changes to the terms and conditions and identify parts that are frequently changed. The identification unit can also allow the generation AI to learn from the past change history which changes are important to users and improve the accuracy of identification. Furthermore, the identification unit can also allow the generation AI to prioritize identifying high-risk changes based on the past change history. In this way, the accuracy of the identification algorithm can be improved by analyzing the past change history.

[0063] When identifying changes to the terms and conditions, the identification unit can determine a specific priority based on the impact of the changes. For example, the identification unit allows the generation AI to evaluate the impact of the changes and prioritize identifying changes that are important to the user. The identification unit can also prioritize identifying changes that pose high risks based on the impact of the changes. Furthermore, the identification unit can also analyze the impact of the changes that the generation AI uses to provide the most important information to the user. In this way, by determining a priority based on the impact of the changes, important changes can be prioritized.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The identification unit identifies the changes to the terms and conditions of the service provided on the web. The identification unit identifies the changes to the terms and conditions using natural language processing technology. Natural language processing technology can accurately identify the changes to the terms and conditions using techniques such as morphological analysis, grammatical analysis, and semantic analysis. Step 2: The explanation unit summarizes the changes identified by the identification unit and explains them to the user in an easy-to-understand manner. The explanation unit uses a generation AI to summarize the identified changes and explains them to the user in an easy-to-understand manner. The generation AI can use a text generation AI (e.g., LLM) or a multimodal generation AI to summarize the identified changes and explain them to the user in an easy-to-understand manner. Step 3: The evaluation collection unit provides an interface for users to evaluate the contract details and usability of the service they used. The interface includes a method for users to input information and a method for displaying evaluation results. Step 4: The rating publishing unit provides a platform for sharing collected ratings with other users. The platform includes a method for displaying ratings and a method for sharing ratings among users. Step 5: The list generator includes an algorithm for generating a list of recommended services by integrating user ratings and risk information. The algorithm includes data to be used, calculation methods, etc. Step 6: The providing unit provides the generated recommended service list to the user. The providing method includes the timing and method of providing the list.

[0066] (Example 2) A contract and terms explanation system according to an embodiment of the present invention uses a generation AI to clearly explain and summarize contracts and terms provided by service providers, enabling the system to confirm their safety from a contractual perspective. This system identifies changes to the terms of services provided online and indicates risks. Next, users rate the contracts and service content and publish the results. Finally, a "recommended services / app services" list is created based on this information and provided to users. This list is monetized through performance-based advertising based on customer referrals from the service. For example, changes to the terms of services provided online can be identified and risks indicated. In this case, the generation AI automatically detects changes to the terms and conditions and provides an easy-to-understand explanation of the changes. For example, by clearly indicating important changes to users, such as changes to privacy policies and revisions to terms of use, users can easily understand the risks. Next, users rate the contracts and service content and publish the results. Users can rate the contract content and usability of the services they use and share their ratings with other users. This information can serve as reference information for other users when choosing services. Furthermore, a "recommended services / app services" list is created based on this information and provided to users. This list is generated based on user ratings and risk information on terms and conditions, and recommends services that users can use with confidence. For example, services with strict privacy policies and high user ratings are included on the list. This list is monetized through performance-based advertising based on customer referrals from this service. Specifically, when a service on the list acquires new users, advertising revenue is generated based on their performance. This system ensures the sustainability of the service's operations. In this way, this invention uses generative AI to clearly explain and summarize contracts and terms and conditions, providing an environment in which users can use services with confidence. This is expected to alleviate concerns about personal information protection and accelerate the use of services, especially on smartphones. As a result, the contract and terms and conditions explanation system makes it easier for users to understand the contents of contracts and terms and conditions, providing an environment in which users can use services with confidence.

[0067] A contract and terms explanation system according to an embodiment includes an identification unit, an explanation unit, a rating collection unit, a rating publication unit, a list generation unit, and a provision unit. The identification unit identifies changes to terms of a service provided on the web. The identification unit identifies changes to the terms using, for example, natural language processing technology. Natural language processing technology can accurately identify changes to the terms using techniques such as morphological analysis, grammatical analysis, and semantic analysis. For example, the identification unit automatically detects changes to the terms and conditions and provides an easy-to-understand explanation of the changes. The explanation unit summarizes the changes identified by the identification unit and provides an easy-to-understand explanation to the user. For example, the explanation unit summarizes the identified changes using a generation AI and provides an easy-to-understand explanation to the user. The generation AI can summarize the identified changes using a text generation AI (e.g., LLM) or a multimodal generation AI, and provides an easy-to-understand explanation to the user. The rating collection unit provides an interface for users to evaluate the contract content and usability of the service they have used. For example, the rating collection unit provides an interface for users to evaluate the contract content and usability of the service they have used. The interface includes a method for users to input ratings and a method for displaying rating results, etc. The rating publishing unit provides a platform for sharing collected ratings with other users. The rating publishing unit, for example, provides a platform for sharing collected ratings with other users. The platform includes a method for displaying ratings and a method for sharing between users, etc. The list generation unit has an algorithm for generating a recommended service list by integrating user ratings and risk information. The list generation unit has, for example, an algorithm for generating a recommended service list by integrating user ratings and risk information. The algorithm includes data to be used, a calculation method, etc. The provision unit provides the generated recommended service list to the user. The provision unit provides, for example, the generated recommended service list to the user. The provision method includes the timing of provision, the method of provision, etc. As a result, the contract and terms and conditions explanation system according to the embodiment makes it easier for users to understand the contents of the contract and terms and conditions, and can provide an environment in which services can be used with peace of mind.

