System

Abstract

An object of a system according to an embodiment is to analyze the content of a clause and evaluate a legal risk and an economic risk in a form that is easy for a user to understand.SOLUTION: A system includes a summarization part, a comparison part, a risk analysis part, a validity determination part, and a problem point presentation part. The summarizing part analyzes and summarizes the contents of the clause. A comparison part performs comparison with a standard clause on the basis of the information summarized by the summarization part. The risk analysis unit analyzes a legal risk and an economic risk based on the information obtained by the comparison unit. The validity determination unit determines the validity of the contract based on the information obtained by the risk analysis unit. The problem point presentation unit presents the individual problem points based on the information obtained by the validity determination unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, users often enter into contracts without fully understanding the terms and conditions, making it difficult to properly assess legal and economic risks.

[0005] The system according to the embodiment aims to analyze the contents of the terms and conditions and evaluate legal and economic risks in a manner that is easy for users to understand. [Means for solving the problem]

[0006] The system according to the embodiment includes a summarizing unit, a comparing unit, a risk analyzing unit, a validity determining unit, and a problem presenting unit. The summarizing unit analyzes and summarizes the contents of the terms and conditions. The comparing unit compares the information summarized by the summarizing unit with standard terms and conditions. The risk analyzing unit analyzes legal risks and economic risks based on the information obtained by the comparing unit. The validity determining unit determines the validity of the contract based on the information obtained by the risk analyzing unit. The problem presenting unit presents individual problems based on the information obtained by the validity determining unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze the contents of the terms and conditions and evaluate legal and economic risks in a manner that is easy for users to understand. [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) The generation AI service according to an embodiment of the present invention is a system that analyzes and summarizes complex text, assesses safety and risk, and provides users with easy-to-understand decision-making information (reports). The generation AI service analyzes and summarizes the contents of contract terms and conditions, compares them with standard contract terms, analyzes legal and economic risks, assesses the validity of the contract, and identifies individual issues. For example, when a user enters into a contract, the generation AI service analyzes the contents of the contract terms and summarizes key points. Next, the generation AI service compares the contract terms with standard contract terms and identifies differences. Furthermore, the generation AI service analyzes legal and economic risks based on the contents of the contract terms and indicates the degree of risk to the user. The generation AI service also assesses the validity of the contract based on the user's prior information and indicates to the user whether the contract is appropriate. Finally, the generation AI service analyzes the contents of the contract terms in detail and points out potential issues for the user. This makes it easier for users to understand complex contract terms and allows them to identify contract risks in advance. This enhances user protection and makes contracts with companies more transparent and fair. For example, when users enter into a contract, they can quickly and accurately understand complex terms and conditions, and understand the risks of the contract in advance. It also allows companies to fulfill their obligation to explain contracts and provide users with highly transparent information.

[0029] The generation AI service according to the embodiment includes a summarization unit, a comparison unit, a risk analysis unit, a validity determination unit, and a problem presentation unit. The summarization unit uses the generation AI to summarize the contents of the terms and conditions. The summarization is performed based on, for example, the length of the sentences and the importance of the information to be summarized, but is not limited to these examples. For example, the generation AI uses a text generation AI (e.g., LLM) to concisely summarize the terms and conditions. The summarization unit can also use the generation AI to extract and summarize important parts of the sentences. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The generation AI uses keyword extraction technology to identify particularly important information in the terms and conditions and perform summarization based on that information. The comparison unit uses the generation AI to compare the information summarized by the summarization unit with standard terms and conditions. The comparison is performed based on, for example, industry standards or legal standards, but is not limited to these examples. For example, the generation AI compares the standard terms and conditions with the terms and conditions of the contract and identifies differences. The comparison unit can also use the generation AI to evaluate the risks of the contract based on the comparison results with the standard terms and conditions. The risk analysis unit uses the generation AI to analyze legal and economic risks based on the information obtained by the comparison unit. Risk analysis is performed based on, for example, the possibility of contract violation, the risk of legal sanctions, the possibility of financial loss, and investment risk, but is not limited to these examples. For example, the generation AI analyzes the terms and conditions of a contract to evaluate legal and economic risks. The risk analysis unit can also use the generation AI to quantify the level of risk and display the level of risk to the user. The validity assessment unit uses the generation AI to determine the validity of the contract based on the information obtained by the risk analysis unit. The validity assessment is performed based on, for example, the fulfillment of legal requirements and the conformity of contract terms, but is not limited to these examples. For example, the generation AI evaluates the validity of the contract based on the user's prior information. The validity assessment unit can also use the generation AI to indicate to the user whether the contract is appropriate. The problem presentation unit uses the generation AI to present individual problems based on the information obtained by the validity assessment unit. The problem presentation is performed based on, for example, the problems and risk details of specific clauses, but is not limited to these examples.For example, the generation AI analyzes the contents of the terms and conditions in detail and points out points that may be problematic for the user. The problem presentation unit can also use the generation AI to suggest specific areas for improvement to the user. As a result, the generation AI service according to the embodiment makes it easier for users to understand complex terms and conditions and can grasp contract risks in advance. By using the generation AI, the accuracy of each process, including summarization, comparison, risk analysis, validity assessment, and problem presentation, is improved, making it possible to provide more appropriate information to the user.

[0030] The summarization unit can summarize the contents of the terms and conditions using a generation AI. Examples of generation AI include, but are not limited to, natural language generation models and machine learning algorithms. The summarization unit concisely summarizes the contents of the terms and conditions using, for example, a generation AI. For example, the generation AI may use a text generation AI (e.g., LLM) to extract and summarize important points of the terms and conditions. The summarization unit can also use the generation AI to extract and summarize important parts of the text. For example, the generation AI may use keyword extraction technology to pick out particularly important information in the terms and conditions and summarize it based on that. This improves the accuracy of the summary of the terms and conditions by using the generation AI. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the summarization unit may input text data of the terms and conditions into the generation AI and have the generation AI perform the summary.

[0031] The comparison unit can use a generation AI to compare the standard terms and conditions. Examples of the generation AI include, but are not limited to, natural language generation models and machine learning algorithms. The comparison unit, for example, uses a generation AI to compare the standard terms and conditions with the contract terms and conditions to clarify differences. For example, the generation AI compares the standard terms and conditions with the contract terms and conditions and extracts the differences. The comparison unit can also use the generation AI to evaluate the risk of the contract based on the comparison results with the standard terms and conditions. For example, the generation AI evaluates the risk of the contract based on the differences between the standard terms and conditions and the contract terms. In this way, using the generation AI improves the accuracy of the comparison of terms and conditions. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input text data of the standard terms and conditions and the contract terms into the generation AI and have the generation AI perform the comparison.

[0032] The risk analysis unit can analyze legal and economic risks using a generative AI. Examples of generative AI include, but are not limited to, natural language generation models and machine learning algorithms. The risk analysis unit, for example, uses a generative AI to analyze contract terms and evaluate legal and economic risks. For example, the generative AI evaluates the possibility of contract breach, the risk of legal sanctions, the possibility of financial loss, and investment risks. The risk analysis unit can also use the generative AI to quantify the degree of risk and display the degree of risk to the user. For example, the generative AI quantifies the degree of risk and displays it to the user. This improves the accuracy of risk analysis by using the generative AI. Some or all of the above-described processing in the risk analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the risk analysis unit can input text data of the contract terms into the generative AI and have the generative AI perform risk analysis.

[0033] The validity determination unit can determine the validity of a contract using a generation AI. Examples of the generation AI include, but are not limited to, natural language generation models and machine learning algorithms. The validity determination unit, for example, uses a generation AI to evaluate the validity of a contract based on the user's prior information. For example, the generation AI evaluates the fulfillment of legal requirements and the conformity of contract terms. The validity determination unit can also use the generation AI to indicate to the user whether the contract is appropriate. For example, the generation AI indicates to the user whether the contract is appropriate. This improves the accuracy of determining the validity of a contract by using the generation AI. Some or all of the above-described processing in the validity determination unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the validity determination unit can input the user's prior information and text data of the contract terms into the generation AI and have the generation AI perform the validity determination.

[0034] The problem presentation unit can present individual problems using a generation AI. Examples of the generation AI include, but are not limited to, natural language generation models and machine learning algorithms. The problem presentation unit, for example, uses the generation AI to analyze the contents of the terms and conditions in detail and point out points that may be problematic for the user. For example, the generation AI points out details of problems and risks in specific clauses. The problem presentation unit can also use the generation AI to suggest specific improvements to the user. For example, the generation AI suggests specific improvements to the user. This improves the accuracy of presenting individual problems by using the generation AI. Some or all of the above-mentioned processing in the problem presentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input text data of the contract terms and conditions into the generation AI and have the generation AI present the problems.

[0035] When generating a summary, the summarization unit can adjust the level of detail of the summary based on the importance of the terms and conditions. The summarization unit, for example, uses a generation AI to evaluate the importance of the terms and conditions. For example, the generation AI evaluates the importance of the terms and conditions based on legal impact, financial impact, etc. The summarization unit can also use the generation AI to adjust the level of detail of the summary based on the importance of the terms and conditions. For example, the generation AI can provide a detailed summary for terms and conditions of high importance. The generation AI can also provide a concise summary for terms and conditions of low importance. The summarization unit can also use the generation AI to adjust the length of the summary based on the importance. In this way, by adjusting the level of detail of the summary based on the importance of the terms and conditions, important information can be appropriately conveyed. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the summarization unit can input text data of the terms and conditions into the generation AI and have the generation AI adjust the level of detail of the summary.

[0036] When generating a summary, the summarization unit can apply different summarization algorithms depending on the category of the terms and conditions. The summarization unit, for example, uses a generation AI to classify the category of terms and conditions. For example, the generation AI classifies terms and conditions based on categories such as insurance terms and conditions or rental contract terms and conditions. The summarization unit can also use a generation AI to apply different summarization algorithms depending on the category of terms and conditions. For example, for legal terms and conditions, the generation AI can summarize them from a legal perspective. For economic terms and conditions, the generation AI can summarize them from an economic perspective. For technical terms and conditions, the generation AI can summarize them from a technical perspective. In this way, by applying a summarization algorithm depending on the category of terms and conditions, the accuracy of the summary is improved. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the summarization unit can input text data of the terms and conditions into the generation AI and have the generation AI apply a summarization algorithm.

[0037] When generating a summary, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. The summarization unit, for example, uses a generation AI to refer to the user's past summarization results. For example, the generation AI can use a database to refer to the user's past summarization results. The summarization unit can also use the generation AI to analyze the user's past summarization results and improve the accuracy of the summary. For example, the generation AI can suggest an optimal summarization method based on the user's past summarization results. The summarization unit can also use the generation AI to adjust the content of the summary by referring to the user's past summarization history. In this way, the accuracy of the summary is improved by referring to the user's past summarization results. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the summarization unit can input data on the user's past summarization results into the generation AI and have the generation AI improve the accuracy of the summary.

