System

Abstract

To efficiently create a contract considering a risk even without having expert knowledge using a system according to an embodiment.SOLUTION: A system according to an embodiment comprises: a reception unit; an analysis unit; a creation unit; and a provision unit. The reception unit receives input of contract content or a contract period. The analysis unit analyzes information input by the reception unit, and evaluates a risk. The creation unit creates a contract on the basis of the risk evaluated by the analysis unit. The provision unit provides the contract created by the creation unit to a user.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, there was a problem that specialized knowledge was required to prepare a contract, and it was difficult to efficiently prepare a contract that took risk into consideration.

[0005] The system according to the embodiment aims to enable efficient creation of contracts that take risk into consideration, even without specialized knowledge. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives input of contract details or contract period. The analysis unit analyzes the information input by the reception unit and evaluates risks. The generation unit generates a contract based on the risks evaluated by the analysis unit. The provision unit provides the contract generated by the generation unit to a user. Effect of the Invention

[0007] The system according to the embodiment makes it possible to efficiently create contracts that take risks into consideration, even without specialized knowledge. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A contract creation system according to an embodiment of the present invention is a system that allows users to create contracts that take risks into consideration when exchanging various contracts and memoranda with new or existing business partners, even without specialized knowledge. In this contract creation system, a user inputs minimum items such as contract contents and contract period, and a large-scale language model (generative AI) analyzes the input information and evaluates the risk. Based on the evaluated risk, the generative AI generates a contract, and the generated contract is provided to the user. The user can confirm and modify the contract. For example, a user inputs minimum items such as contract contents and contract period. For example, information such as "contract contents: product sales" and "contract period: 1 year" is input. This information is input to a reception unit (which may include AI processing). Next, the information input by the reception unit is analyzed by a large-scale language model (generative AI). The analysis unit (including generation AI processing) analyzes the input information and evaluates legal risks, financial risks, operational risks, and the like. For example, if the contract contents are product sales, risks related to product quality assurance and risks related to delivery delays are evaluated. Based on the evaluated risks, the generation AI generates a contract. The generation unit (including the processing of the generation AI) automatically inserts clauses for minimizing risks and generates a contract. For example, clauses regarding product quality assurance and clauses regarding delivery delays are automatically inserted. The generated contract is provided to the user by the provision unit (which may include the processing of AI). The user can check the provided contract and modify it as necessary. The modification unit (which may include the processing of AI) provides a function for the user to check and modify the contract. Furthermore, the risk identification unit (which may include the processing of AI) can specifically list the types of risk. For example, specific risks such as legal risk, financial risk, and operational risk can be identified. Furthermore, the learning unit (which may include the processing of AI) can learn from past contract data and perform more accurate risk evaluation and contract generation. For example, by learning from past contract data, risks in similar contracts can be more accurately evaluated. This system makes it possible to easily create contracts that take risks into consideration even without specialized knowledge.For example, when creating a contract with a new business partner, it is possible to automatically generate a contract that takes into account risks related to product quality assurance and delivery delays. Also, when renewing a contract with an existing business partner, it is possible to evaluate risks based on past contract data and generate an optimal contract. This allows the contract creation system to create contracts that take risks into account even without specialized knowledge.

[0029] The contract creation system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives input of contract contents or contract period. For example, a user can input information such as "contract contents: product sales" and "contract period: 1 year". The reception unit may include AI processing and provides an interface for receiving the user's input. The analysis unit uses a large-scale language model (generative AI) to analyze the information input by the reception unit and evaluates risks. For example, if the contract contents are product sales, it evaluates risks related to product quality assurance and risks related to delivery delays. The generation unit uses a large-scale language model (generative AI) to generate a contract based on the risks evaluated by the analysis unit. The generation unit automatically inserts clauses for minimizing risks and generates a contract. For example, clauses related to product quality assurance and clauses related to delivery delays are automatically inserted. The provision unit provides the contract generated by the generation unit to the user. The provision unit may include AI processing and provides an interface for the user to confirm and modify the contract. This allows the contract creation system to create a contract that takes risks into consideration even without specialized knowledge. For example, a user inputs the contract details and contract period, and the generation AI evaluates the risks, generates a contract, and provides it to the user. The user can then review the provided contract and amend it as necessary. This allows the contract creation system to create contracts quickly and accurately.

[0030] The reception unit accepts input of the contract contents or contract period. For example, the user can input information such as "contract contents: product sales" and "contract period: 1 year". The reception unit may include AI processing and provides an interface for accepting user input. Specifically, the reception unit provides a graphical user interface (GUI) that the user can intuitively operate, making it easy to input the contract contents and contract period. For example, the reception unit allows the user to easily input the required information using drop-down menus, check boxes, and text input fields. In addition, by incorporating a voice input function, the user can input the contract contents by voice. Furthermore, the reception unit checks the consistency of the input information, and provides appropriate feedback to the user if there is missing or incorrect information. For example, if the contract period has not been entered, a pop-up message is displayed to prompt the user to enter the information. In addition, natural language processing technology using AI can be used to analyze the meaning of the text entered by the user and automatically assign it to the appropriate field. This allows the user to input information smoothly, and the reception unit can collect accurate data. Furthermore, the reception unit improves the efficiency of input work by saving and reusing the user's past input history. For example, the reception unit automatically suggests contract details and contract periods that were previously input, allowing the user to easily select them. This reduces the burden on the user and enables quick and accurate information collection.