[0068] The identification unit can identify the changes to the terms and conditions using natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. The identification unit can identify the changes to the terms and conditions using, for example, morphological analysis. Morphological analysis is a technology that divides a sentence into words and analyzes the part of speech of each word. For example, the identification unit can identify the changes to the terms and conditions using morphological analysis and explain the changes in an easy-to-understand manner. The identification unit can also identify the changes to the terms and conditions using grammatical analysis. Grammatical analysis is a technology that analyzes the grammatical structure of a sentence and identifies the subject, predicate, object, etc. of each sentence. For example, the identification unit can identify the changes to the terms and conditions using grammatical analysis and explain the changes in an easy-to-understand manner. The identification unit can also identify the changes to the terms and conditions using semantic analysis. Semantic analysis is a technology that analyzes the meaning of a sentence and identifies the semantic relationship between each sentence. For example, the identification unit can identify the changes to the terms and conditions using semantic analysis and explain the changes in an easy-to-understand manner. This allows the use of natural language processing technology to accurately identify changes to the terms and conditions. Some or all of the above-described processing in the identification unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the identification unit may identify changes using a generation AI model for identifying changes to the terms and conditions.

[0069] The explanation unit can summarize the identified changes and provide an easy-to-understand explanation to the user. The explanation unit can, for example, use a generation AI to summarize the identified changes and provide an easy-to-understand explanation to the user. The generation AI can summarize the identified changes and provide an easy-to-understand explanation to the user using a text generation AI (e.g., LLM) or a multimodal generation AI. For example, to summarize the identified changes, the generation AI can perform summarization based on the length of the sentence and the importance of the information to be summarized. The generation AI can summarize the identified changes based on, for example, the length of the sentence. The length of the sentence is an indicator of the amount of information to be summarized, and the generation AI can perform summarization based on the length of the sentence. The generation AI can also perform summarization based on the importance of the information to be summarized. The importance of the information to be summarized is an indicator of the importance of the information to be summarized, and the generation AI can perform summarization based on the importance of the information to be summarized. For example, the generation AI can evaluate the importance of the information to be summarized and prioritize summarizing important information. This makes it easier for the user to understand by summarizing the identified changes. Some or all of the above-described processing in the explanation unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the explanation unit may perform summarization using a generative AI model for summarizing the identified changes.

[0070] The evaluation collection unit can provide an interface for users to evaluate the contract details or usability of the service they have used. The evaluation collection unit provides, for example, an interface for users to evaluate the contract details or usability of the service they have used. The interface includes a method for users to input information and a method for displaying evaluation results. For example, the evaluation collection unit provides an interface for users to evaluate the contract details of the service they have used. The user can evaluate the contract details of the service they have used through the interface. The evaluation collection unit can also provide an interface for users to evaluate the usability of the service they have used. The user can evaluate the usability of the service they have used through the interface. For example, the evaluation collection unit provides a questionnaire-style interface for users to evaluate the contract details or usability of the service they have used. The user can evaluate the contract details or usability of the service they have used through the questionnaire-style interface. The evaluation collection unit can also provide a feedback-style interface for users to evaluate the contract details or usability of the service they have used. The user can evaluate the contract details or usability of the service they have used through the feedback-style interface. This allows the user to evaluate the contract details or usability of the service. Some or all of the above-described processing in the evaluation collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the evaluation collection unit may perform evaluations using a generation AI model for evaluating the contract details and usability of the service used by the user.

[0071] The rating publishing unit may provide a platform for sharing collected ratings with other users. The rating publishing unit may, for example, provide a platform for sharing collected ratings with other users. The platform may include a method for displaying ratings and a method for sharing ratings between users. For example, the rating publishing unit may provide a web platform for sharing collected ratings with other users. A user may view the collected ratings and share them with other users through the web platform. The rating publishing unit may also provide a mobile application for sharing collected ratings with other users. A user may view the collected ratings and share them with other users through the mobile application. For example, the rating publishing unit may provide a social media platform for sharing collected ratings with other users. A user may view the collected ratings and share them with other users through the social media platform. The rating publishing unit may also provide an email service for sharing collected ratings with other users. A user may share the collected ratings with other users through the email service. In this way, sharing ratings with other users can provide reference information for selecting a service. Some or all of the above-described processing in the rating publishing unit may be performed using, for example, a generating AI, or may be performed without using a generating AI. For example, the rating publishing unit may publish the ratings using a generating AI model for sharing collected ratings with other users.

[0072] The list generation unit may include an algorithm that integrates user ratings and risk information to generate a recommended service list. The list generation unit may include, for example, an algorithm that integrates user ratings and risk information to generate a recommended service list. The algorithm includes data to be used and a calculation method. For example, the list generation unit generates a recommended service list based on user ratings and risk information. The user ratings are the results of users' evaluations of the contract details and usability of the services they used, and the risk information is information indicating changes to the terms and conditions and high-risk areas. The list generation unit integrates this information to generate a list of recommended services that the user can use with confidence. For example, the list generation unit prioritizes services with high user ratings and low risk information in the list. The list generation unit may also determine the update frequency of the list based on the user ratings and risk information. For example, the list generation unit periodically collects user ratings and risk information and updates the list. This allows the user to always select services based on the latest information. Some or all of the above-described processing in the list generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the list generator can generate the list using a generative AI model for integrating user ratings and risk information to generate a recommended service list.

[0073] The providing unit can provide the generated recommended service list to the user. For example, the providing unit provides the generated recommended service list to the user. The providing method includes the timing of providing, the providing method, etc. For example, the providing unit can provide the generated recommended service list to the user through a web platform. The user can view and use the generated recommended service list through the web platform. The providing unit can also provide the generated recommended service list to the user through a mobile application. The user can view and use the generated recommended service list through the mobile application. For example, the providing unit can provide the generated recommended service list to the user through email. The user can receive and use the generated recommended service list through email. The providing unit can also provide the generated recommended service list to the user through a social media platform. The user can view and use the generated recommended service list through the social media platform. Thus, by providing the recommended service list to the user, the service can be used with peace of mind. Some or all of the above-described processing in the providing unit can be performed, for example, using a generation AI or without using a generation AI. For example, the providing unit can provide the list using a generative AI model for providing the generated recommended service list.