[0038] When generating summaries, the summarization unit can determine the priority of summaries based on the submission date of the terms and conditions. The summarization unit, for example, uses a generation AI to evaluate the submission date of the terms and conditions. For example, the generation AI evaluates the submission date of the terms and conditions based on the submission date, submission frequency, etc. The summarization unit can also use the generation AI to determine the priority of summaries based on the submission date of the terms and conditions. For example, the generation AI can prioritize summaries for terms and conditions that have been submitted recently. The generation AI can also postpone summarization for terms and conditions that have been submitted recently. The summarization unit can also use the generation AI to adjust the priority of summaries based on the submission date. In this way, by determining the priority of summaries based on the submission date of the terms and conditions, the latest information is provided preferentially. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the summarization unit can input data on the submission date of the terms and conditions into the generation AI and have the generation AI determine the priority of summaries.

[0039] The summarization unit can adjust the order of summaries based on the relevance of the terms and conditions when generating summaries. The summarization unit, for example, uses a generation AI to evaluate the relevance of the terms and conditions. For example, the generation AI evaluates the relevance of the terms and conditions based on the degree of similarity of content, relevant legal standards, etc. The summarization unit can also use the generation AI to adjust the order of summaries based on the relevance of the terms and conditions. For example, the generation AI can prioritize summarization of highly relevant terms and conditions. Alternatively, the generation AI can postpone summarization of less relevant terms and conditions. The summarization unit can also use the generation AI to adjust the order of summaries based on their relevance. In this way, by adjusting the order of summaries based on the relevance of the terms and conditions, important information is provided preferentially. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the summarization unit can input data on the relevance of the terms and conditions into the generation AI and have the generation AI adjust the order of summaries.

[0040] When generating a summary, the summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise. The summarization unit, for example, uses a generation AI to evaluate the user's level of expertise. For example, the generation AI evaluates the user's level of expertise based on the user's occupation, past experience, etc. The summarization unit can also use the generation AI to adjust the use of technical terms in the summary according to the user's level of expertise. For example, if the user has technical expertise, the generation AI can provide a summary that uses a lot of technical terms. On the other hand, if the user does not have technical expertise, the generation AI can provide a concise summary that avoids technical terms. The summarization unit can also use the generation AI to adjust the use of technical terms in the summary according to the user's level of expertise. In this way, by adjusting the use of technical terms in the summary according to the user's level of expertise, a more understandable summary can be provided. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the summarization unit can input data on the user's level of expertise into the generation AI and cause the generation AI to adjust the use of technical terms in the summary.

[0041] The comparison unit can improve the accuracy of the comparison based on the version of the standard terms and conditions during the comparison. The comparison unit, for example, uses a generation AI to evaluate the version of the standard terms and conditions. For example, the generation AI evaluates the version of the standard terms and conditions based on industry standards, legal standards, etc. The comparison unit can also use the generation AI to improve the accuracy of the comparison based on the version of the standard terms and conditions. For example, the comparison unit can improve the accuracy of the comparison based on the latest version of the standard terms and conditions. The comparison unit can also improve the accuracy of the comparison based on past versions of the standard terms and conditions. The comparison unit can also use the generation AI to adjust the accuracy of the comparison depending on the version of the standard terms and conditions. In this way, improving the accuracy of the comparison based on the version of the standard terms and conditions provides a more accurate comparison. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input data on the version of the standard terms and conditions into the generation AI and have the generation AI improve the accuracy of the comparison.

[0042] The comparison unit can make the comparison taking into account the attribute information of the person who submitted the terms and conditions. The comparison unit, for example, uses a generation AI to evaluate the attribute information of the person who submitted the terms and conditions. For example, the generation AI evaluates the attribute information of the person who submitted the terms and conditions based on the submitter's occupation, past contract history, etc. The comparison unit can also use the generation AI to make the comparison taking into account the attribute information of the person who submitted the terms and conditions. For example, if the submitter is a company, the comparison can take into account the company's attribute information. If the submitter is an individual, the comparison can take into account the individual's attribute information. The comparison unit can also use the generation AI to adjust the comparison method depending on the attribute information of the submitter. This allows for a more appropriate comparison by taking into account the attribute information of the person who submitted the terms and conditions. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input attribute information data of the person who submitted the terms and conditions into the generation AI and have the generation AI perform the comparison.

[0043] The comparison unit can weight the comparison based on the submission frequency of the terms and conditions when making the comparison. The comparison unit, for example, uses a generation AI to evaluate the submission frequency of the terms and conditions. For example, the generation AI evaluates the submission frequency of the terms and conditions based on the number of submissions, the submission interval, etc. The comparison unit can also weight the comparison based on the submission frequency of the terms and conditions using the generation AI. For example, terms and conditions that are submitted frequently can be weighted higher for comparison. Also, terms and conditions that are submitted less frequently can be weighted lower for comparison. The comparison unit can also adjust the comparison weight according to the submission frequency using the generation AI. In this way, by weighting the comparison based on the submission frequency of the terms and conditions, more important information is provided preferentially. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input data on the submission frequency of the terms and conditions into the generation AI and have the generation AI perform the comparison weighting.

[0044] The comparison unit can take into account the geographical distribution of the terms and conditions when making the comparison. The comparison unit, for example, uses a generation AI to evaluate the geographical distribution of the terms and conditions. For example, the generation AI evaluates the geographical distribution of the terms and conditions based on regional legal standards, market characteristics, etc. The comparison unit can also use the generation AI to make the comparison while taking into account the geographical distribution of the terms and conditions. For example, the comparison unit can prioritize terms and conditions from geographically close regions. Alternatively, the comparison unit can compare terms and conditions from geographically distant regions later. The comparison unit can also use the generation AI to adjust the comparison method according to the geographical distribution. This provides a more appropriate comparison by taking into account the geographical distribution of the terms and conditions. Some or all of the above-described processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input data on the geographical distribution of the terms and conditions into the generation AI and have the generation AI perform the comparison.

[0045] The comparison unit can improve the accuracy of the comparison by referring to literature related to the terms and conditions during the comparison. The comparison unit, for example, uses a generation AI to refer to literature related to the terms and conditions. For example, the generation AI refers to literature related to the terms and conditions based on legal literature, industry reports, etc. The comparison unit can also improve the accuracy of the comparison by using the generation AI to refer to literature related to the terms and conditions. For example, the comparison unit can improve the accuracy of the comparison based on the related literature. The comparison unit can also adjust the comparison method by referring to the related literature. The comparison unit can also use the generation AI to set comparison criteria based on the related literature. In this way, the accuracy of the comparison is improved by referring to literature related to the terms and conditions. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input data on literature related to the terms and conditions into the generation AI and have the generation AI improve the accuracy of the comparison.

[0046] The comparison unit can take into account the market value of the terms and conditions when making the comparison. The comparison unit, for example, uses a generation AI to evaluate the market value of the terms and conditions. For example, the generation AI evaluates the market value of the terms and conditions based on financial evaluation, market analysis, etc. The comparison unit can also use the generation AI to make the comparison taking into account the market value of the terms and conditions. For example, terms and conditions with high market value can be compared with a higher weighting. Terms and conditions with low market value can be compared with a lower weighting. The comparison unit can also use the generation AI to adjust the comparison method depending on the market value. In this way, by taking the market value of the terms and conditions into consideration, more important information can be provided preferentially. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input data on the market value of the terms and conditions into the generation AI and have the generation AI perform the comparison.

[0047] During risk analysis, the risk analysis unit can predict current risks by referring to past risk data. The risk analysis unit, for example, uses a generation AI to refer to past risk data. For example, the generation AI refers to past risk data based on past risk assessment results, risk occurrence cases, etc. The risk analysis unit can also use the generation AI to predict current risks based on past risk data. For example, the generation AI predicts current risks based on past risk data. The risk analysis unit can also use the generation AI to analyze risk trends by referring to past risk data. In this way, current risks can be predicted more accurately by referring to past risk data. Some or all of the above-described processing in the risk analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the risk analysis unit can input past risk data into the generation AI and have the generation AI predict current risks.

[0048] The risk analysis unit can apply different risk analysis methods to each category of terms and conditions during risk analysis. The risk analysis unit, for example, uses a generation AI to classify the terms and conditions. For example, the generation AI classifies the terms and conditions based on categories such as legal terms and conditions or economic terms and conditions. The risk analysis unit can also use the generation AI to apply different risk analysis methods to each category of terms and conditions. For example, a legal risk analysis method can be applied to legal terms and conditions. An economic risk analysis method can be applied to economic terms and conditions. A technical risk analysis method can be applied to technical terms and conditions. This improves the accuracy of risk analysis by applying a risk analysis method according to the category of terms and conditions. Some or all of the above-mentioned processing in the risk analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the risk analysis unit can input data on the category of terms and conditions into the generation AI and have the generation AI apply the risk analysis method.

[0049] During risk analysis, the risk analysis unit can analyze risks by taking into account the attribute information of the person submitting the terms and conditions. The risk analysis unit, for example, uses a generation AI to evaluate the attribute information of the person submitting the terms and conditions. For example, the generation AI evaluates the attribute information of the person submitting the terms and conditions based on the submitter's occupation, past contract history, etc. The risk analysis unit can also use the generation AI to analyze risks by taking into account the attribute information of the person submitting the terms and conditions. For example, if the submitter is a company, the risk analysis can be performed by taking into account the company's attribute information. If the submitter is an individual, the risk analysis can be performed by taking into account the individual's attribute information. The risk analysis unit can also use the generation AI to adjust the risk analysis method according to the submitter's attribute information. This provides a more appropriate risk analysis by taking into account the attribute information of the person submitting the terms and conditions. Some or all of the above-described processing in the risk analysis unit may be performed by, for example, the generation AI, or may be performed without using the generation AI. For example, the risk analysis unit can input attribute information data of the person submitting the terms and conditions into the generation AI and have the generation AI perform the risk analysis.

[0050] During risk analysis, the risk analysis unit can analyze changes in risk based on the submission timing of the terms and conditions. The risk analysis unit, for example, uses a generation AI to evaluate the submission timing of the terms and conditions. For example, the generation AI evaluates the submission timing of the terms and conditions based on the submission date, submission frequency, etc. The risk analysis unit can also use the generation AI to analyze changes in risk based on the submission timing of the terms and conditions. For example, recently submitted terms and conditions are analyzed based on the latest risk information. Also, older submitted terms and conditions can be analyzed based on past risk data. The risk analysis unit can also use the generation AI to evaluate changes in risk according to the submission timing. In this way, analyzing changes in risk based on the submission timing of the terms and conditions provides more accurate risk information. Some or all of the above-mentioned processing in the risk analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the risk analysis unit can input data on the submission timing of the terms and conditions into the generation AI and have the generation AI perform an analysis of changes in risk.

[0051] During risk analysis, the risk analysis unit can analyze risk by referring to market data related to the terms and conditions. The risk analysis unit, for example, uses a generation AI to refer to market data related to the terms and conditions. For example, the generation AI refers to market data related to the terms and conditions based on market reports, industry analysis data, etc. The risk analysis unit can also use a generation AI to analyze risk based on market data related to the terms and conditions. For example, the generation AI evaluates the level of risk based on the relevant market data. The risk analysis unit can also use a generation AI to analyze risk trends by referring to the relevant market data. In this way, referring to market data related to the terms and conditions improves the accuracy of risk analysis. Some or all of the above-mentioned processing in the risk analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the risk analysis unit can input market data related to the terms and conditions into the generation AI and have the generation AI perform risk analysis.