[0031] The analysis unit uses a large-scale language model (generative AI) to analyze the information input by the reception unit and evaluate the risk. For example, if the contract content is product sales, the analysis unit evaluates the risk related to the quality assurance of the product and the risk related to delivery delay. Specifically, the analysis unit uses the generative AI to analyze the contract content input in detail and identify related risk factors. The generative AI has learned past contract data and industry best practices, and evaluates risks based on the input information. For example, when evaluating the risk related to the quality assurance of the product, it refers to past quality problems and complaint data and predicts the possibility of similar risks occurring. In addition, when evaluating the risk related to delivery delay, it takes into account past delivery delay data and the status of the supply chain and predicts the possibility of delay. Furthermore, the analysis unit provides the user with the results of the risk evaluation and presents details of the risk and countermeasures. For example, if the risk related to the quality assurance of the product is high, it proposes strengthening quality control and extending the warranty period. In addition, if the risk of delivery delay is high, it proposes reviewing the delivery date and improving the supply chain. In this way, the analysis unit can provide information for the user to understand the risk and take appropriate measures. Furthermore, the analysis unit continuously collects data and updates the model of the generative AI in order to improve the accuracy of the risk evaluation. This enables the analysis unit to provide highly accurate risk assessments based on the latest information at all times, and assist users in creating contracts.

[0032] The generation unit uses a large-scale language model (generative AI) to generate a contract based on the risks evaluated by the analysis unit. The generation unit automatically inserts clauses to minimize risks and generates a contract. For example, clauses regarding product quality assurance and clauses regarding delivery delays are automatically inserted. Specifically, the generation unit automatically generates each clause of the contract using the generation AI and inserts appropriate clauses based on the results of risk assessment. The generation AI learns from past contract data and legal document templates, and generates an optimal contract based on the user's input information and the results of risk assessment. For example, if there is a high risk of product quality assurance, detailed clauses of the quality assurance are inserted to clarify the warranty period and scope. In addition, if there is a high risk of delivery delays, penalty clauses regarding delivery delays and measures to be taken in the event of delays are inserted. In addition, the generation unit checks the consistency of the generated contract and confirms whether it meets the requirements for a legally valid document. For example, it checks whether each clause of the contract is properly linked and whether the necessary signature and date columns are included. This allows the generation unit to provide high-quality contracts that users can use with confidence. Furthermore, the generation unit can adjust the contents of the contract based on user feedback and customize it to meet the needs of the user. This allows the generation unit to flexibly generate contracts in response to user requests, improving the efficiency and accuracy of contract creation.

[0033] The providing unit provides the user with the contract generated by the generating unit. The providing unit may include AI processing and provides an interface for the user to confirm and modify the contract. Specifically, the providing unit provides an interface that allows the user to view the generated contract and modify it as necessary. For example, an interface that runs on a web browser is provided, allowing the user to confirm each clause of the contract and modify it using a text editor. The providing unit also reflects the modification content in real time, allowing the user to immediately confirm the modification results. Furthermore, the providing unit uses AI to analyze the user's modification content and check whether the modification is legally valid. For example, when a user modifies a clause of the contract, it automatically checks whether the modification is inconsistent with other clauses and meets legal requirements, and displays a warning as necessary. This allows the user to modify the contract with peace of mind. Furthermore, the providing unit outputs the final version of the contract in PDF format or a format compatible with electronic signatures, allowing the user to easily save and share it. For example, the final version of the contract is saved in cloud storage, allowing the user to access it at any time. In addition, outputting it in a format compatible with electronic signatures streamlines the contract signing and approval process. This enables the provision unit to provide the user with a contract quickly and accurately, greatly improving the efficiency of the contract creation process.

[0034] The contract creation system includes a risk identification unit that lists specific types of risk. The risk identification unit identifies specific risks such as legal risks, financial risks, and operational risks. For example, as a legal risk, it evaluates whether the contract contents violate laws and regulations. As a financial risk, it evaluates whether the contract contents are financially sound. As an operational risk, it evaluates whether the contract contents cause operational problems. In this way, the risk identification unit can identify specific risks and perform more detailed risk evaluation. Some or all of the above-mentioned processing in the risk identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the risk identification unit can identify risks using an AI model that inputs the contract contents and outputs risks.

[0035] The contract creation system includes a learning unit that learns past contract data. The learning unit learns past contract data to improve the accuracy of risk assessment and contract generation. For example, the learning unit learns contract data from the past five years, and can more accurately evaluate risks in similar contracts. The learning unit may include AI processing and executes an algorithm for learning past contract data. As a result, the learning unit improves the accuracy of risk assessment and contract generation by learning past data. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can perform learning using a model for improving the accuracy of risk assessment and contract generation using past contract data as input.