[0074] The identification unit can estimate the user's emotions and adjust the accuracy of identifying changes to the terms and conditions based on the estimated user emotions. The identification unit can, for example, use a generation AI to estimate the user's emotions and adjust the accuracy of identifying changes to the terms and conditions based on the estimated user emotions. The generation AI can estimate the user's emotions using an emotion analysis algorithm. For example, if the identification unit determines that the user is anxious, the generation AI can identify more detailed changes and clarify risks. Furthermore, if the user is relaxed, the identification unit can identify only important changes and provide a concise explanation. Furthermore, if the user is in a hurry, the identification unit can quickly identify changes and provide information that focuses on the key points. This allows the identification accuracy to be adjusted according to the user's emotions, thereby providing more appropriate information. Emotion estimation is achieved 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 may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the identification unit can estimate a user's emotions and adjust the identification accuracy using a generation AI model for adjusting the identification accuracy of the changes to the terms and conditions based on the estimated user's emotions.

[0075] The identification unit can analyze the history of past changes to the terms and conditions and optimize the algorithm for identifying changes. The identification unit can, for example, use a generation AI to analyze the history of past changes to the terms and conditions and optimize the algorithm for identifying changes. The generation AI can analyze the history of past changes to the terms and conditions and identify parts that are frequently changed. For example, the identification unit allows the generation AI to analyze the history of past changes to the terms and conditions and identify parts that are frequently changed. The identification unit can also allow the generation AI to learn changes that are important to users from the past change history and improve the identification accuracy. Furthermore, the identification unit can allow the generation AI to prioritize high-risk changes based on the past change history. In this way, the accuracy of the identification algorithm can be improved by analyzing the past change history. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the identification unit can analyze the history of past changes to the terms and conditions and optimize the identification algorithm using a generation AI model for optimizing the algorithm for identifying changes.

[0076] When identifying changes to the terms and conditions, the identification unit can determine a specific priority based on the impact of the changes. For example, when identifying changes to the terms and conditions, the identification unit can use a generation AI to determine a specific priority based on the impact of the changes. The generation AI can evaluate the impact of the changes and prioritize identifying changes that are important to the user. For example, the identification unit can use the generation AI to evaluate the impact of the changes and prioritize identifying changes that are important to the user. The identification unit can also prioritize identifying changes with high risk based on the impact of the changes. Furthermore, the identification unit can use the generation AI to analyze the impact of the changes and provide the most important information to the user. In this way, important changes can be prioritized by determining the priority based on the impact of the changes. Some or all of the above-described processing in the identification unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, when identifying changes to the terms and conditions, the identification unit can determine the specific priority using a generation AI model for determining the specific priority based on the impact of the changes.

[0077] The identification unit can estimate the user's emotions and adjust the display order of the identified changes based on the estimated user emotions. The identification unit can, for example, use a generation AI to estimate the user's emotions and adjust the display order of the identified changes based on the estimated user emotions. The generation AI can estimate the user's emotions using an emotion analysis algorithm. For example, if the identification unit is anxious, the generation AI can display high-risk changes first. Alternatively, if the user is relaxed, the identification unit can display important changes concisely. Furthermore, if the user is in a hurry, the identification unit can prioritize changes that highlight the main points. This allows for more appropriate information to be provided by adjusting the display order according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the identification unit can be performed, for example, using the generation AI, or without the generation AI. For example, the identification unit can estimate a user's emotions and adjust the display order using a generative AI model for adjusting the display order of the identified changes based on the estimated user's emotions.

[0078] The identification unit can improve the accuracy of identification by taking into account the user's geographical location information when identifying changes to the terms and conditions. For example, the identification unit can improve the accuracy of identification by taking into account the user's geographical location information when identifying changes to the terms and conditions using a generation AI. The generation AI can identify region-specific changes to the terms and conditions based on the user's geographical location information. For example, the identification unit can identify region-specific changes to the terms and conditions based on the user's geographical location information. The identification unit can also indicate risks related to the region by taking into account the user's geographical location information. Furthermore, the identification unit can identify changes by taking into account region-specific legal requirements based on the user's geographical location information. In this way, region-specific changes can be accurately identified by taking into account the geographical location information. Some or all of the above-described processing in the identification unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the identification unit can improve the accuracy of identification by using a generation AI model that takes into account the user's geographical location information when identifying changes to the terms and conditions.

[0079] The identification unit can improve the accuracy of identification by referring to related legal documents when identifying changes to the terms and conditions. For example, the identification unit can improve the accuracy of identification by referring to related legal documents when identifying changes to the terms and conditions using a generation AI. The generation AI can identify changes to the terms and conditions by referring to related legal documents. For example, the identification unit can identify changes to the terms and conditions by having the generation AI refer to related legal documents. The identification unit can also identify high-risk changes based on legal documents. Furthermore, the identification unit can identify changes that are important to the user by having the generation AI refer to legal documents. In this way, the accuracy of identification can be improved by referring to related legal documents. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the identification unit can improve the accuracy of identification by using a generative AI model that improves the accuracy of identification by referring to related legal documents when identifying changes to the terms and conditions.

[0080] The explanation unit can estimate the user's emotions and adjust the way the explanation is presented based on the estimated user's emotions. The explanation unit can estimate the user's emotions using, for example, a generation AI and adjust the way the explanation is presented based on the estimated user's emotions. The generation AI can estimate the user's emotions using a sentiment analysis algorithm. For example, if the user is feeling anxious, the explanation unit can provide a detailed explanation and clarify the risks. If the user is relaxed, the explanation unit can provide a concise explanation and get to the main points. Furthermore, if the user is in a hurry, the explanation unit can quickly explain the main points and provide important information. This allows for more appropriate information to be provided by adjusting the way the explanation is presented based on the user's emotions. The emotion estimation is achieved using, for example, an emotion engine or a generation AI with an emotion estimation function. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the explanation unit can be performed using, for example, a generation AI, or without a generation AI. For example, the explanation unit can estimate the user's emotions and adjust the way the explanation is expressed using a generative AI model for adjusting the way the explanation is expressed based on the estimated user's emotions.