[0052] The risk analysis unit can analyze risks by taking into account the technical maturity of the terms and conditions during risk analysis. The risk analysis unit, for example, uses a generation AI to evaluate the technical maturity of the terms and conditions. For example, the generation AI evaluates the technical maturity of the terms and conditions based on the development stage of the technology and the market introduction status of the technology. The risk analysis unit can also use the generation AI to analyze risks by taking into account the technical maturity of the terms and conditions. For example, the generation AI can evaluate the risk low for technically mature terms and conditions. The risk analysis unit can also evaluate the risk high for technically immature terms and conditions. The risk analysis unit can also use the generation AI to adjust the risk evaluation criteria according to the technical maturity. This provides a more appropriate risk analysis by taking into account the technical maturity of the terms and conditions. Some or all of the above-mentioned processing in the risk analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the risk analysis unit can input data on the technical maturity of the terms and conditions into the generation AI and have the generation AI perform the risk analysis.

[0053] When making a validity judgment, the validity judgment unit can predict current validity by referring to past validity data. The validity judgment unit, for example, uses a generation AI to refer to past validity data. For example, the generation AI refers to past validity data based on past validity evaluation results and cases in which validity has occurred. The validity judgment unit can also predict current validity based on past validity data using the generation AI. For example, the generation AI predicts current validity based on past validity data. The validity judgment unit can also use the generation AI to analyze validity trends by referring to past validity data. In this way, by referring to past validity data, current validity can be predicted more accurately. Some or all of the above-described processing in the validity judgment unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the validity judgment unit can input past validity data into the generation AI and have the generation AI predict current validity.

[0054] When determining validity, the validity determination unit can apply different validity determination methods to each category of terms and conditions. The validity determination unit, for example, uses a generation AI to classify the terms and conditions. For example, the generation AI classifies the terms and conditions based on categories such as legal terms and conditions or economic terms and conditions. The validity determination unit can also use the generation AI to apply different validity determination methods to each category of terms and conditions. For example, a legal validity determination method can be applied to legal terms and conditions. An economic validity determination method can be applied to economic terms and conditions. A technical validity determination method can be applied to technical terms and conditions. This improves the accuracy of validity determination by applying a validity determination method according to the category of terms and conditions. Some or all of the above-mentioned processing in the validity determination unit may be performed using, or without, the generation AI. For example, the validity determination unit can input data on the category of terms and conditions into the generation AI and have the generation AI apply the validity determination method.

[0055] When determining validity, the validity determination unit can determine validity by taking into account attribute information of the person who submitted the terms and conditions. The validity determination unit, for example, uses a generation AI to evaluate the attribute information of the person who submitted the terms and conditions. For example, the generation AI evaluates the attribute information of the person who submitted the terms and conditions based on the submitter's occupation, past contract history, etc. The validity determination unit can also use the generation AI to determine validity by taking into account attribute information of the person who submitted the terms and conditions. For example, if the submitter is a company, the validity can be determined by taking into account the company's attribute information. If the submitter is an individual, the validity can be determined by taking into account the individual's attribute information. The validity determination unit can also use the generation AI to adjust the method of determining validity depending on the attribute information of the submitter. This allows for a more appropriate validity determination by taking into account the attribute information of the person who submitted the terms and conditions. Some or all of the above-described processing in the validity determination unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the validity determination unit can input attribute information data of the person who submitted the terms and conditions into the generation AI and have the generation AI perform the validity determination.

[0056] The validity determination unit can analyze changes in validity based on the submission date of the terms and conditions when determining validity. The validity determination unit, for example, uses a generation AI to evaluate the submission date of the terms and conditions. For example, the generation AI evaluates the submission date of the terms and conditions based on the submission date, submission frequency, etc. The validity determination unit can also use the generation AI to analyze changes in validity based on the submission date of the terms and conditions. For example, recently submitted terms and conditions are analyzed based on the latest validity information. Also, older submitted terms and conditions can be analyzed based on past validity data. The validity determination unit can also use the generation AI to evaluate changes in validity according to the submission date. In this way, analyzing changes in validity based on the submission date of the terms and conditions provides more accurate validity information. Some or all of the above-mentioned processing in the validity determination unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the validity determination unit can input data on the submission date of the terms and conditions into the generation AI and have the generation AI perform an analysis of changes in validity.

[0057] When determining validity, the validity determination unit can analyze validity by referring to market data related to the terms and conditions. The validity determination unit, for example, uses a generation AI to refer to market data related to the terms and conditions. For example, the generation AI refers to market data related to the terms and conditions based on market reports, industry analysis data, etc. The validity determination unit can also use a generation AI to analyze validity based on market data related to the terms and conditions. For example, the generation AI evaluates the degree of validity based on the relevant market data. The validity determination unit can also use a generation AI to analyze trends in validity by referring to the relevant market data. In this way, referring to market data related to the terms and conditions improves the accuracy of validity determination. Some or all of the above-mentioned processing in the validity determination unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the validity determination unit can input market data related to the terms and conditions into the generation AI and have the generation AI perform validity analysis.

[0058] The validity determination unit can analyze the validity taking into account the technical maturity of the terms and conditions when determining validity. The validity determination unit, for example, uses a generation AI to evaluate the technical maturity of the terms and conditions. For example, the generation AI evaluates the technical maturity of the terms and conditions based on the development stage of the technology and the market introduction status of the technology. The validity determination unit can also use the generation AI to analyze the validity taking into account the technical maturity of the terms and conditions. For example, the generation AI can evaluate the effectiveness of technically mature terms and conditions highly. The validity determination unit can also evaluate the effectiveness of technically immature terms and conditions low. The validity determination unit can also use the generation AI to adjust the effectiveness evaluation criteria according to the technical maturity. This allows for a more appropriate validity determination by taking the technical maturity of the terms and conditions into account. Some or all of the above-mentioned processing in the validity determination unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the validity determination unit can input data on the technical maturity of the terms and conditions into the generation AI and have the generation AI perform the validity analysis.

[0059] When presenting a problem, the problem presentation unit can predict a current problem by referring to past problem data. The problem presentation unit, for example, uses a generation AI to refer to past problem data. For example, the generation AI refers to past problem data based on past problem evaluation results and cases where the problem has occurred. The problem presentation unit can also predict a current problem based on past problem data using the generation AI. For example, the generation AI predicts a current problem based on past problem data. The problem presentation unit can also use the generation AI to analyze problem trends by referring to past problem data. In this way, by referring to past problem data, current problems can be predicted more accurately. Some or all of the above-mentioned processing in the problem presentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input past problem data to the generation AI and cause the generation AI to predict a current problem.

[0060] The problem presentation unit can apply different problem presentation methods to different clause categories when presenting a problem. The problem presentation unit, for example, uses a generation AI to classify clause categories. For example, the generation AI classifies clauses based on categories such as legal clauses and economic clauses. The problem presentation unit can also use the generation AI to apply different problem presentation methods to different clause categories. For example, a legal problem presentation method can be applied to legal clauses. An economic problem presentation method can be applied to economic clauses. A technical problem presentation method can be applied to technical clauses. This improves the accuracy of problem presentation by applying a problem presentation method according to the clause category. Some or all of the above-described processing in the problem presentation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the problem presentation unit can input clause category data to the generation AI and cause the generation AI to apply a problem presentation method.

[0061] When presenting a problem, the problem presentation unit can present a problem by taking into account the attribute information of the person who submitted the terms and conditions. The problem presentation unit, for example, uses a generation AI to evaluate the attribute information of the person who submitted the terms and conditions. For example, the generation AI evaluates the attribute information of the person who submitted the terms and conditions based on the submitter's occupation, past contract history, etc. The problem presentation unit can also use the generation AI to present a problem by taking into account the attribute information of the person who submitted the terms and conditions. For example, if the submitter is a company, the problem presentation unit can present a problem by taking into account the company's attribute information. Also, if the submitter is an individual, the problem presentation unit can present a problem by taking into account the individual's attribute information. The problem presentation unit can also use the generation AI to adjust the method of presenting a problem according to the attribute information of the submitter. In this way, by taking into account the attribute information of the person who submitted the terms and conditions, more appropriate problem presentation is provided. Some or all of the above-mentioned processing in the problem presentation unit may be performed by, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input attribute information data of the person who submitted the terms and conditions into the generation AI and cause the generation AI to present a problem.

[0062] When a problem is presented, the problem presentation unit can analyze changes in the problem based on the submission date of the terms and conditions. The problem presentation unit, for example, uses a generation AI to evaluate the submission date of the terms and conditions. For example, the generation AI evaluates the submission date of the terms and conditions based on the submission date, submission frequency, etc. The problem presentation unit can also use the generation AI to analyze changes in the problem based on the submission date of the terms and conditions. For example, recently submitted terms and conditions can be analyzed based on the latest problem information. Also, older submitted terms and conditions can be analyzed based on past problem data. The problem presentation unit can also use the generation AI to evaluate changes in the problem based on the submission date. In this way, by analyzing changes in the problem based on the submission date of the terms and conditions, more accurate problem information can be provided. Some or all of the above-mentioned processing in the problem presentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input data on the submission date of the terms and conditions to the generation AI and have the generation AI analyze changes in the problem.

[0063] When presenting a problem, the problem presentation unit can analyze the problem by referring to market data related to the terms and conditions. The problem presentation unit, for example, uses a generation AI to refer to market data related to the terms and conditions. For example, the generation AI refers to market data related to the terms and conditions based on market reports, industry analysis data, etc. The problem presentation unit can also use the generation AI to analyze the problem based on market data related to the terms and conditions. For example, the generation AI evaluates the severity of the problem based on the relevant market data. The problem presentation unit can also use the generation AI to analyze the trend of the problem by referring to the relevant market data. In this way, referring to the market data related to the terms and conditions improves the accuracy of the problem presentation. Some or all of the above-mentioned processing in the problem presentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input market data related to the terms and conditions to the generation AI and cause the generation AI to perform problem analysis.

[0064] The problem presentation unit can analyze the problem by taking into account the technical maturity of the terms and conditions when presenting the problem. The problem presentation unit, for example, uses a generation AI to evaluate the technical maturity of the terms and conditions. For example, the generation AI evaluates the technical maturity of the terms and conditions based on the development stage of the technology and the market introduction status of the technology. The problem presentation unit can also analyze the problem by taking into account the technical maturity of the terms and conditions using the generation AI. For example, for technically mature terms and conditions, the problem can be evaluated low. For technically immature terms and conditions, the problem can be evaluated high. The problem presentation unit can also adjust the problem evaluation criteria according to the technical maturity using the generation AI. In this way, more appropriate problem presentation is provided by taking the technical maturity of the terms and conditions into account. Some or all of the above-mentioned processing in the problem presentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input data on the technical maturity of the terms and conditions into the generation AI and have the generation AI perform problem analysis.