[0036] The contract creation system includes a correction unit that allows a user to confirm and correct a contract generated by the user. The correction unit provides a function for the user to confirm and correct the generated contract. For example, the user can confirm the contents of the contract and correct it as necessary. The correction unit may include AI processing and provide an interface for the user to confirm and correct the contract. This allows the correction unit to create a more appropriate contract by allowing the user to confirm and correct the contract. Some or all of the above-mentioned processing in the correction unit may be performed, for example, using AI, or may be performed without using AI. For example, the correction unit can perform the correction using an AI model that corrects the contract using the user's correction content as input.

[0037] The analysis unit can evaluate legal risks, financial risks, and operational risks. The analysis unit evaluates legal risks, financial risks, and operational risks. For example, as a legal risk, it evaluates whether the contract contents violate laws and regulations. As a financial risk, it evaluates whether the contract contents are financially sound. As an operational risk, it evaluates whether the contract contents cause operational problems. In this way, the analysis unit can perform comprehensive risk management by evaluating various risks. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can evaluate risks using an AI model that inputs the contract contents and outputs risks.

[0038] The generation unit can automatically insert clauses for reducing risk. The generation unit automatically inserts clauses for reducing risk. For example, clauses regarding product quality assurance and clauses regarding delivery delays are automatically inserted. This allows the generation unit to automatically generate a contract that minimizes risk. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or may be performed without using AI. For example, the generation unit can generate a contract using an AI model that automatically inserts clauses for reducing risk.

[0039] The reception unit can analyze the user's past input history and propose the optimal input method. The reception unit analyzes the user's past input history and proposes the optimal input method. For example, the contract contents and periods frequently input by the user in the past are automatically displayed as candidates. The input method (voice, text, etc.) used by the user in the past is preferentially proposed. The contract contents and periods to be used in a specific time period are predicted and proposed from the user's past input history. As a result, the reception unit proposes the optimal input method based on the past input history, thereby improving input efficiency. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's past input history to the generation AI and cause the generation AI to execute the proposal of the optimal input method.

[0040] The reception unit can automatically acquire the user's current business situation when inputting the minimum items such as the contract contents and the period, and simplify the input. The reception unit automatically acquires the user's current business situation when inputting the minimum items such as the contract contents and the period, and simplifies the input. For example, when the user opens the app, the current business situation is automatically acquired and the contract contents and the period are set. When the user inputs the contract contents, the optimal candidate is suggested based on the current business situation. When the user changes the business situation, it is updated in real time and reflected in the contract contents and the period. As a result, the reception unit automatically acquires the current business situation, and the input work is simplified. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's business situation data to the generation AI and cause the generation AI to execute simplification of the input.

[0041] The reception unit can automatically propose region-specific contract terms in consideration of the geographical location information of the user. The reception unit automatically proposes region-specific contract terms in consideration of the geographical location information of the user. For example, when the user is in a specific region, the reception unit proposes contract terms based on the laws and regulations of the region. When the user moves to a different region, the reception unit automatically updates the region-specific contract terms. When the user makes an international contract, the reception unit proposes contract terms based on the laws and regulations of each country. In this way, the reception unit can create a contract suitable for the region by automatically proposing region-specific contract terms. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's geographical location information to the generation AI and cause the generation AI to execute the proposal of region-specific contract terms.

[0042] The reception unit can analyze the social media activity of the user and propose relevant contract contents. The reception unit analyzes the social media activity of the user and proposes relevant contract contents. For example, the reception unit proposes contract contents based on business activities mentioned by the user on social media. The reception unit proposes relevant contract contents based on the user's social media followers and interests. The reception unit proposes contract contents based on events and projects shared by the user on social media. In this way, the reception unit can create a contract suitable for the user by proposing contract contents based on social media activities. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's social media activity data to the generation AI and cause the generation AI to execute the proposal of relevant contract contents.

[0043] The analysis unit can evaluate environmental and social risks in addition to legal, financial, and operational risks. The analysis unit evaluates environmental and social risks in addition to legal, financial, and operational risks. For example, as environmental risks, it evaluates the impact of the contract contents on the environment. As social risks, it evaluates the impact of the contract contents on society. In addition to legal, financial, and operational risks, it comprehensively evaluates environmental and social risks. This enables the analysis unit to evaluate various risks and perform comprehensive risk management. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can evaluate risks using an AI model that inputs the contract contents and outputs risks.

[0044] The analysis unit can apply different analysis algorithms depending on the complexity of the contract contents. The analysis unit applies different analysis algorithms depending on the complexity of the contract contents. For example, a simple analysis algorithm is applied to simple contract contents. A detailed analysis algorithm is applied to complex contract contents. An appropriate analysis algorithm is selected depending on the complexity of the contract contents. This allows the analysis unit to perform an analysis according to the complexity of the contract contents, thereby enabling more appropriate risk assessment. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can assess risk using an AI model that inputs the contract contents and outputs risk.