[0081] When summarizing the identified changes, the explanation unit can adjust the level of detail of the summary based on the importance of the changes. When summarizing the identified changes, the explanation unit can adjust the level of detail of the summary based on the importance of the changes, for example, using a generation AI. The generation AI can evaluate the importance of the changes and summarize important changes in detail. For example, the explanation unit can have the generation AI evaluate the importance of the changes and summarize important changes in detail. The explanation unit can also have the generation AI analyze the importance of the changes and provide important information to the user. In this way, important information can be provided in detail by adjusting the level of detail of the summary based on the importance of the changes. Some or all of the above-described processing in the explanation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, when summarizing the identified changes, the explanation unit can adjust the level of detail of the summary using a generation AI model for adjusting the level of detail of the summary based on the importance of the changes.

[0082] The explanation unit can apply different summarization algorithms depending on the category of changes when summarizing the identified changes. For example, the explanation unit can use a generation AI to apply different summarization algorithms depending on the category of changes when summarizing the identified changes. The generation AI can identify the category of changes and apply an appropriate summarization algorithm. For example, the explanation unit can have the generation AI identify the category of changes and apply an appropriate summarization algorithm. The explanation unit can also have the generation AI summarize high-risk changes in detail depending on the category. Furthermore, the explanation unit can have the generation AI provide information important to the user based on the category. In this way, applying a summarization algorithm depending on the category of changes can provide a more appropriate summary. Some or all of the above-described processing in the explanation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the explanation unit can apply a summarization algorithm using a generation AI model for applying different summarization algorithms depending on the category of changes when summarizing the identified changes.

[0083] The explanation unit can estimate the user's emotions and adjust the length of the summary based on the estimated user emotions. The explanation unit can estimate the user's emotions using, for example, a generation AI and adjust the length of the summary based on the estimated user emotions. The generation AI can estimate the user's emotions using a sentiment analysis algorithm. For example, if the user is feeling anxious, the explanation unit can provide a detailed summary to clarify risks. If the user is relaxed, the explanation unit can provide a concise summary to get to the main points. Furthermore, if the user is in a hurry, the explanation unit can quickly summarize the main points and provide important information. This allows for more appropriate information to be provided by adjusting the length of the summary based on the user's emotions. The emotion estimation is achieved using, for example, an emotion engine or a generation AI with an emotion estimation function. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the explanation unit can be performed using, for example, a generation AI, or without a generation AI. For example, the explanation unit may estimate a user's emotion and adjust the length of the summary using a generative AI model for adjusting the length of the summary based on the estimated user's emotion.

[0084] When summarizing the identified changes, the explanation unit can determine the priority of summaries based on the time the changes were submitted. When summarizing the identified changes, the explanation unit, for example, uses a generation AI to determine the priority of summaries based on the time the changes were submitted. The generation AI can prioritize summarizing the most recent changes, taking into account the time the changes were submitted. For example, the explanation unit can prioritize summarizing the most recent changes, taking into account the time the changes were submitted. The explanation unit can also prioritize summarizing high-risk changes, taking into account the time the changes were submitted. Furthermore, the explanation unit can provide information important to the user based on the time the changes were submitted. In this way, by determining the priority of summaries based on the time of submission, the most recent information can be provided preferentially. Some or all of the above-described processing in the explanation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, when summarizing the identified changes, the explanation unit can determine the priority of summaries using a generation AI model for determining the priority of summaries based on the time the changes were submitted.

[0085] When summarizing the identified changes, the explanation unit can adjust the order of summaries based on the relevance of the changes. When summarizing the identified changes, the explanation unit can adjust the order of summaries based on the relevance of the changes, for example, using a generation AI. The generation AI can evaluate the relevance of the changes and prioritize summarizing important changes. For example, the explanation unit can use the generation AI to evaluate the relevance of the changes and prioritize summarizing important changes. The explanation unit can also use the generation AI to prioritize summarizing high-risk changes based on their relevance. Furthermore, the explanation unit can provide information important to the user based on their relevance. In this way, by adjusting the order of summaries based on the relevance of the changes, important information can be prioritized and provided to the user. Some or all of the above-described processing in the explanation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, when summarizing the identified changes, the explanation unit can adjust the order of summaries using a generation AI model for adjusting the order of summaries based on the relevance of the changes.

[0086] The evaluation collection unit can estimate the user's emotions and adjust the evaluation collection method based on the estimated user emotions. The evaluation collection unit can estimate the user's emotions using, for example, a generation AI and adjust the evaluation collection method based on the estimated user emotions. The generation AI can estimate the user's emotions using an emotion analysis algorithm. For example, if the user is feeling anxious, the evaluation collection unit can provide simple evaluation items to reduce stress. Also, if the user is relaxed, the evaluation collection unit can provide detailed evaluation items to collect accurate evaluations. Furthermore, if the user is in a hurry, the evaluation collection unit can provide an interface that allows users to quickly collect evaluations. This allows for more appropriate evaluations to be collected by adjusting the evaluation collection method according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the evaluation collection unit can be performed using, for example, the generation AI, or without the generation AI. For example, the rating collection unit can estimate a user's emotions and adjust the collection method using a generative AI model to adjust the rating collection method based on the estimated user's emotions.

[0087] The rating collection unit can analyze the user's past rating history and select the optimal rating collection method. The rating collection unit can analyze the user's past rating history using, for example, a generation AI and select the optimal rating collection method. The generation AI can analyze the user's past rating history and suggest optimal rating items. For example, the rating collection unit can have the generation AI suggest optimal rating items based on the user's past rating history. The rating collection unit can also have the generation AI analyze the user's past rating history and provide an appropriate rating method. Furthermore, the rating collection unit can have the generation AI refer to the user's past rating history to improve the accuracy of the ratings. In this way, the optimal rating collection method can be provided by analyzing the past rating history. Some or all of the above-described processing in the rating collection unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the rating collection unit can analyze the user's past rating history and select the rating collection method using a generation AI model for selecting the optimal rating collection method.

[0088] The rating collection unit can customize rating items based on the user's current usage status when collecting ratings. The rating collection unit, for example, uses a generation AI to customize rating items based on the user's current usage status when collecting ratings. The generation AI can analyze the user's current usage status and provide appropriate rating items. For example, the rating collection unit allows the generation AI to provide appropriate rating items based on the user's current usage status. The rating collection unit can also customize the rating items by taking the user's current usage status into consideration. Furthermore, the rating collection unit can allow the generation AI to improve the accuracy of ratings according to the user's usage status. As a result, more appropriate ratings can be collected by customizing the rating items based on the current usage status. Some or all of the above-described processing in the rating collection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the rating collection unit can customize the rating items using a generation AI model for customizing rating items based on the user's current usage status when collecting ratings.