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

[0066] When generating a summary, the summarization unit can adjust the level of detail of the summary based on the importance of the terms and conditions. For example, the generation AI evaluates the importance of the terms and conditions based on legal impact, financial impact, etc. The summarization unit can also use the generation AI to adjust the level of detail of the summary based on the importance of the terms and conditions. For example, the generation AI can provide a detailed summary for terms and conditions of high importance. On the other hand, the generation AI can provide a concise summary for terms and conditions of low importance. The summarization unit can also use the generation AI to adjust the length of the summary based on the importance. In this way, by adjusting the level of detail of the summary based on the importance of the terms and conditions, important information can be appropriately conveyed. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the summarization unit can input text data of the terms and conditions into the generation AI and have the generation AI adjust the level of detail of the summary.

[0067] During comparison, the comparison unit can improve the accuracy of the comparison based on the version of the standard terms and conditions. For example, the generation AI evaluates the version of the standard terms and conditions based on industry standards, legal standards, etc. The comparison unit can also use the generation AI to improve the accuracy of the comparison based on the version of the standard terms and conditions. For example, the comparison unit can improve the accuracy of the comparison based on the latest version of the standard terms and conditions. The comparison unit can also improve the accuracy of the comparison based on past versions of the standard terms and conditions. The comparison unit can also use the generation AI to adjust the accuracy of the comparison depending on the version of the standard terms and conditions. This improves the accuracy of the comparison based on the version of the standard terms and conditions, providing a more accurate comparison. Some or all of the above-mentioned processing in the comparison unit may be performed using, or without, the generation AI. For example, the comparison unit can input data on the version of the standard terms and conditions into the generation AI and have the generation AI improve the accuracy of the comparison.

[0068] During risk analysis, the risk analysis unit can predict current risks by referring to past risk data. For example, the generation AI refers to past risk data based on past risk assessment results and risk occurrence cases. The risk analysis unit can also use the generation AI to predict current risks based on past risk data. For example, the generation AI predicts current risks based on past risk data. The risk analysis unit can also use the generation AI to analyze risk trends by referring to past risk data. In this way, current risks can be predicted more accurately by referring to past risk data. Some or all of the above-described processing in the risk analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the risk analysis unit can input past risk data into the generation AI and have the generation AI predict current risks.

[0069] When determining validity, the validity determination unit can apply different validity determination methods to different clause categories. For example, the generation AI classifies clauses based on categories such as legal clauses and economic clauses. The validity determination unit can also use the generation AI to apply different validity determination methods to different clause categories. For example, a legal validity determination method can be applied to legal clauses. An economic validity determination method can be applied to economic clauses. A technical validity determination method can be applied to technical clauses. This improves the accuracy of validity determination by applying a validity determination method according to the clause category. Some or all of the above-described processing in the validity determination unit may be performed using, or without, the generation AI. For example, the validity determination unit can input clause category data into the generation AI and have the generation AI apply the validity determination method.

[0070] When presenting a problem, the problem presentation unit can present a problem by taking into account the attribute information of the person who submitted the terms and conditions. For example, the generation AI evaluates the attribute information of the person who submitted the terms and conditions based on the submitter's occupation, past contract history, etc. The problem presentation unit can also use the generation AI to present a problem by taking into account the attribute information of the person who submitted the terms and conditions. For example, if the submitter is a company, the problem presentation unit can present a problem by taking into account the company's attribute information. Also, if the submitter is an individual, the problem presentation unit can present a problem by taking into account the individual's attribute information. Furthermore, the problem presentation unit can use the generation AI to adjust the method of presenting a problem according to the attribute information of the submitter. In this way, by taking into account the attribute information of the person who submitted the terms and conditions, more appropriate problem presentations can be provided. Some or all of the above-mentioned processing in the problem presentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input attribute information data of the person who submitted the terms and conditions into the generation AI and cause the generation AI to present a problem.

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

[0072] Step 1: The summarization section uses a generation AI to summarize the contents of the terms and conditions. The summarization is based on the length of the text and the importance of the information being summarized. For example, a text generation AI (e.g., LLM) can be used to concisely summarize the terms and conditions, extracting and summarizing the important parts. Step 2: The comparison unit uses the generation AI to compare the information summarized by the summary unit with the standard terms and conditions. The comparison is based on industry and legal standards, and the standard terms and conditions are compared with the contract terms to clarify any differences. Step 3: The risk analysis unit uses generative AI to analyze legal and economic risks based on the information obtained by the comparison unit. Risk analysis is based on the possibility of contract breach, risk of legal sanctions, potential financial loss, investment risk, etc. Step 4: The validity determination unit uses the generative AI to determine the validity of the contract based on the information obtained by the risk analysis unit. The validity determination is based on the fulfillment of legal requirements and the conformity of the contract terms. Step 5: The problem presentation unit uses the generative AI to present specific problems based on the information obtained by the validity assessment unit. The problem presentation is based on the details of the problems and risks of specific clauses.

[0073] (Example 2) The generation AI service according to an embodiment of the present invention is a system that analyzes and summarizes complex text, assesses safety and risk, and provides users with easy-to-understand decision-making information (reports). The generation AI service analyzes and summarizes the contents of contract terms and conditions, compares them with standard contract terms, analyzes legal and economic risks, assesses the validity of the contract, and identifies individual issues. For example, when a user enters into a contract, the generation AI service analyzes the contents of the contract terms and summarizes key points. Next, the generation AI service compares the contract terms with standard contract terms and identifies differences. Furthermore, the generation AI service analyzes legal and economic risks based on the contents of the contract terms and indicates the degree of risk to the user. The generation AI service also assesses the validity of the contract based on the user's prior information and indicates to the user whether the contract is appropriate. Finally, the generation AI service analyzes the contents of the contract terms in detail and points out potential issues for the user. This makes it easier for users to understand complex contract terms and allows them to identify contract risks in advance. This enhances user protection and makes contracts with companies more transparent and fair. For example, when users enter into a contract, they can quickly and accurately understand complex terms and conditions, and understand the risks of the contract in advance. It also allows companies to fulfill their obligation to explain contracts and provide users with highly transparent information.

[0074] The generation AI service according to the embodiment includes a summarization unit, a comparison unit, a risk analysis unit, a validity determination unit, and a problem presentation unit. The summarization unit uses the generation AI to summarize the contents of the terms and conditions. The summarization is performed based on, for example, the length of the sentences and the importance of the information to be summarized, but is not limited to these examples. For example, the generation AI uses a text generation AI (e.g., LLM) to concisely summarize the terms and conditions. The summarization unit can also use the generation AI to extract and summarize important parts of the sentences. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The generation AI uses keyword extraction technology to identify particularly important information in the terms and conditions and perform summarization based on that information. The comparison unit uses the generation AI to compare the information summarized by the summarization unit with standard terms and conditions. The comparison is performed based on, for example, industry standards or legal standards, but is not limited to these examples. For example, the generation AI compares the standard terms and conditions with the terms and conditions of the contract and identifies differences. The comparison unit can also use the generation AI to evaluate the risks of the contract based on the comparison results with the standard terms and conditions. The risk analysis unit uses the generation AI to analyze legal and economic risks based on the information obtained by the comparison unit. Risk analysis is performed based on, for example, the possibility of contract violation, the risk of legal sanctions, the possibility of financial loss, and investment risk, but is not limited to these examples. For example, the generation AI analyzes the terms and conditions of a contract to evaluate legal and economic risks. The risk analysis unit can also use the generation AI to quantify the level of risk and display the level of risk to the user. The validity assessment unit uses the generation AI to determine the validity of the contract based on the information obtained by the risk analysis unit. The validity assessment is performed based on, for example, the fulfillment of legal requirements and the conformity of contract terms, but is not limited to these examples. For example, the generation AI evaluates the validity of the contract based on the user's prior information. The validity assessment unit can also use the generation AI to indicate to the user whether the contract is appropriate. The problem presentation unit uses the generation AI to present individual problems based on the information obtained by the validity assessment unit. The problem presentation is performed based on, for example, the problems and risk details of specific clauses, but is not limited to these examples.For example, the generation AI analyzes the contents of the terms and conditions in detail and points out points that may be problematic for the user. The problem presentation unit can also use the generation AI to suggest specific areas for improvement to the user. As a result, the generation AI service according to the embodiment makes it easier for users to understand complex terms and conditions and can grasp contract risks in advance. By using the generation AI, the accuracy of each process, including summarization, comparison, risk analysis, validity assessment, and problem presentation, is improved, making it possible to provide more appropriate information to the user.

[0075] The summarization unit can summarize the contents of the terms and conditions using a generation AI. Examples of generation AI include, but are not limited to, natural language generation models and machine learning algorithms. The summarization unit concisely summarizes the contents of the terms and conditions using, for example, a generation AI. For example, the generation AI may use a text generation AI (e.g., LLM) to extract and summarize important points of the terms and conditions. The summarization unit can also use the generation AI to extract and summarize important parts of the text. For example, the generation AI may use keyword extraction technology to pick out particularly important information in the terms and conditions and summarize it based on that. This improves the accuracy of the summary of the terms and conditions by using the generation AI. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the summarization unit may input text data of the terms and conditions into the generation AI and have the generation AI perform the summary.

[0076] The comparison unit can use a generation AI to compare the standard terms and conditions. Examples of the generation AI include, but are not limited to, natural language generation models and machine learning algorithms. The comparison unit, for example, uses a generation AI to compare the standard terms and conditions with the contract terms and conditions to clarify differences. For example, the generation AI compares the standard terms and conditions with the contract terms and conditions and extracts the differences. The comparison unit can also use the generation AI to evaluate the risk of the contract based on the comparison results with the standard terms and conditions. For example, the generation AI evaluates the risk of the contract based on the differences between the standard terms and conditions and the contract terms. In this way, using the generation AI improves the accuracy of the comparison of terms and conditions. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input text data of the standard terms and conditions and the contract terms into the generation AI and have the generation AI perform the comparison.

[0077] The risk analysis unit can analyze legal and economic risks using a generative AI. Examples of generative AI include, but are not limited to, natural language generation models and machine learning algorithms. The risk analysis unit, for example, uses a generative AI to analyze contract terms and evaluate legal and economic risks. For example, the generative AI evaluates the possibility of contract breach, the risk of legal sanctions, the possibility of financial loss, and investment risks. The risk analysis unit can also use the generative AI to quantify the degree of risk and display the degree of risk to the user. For example, the generative AI quantifies the degree of risk and displays it to the user. This improves the accuracy of risk analysis by using the generative AI. Some or all of the above-described processing in the risk analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the risk analysis unit can input text data of the contract terms into the generative AI and have the generative AI perform risk analysis.

[0078] The validity determination unit can determine the validity of a contract using a generation AI. Examples of the generation AI include, but are not limited to, natural language generation models and machine learning algorithms. The validity determination unit, for example, uses a generation AI to evaluate the validity of a contract based on the user's prior information. For example, the generation AI evaluates the fulfillment of legal requirements and the conformity of contract terms. The validity determination unit can also use the generation AI to indicate to the user whether the contract is appropriate. For example, the generation AI indicates to the user whether the contract is appropriate. This improves the accuracy of determining the validity of a contract by using the generation AI. Some or all of the above-described processing in the validity determination unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the validity determination unit can input the user's prior information and text data of the contract terms into the generation AI and have the generation AI perform the validity determination.