[0045] The analysis unit can perform risk assessment taking into account the geographical distribution of the contract contents. The analysis unit performs risk assessment taking into account the geographical distribution of the contract contents. For example, if the contract contents relate to a specific region, the risk assessment is performed based on the laws and regulations of that region. If the contract contents relate to multiple regions, the risk assessment is performed based on the laws and regulations of each region. A comprehensive risk assessment is performed taking into account the geographical distribution of the contract contents. As a result, the analysis unit performs risk assessment taking into account the geographical distribution, thereby enabling risk management appropriate for the region. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input geographical distribution data of the contract contents to the generation AI and cause the generation AI to perform risk assessment.

[0046] The analysis unit can automatically refer to relevant laws and regulations and reflect them in the risk assessment. The analysis unit automatically refers to relevant laws and regulations and reflects them in the risk assessment. For example, the analysis unit automatically refers to laws and regulations related to the contract contents and reflects them in the risk assessment. When laws and regulations are changed, they are automatically reflected in the risk assessment. The analysis unit always refers to the latest laws and regulations related to the contract contents and reflects them in the risk assessment. This enables the analysis unit to perform risk assessment that reflects the latest laws and regulations. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input legal and regulatory data to the generation AI and have the generation AI reflect the data in the risk assessment.

[0047] The generation unit can automatically reflect region-specific laws and regulations when generating a contract. The generation unit automatically reflects region-specific laws and regulations when generating a contract. For example, the generation unit automatically reflects the laws and regulations of a specific region when generating a contract. The generation unit automatically reflects the laws and regulations of a plurality of regions when generating a contract. The generation unit automatically reflects the latest laws and regulations when generating a contract. This allows the generation unit to generate a contract that reflects region-specific laws and regulations. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input region-specific laws and regulations data into a generation AI and reflect them when generating a contract.

[0048] The generation unit can automatically refer to the related contract contents when generating a contract. The generation unit automatically refers to the related contract contents when generating a contract. For example, similar contracts in the past are automatically referred to when generating a contract. The related contract contents are automatically referred to when generating a contract. When generating a contract, optimal clauses are proposed based on the related contract contents when generating a contract. In this way, the generation unit can generate a more appropriate contract by referring to the related contract contents. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input related contract content data to the generation AI and have it referred to when generating a contract.

[0049] The provision unit can select the optimal provision method by referring to the user's past confirmation history when providing the contract. The provision unit selects the optimal provision method by referring to the user's past confirmation history when providing the contract. For example, the optimal provision method is selected based on the provision method used by the user in the past. The most efficient provision method is selected from the user's past confirmation history. The user's past confirmation history is analyzed and the optimal provision method is proposed. As a result, the provision unit selects the optimal provision method based on the past confirmation history, thereby making the provision of the contract more efficient. Part or all of the above-mentioned processing in the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the provision unit can input the user's past confirmation history data to the generation AI and cause the generation AI to select the provision method.

[0050] The provision unit can propose the optimal timing of provision in consideration of the user's work schedule when providing the contract. The provision unit proposes the optimal timing of provision in consideration of the user's work schedule when providing the contract. For example, the provision unit refers to the user's work schedule and proposes the optimal timing of provision. The provision unit adjusts the timing of provision of the contract based on the user's work schedule. The provision unit selects the optimal timing of provision in consideration of the user's work schedule. As a result, the provision unit proposes the timing of provision in consideration of the work schedule, thereby making the provision of the contract more efficient. Part or all of the above-mentioned processing in the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the provision unit can input the user's work schedule data to the generation AI and cause the generation AI to execute the proposal of the timing of provision.

[0051] The provision unit can analyze the social media activity of the user and provide related information when providing the contract. The provision unit analyzes the social media activity of the user and provides related information when providing the contract. For example, the provision unit provides related information based on business activities mentioned by the user on social media. The provision unit provides related information based on the user's social media followers and interests. The provision unit provides related information based on events and projects shared by the user on social media. As a result, the provision unit provides related information based on social media activities, thereby deepening understanding of the contract. Part or all of the above-mentioned processing in the provision unit may be performed, for example, using AI or may be performed without using AI. For example, the provision unit can input the user's social media activity data to the generation AI and cause the generation AI to provide related information.

[0052] The providing unit can select the optimal providing method in consideration of the device information of the user when providing the contract. The providing unit selects the optimal providing method in consideration of the device information of the user when providing the contract. For example, when the user is using a smartphone, a providing method according to the screen size is provided. When the user is using a tablet, a providing method optimized for a large screen is provided. When the user is using a smartwatch, a providing method that is simple and highly visible is provided. As a result, the providing unit provides a providing method that takes device information into consideration, thereby making the provision of the contract more efficient. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the device information of the user to the generating AI and cause the generating AI to select the providing method.