[0089] The evaluation collection unit can estimate the user's emotions and prioritize the evaluations based on the estimated user emotions. The evaluation collection unit can estimate the user's emotions using, for example, a generation AI and prioritize the evaluations based on the estimated user emotions. The generation AI can estimate the user's emotions using a sentiment analysis algorithm. For example, if the user is feeling anxious, the evaluation collection unit can prioritize collecting important evaluation items. Also, if the user is relaxed, the evaluation collection unit can provide detailed evaluation items and collect accurate evaluations. Furthermore, if the user is in a hurry, the evaluation collection unit can provide an interface that allows users to quickly collect evaluations. This allows important evaluations to be prioritized by prioritizing the evaluations according to the user's emotions. Emotion estimation is achieved 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 evaluation collection unit can be performed using, for example, the generation AI, or without the generation AI. For example, the rating collection unit can determine the priorities using a generative AI model that estimates a user's emotions and determines the priorities of ratings based on the estimated user's emotions.

[0090] The evaluation collection unit can select evaluation items taking into account the user's geographical location information when collecting evaluations. The evaluation collection unit, for example, uses a generation AI to select evaluation items taking into account the user's geographical location information when collecting evaluations. The generation AI can provide region-specific evaluation items based on the user's geographical location information. For example, the evaluation collection unit can provide region-specific evaluation items based on the user's geographical location information using the generation AI. The evaluation collection unit can also select appropriate evaluation items by taking into account the user's geographical location information. Furthermore, the evaluation collection unit can improve the accuracy of the evaluations based on the user's geographical location information. In this way, region-specific evaluation items can be provided by taking into account the geographical location information. Some or all of the above-described processing in the evaluation collection unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the evaluation collection unit can select evaluation items using a generation AI model for selecting evaluation items taking into account the user's geographical location information when collecting evaluations.

[0091] The rating disclosure unit can estimate the user's emotions and adjust the rating disclosure method based on the estimated user emotions. The rating disclosure unit can estimate the user's emotions using, for example, a generation AI and adjust the rating disclosure method based on the estimated user emotions. The generation AI can estimate the user's emotions using an emotion analysis algorithm. For example, if the user is feeling anxious, the rating disclosure unit can disclose a detailed rating to clarify risks. If the user is relaxed, the rating disclosure unit can disclose a concise rating to focus on the main points. Furthermore, if the user is in a hurry, the rating disclosure unit can disclose a rating quickly to provide important information. This allows for more appropriate information to be provided by adjusting the rating disclosure method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the rating disclosure unit can be performed using, for example, the generation AI, or without the generation AI. For example, the rating publishing unit can estimate a user's emotions and adjust the publishing method using a generative AI model for adjusting the rating publishing method based on the estimated user's emotions.

[0092] The rating publishing unit can select the optimal publishing method by referring to the user's past rating history when publishing a rating. The rating publishing unit can select the optimal publishing method by referring to the user's past rating history, for example, using a generation AI. The generation AI can analyze the user's past rating history and propose the optimal publishing method. For example, the rating publishing unit can propose the optimal publishing method based on the user's past rating history. The rating publishing unit can also analyze rating trends from the user's past rating history and provide an appropriate publishing method. Furthermore, the rating publishing unit can improve the accuracy of the ratings by referring to the user's past rating history. In this way, the optimal publishing method can be provided by referring to the past rating history. Some or all of the above-described processing in the rating publishing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the rating publishing unit can select the publishing method by referring to the user's past rating history when publishing a rating, using a generation AI model for selecting the optimal publishing method.

[0093] The rating disclosure unit can adjust the level of detail of disclosure based on the importance of the rating when disclosing the rating. The rating disclosure unit can adjust the level of detail of disclosure based on the importance of the rating, for example, using a generation AI. The generation AI can evaluate the importance of the rating and disclose important ratings in detail. For example, the rating disclosure unit can evaluate the importance of the rating and disclose important ratings in detail. The rating disclosure unit can also disclose high-risk ratings in detail based on the importance of the rating. Furthermore, the rating disclosure unit can analyze the importance of the rating and provide information that is important to the user. In this way, important information can be provided in detail by adjusting the level of detail of disclosure based on the importance of the rating. Some or all of the above-described processing in the rating disclosure unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the rating disclosure unit can adjust the level of detail when disclosing the rating using a generation AI model for adjusting the level of detail of disclosure based on the importance of the rating.

[0094] The rating publishing unit can estimate the user's emotions and adjust the display order of the ratings based on the estimated user emotions. The rating publishing unit can estimate the user's emotions using, for example, a generation AI and adjust the display order of the ratings based on the estimated user emotions. The generation AI can estimate the user's emotions using an emotion analysis algorithm. For example, if the user is feeling anxious, the rating publishing unit can display high-risk ratings first. Furthermore, if the user is relaxed, the rating publishing unit can also display important ratings concisely. Furthermore, if the user is in a hurry, the rating publishing unit can also prioritize displaying ratings that highlight the main points. This allows important information to be provided preferentially by adjusting the display order according to the user's emotions. The emotion estimation is realized using, for example, an emotion engine or a generation AI with an emotion estimation function. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the rating publishing unit can be performed using, for example, a generation AI, or without a generation AI. For example, the rating publishing unit can estimate a user's emotions and adjust the display order of ratings using a generative AI model for adjusting the display order of ratings based on the estimated user's emotions.