[0079] The problem presentation unit can present individual problems using a generation AI. Examples of the generation AI include, but are not limited to, natural language generation models and machine learning algorithms. The problem presentation unit, for example, uses the generation AI to analyze the contents of the terms and conditions in detail and point out points that may be problematic for the user. For example, the generation AI points out details of problems and risks in specific clauses. The problem presentation unit can also use the generation AI to suggest specific improvements to the user. For example, the generation AI suggests specific improvements to the user. This improves the accuracy of presenting individual problems by using the generation AI. Some or all of the above-mentioned processing in the problem presentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input text data of the contract terms and conditions into the generation AI and have the generation AI present the problems.

[0080] The summarization unit can estimate the user's emotions and adjust the presentation style of the summary based on the estimated user's emotions. The summarization unit can estimate the user's emotions using, for example, a generation AI. For example, the generation AI can estimate the user's emotions using a sentiment analysis algorithm. The summarization unit can also adjust the presentation style of the summary based on the estimated user's emotions using the generation AI. For example, if the user is stressed, the generation AI can provide a concise summary that covers the main points. If the user is relaxed, the generation AI can provide a summary that includes detailed explanations. If the user is in a hurry, the generation AI can provide a summary that highlights only the most important points. This allows the summary to be adjusted according to the user's emotions, resulting in a more appropriate summary. Emotion estimation is achieved using, for example, an emotion estimation function using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the summarization unit can be performed using, for example, the generation AI, or without the generation AI. For example, the summarization unit can input user emotional data into the generation AI and have the generation AI adjust the way the summary is expressed.

[0081] When generating a summary, the summarization unit can adjust the level of detail of the summary based on the importance of the terms and conditions. The summarization unit, for example, uses a generation AI to evaluate the importance of the terms and conditions. For example, the generation AI evaluates the importance of the terms and conditions based on legal impact, financial impact, etc. The summarization unit can also use the generation AI to adjust the level of detail of the summary based on the importance of the terms and conditions. For example, the generation AI can provide a detailed summary for terms and conditions of high importance. The generation AI can also provide a concise summary for terms and conditions of low importance. The summarization unit can also use the generation AI to adjust the length of the summary based on the importance. In this way, by adjusting the level of detail of the summary based on the importance of the terms and conditions, important information can be appropriately conveyed. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the summarization unit can input text data of the terms and conditions into the generation AI and have the generation AI adjust the level of detail of the summary.

[0082] When generating a summary, the summarization unit can apply different summarization algorithms depending on the category of the terms and conditions. The summarization unit, for example, uses a generation AI to classify the category of terms and conditions. For example, the generation AI classifies terms and conditions based on categories such as insurance terms and conditions or rental contract terms and conditions. The summarization unit can also use a generation AI to apply different summarization algorithms depending on the category of terms and conditions. For example, for legal terms and conditions, the generation AI can summarize them from a legal perspective. For economic terms and conditions, the generation AI can summarize them from an economic perspective. For technical terms and conditions, the generation AI can summarize them from a technical perspective. In this way, by applying a summarization algorithm depending on the category of terms and conditions, the accuracy of the summary is improved. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the summarization unit can input text data of the terms and conditions into the generation AI and have the generation AI apply a summarization algorithm.

[0083] When generating a summary, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. The summarization unit, for example, uses a generation AI to refer to the user's past summarization results. For example, the generation AI can use a database to refer to the user's past summarization results. The summarization unit can also use the generation AI to analyze the user's past summarization results and improve the accuracy of the summary. For example, the generation AI can suggest an optimal summarization method based on the user's past summarization results. The summarization unit can also use the generation AI to adjust the content of the summary by referring to the user's past summarization history. In this way, the accuracy of the summary is improved by referring to the user's past summarization results. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the summarization unit can input data on the user's past summarization results into the generation AI and have the generation AI improve the accuracy of the summary.

[0084] The summarization unit can estimate the user's emotions and adjust the length of the summary based on the estimated user's emotions. The summarization unit can estimate the user's emotions using, for example, a generation AI. For example, the generation AI can estimate the user's emotions using a sentiment analysis algorithm. The summarization unit can also adjust the length of the summary based on the estimated user's emotions using the generation AI. For example, if the user is stressed, the generation AI can provide a short, concise summary. If the user is relaxed, the generation AI can provide a longer summary with detailed explanations. If the user is in a hurry, the generation AI can provide a short summary that highlights only the most important points. This allows the length of the summary to be adjusted according to the user's emotions, resulting in a more appropriate summary. 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 summarization unit can be performed using, for example, the generation AI, or without the generation AI. For example, the summarization unit can input user emotion data into the generation AI and have the generation AI adjust the length of the summary.

[0085] When generating summaries, the summarization unit can determine the priority of summaries based on the submission date of the terms and conditions. The summarization unit, for example, uses a generation AI to evaluate the submission date of the terms and conditions. For example, the generation AI evaluates the submission date of the terms and conditions based on the submission date, submission frequency, etc. The summarization unit can also use the generation AI to determine the priority of summaries based on the submission date of the terms and conditions. For example, the generation AI can prioritize summaries for terms and conditions that have been submitted recently. The generation AI can also postpone summarization for terms and conditions that have been submitted recently. The summarization unit can also use the generation AI to adjust the priority of summaries based on the submission date. In this way, by determining the priority of summaries based on the submission date of the terms and conditions, the latest information is provided preferentially. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the summarization unit can input data on the submission date of the terms and conditions into the generation AI and have the generation AI determine the priority of summaries.

[0086] The summarization unit can adjust the order of summaries based on the relevance of the terms and conditions when generating summaries. The summarization unit, for example, uses a generation AI to evaluate the relevance of the terms and conditions. For example, the generation AI evaluates the relevance of the terms and conditions based on the degree of similarity of content, relevant legal standards, etc. The summarization unit can also use the generation AI to adjust the order of summaries based on the relevance of the terms and conditions. For example, the generation AI can prioritize summarization of highly relevant terms and conditions. Alternatively, the generation AI can postpone summarization of less relevant terms and conditions. The summarization unit can also use the generation AI to adjust the order of summaries based on their relevance. In this way, by adjusting the order of summaries based on the relevance of the terms and conditions, important information is provided preferentially. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the summarization unit can input data on the relevance of the terms and conditions into the generation AI and have the generation AI adjust the order of summaries.

[0087] When generating a summary, the summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise. The summarization unit, for example, uses a generation AI to evaluate the user's level of expertise. For example, the generation AI evaluates the user's level of expertise based on the user's occupation, past experience, etc. The summarization unit can also use the generation AI to adjust the use of technical terms in the summary according to the user's level of expertise. For example, if the user has technical expertise, the generation AI can provide a summary that uses a lot of technical terms. On the other hand, if the user does not have technical expertise, the generation AI can provide a concise summary that avoids technical terms. The summarization unit can also use the generation AI to adjust the use of technical terms in the summary according to the user's level of expertise. In this way, by adjusting the use of technical terms in the summary according to the user's level of expertise, a more understandable summary can be provided. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the summarization unit can input data on the user's level of expertise into the generation AI and cause the generation AI to adjust the use of technical terms in the summary.

[0088] The comparison unit can estimate the user's emotion and adjust the comparison criteria based on the estimated user's emotion. The comparison unit, for example, uses a generation AI to estimate the user's emotion. For example, the generation AI estimates the user's emotion using an emotion analysis algorithm. The comparison unit can also adjust the comparison criteria based on the estimated user's emotion using the generation AI. For example, if the user is stressed, the generation AI can provide a concise and to-the-point comparison criteria. If the user is relaxed, the generation AI can provide a detailed comparison criteria. If the user is in a hurry, the generation AI can provide a comparison criteria that highlights only the most important points. This allows for a more appropriate comparison by adjusting the comparison criteria according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the comparison unit can be performed using, for example, the generation AI, or without the generation AI. For example, the comparison unit can input user emotion data to the generation AI and cause the generation AI to adjust the comparison criteria.

[0089] The comparison unit can improve the accuracy of the comparison based on the version of the standard terms and conditions during the comparison. The comparison unit, for example, uses a generation AI to evaluate the version of the standard terms and conditions. For example, the generation AI evaluates the version of the standard terms and conditions based on industry standards, legal standards, etc. The comparison unit can also use the generation AI to improve the accuracy of the comparison based on the version of the standard terms and conditions. For example, the comparison unit can improve the accuracy of the comparison based on the latest version of the standard terms and conditions. The comparison unit can also improve the accuracy of the comparison based on past versions of the standard terms and conditions. The comparison unit can also use the generation AI to adjust the accuracy of the comparison depending on the version of the standard terms and conditions. In this way, improving the accuracy of the comparison based on the version of the standard terms and conditions provides a more accurate comparison. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input data on the version of the standard terms and conditions into the generation AI and have the generation AI improve the accuracy of the comparison.

[0090] The comparison unit can make the comparison taking into account the attribute information of the person who submitted the terms and conditions. The comparison unit, for example, uses a generation AI to evaluate the attribute information of the person who submitted the terms and conditions. For example, the generation AI evaluates the attribute information of the person who submitted the terms and conditions based on the submitter's occupation, past contract history, etc. The comparison unit can also use the generation AI to make the comparison taking into account the attribute information of the person who submitted the terms and conditions. For example, if the submitter is a company, the comparison can take into account the company's attribute information. If the submitter is an individual, the comparison can take into account the individual's attribute information. The comparison unit can also use the generation AI to adjust the comparison method depending on the attribute information of the submitter. This allows for a more appropriate comparison by taking into account the attribute information of the person who submitted the terms and conditions. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input attribute information data of the person who submitted the terms and conditions into the generation AI and have the generation AI perform the comparison.

[0091] The comparison unit can weight the comparison based on the submission frequency of the terms and conditions when making the comparison. The comparison unit, for example, uses a generation AI to evaluate the submission frequency of the terms and conditions. For example, the generation AI evaluates the submission frequency of the terms and conditions based on the number of submissions, the submission interval, etc. The comparison unit can also weight the comparison based on the submission frequency of the terms and conditions using the generation AI. For example, terms and conditions that are submitted frequently can be weighted higher for comparison. Also, terms and conditions that are submitted less frequently can be weighted lower for comparison. The comparison unit can also adjust the comparison weight according to the submission frequency using the generation AI. In this way, by weighting the comparison based on the submission frequency of the terms and conditions, more important information is provided preferentially. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input data on the submission frequency of the terms and conditions into the generation AI and have the generation AI perform the comparison weighting.

[0092] The comparison unit can estimate the user's emotion and adjust the display method of the comparison results based on the estimated user's emotion. The comparison unit, for example, uses a generation AI to estimate the user's emotion. For example, the generation AI estimates the user's emotion using an emotion analysis algorithm. The comparison unit can also use the generation AI to adjust the display method of the comparison results based on the estimated user's emotion. For example, if the user is stressed, the generation AI can provide a concise and highly visible display method. If the user is relaxed, the generation AI can provide a display method that includes detailed information. If the user is in a hurry, the generation AI can provide a display method that focuses on the main points. This allows the display method of the comparison results to be adjusted according to the user's emotion, providing a more appropriate display. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the comparison unit may be performed using, for example, the generation AI, or without the generation AI. For example, the comparison unit can input user emotion data to the generation AI and cause the generation AI to adjust the display method of the comparison results.