[0053] The risk identification unit can identify environmental and social risks in addition to legal, financial, and operational risks. The risk identification unit identifies environmental and social risks in addition to legal, financial, and operational risks. For example, as environmental risks, it identifies the impact of the contract contents on the environment. As social risks, it identifies the impact of the contract contents on society. In addition to legal, financial, and operational risks, it also comprehensively identifies environmental and social risks. This enables the risk identification unit to identify various risks and perform comprehensive risk management. Some or all of the above-mentioned processing in the risk identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the risk identification unit can identify risks using an AI model that inputs the contract contents and outputs risks.

[0054] The risk identification unit can improve the accuracy of risk identification by referring to past contract data. The risk identification unit improves the accuracy of risk identification by referring to past contract data. For example, the risk identification unit identifies risks in similar contracts by referring to past contract data. The risk identification unit analyzes past contract data and improves the accuracy of risk identification. The risk identification algorithm is optimized based on the past contract data. As a result, the risk identification unit improves the accuracy of risk identification by referring to past data. Some or all of the above-mentioned processing in the risk identification unit may be performed using AI, for example, or may be performed without using AI. For example, the risk identification unit can input past contract data to a generation AI and cause the generation AI to improve the accuracy of risk identification.

[0055] The risk identification unit can perform risk identification in consideration of the geographical distribution of the contract contents. The risk identification unit performs risk identification in consideration of the geographical distribution of the contract contents. For example, if the contract contents relate to a specific region, risk identification is performed based on the laws and regulations of that region. If the contract contents relate to multiple regions, risk identification is performed based on the laws and regulations of each region. Comprehensive risk identification is performed in consideration of the geographical distribution of the contract contents. As a result, the risk identification unit performs risk identification in consideration of the geographical distribution, thereby enabling risk management appropriate for the region. Part or all of the above-mentioned processing in the risk identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the risk identification unit can input geographical distribution data of the contract contents to the generation AI and cause the generation AI to execute risk identification.

[0056] The risk identification unit can automatically refer to relevant laws and regulations and reflect them in risk identification. The risk identification unit automatically refers to relevant laws and regulations and reflects them in risk identification. For example, the risk identification unit automatically refers to laws and regulations related to the contract contents and reflects them in risk identification. When laws and regulations are changed, they are automatically reflected in risk identification. The latest laws and regulations related to the contract contents are always referred to and reflected in risk identification. This enables the risk identification unit to identify risks that reflect the latest laws and regulations. Some or all of the above-mentioned processing in the risk identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the risk identification unit can input legal and regulatory data to the generation AI and have the generation AI reflect the data in the risk identification.

[0057] The learning unit can learn from past contract data and improve the accuracy of risk assessment and contract generation. The learning unit learns from past contract data and improves the accuracy of risk assessment and contract generation. For example, the learning unit learns from past contract data and improves the accuracy of risk assessment in similar contracts. The learning unit analyzes past contract data and improves the accuracy of contract generation. The algorithms for risk assessment and contract generation are optimized based on the past contract data. As a result, the learning unit improves the accuracy of risk assessment and contract generation by learning from past data. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input past contract data to the generation AI and cause the generation AI to perform improvement in the accuracy of risk assessment and contract generation.

[0058] The learning unit can optimize the learning algorithm by referring to the change history of the contract content during learning. The learning unit optimizes the learning algorithm by referring to the change history of the contract content during learning. For example, the learning algorithm is optimized by referring to the change history of the contract content. The change history of the contract content is analyzed to improve the accuracy of the learning algorithm. The learning algorithm is optimized based on the change history of the contract content. As a result, the learning unit improves the accuracy of the learning algorithm by referring to the change history. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the change history data of the contract content to the generation AI and cause the generation AI to optimize the learning algorithm.

[0059] The learning unit can select learning data in consideration of the geographical distribution of the contract contents during learning. The learning unit selects learning data in consideration of the geographical distribution of the contract contents during learning. For example, if the contract contents relate to a specific region, data for that region is preferentially learned. If the contract contents relate to multiple regions, data for each region is learned in a balanced manner. Optimal learning data is selected in consideration of the geographical distribution of the contract contents. As a result, the learning unit selects learning data in consideration of the geographical distribution, thereby improving the efficiency of learning. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input geographical distribution data of the contract contents to the generation AI and cause the generation AI to select the learning data.

[0060] The learning unit can automatically refer to relevant laws and regulations during learning and reflect them in the learning data. The learning unit can automatically refer to relevant laws and regulations during learning and reflect them in the learning data. For example, the learning unit can automatically refer to laws and regulations related to the contract contents and reflect them in the learning data. When laws and regulations are changed, they are automatically reflected in the learning data. The learning unit can always refer to the latest laws and regulations related to the contract contents and reflect them in the learning data. As a result, the learning unit can provide learning data that reflects the latest laws and regulations, thereby improving the accuracy of learning. Some or all of the above-mentioned processing in the learning unit can be performed, for example, using AI or can be performed without using AI. For example, the learning unit can input legal and regulatory data to a generation AI and have the generation AI execute the reflection in the learning data.