[0095] The rating publishing unit can select the optimal display method by taking into consideration the user's device information when publishing the rating. The rating publishing unit can select the optimal display method by taking into consideration the user's device information, for example, using a generation AI. The generation AI can provide an appropriate display method based on the user's device information. For example, the rating publishing unit can provide an appropriate display method by using the generation AI based on the user's device information. The rating publishing unit can also select the optimal display method by taking into consideration the user's device information. Furthermore, the rating publishing unit can also improve the accuracy of the display based on the user's device information. This makes it possible to provide the optimal display method by taking into consideration the device information. Some or all of the above-described processing in the rating publishing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the rating publishing unit can select the display method by using a generation AI model for selecting the optimal display method by taking into consideration the user's device information when publishing the rating.

[0096] The list generation unit can estimate the user's emotions and adjust the list generation method based on the estimated user emotions. The list generation unit can estimate the user's emotions using, for example, a generation AI and adjust the list generation method based on the estimated user emotions. The generation AI can estimate the user's emotions using an emotion analysis algorithm. For example, if the user is feeling anxious, the list generation unit can prioritize low-risk services in the list. Also, if the user is relaxed, the list generation unit can include a variety of services in the list. Furthermore, if the user is in a hurry, the list generation unit can quickly generate a list and provide information that focuses on the main points. This allows the list generation method to be adjusted according to the user's emotions, thereby providing a more appropriate list. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the list generation unit can be performed, for example, using the generation AI, or without the generation AI. For example, the list generation unit can estimate a user's emotions and adjust the generation method using a generative AI model for adjusting the list generation method based on the estimated user's emotions.

[0097] When generating a list, the list generation unit can select an optimal list generation method by referring to the user's past rating history. When generating a list, the list generation unit can, for example, use a generation AI to select an optimal list generation method by referring to the user's past rating history. The generation AI can analyze the user's past rating history and include optimal services in the list. For example, the list generation unit can include optimal services in the list based on the user's past rating history. The list generation unit can also prioritize highly rated services in the list based on the user's past rating history. Furthermore, the list generation unit can improve the accuracy of the list by referring to the user's past rating history. In this way, an optimal list generation method can be provided by referring to the past rating history. Some or all of the above-described processing in the list generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, when generating a list, the list generation unit can select a generation method using a generation AI model that selects an optimal list generation method by referring to the user's past rating history.

[0098] The list generation unit can adjust the level of detail of the list based on the importance of the evaluation when generating the list. The list generation unit can adjust the level of detail of the list based on the importance of the evaluation when generating the list, for example, using a generation AI. The generation AI can evaluate the importance of the evaluation and include important services in the list in detail. For example, the list generation unit can evaluate the importance of the evaluation and include important services in the list in detail. The list generation unit can also include high-risk services in the list in detail based on the importance of the evaluation. Furthermore, the list generation unit can analyze the importance of the evaluation and provide information that is important to the user. As a result, important information can be provided in detail by adjusting the level of detail of the list based on the importance of the evaluation. Some or all of the above-mentioned processing in the list generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the list generation unit can adjust the level of detail of the list based on the importance of the evaluation when generating the list, using a generation AI model for adjusting the level of detail of the list based on the importance of the evaluation.

[0099] The list generation unit can estimate the user's emotions and adjust the display order of the list based on the estimated user's emotions. The list generation unit can estimate the user's emotions using, for example, a generation AI and adjust the display order of the list based on the estimated user's emotions. The generation AI can estimate the user's emotions using a sentiment analysis algorithm. For example, if the user is feeling anxious, the list generation unit can cause the generation AI to first display low-risk services. Also, if the user is relaxed, the list generation unit can cause the generation AI to concisely display important services. Furthermore, if the user is in a hurry, the list generation unit can cause the generation AI to prioritize displaying services that focus on the main points. This allows important information to be provided preferentially by adjusting the display order 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 a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the list generation unit can be performed using, for example, a generation AI, or without a generation AI. For example, the list generation unit can estimate a user's emotions and adjust the display order of the list using a generative AI model for adjusting the display order of the list based on the estimated user's emotions.

[0100] The list generation unit can select the optimal list generation method by taking into account the user's geographical location information when generating the list. The list generation unit can select the optimal list generation method by taking into account the user's geographical location information when generating the list, for example, using a generation AI. The generation AI can include region-specific services in the list based on the user's geographical location information. For example, the list generation unit can include region-specific services in the list by taking into account the user's geographical location information. The list generation unit can also include appropriate services in the list by taking into account the user's geographical location information. Furthermore, the list generation unit can improve the accuracy of the list by taking into account the user's geographical location information. In this way, region-specific services can be included in the list by taking into account the geographical location information. Some or all of the above-described processing in the list generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the list generation unit can select the generation method by using a generation AI model for selecting the optimal list generation method by taking into account the user's geographical location information when generating the list.

[0101] The list generation unit can improve the accuracy of the list by referring to related market data when generating the list. The list generation unit can improve the accuracy of the list by referring to related market data when generating the list, for example, using a generation AI. The generation AI can refer to market data and include popular services in the list. For example, the list generation unit can refer to market data and include popular services in the list. The list generation unit can also include highly rated services in the list based on the market data. Furthermore, the list generation unit can refer to market data and provide information important to users. In this way, the accuracy of the list can be improved by referring to market data. Some or all of the above-mentioned processing in the list generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the list generation unit can improve the accuracy by using a generation AI model for improving the accuracy of the list by referring to related market data when generating the list.

[0102] The providing unit can estimate the user's emotions and adjust the method of providing the list based on the estimated user's emotions. The providing unit can estimate the user's emotions using, for example, a generation AI and adjust the method of providing the list based on the estimated user's emotions. The generation AI can estimate the user's emotions using an emotion analysis algorithm. For example, if the user is feeling anxious, the providing unit can provide a detailed list to clarify risks. If the user is relaxed, the providing unit can provide a concise list to focus on the main points. Furthermore, if the user is in a hurry, the providing unit can quickly provide a list to provide important information. This allows the user to provide more appropriate information by adjusting the method of providing the list based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the providing unit can be performed using, for example, the generation AI, or without the generation AI. For example, the providing unit can estimate a user's emotions and adjust the method of providing the list using a generative AI model for adjusting the method of providing the list based on the estimated user's emotions.