[0093] The comparison unit can take into account the geographical distribution of the terms and conditions when making the comparison. The comparison unit, for example, uses a generation AI to evaluate the geographical distribution of the terms and conditions. For example, the generation AI evaluates the geographical distribution of the terms and conditions based on regional legal standards, market characteristics, etc. The comparison unit can also use the generation AI to make the comparison while taking into account the geographical distribution of the terms and conditions. For example, the comparison unit can prioritize terms and conditions from geographically close regions. Alternatively, the comparison unit can compare terms and conditions from geographically distant regions later. The comparison unit can also use the generation AI to adjust the comparison method according to the geographical distribution. This provides a more appropriate comparison by taking into account the geographical distribution of the terms and conditions. Some or all of the above-described processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input data on the geographical distribution of the terms and conditions into the generation AI and have the generation AI perform the comparison.

[0094] The comparison unit can improve the accuracy of the comparison by referring to literature related to the terms and conditions during the comparison. The comparison unit, for example, uses a generation AI to refer to literature related to the terms and conditions. For example, the generation AI refers to literature related to the terms and conditions based on legal literature, industry reports, etc. The comparison unit can also improve the accuracy of the comparison by using the generation AI to refer to literature related to the terms and conditions. For example, the comparison unit can improve the accuracy of the comparison based on the related literature. The comparison unit can also adjust the comparison method by referring to the related literature. The comparison unit can also use the generation AI to set comparison criteria based on the related literature. In this way, the accuracy of the comparison is improved by referring to literature related to the terms and conditions. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input data on literature related to the terms and conditions into the generation AI and have the generation AI improve the accuracy of the comparison.

[0095] The comparison unit can take into account the market value of the terms and conditions when making the comparison. The comparison unit, for example, uses a generation AI to evaluate the market value of the terms and conditions. For example, the generation AI evaluates the market value of the terms and conditions based on financial evaluation, market analysis, etc. The comparison unit can also use the generation AI to make the comparison taking into account the market value of the terms and conditions. For example, terms and conditions with high market value can be compared with a higher weighting. Terms and conditions with low market value can be compared with a lower weighting. The comparison unit can also use the generation AI to adjust the comparison method depending on the market value. In this way, by taking the market value of the terms and conditions into consideration, more important information can be provided preferentially. Some or all of the above-mentioned processing in the comparison unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the comparison unit can input data on the market value of the terms and conditions into the generation AI and have the generation AI perform the comparison.

[0096] The risk analysis unit can estimate the user's emotions and adjust the risk display method based on the estimated user's emotions. The risk analysis unit, for example, uses a generation AI to estimate the user's emotions. For example, the generation AI estimates the user's emotions using an emotion analysis algorithm. The risk analysis unit can also use the generation AI to adjust the risk display method based on the estimated user's emotions. For example, if the user is stressed, the generation AI can provide a concise and highly visible risk display. If the user is relaxed, the generation AI can provide detailed risk information. If the user is in a hurry, the generation AI can provide a risk display that focuses on the main points. This allows for more appropriate risk information to be provided by adjusting the risk display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the risk analysis unit may be performed using, for example, the generation AI, or without the generation AI. For example, the risk analysis unit can input user emotional data into the generation AI and have the generation AI adjust the way the risk is displayed.

[0097] During risk analysis, the risk analysis unit can predict current risks by referring to past risk data. The risk analysis unit, for example, uses a generation AI to refer to past risk data. For example, the generation AI refers to past risk data based on past risk assessment results, risk occurrence cases, etc. The risk analysis unit can also use the generation AI to predict current risks based on past risk data. For example, the generation AI predicts current risks based on past risk data. The risk analysis unit can also use the generation AI to analyze risk trends by referring to past risk data. In this way, current risks can be predicted more accurately by referring to past risk data. Some or all of the above-described processing in the risk analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the risk analysis unit can input past risk data into the generation AI and have the generation AI predict current risks.

[0098] The risk analysis unit can apply different risk analysis methods to each category of terms and conditions during risk analysis. The risk analysis unit, for example, uses a generation AI to classify the terms and conditions. For example, the generation AI classifies the terms and conditions based on categories such as legal terms and conditions or economic terms and conditions. The risk analysis unit can also use the generation AI to apply different risk analysis methods to each category of terms and conditions. For example, a legal risk analysis method can be applied to legal terms and conditions. An economic risk analysis method can be applied to economic terms and conditions. A technical risk analysis method can be applied to technical terms and conditions. This improves the accuracy of risk analysis by applying a risk analysis method according to the category of terms and conditions. Some or all of the above-mentioned processing in the risk analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the risk analysis unit can input data on the category of terms and conditions into the generation AI and have the generation AI apply the risk analysis method.

[0099] During risk analysis, the risk analysis unit can analyze risks by taking into account the attribute information of the person submitting the terms and conditions. The risk analysis unit, for example, uses a generation AI to evaluate the attribute information of the person submitting the terms and conditions. For example, the generation AI evaluates the attribute information of the person submitting the terms and conditions based on the submitter's occupation, past contract history, etc. The risk analysis unit can also use the generation AI to analyze risks by taking into account the attribute information of the person submitting the terms and conditions. For example, if the submitter is a company, the risk analysis can be performed by taking into account the company's attribute information. If the submitter is an individual, the risk analysis can be performed by taking into account the individual's attribute information. The risk analysis unit can also use the generation AI to adjust the risk analysis method according to the submitter's attribute information. This provides a more appropriate risk analysis by taking into account the attribute information of the person submitting the terms and conditions. Some or all of the above-described processing in the risk analysis unit may be performed by, for example, the generation AI, or may be performed without using the generation AI. For example, the risk analysis unit can input attribute information data of the person submitting the terms and conditions into the generation AI and have the generation AI perform the risk analysis.

[0100] The risk analysis unit can estimate the user's emotions and adjust the importance of risks based on the estimated user emotions. The risk analysis unit, for example, uses a generation AI to estimate the user's emotions. For example, the generation AI estimates the user's emotions using an emotion analysis algorithm. The risk analysis unit can also adjust the importance of risks based on the estimated user emotions using the generation AI. For example, if the user is stressed, only high-importance risks can be highlighted and displayed. If the user is relaxed, detailed risk information can be provided. If the user is in a hurry, only the most important risks can be displayed. This allows for more appropriate risk information to be provided by adjusting the importance of risks 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 risk analysis unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the risk analysis unit can input user emotional data into the generation AI and have the generation AI adjust the importance of the risk.

[0101] During risk analysis, the risk analysis unit can analyze changes in risk based on the submission timing of the terms and conditions. The risk analysis unit, for example, uses a generation AI to evaluate the submission timing of the terms and conditions. For example, the generation AI evaluates the submission timing of the terms and conditions based on the submission date, submission frequency, etc. The risk analysis unit can also use the generation AI to analyze changes in risk based on the submission timing of the terms and conditions. For example, recently submitted terms and conditions are analyzed based on the latest risk information. Also, older submitted terms and conditions can be analyzed based on past risk data. The risk analysis unit can also use the generation AI to evaluate changes in risk according to the submission timing. In this way, analyzing changes in risk based on the submission timing of the terms and conditions provides more accurate risk information. Some or all of the above-mentioned processing in the risk analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the risk analysis unit can input data on the submission timing of the terms and conditions into the generation AI and have the generation AI perform an analysis of changes in risk.

[0102] During risk analysis, the risk analysis unit can analyze risk by referring to market data related to the terms and conditions. The risk analysis unit, for example, uses a generation AI to refer to market data related to the terms and conditions. For example, the generation AI refers to market data related to the terms and conditions based on market reports, industry analysis data, etc. The risk analysis unit can also use a generation AI to analyze risk based on market data related to the terms and conditions. For example, the generation AI evaluates the level of risk based on the relevant market data. The risk analysis unit can also use a generation AI to analyze risk trends by referring to the relevant market data. In this way, referring to market data related to the terms and conditions improves the accuracy of risk analysis. Some or all of the above-mentioned processing in the risk analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the risk analysis unit can input market data related to the terms and conditions into the generation AI and have the generation AI perform risk analysis.

[0103] The risk analysis unit can analyze risks by taking into account the technical maturity of the terms and conditions during risk analysis. The risk analysis unit, for example, uses a generation AI to evaluate the technical maturity of the terms and conditions. For example, the generation AI evaluates the technical maturity of the terms and conditions based on the development stage of the technology and the market introduction status of the technology. The risk analysis unit can also use the generation AI to analyze risks by taking into account the technical maturity of the terms and conditions. For example, the generation AI can evaluate the risk low for technically mature terms and conditions. The risk analysis unit can also evaluate the risk high for technically immature terms and conditions. The risk analysis unit can also use the generation AI to adjust the risk evaluation criteria according to the technical maturity. This provides a more appropriate risk analysis by taking into account the technical maturity of the terms and conditions. Some or all of the above-mentioned processing in the risk analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the risk analysis unit can input data on the technical maturity of the terms and conditions into the generation AI and have the generation AI perform the risk analysis.

[0104] The validity determination unit can estimate the user's emotions and adjust the validity display method based on the estimated user's emotions. The validity determination unit, for example, uses a generation AI to estimate the user's emotions. For example, the generation AI estimates the user's emotions using an emotion analysis algorithm. The validity determination unit can also adjust the validity display method based on the estimated user's emotions using the generation AI. For example, if the user is stressed, the generation AI can provide a concise and highly visible validity display. If the user is relaxed, the generation AI can provide detailed validity information. If the user is in a hurry, the generation AI can provide a validity display that focuses on the main points. In this way, by adjusting the validity display method according to the user's emotions, more appropriate validity information can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the validity determination unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the validity determination unit can input user emotion data to the generation AI and cause the generation AI to adjust the method of displaying validity.

[0105] When making a validity judgment, the validity judgment unit can predict current validity by referring to past validity data. The validity judgment unit, for example, uses a generation AI to refer to past validity data. For example, the generation AI refers to past validity data based on past validity evaluation results and cases in which validity has occurred. The validity judgment unit can also predict current validity based on past validity data using the generation AI. For example, the generation AI predicts current validity based on past validity data. The validity judgment unit can also use the generation AI to analyze validity trends by referring to past validity data. In this way, by referring to past validity data, current validity can be predicted more accurately. Some or all of the above-described processing in the validity judgment unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the validity judgment unit can input past validity data into the generation AI and have the generation AI predict current validity.

[0106] When determining validity, the validity determination unit can apply different validity determination methods to each category of terms and conditions. The validity determination unit, for example, uses a generation AI to classify the terms and conditions. For example, the generation AI classifies the terms and conditions based on categories such as legal terms and conditions or economic terms and conditions. The validity determination unit can also use the generation AI to apply different validity determination methods to each category of terms and conditions. For example, a legal validity determination method can be applied to legal terms and conditions. An economic validity determination method can be applied to economic terms and conditions. A technical validity determination method can be applied to technical terms and conditions. This improves the accuracy of validity determination by applying a validity determination method according to the category of terms and conditions. Some or all of the above-mentioned processing in the validity determination unit may be performed using, or without, the generation AI. For example, the validity determination unit can input data on the category of terms and conditions into the generation AI and have the generation AI apply the validity determination method.