[0061] The correction unit can suggest the optimal correction method by referring to the user's past correction history at the time of correction. The correction unit suggests the optimal correction method by referring to the user's past correction history at the time of correction. For example, the optimal correction method is suggested based on the correction contents made by the user in the past. Frequently made correction contents are automatically suggested from the user's past correction history. The user's past correction history is analyzed and the optimal correction method is suggested. As a result, the correction unit suggests the optimal correction method based on the past correction history, thereby making the correction work more efficient. Part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI, or may be performed without using AI. For example, the correction unit can input the user's past correction history data to the generation AI and have the generation AI execute the suggestion of the correction method.

[0062] The modification unit can track the change history of the contract contents at the time of modification and reflect it in the modification. The modification unit can track the change history of the contract contents at the time of modification and reflect it in the modification. For example, the modification unit refers to the change history of the contract contents and reflects it in the modification. The modification unit analyzes the change history of the contract contents and improves the accuracy of the modification. The modification unit optimizes the modification contents based on the change history of the contract contents. In this way, the modification unit improves the accuracy of the modification contents by tracking the change history. Some or all of the above-mentioned processing in the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can input the change history data of the contract contents to the generation AI and cause the generation AI to reflect the modification contents.

[0063] The correction unit can propose a correction method taking into consideration the geographical distribution of the contract contents at the time of correction. The correction unit proposes a correction method taking into consideration the geographical distribution of the contract contents at the time of correction. For example, if the contract contents relate to a specific region, the correction unit proposes a correction method based on the laws and regulations of the region. If the contract contents relate to multiple regions, the correction unit proposes a correction method based on the laws and regulations of each region. The correction unit proposes an optimal correction method taking into consideration the geographical distribution of the contract contents. As a result, the correction unit provides a correction method that takes into consideration the geographical distribution, thereby making the correction work more efficient. A part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI, or may be performed without using AI. For example, the correction unit can input geographical distribution data of the contract contents to the generation AI and cause the generation AI to execute the proposal of the correction method.

[0064] The correction unit can automatically refer to related laws and regulations at the time of correction and reflect them in the correction. The correction unit can automatically refer to related laws and regulations at the time of correction and reflect them in the correction. For example, the correction unit automatically refers to laws and regulations related to the contract content and reflects them in the correction content. If there is a change in laws or regulations, they are automatically reflected in the correction content. The latest laws and regulations related to the contract content are always referred to and reflected in the correction content. This enables the correction unit to make corrections that reflect the latest laws and regulations. A part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI, or may be performed without using AI. For example, the correction unit can input legal and regulatory data to the generation AI and have the generation AI execute the reflection in the correction content.

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

[0066] The contract creation system can analyze a user's past contract creation history and suggest optimal contract templates. For example, similar contract templates can be automatically suggested based on the content and format of contracts created by the user in the past. Clauses and formats frequently used by the user are preferentially displayed, improving the efficiency of contract creation. Furthermore, the system can learn the content of revisions made by the user in the past and automatically suggest them when similar revisions are necessary. This allows the contract creation system to create contracts more quickly and accurately by utilizing the user's past history.

[0067] The contract creation system can suggest the optimal timing for creating a contract, taking into account the user's work schedule. For example, by referencing the user's calendar, it can suggest creating a contract during a time when there is less work to do. If the user needs to create a contract before an important meeting or project, it can set a reminder to notify the user. It can suggest that the user create necessary contracts in advance before taking an extended vacation. In this way, the contract creation system can support efficient contract creation that matches the user's work schedule.

[0068] The contract drafting system can automatically insert region-specific contract clauses by taking into account the user's geographic location. For example, if the user is signing a contract in a specific region, clauses based on the laws and regulations of that region will be automatically added. If the user moves to a different region, the contract clauses specific to that region will be automatically updated. If the user is signing an international contract, clauses based on the laws and regulations of each country will be suggested. This allows the contract drafting system to create contracts that are appropriate for the region.

[0069] The contract creation system can analyze the user's social media activity and suggest relevant contract content. For example, suggest contract content based on business activities mentioned by the user on social media; suggest relevant contract content based on the user's social media followers and interests; suggest contract content based on events or projects shared by the user on social media. In this way, the contract creation system can create a contract that is suitable for the user by suggesting contract content based on social media activity.

[0070] The contract creation system can provide an optimal contract creation interface by taking into account the device information of the user. For example, if the user is using a smartphone, an interface that matches the screen size is provided. If the user is using a tablet, an interface optimized for a large screen is provided. If the user is using a smartwatch, an interface that is simple and highly visible is provided. In this way, the contract creation system provides an interface that takes into account device information, thereby making contract creation more efficient.

[0071] The process flow of the first embodiment will be briefly described below.