[0103] When providing the list, the providing unit can select the optimal provision method by referring to the user's past usage history. When providing the list, the providing unit can, for example, use a generation AI to select the optimal provision method by referring to the user's past usage history. The generation AI can analyze the user's past usage history and provide the optimal list. For example, the providing unit can provide the optimal list based on the user's past usage history. The providing unit can also cause the generation AI to prioritize highly rated services in the user's past usage history. Furthermore, the providing unit can also cause the generation AI to improve the accuracy of the list by referring to the user's past usage history. In this way, the optimal list provision method can be provided by referring to the past usage history. Some or all of the above-described processing in the providing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, when providing the list, the providing unit can select the provision method using a generation AI model that refers to the user's past usage history to select the optimal provision method.

[0104] The providing unit can adjust the level of detail of the list provided based on the importance of the list when providing the list. The providing unit can adjust the level of detail of the list provided based on the importance of the list, for example, using a generation AI. The generation AI can evaluate the importance of the list and include important services in the list in detail. For example, the providing unit can evaluate the importance of the list using the generation AI and include important services in the list in detail. The providing unit can also include high-risk services in the list in detail based on the importance of the list. Furthermore, the providing unit can analyze the importance of the list using the generation AI to provide information that is important to the user. As a result, important information can be provided in detail by adjusting the level of detail of the list based on the importance of the list. Some or all of the above-described processing in the providing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the providing unit can adjust the level of detail of the list provided based on the importance of the list when providing the list, using a generation AI model for adjusting the level of detail of the list.

[0105] The providing unit can estimate the user's emotions and adjust the display order of the list based on the estimated user's emotions. The providing unit can estimate the user's emotions using, for example, a generation AI and adjust the display order of the list based on the estimated user's emotions. The generation AI can estimate the user's emotions using a sentiment analysis algorithm. For example, if the user is feeling anxious, the providing unit can cause the generation AI to first display low-risk services. Also, if the user is relaxed, the providing unit can cause the generation AI to concisely display important services. Furthermore, if the user is in a hurry, the providing unit can cause the generation AI to prioritize displaying services that focus on the main points. This allows important information to be prioritized by adjusting the display order 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 a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit can be performed using, for example, the generation AI, or without the generation AI. For example, the providing unit can estimate a user's emotion and adjust the display order of the list using a generative AI model for adjusting the display order of the list based on the estimated user's emotion.

[0106] The providing unit can select the optimal display method by taking into account the user's device information when providing the list. The providing unit can select the optimal display method by taking into account the user's device information, for example, using a generation AI when providing the list. The generation AI can provide an appropriate display method based on the user's device information. For example, the providing unit can provide an appropriate display method by having the generation AI provide the appropriate display method based on the user's device information. The providing unit can also select the optimal display method by having the generation AI take into account the user's device information. Furthermore, the providing unit can also improve the accuracy of the display based on the user's device information. This makes it possible to provide the optimal display method by taking into account the device information. Some or all of the above-described processing in the providing unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the providing unit can select the display method by using a generation AI model for selecting the optimal display method by taking into account the user's device information when providing the list. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned identification unit, explanation unit, evaluation collection unit, evaluation publication unit, list generation unit, and provision unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the identification unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The explanation unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The evaluation collection unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The evaluation publication unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The list generation unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The provision unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned identification unit, explanation unit, rating collection unit, rating publication unit, list generation unit, and providing unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the identification unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The explanation unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The rating collection unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The rating publication unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The list generation unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The providing unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned identification unit, explanation unit, evaluation collection unit, evaluation publication unit, list creation unit, and provision unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the identification unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The explanation unit is realized, for example, by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The evaluation collection unit is realized, for example, by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The evaluation publication unit is realized, for example, by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The list creation unit is realized, for example, by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The providing unit is realized by, for example, the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned identification unit, explanation unit, evaluation collection unit, evaluation publication unit, list creation unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the identification unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The explanation unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The evaluation collection unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The evaluation publication unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The list creation unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The provision unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12.

[0107] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0108] The contract and clause explanation system can further include a history analysis unit that analyzes the user's past contract history. The history analysis unit can identify changes that are important to the user by analyzing services that the user has previously subscribed to and their ratings, and comparing them with the current contract content. For example, the history analysis unit can extract characteristics of services that the user has previously rated highly and check whether there are similarities with the current contract content. The history analysis unit can also identify contract items that the user is particularly interested in from the past contract history and prioritize notifying the user of changes related to those items. Furthermore, the history analysis unit can identify high-risk changes based on contract content in which the user has previously reported problems, and issue a warning to the user. This makes it possible to provide more personalized information by utilizing the user's past contract history.

[0109] The identification unit can estimate the user's emotions and adjust the accuracy of identifying changes to the terms and conditions based on the estimated user emotions. For example, if the identification unit determines that the user is feeling anxious, the generation AI can identify changes in more detail and clarify risks. In addition, if the user is relaxed, the identification unit can determine that the generation AI can identify only important changes and provide a concise explanation. Furthermore, if the user is in a hurry, the identification unit can determine that the generation AI can quickly identify changes and provide information that focuses on the key points. This allows the generation AI to provide more appropriate information by adjusting the identification accuracy according to the user's emotions.

[0110] When summarizing the identified changes, the explanation unit can apply different summarization algorithms depending on the category of the change. For example, the explanation unit allows the generation AI to identify the category of the change and apply an appropriate summarization algorithm. The explanation unit can also allow the generation AI to summarize high-risk changes in detail depending on the category. Furthermore, the explanation unit allows the generation AI to provide important information to the user based on the category. This allows the generation AI to provide a more appropriate summary by applying a summarization algorithm depending on the category of the change.

[0111] The evaluation collection unit can estimate the user's emotions and adjust the evaluation collection method based on the estimated user's emotions. For example, if the user feels anxious, the evaluation collection unit provides simple evaluation items to reduce stress. Alternatively, if the user feels relaxed, the evaluation collection unit can provide detailed evaluation items to collect accurate evaluations. Furthermore, if the user is in a hurry, the evaluation collection unit can provide an interface that allows the user to quickly collect evaluations. In this way, by adjusting the evaluation collection method according to the user's emotions, more appropriate evaluations can be collected.