[0107] When determining validity, the validity determination unit can determine validity by taking into account attribute information of the person who submitted the terms and conditions. The validity determination unit, for example, uses a generation AI to evaluate the attribute information of the person who submitted the terms and conditions. For example, the generation AI evaluates the attribute information of the person who submitted the terms and conditions based on the submitter's occupation, past contract history, etc. The validity determination unit can also use the generation AI to determine validity by taking into account attribute information of the person who submitted the terms and conditions. For example, if the submitter is a company, the validity can be determined by taking into account the company's attribute information. If the submitter is an individual, the validity can be determined by taking into account the individual's attribute information. The validity determination unit can also use the generation AI to adjust the method of determining validity depending on the attribute information of the submitter. This allows for a more appropriate validity determination by taking into account the attribute information of the person who submitted the terms and conditions. Some or all of the above-described processing in the validity determination unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the validity determination unit can input attribute information data of the person who submitted the terms and conditions into the generation AI and have the generation AI perform the validity determination.

[0108] The validity determination unit can estimate the user's emotions and adjust the importance of validity based on the estimated user's emotions. The validity determination unit, for example, uses a generation AI to estimate the user's emotions. For example, the generation AI estimates the user's emotions using an emotion analysis algorithm. The validity determination unit can also adjust the importance of validity based on the estimated user's emotions using the generation AI. For example, if the user is stressed, only highly important validities can be highlighted and displayed. Also, if the user is relaxed, detailed validity information can be provided. Also, if the user is in a hurry, only the most important validity can be displayed. In this way, by adjusting the importance of validity according to the user's emotions, more appropriate validity information can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the validity determination unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the validity determination unit can input user emotion data to the generation AI and cause the generation AI to adjust the importance of validity.

[0109] The validity determination unit can analyze changes in validity based on the submission date of the terms and conditions when determining validity. The validity determination unit, for example, uses a generation AI to evaluate the submission date of the terms and conditions. For example, the generation AI evaluates the submission date of the terms and conditions based on the submission date, submission frequency, etc. The validity determination unit can also use the generation AI to analyze changes in validity based on the submission date of the terms and conditions. For example, recently submitted terms and conditions are analyzed based on the latest validity information. Also, older submitted terms and conditions can be analyzed based on past validity data. The validity determination unit can also use the generation AI to evaluate changes in validity according to the submission date. In this way, analyzing changes in validity based on the submission date of the terms and conditions provides more accurate validity information. Some or all of the above-mentioned processing in the validity determination unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the validity determination unit can input data on the submission date of the terms and conditions into the generation AI and have the generation AI perform an analysis of changes in validity.

[0110] When determining validity, the validity determination unit can analyze validity by referring to market data related to the terms and conditions. The validity determination unit, for example, uses a generation AI to refer to market data related to the terms and conditions. For example, the generation AI refers to market data related to the terms and conditions based on market reports, industry analysis data, etc. The validity determination unit can also use a generation AI to analyze validity based on market data related to the terms and conditions. For example, the generation AI evaluates the degree of validity based on the relevant market data. The validity determination unit can also use a generation AI to analyze trends in validity by referring to the relevant market data. In this way, referring to market data related to the terms and conditions improves the accuracy of validity determination. Some or all of the above-mentioned processing in the validity determination unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the validity determination unit can input market data related to the terms and conditions into the generation AI and have the generation AI perform validity analysis.

[0111] The validity determination unit can analyze the validity taking into account the technical maturity of the terms and conditions when determining validity. The validity determination unit, for example, uses a generation AI to evaluate the technical maturity of the terms and conditions. For example, the generation AI evaluates the technical maturity of the terms and conditions based on the development stage of the technology and the market introduction status of the technology. The validity determination unit can also use the generation AI to analyze the validity taking into account the technical maturity of the terms and conditions. For example, the generation AI can evaluate the effectiveness of technically mature terms and conditions highly. The validity determination unit can also evaluate the effectiveness of technically immature terms and conditions low. The validity determination unit can also use the generation AI to adjust the effectiveness evaluation criteria according to the technical maturity. This allows for a more appropriate validity determination by taking the technical maturity of the terms and conditions into account. Some or all of the above-mentioned processing in the validity determination unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the validity determination unit can input data on the technical maturity of the terms and conditions into the generation AI and have the generation AI perform the validity analysis.

[0112] The problem presentation unit can estimate the user's emotion and adjust the display method of the problem based on the estimated user's emotion. The problem presentation unit can estimate the user's emotion using, for example, a generation AI. For example, the generation AI can estimate the user's emotion using an emotion analysis algorithm. The problem presentation unit can also adjust the display method of the problem based on the estimated user's emotion using the generation AI. For example, if the user is stressed, the generation AI can provide a concise and highly visible problem display. Also, if the user is relaxed, the generation AI can provide detailed problem information. Also, if the user is in a hurry, the generation AI can provide a problem display that focuses on the main points. In this way, by adjusting the display method of the problem according to the user's emotion, more appropriate problem information can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the problem presentation unit can be performed using, for example, the generation AI, or without the generation AI. For example, the problem presentation unit can input user emotion data to the generation AI and cause the generation AI to adjust the way the problem is displayed.

[0113] When presenting a problem, the problem presentation unit can predict a current problem by referring to past problem data. The problem presentation unit, for example, uses a generation AI to refer to past problem data. For example, the generation AI refers to past problem data based on past problem evaluation results and cases where the problem has occurred. The problem presentation unit can also predict a current problem based on past problem data using the generation AI. For example, the generation AI predicts a current problem based on past problem data. The problem presentation unit can also use the generation AI to analyze problem trends by referring to past problem data. In this way, by referring to past problem data, current problems can be predicted more accurately. Some or all of the above-mentioned processing in the problem presentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input past problem data to the generation AI and cause the generation AI to predict a current problem.

[0114] The problem presentation unit can apply different problem presentation methods to different clause categories when presenting a problem. The problem presentation unit, for example, uses a generation AI to classify clause categories. For example, the generation AI classifies clauses based on categories such as legal clauses and economic clauses. The problem presentation unit can also use the generation AI to apply different problem presentation methods to different clause categories. For example, a legal problem presentation method can be applied to legal clauses. An economic problem presentation method can be applied to economic clauses. A technical problem presentation method can be applied to technical clauses. This improves the accuracy of problem presentation by applying a problem presentation method according to the clause category. Some or all of the above-described processing in the problem presentation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the problem presentation unit can input clause category data to the generation AI and cause the generation AI to apply a problem presentation method.

[0115] When presenting a problem, the problem presentation unit can present a problem by taking into account the attribute information of the person who submitted the terms and conditions. The problem presentation unit, for example, uses a generation AI to evaluate the attribute information of the person who submitted the terms and conditions. For example, the generation AI evaluates the attribute information of the person who submitted the terms and conditions based on the submitter's occupation, past contract history, etc. The problem presentation unit can also use the generation AI to present a problem by taking into account the attribute information of the person who submitted the terms and conditions. For example, if the submitter is a company, the problem presentation unit can present a problem by taking into account the company's attribute information. Also, if the submitter is an individual, the problem presentation unit can present a problem by taking into account the individual's attribute information. The problem presentation unit can also use the generation AI to adjust the method of presenting a problem according to the attribute information of the submitter. In this way, by taking into account the attribute information of the person who submitted the terms and conditions, more appropriate problem presentation is provided. Some or all of the above-mentioned processing in the problem presentation unit may be performed by, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input attribute information data of the person who submitted the terms and conditions into the generation AI and cause the generation AI to present a problem.

[0116] The problem presentation unit can estimate the user's emotions and adjust the importance of each issue based on the estimated user's emotions. The problem presentation unit can estimate the user's emotions using, for example, a generation AI. For example, the generation AI can estimate the user's emotions using an emotion analysis algorithm. The problem presentation unit can also adjust the importance of each issue based on the estimated user's emotions using the generation AI. For example, if the user is stressed, only issues with high importance can be highlighted and displayed. If the user is relaxed, detailed problem information can be provided. If the user is in a hurry, only the most important issues can be displayed. This allows for more appropriate problem information to be provided by adjusting the importance of each issue 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-described processing in the problem presentation unit can be performed using, for example, the generation AI, or without the generation AI. For example, the problem presentation unit can input user emotion data to the generation AI and cause the generation AI to adjust the importance of the problem.

[0117] When a problem is presented, the problem presentation unit can analyze changes in the problem based on the submission date of the terms and conditions. The problem presentation unit, for example, uses a generation AI to evaluate the submission date of the terms and conditions. For example, the generation AI evaluates the submission date of the terms and conditions based on the submission date, submission frequency, etc. The problem presentation unit can also use the generation AI to analyze changes in the problem based on the submission date of the terms and conditions. For example, recently submitted terms and conditions can be analyzed based on the latest problem information. Also, older submitted terms and conditions can be analyzed based on past problem data. The problem presentation unit can also use the generation AI to evaluate changes in the problem based on the submission date. In this way, by analyzing changes in the problem based on the submission date of the terms and conditions, more accurate problem information can be provided. Some or all of the above-mentioned processing in the problem presentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input data on the submission date of the terms and conditions to the generation AI and have the generation AI analyze changes in the problem.

[0118] When presenting a problem, the problem presentation unit can analyze the problem by referring to market data related to the terms and conditions. The problem presentation unit, for example, uses a generation AI to refer to market data related to the terms and conditions. For example, the generation AI refers to market data related to the terms and conditions based on market reports, industry analysis data, etc. The problem presentation unit can also use the generation AI to analyze the problem based on market data related to the terms and conditions. For example, the generation AI evaluates the severity of the problem based on the relevant market data. The problem presentation unit can also use the generation AI to analyze the trend of the problem by referring to the relevant market data. In this way, referring to the market data related to the terms and conditions improves the accuracy of the problem presentation. Some or all of the above-mentioned processing in the problem presentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input market data related to the terms and conditions to the generation AI and cause the generation AI to perform problem analysis.