[0072] Step 1: The reception unit receives input of the contract contents or contract period. For example, the user can input information such as "contract contents: product sales" and "contract period: 1 year." The reception unit may include AI processing and provides an interface for receiving user input. Step 2: The analysis unit uses a large-scale language model (generative AI) to analyze the information entered by the reception unit and evaluate the risks. For example, if the contract content is product sales, it evaluates risks related to product quality assurance and delivery delays. Step 3: The generator uses a large-scale language model (generative AI) to generate a contract based on the risks assessed by the analyzer. The generator automatically inserts clauses to minimize risks and generates a contract. For example, clauses regarding product quality assurance and delivery delays are automatically inserted. Step 4: The provision unit provides the contract generated by the generation unit to the user. The provision unit may include AI processing and provides an interface for the user to confirm and modify the contract.

[0073] (Example 2) A contract creation system according to an embodiment of the present invention is a system that allows users to create contracts that take risks into consideration when exchanging various contracts and memoranda with new or existing business partners, even without specialized knowledge. In this contract creation system, a user inputs minimum items such as contract contents and contract period, and a large-scale language model (generative AI) analyzes the input information and evaluates the risk. Based on the evaluated risk, the generative AI generates a contract, and the generated contract is provided to the user. The user can confirm and modify the contract. For example, a user inputs minimum items such as contract contents and contract period. For example, information such as "contract contents: product sales" and "contract period: 1 year" is input. This information is input to a reception unit (which may include AI processing). Next, the information input by the reception unit is analyzed by a large-scale language model (generative AI). The analysis unit (including generation AI processing) analyzes the input information and evaluates legal risks, financial risks, operational risks, and the like. For example, if the contract contents are product sales, risks related to product quality assurance and risks related to delivery delays are evaluated. Based on the evaluated risks, the generation AI generates a contract. The generation unit (including the processing of the generation AI) automatically inserts clauses for minimizing risks and generates a contract. For example, clauses regarding product quality assurance and clauses regarding delivery delays are automatically inserted. The generated contract is provided to the user by the provision unit (which may include the processing of AI). The user can check the provided contract and modify it as necessary. The modification unit (which may include the processing of AI) provides a function for the user to check and modify the contract. Furthermore, the risk identification unit (which may include the processing of AI) can specifically list the types of risk. For example, specific risks such as legal risk, financial risk, and operational risk can be identified. Furthermore, the learning unit (which may include the processing of AI) can learn from past contract data and perform more accurate risk evaluation and contract generation. For example, by learning from past contract data, risks in similar contracts can be more accurately evaluated. This system makes it possible to easily create contracts that take risks into consideration even without specialized knowledge.For example, when creating a contract with a new business partner, it is possible to automatically generate a contract that takes into account risks related to product quality assurance and delivery delays. Also, when renewing a contract with an existing business partner, it is possible to evaluate risks based on past contract data and generate an optimal contract. This allows the contract creation system to create contracts that take risks into account even without specialized knowledge.

[0074] The contract creation system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives input of contract contents or contract period. For example, a user can input information such as "contract contents: product sales" and "contract period: 1 year". The reception unit may include AI processing and provides an interface for receiving the user's input. The analysis unit uses a large-scale language model (generative AI) to analyze the information input by the reception unit and evaluates risks. For example, if the contract contents are product sales, it evaluates risks related to product quality assurance and risks related to delivery delays. The generation unit uses a large-scale language model (generative AI) to generate a contract based on the risks evaluated by the analysis unit. The generation unit automatically inserts clauses for minimizing risks and generates a contract. For example, clauses related to product quality assurance and clauses related to delivery delays are automatically inserted. The provision unit provides the contract generated by the generation unit to the user. The provision unit may include AI processing and provides an interface for the user to confirm and modify the contract. This allows the contract creation system to create a contract that takes risks into consideration even without specialized knowledge. For example, a user inputs the contract details and contract period, and the generation AI evaluates the risks, generates a contract, and provides it to the user. The user can then review the provided contract and amend it as necessary. This allows the contract creation system to create contracts quickly and accurately.

[0075] The reception unit accepts input of the contract contents or contract period. For example, the user can input information such as "contract contents: product sales" and "contract period: 1 year". The reception unit may include AI processing and provides an interface for accepting user input. Specifically, the reception unit provides a graphical user interface (GUI) that the user can intuitively operate, making it easy to input the contract contents and contract period. For example, the reception unit allows the user to easily input the required information using drop-down menus, check boxes, and text input fields. In addition, by incorporating a voice input function, the user can input the contract contents by voice. Furthermore, the reception unit checks the consistency of the input information, and provides appropriate feedback to the user if there is missing or incorrect information. For example, if the contract period has not been entered, a pop-up message is displayed to prompt the user to enter the information. In addition, natural language processing technology using AI can be used to analyze the meaning of the text entered by the user and automatically assign it to the appropriate field. This allows the user to input information smoothly, and the reception unit can collect accurate data. Furthermore, the reception unit improves the efficiency of input work by saving and reusing the user's past input history. For example, the reception unit automatically suggests contract details and contract periods that were previously input, allowing the user to easily select them. This reduces the burden on the user and enables quick and accurate information collection.