[0112] The rating publishing unit may provide a platform for sharing collected ratings with other users. For example, the rating publishing unit may provide a web platform for sharing collected ratings with other users. Users may view the collected ratings and share them with other users through the web platform. The rating publishing unit may also provide a mobile application for sharing collected ratings with other users. Users may view the collected ratings and share them with other users through the mobile application. For example, the rating publishing unit may provide a social media platform for sharing collected ratings with other users. Users may view the collected ratings and share them with other users through the social media platform. The rating publishing unit may also provide an email service for sharing collected ratings with other users. Users may share the collected ratings with other users through the email service. In this way, sharing ratings with other users can provide reference information for selecting a service.

[0113] The list generation unit can estimate the user's emotions and adjust the list generation method based on the estimated user emotions. For example, if the user is feeling anxious, the list generation unit causes the generation AI to prioritize low-risk services in the list. Also, if the user is relaxed, the list generation unit can cause the generation AI to include a variety of services in the list. Furthermore, if the user is in a hurry, the list generation unit can cause the generation AI to quickly generate a list and provide information that focuses on the main points. This makes it possible to provide a more appropriate list by adjusting the list generation method according to the user's emotions.

[0114] The providing unit may provide the generated recommended service list to a user. For example, the providing unit may provide the generated recommended service list to a user through a web platform. The user may view and use the generated recommended service list through the web platform. The providing unit may also provide the generated recommended service list to a user through a mobile application. The user may view and use the generated recommended service list through the mobile application. For example, the providing unit may provide the generated recommended service list to a user through email. The user may receive and use the generated recommended service list through email. The providing unit may also provide the generated recommended service list to a user through a social media platform. The user may view and use the generated recommended service list through the social media platform. Thus, providing the recommended service list to a user allows the user to use the service with peace of mind.

[0115] The identification unit can analyze the history of past changes to the terms and conditions and optimize the algorithm for identifying changes. For example, the identification unit allows the generation AI to analyze the history of past changes to the terms and conditions and identify parts that are frequently changed. The identification unit can also allow the generation AI to learn from the past change history which changes are important to users and improve the accuracy of identification. Furthermore, the identification unit can also allow the generation AI to prioritize identifying high-risk changes based on the past change history. In this way, the accuracy of the identification algorithm can be improved by analyzing the past change history.

[0116] When identifying changes to the terms and conditions, the identification unit can determine a specific priority based on the impact of the changes. For example, the identification unit allows the generation AI to evaluate the impact of the changes and prioritize identifying changes that are important to the user. The identification unit can also prioritize identifying changes that pose high risks based on the impact of the changes. Furthermore, the identification unit can also analyze the impact of the changes that the generation AI uses to provide the most important information to the user. In this way, by determining a priority based on the impact of the changes, important changes can be prioritized.

[0117] The identification unit can estimate the user's emotions and adjust the display order of the identified changes based on the estimated user emotions. For example, if the identification unit is feeling anxious, the generation AI can display high-risk changes first. Also, if the user is relaxed, the identification unit can display important changes concisely. Furthermore, if the user is in a hurry, the identification unit can display changes that highlight the main points first. In this way, by adjusting the display order according to the user's emotions, more appropriate information can be provided.

[0118] The processing flow of the second embodiment will be briefly explained below.

[0119] Step 1: The identification unit identifies the changes to the terms and conditions of the service provided on the web. The identification unit identifies the changes to the terms and conditions using natural language processing technology. Natural language processing technology can accurately identify the changes to the terms and conditions using techniques such as morphological analysis, grammatical analysis, and semantic analysis. Step 2: The explanation unit summarizes the changes identified by the identification unit and explains them to the user in an easy-to-understand manner. The explanation unit uses a generation AI to summarize the identified changes and explains them to the user in an easy-to-understand manner. The generation AI can use a text generation AI (e.g., LLM) or a multimodal generation AI to summarize the identified changes and explain them to the user in an easy-to-understand manner. Step 3: The evaluation collection unit provides an interface for users to evaluate the contract details and usability of the service they used. The interface includes a method for users to input information and a method for displaying evaluation results. Step 4: The rating publishing unit provides a platform for sharing collected ratings with other users. The platform includes a method for displaying ratings and a method for sharing ratings among users. Step 5: The list generator includes an algorithm for generating a list of recommended services by integrating user ratings and risk information. The algorithm includes data to be used, calculation methods, etc. Step 6: The providing unit provides the generated recommended service list to the user. The providing method includes the timing and method of providing the list.

[0120] 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.

[0121] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0122] 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.

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

[0124] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0125] 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.

[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 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.

[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. 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.

[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 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.

[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 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.

[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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0138] 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.

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

[0140] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0141] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[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 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.

[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 (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).

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

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0171] 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.

[0172] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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."

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0190] 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.

[0191] [Explanation of symbols]

[0192] 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. an identifying unit for identifying a change location; an explanation section that clearly explains the change portion identified by the identification section; an evaluation collection unit for allowing users to rate the contract or service content; a rating publishing unit that publishes the ratings collected by the rating collection unit; a list generation unit that generates a recommended service list based on the evaluations and risk information published by the evaluation publication unit; a providing unit that provides the list generated by the list generating unit. A system characterized by:

2. The identification unit Identifying changes to terms and conditions using natural language processing technology 2. The system of claim 1.

3. The explanation section Summarize the identified changes and provide clear instructions for users 2. The system of claim 1.

4. The evaluation collection unit Provides an interface for users to evaluate the contract details or usability of the services they have used 2. The system of claim 1.

5. The evaluation disclosure unit Providing a platform for sharing collected ratings with other users 2. The system of claim 1.

6. The list generation unit Equipped with an algorithm that integrates user ratings and risk information to generate a list of recommended services 2. The system of claim 1.

7. The providing unit Providing the generated recommended service list to the user 2. The system of claim 1.

8. The identification unit Estimate user sentiment and adjust the accuracy of identifying changes to terms and conditions based on the estimated user sentiment 2. The system of claim 1.

Images