[0119] The problem presentation unit can analyze the problem by taking into account the technical maturity of the terms and conditions when presenting the problem. The problem presentation unit, for example, uses a generation AI to evaluate the technical maturity of the terms and conditions. For example, the generation AI evaluates the technical maturity of the terms and conditions based on the development stage of the technology and the market introduction status of the technology. The problem presentation unit can also analyze the problem by taking into account the technical maturity of the terms and conditions using the generation AI. For example, for technically mature terms and conditions, the problem can be evaluated low. For technically immature terms and conditions, the problem can be evaluated high. The problem presentation unit can also adjust the problem evaluation criteria according to the technical maturity using the generation AI. In this way, more appropriate problem presentation is provided by taking the technical maturity of the terms and conditions into account. Some or all of the above-mentioned processing in the problem presentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input data on the technical maturity of the terms and conditions into the generation AI and have the generation AI perform problem analysis. === Hard Collateral 1-1 === Each of the multiple elements, including the summarizing unit, comparison unit, risk analysis unit, validity determination unit, and problem presentation unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the summarizing unit is realized by the control unit 46A of the smart device 14 and summarizes the contents of the terms and conditions using a generation AI. The comparison unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and compares the summarized information with standard terms and conditions. The risk analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes legal and economic risks. The validity determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and determines the validity of the contract. The problem presentation unit is realized, for example, by the control unit 46A of the smart device 14 and points out potential problems for the user. === Hard Collateral 1-2 === Each of the multiple elements, including the summarizing unit, comparing unit, risk analyzing unit, validity determining unit, and problem presenting unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the summarizing unit is realized by the control unit 46A of the smart glasses 214 and summarizes the contents of the terms and conditions using a generation AI. The comparing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and compares the summarized information with standard terms and conditions. The risk analyzing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes legal and economic risks. The validity determining unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and determines the validity of the contract. The problem presenting unit is realized, for example, by the control unit 46A of the smart glasses 214 and points out potential problems for the user. === Hard Collateral 1-3 === Each of the multiple elements, including the summarizing unit, comparison unit, risk analysis unit, validity determination unit, and problem presentation unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the summarizing unit is implemented by the control unit 46A of the headset terminal 314 and summarizes the contents of the terms and conditions using a generation AI. The comparison unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and compares the summarized information with standard terms and conditions. The risk analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes legal and economic risks. The validity determination unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and determines the validity of the contract. The problem presentation unit is implemented, for example, by the control unit 46A of the headset terminal 314 and points out potential problems for the user. === Hard Collateral 1-4 === Each of the multiple elements, including the summarizing unit, comparison unit, risk analysis unit, validity determination unit, and problem presentation unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the summarizing unit is realized by the control unit 46A of the robot 414 and summarizes the contents of the terms and conditions using a generation AI. The comparison unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and compares the summarized information with standard terms and conditions. The risk analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes legal and economic risks. The validity determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and determines the validity of the contract. The problem presentation unit is realized, for example, by the control unit 46A of the robot 414 and points out potential problems for the user.

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

[0121] The summarization unit can estimate the user's emotions and adjust the summary presentation style based on the estimated user emotions. For example, if the user is stressed, the generation AI can provide a concise summary that focuses on the main points. If the user is relaxed, the generation AI can provide a summary that includes detailed explanations. Furthermore, if the user is in a hurry, the generation AI can provide a summary that emphasizes only the most important points. This allows for a more appropriate summary to be provided by adjusting the summary presentation style 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 summarization unit can be performed using, for example, the generation AI, or without the generation AI. For example, the summarization unit can input user emotion data into the generation AI and have the generation AI adjust the summary presentation style.

[0122] The comparison unit can estimate the user's emotions and adjust the comparison criteria based on the estimated user emotions. For example, if the user is stressed, the generation AI can provide concise and concise comparison criteria. Alternatively, if the user is relaxed, the generation AI can provide detailed comparison criteria. Furthermore, if the user is in a hurry, the generation AI can provide comparison criteria that emphasize only the most important points. This allows for more appropriate comparison by adjusting the comparison criteria according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the comparison unit can be performed using, for example, the generation AI, or without the generation AI. For example, the comparison unit can input user emotion data into the generation AI and have the generation AI adjust the comparison criteria.

[0123] The risk analysis unit can estimate the user's emotions and adjust the risk display method based on the estimated user emotions. For example, if the user is feeling stressed, the generation AI can provide a concise and highly visible risk display. Furthermore, if the user is relaxed, the generation AI can provide detailed risk information. Furthermore, if the user is in a hurry, the generation AI can provide a risk display that focuses on the key points. By adjusting the risk display method according to the user's emotions, more appropriate risk information can be provided. The emotion estimation is realized using an emotion estimation function, for example, with 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 risk analysis unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the risk analysis unit can input user emotion data into the generation AI and have the generation AI adjust the risk display method.

[0124] The validity determination unit can estimate the user's emotions and adjust the validity display method based on the estimated user's emotions. For example, if the user is stressed, the generation AI can provide a concise and highly visible validity display. Furthermore, if the user is relaxed, the generation AI can provide detailed validity information. Furthermore, if the user is in a hurry, the generation AI can provide a validity display that focuses on the main points. By adjusting the validity display method according to the user's emotions, more appropriate validity information can be provided. The emotion estimation is realized using an emotion estimation function, for example, with 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 validity determination unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the validity determination unit can input user emotion data into the generation AI and cause the generation AI to adjust the validity display method.

[0125] The problem presentation unit can estimate the user's emotions and adjust the problem display method based on the estimated user emotions. For example, if the user is stressed, the generation AI can provide a concise and highly visible problem display. Furthermore, if the user is relaxed, the generation AI can provide detailed problem information. Furthermore, if the user is in a hurry, the generation AI can provide a problem display that focuses on the main points. By adjusting the problem display method according to the user's emotions, more appropriate problem information can be provided. The emotion estimation is realized using an emotion estimation function, for example, with 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 problem presentation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the problem presentation unit can input user emotion data into the generation AI and cause the generation AI to adjust the problem display method.

[0126] When generating a summary, the summarization unit can adjust the level of detail of the summary based on the importance of the terms and conditions. For example, the generation AI evaluates the importance of the terms and conditions based on legal impact, financial impact, etc. The summarization unit can also use the generation AI to adjust the level of detail of the summary based on the importance of the terms and conditions. For example, the generation AI can provide a detailed summary for terms and conditions of high importance. On the other hand, the generation AI can provide a concise summary for terms and conditions of low importance. The summarization unit can also use the generation AI to adjust the length of the summary based on the importance. In this way, by adjusting the level of detail of the summary based on the importance of the terms and conditions, important information can be appropriately conveyed. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the summarization unit can input text data of the terms and conditions into the generation AI and have the generation AI adjust the level of detail of the summary.

[0127] During comparison, the comparison unit can improve the accuracy of the comparison based on the version of the standard terms and conditions. For example, the generation AI evaluates the version of the standard terms and conditions based on industry standards, legal standards, etc. The comparison unit can also use the generation AI to improve the accuracy of the comparison based on the version of the standard terms and conditions. For example, the comparison unit can improve the accuracy of the comparison based on the latest version of the standard terms and conditions. The comparison unit can also improve the accuracy of the comparison based on past versions of the standard terms and conditions. The comparison unit can also use the generation AI to adjust the accuracy of the comparison depending on the version of the standard terms and conditions. This improves the accuracy of the comparison based on the version of the standard terms and conditions, providing a more accurate comparison. Some or all of the above-mentioned processing in the comparison unit may be performed using, or without, the generation AI. For example, the comparison unit can input data on the version of the standard terms and conditions into the generation AI and have the generation AI improve the accuracy of the comparison.

[0128] During risk analysis, the risk analysis unit can predict current risks by referring to past risk data. For example, the generation AI refers to past risk data based on past risk assessment results and risk occurrence cases. The risk analysis unit can also use the generation AI to predict current risks based on past risk data. For example, the generation AI predicts current risks based on past risk data. The risk analysis unit can also use the generation AI to analyze risk trends by referring to past risk data. In this way, current risks can be predicted more accurately by referring to past risk data. Some or all of the above-described processing in the risk analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the risk analysis unit can input past risk data into the generation AI and have the generation AI predict current risks.

[0129] When determining validity, the validity determination unit can apply different validity determination methods to different clause categories. For example, the generation AI classifies clauses based on categories such as legal clauses and economic clauses. The validity determination unit can also use the generation AI to apply different validity determination methods to different clause categories. For example, a legal validity determination method can be applied to legal clauses. An economic validity determination method can be applied to economic clauses. A technical validity determination method can be applied to technical clauses. This improves the accuracy of validity determination by applying a validity determination method according to the clause category. Some or all of the above-described processing in the validity determination unit may be performed using, or without, the generation AI. For example, the validity determination unit can input clause category data into the generation AI and have the generation AI apply the validity determination method.

[0130] When presenting a problem, the problem presentation unit can present a problem by taking into account the attribute information of the person who submitted the terms and conditions. For example, the generation AI evaluates the attribute information of the person who submitted the terms and conditions based on the submitter's occupation, past contract history, etc. The problem presentation unit can also use the generation AI to present a problem by taking into account the attribute information of the person who submitted the terms and conditions. For example, if the submitter is a company, the problem presentation unit can present a problem by taking into account the company's attribute information. Also, if the submitter is an individual, the problem presentation unit can present a problem by taking into account the individual's attribute information. Furthermore, the problem presentation unit can use the generation AI to adjust the method of presenting a problem according to the attribute information of the submitter. In this way, by taking into account the attribute information of the person who submitted the terms and conditions, more appropriate problem presentations can be provided. Some or all of the above-mentioned processing in the problem presentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the problem presentation unit can input attribute information data of the person who submitted the terms and conditions into the generation AI and cause the generation AI to present a problem.

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

[0132] Step 1: The summarization section uses a generation AI to summarize the contents of the terms and conditions. The summarization is based on the length of the text and the importance of the information being summarized. For example, a text generation AI (e.g., LLM) can be used to concisely summarize the terms and conditions, extracting and summarizing the important parts. Step 2: The comparison unit uses the generation AI to compare the information summarized by the summary unit with the standard terms and conditions. The comparison is based on industry and legal standards, and the standard terms and conditions are compared with the contract terms to clarify any differences. Step 3: The risk analysis unit uses generative AI to analyze legal and economic risks based on the information obtained by the comparison unit. Risk analysis is based on the possibility of contract breach, risk of legal sanctions, potential financial loss, investment risk, etc. Step 4: The validity determination unit uses the generative AI to determine the validity of the contract based on the information obtained by the risk analysis unit. The validity determination is based on the fulfillment of legal requirements and the conformity of the contract terms. Step 5: The problem presentation unit uses the generative AI to present specific problems based on the information obtained by the validity assessment unit. The problem presentation is based on the details of the problems and risks of specific clauses.

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

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

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

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

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

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

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0160] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0161] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0162] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0163] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0164] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0165] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0167] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

[0170] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0171] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0172] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0173] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0175] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0176] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0177] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0178] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0179] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

[0181] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0182] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0183] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0184] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0186] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0187] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0188] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0189] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0190] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0191] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0192] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0193] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0194] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0195] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0196] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0197] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0198] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0199] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0200] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0201] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0202] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, 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.

[0203] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0204] [Explanation of symbols]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A summary section that analyzes and summarizes the contents of the terms and conditions; a comparison unit that compares the information summarized by the summary unit with standard terms and conditions; a risk analysis unit that analyzes legal risks and economic risks based on the information obtained by the comparison unit; a validity determination unit that determines the validity of a contract based on the information obtained by the risk analysis unit; a problem presentation unit that presents individual problems based on the information obtained by the validity determination unit. A system characterized by:

2. The summary section Summarizing the contents of the terms and conditions using generative AI 2. The system of claim 1.

3. The comparison unit Comparison with standard terms and conditions is performed using generation AI 2. The system of claim 1.

4. The risk analysis unit Analyzing legal and economic risks with generative AI 2. The system of claim 1.

5. The validity determination unit Determine the validity of the contract using generative AI 2. The system of claim 1.

6. The problem presentation unit Present individual problems using generative AI 2. The system of claim 1.

7. The summary section Estimate the user's emotions and adjust the way summaries are presented based on the estimated user emotions.

2. The system of claim 1.

8. The summary section When generating a summary, adjust the level of detail of the summary based on the importance of the clauses 2. The system of claim 1.

Images