[0076] The analysis unit uses a large-scale language model (generative AI) to analyze the information input by the reception unit and evaluate the risk. For example, if the contract content is product sales, the analysis unit evaluates the risk related to the quality assurance of the product and the risk related to delivery delay. Specifically, the analysis unit uses the generative AI to analyze the contract content input in detail and identify related risk factors. The generative AI has learned past contract data and industry best practices, and evaluates risks based on the input information. For example, when evaluating the risk related to the quality assurance of the product, it refers to past quality problems and complaint data and predicts the possibility of similar risks occurring. In addition, when evaluating the risk related to delivery delay, it takes into account past delivery delay data and the status of the supply chain and predicts the possibility of delay. Furthermore, the analysis unit provides the user with the results of the risk evaluation and presents details of the risk and countermeasures. For example, if the risk related to the quality assurance of the product is high, it proposes strengthening quality control and extending the warranty period. In addition, if the risk of delivery delay is high, it proposes reviewing the delivery date and improving the supply chain. In this way, the analysis unit can provide information for the user to understand the risk and take appropriate measures. Furthermore, the analysis unit continuously collects data and updates the model of the generative AI in order to improve the accuracy of the risk evaluation. This enables the analysis unit to provide highly accurate risk assessments based on the latest information at all times, and assist users in creating contracts.

[0077] The generation unit uses a large-scale language model (generative AI) to generate a contract based on the risks evaluated by the analysis unit. The generation unit automatically inserts clauses to minimize risks and generates a contract. For example, clauses regarding product quality assurance and clauses regarding delivery delays are automatically inserted. Specifically, the generation unit automatically generates each clause of the contract using the generation AI and inserts appropriate clauses based on the results of risk assessment. The generation AI learns from past contract data and legal document templates, and generates an optimal contract based on the user's input information and the results of risk assessment. For example, if there is a high risk of product quality assurance, detailed clauses of the quality assurance are inserted to clarify the warranty period and scope. In addition, if there is a high risk of delivery delays, penalty clauses regarding delivery delays and measures to be taken in the event of delays are inserted. In addition, the generation unit checks the consistency of the generated contract and confirms whether it meets the requirements for a legally valid document. For example, it checks whether each clause of the contract is properly linked and whether the necessary signature and date columns are included. This allows the generation unit to provide high-quality contracts that users can use with confidence. Furthermore, the generation unit can adjust the contents of the contract based on user feedback and customize it to meet the needs of the user. This allows the generation unit to flexibly generate contracts in response to user requests, improving the efficiency and accuracy of contract creation.

[0078] The providing unit provides the user with the contract generated by the generating unit. The providing unit may include AI processing and provides an interface for the user to confirm and modify the contract. Specifically, the providing unit provides an interface that allows the user to view the generated contract and modify it as necessary. For example, an interface that runs on a web browser is provided, allowing the user to confirm each clause of the contract and modify it using a text editor. The providing unit also reflects the modification content in real time, allowing the user to immediately confirm the modification results. Furthermore, the providing unit uses AI to analyze the user's modification content and check whether the modification is legally valid. For example, when a user modifies a clause of the contract, it automatically checks whether the modification is inconsistent with other clauses and meets legal requirements, and displays a warning as necessary. This allows the user to modify the contract with peace of mind. Furthermore, the providing unit outputs the final version of the contract in PDF format or a format compatible with electronic signatures, allowing the user to easily save and share it. For example, the final version of the contract is saved in cloud storage, allowing the user to access it at any time. In addition, outputting it in a format compatible with electronic signatures streamlines the contract signing and approval process. This enables the provision unit to provide the user with a contract quickly and accurately, greatly improving the efficiency of the contract creation process.

[0079] The contract creation system includes a risk identification unit that lists specific types of risk. The risk identification unit identifies specific risks such as legal risks, financial risks, and operational risks. For example, as a legal risk, it evaluates whether the contract contents violate laws and regulations. As a financial risk, it evaluates whether the contract contents are financially sound. As an operational risk, it evaluates whether the contract contents cause operational problems. In this way, the risk identification unit can identify specific risks and perform more detailed risk evaluation. Some or all of the above-mentioned processing in the risk identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the risk identification unit can identify risks using an AI model that inputs the contract contents and outputs risks.

[0080] The contract creation system includes a learning unit that learns past contract data. The learning unit learns past contract data to improve the accuracy of risk assessment and contract generation. For example, the learning unit learns contract data from the past five years, and can more accurately evaluate risks in similar contracts. The learning unit may include AI processing and executes an algorithm for learning past contract data. As a result, the learning unit improves the accuracy of risk assessment and contract generation by learning past data. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can perform learning using a model for improving the accuracy of risk assessment and contract generation using past contract data as input.

[0081] The contract creation system includes a correction unit that allows a user to confirm and correct a contract generated by the user. The correction unit provides a function for the user to confirm and correct the generated contract. For example, the user can confirm the contents of the contract and correct it as necessary. The correction unit may include AI processing and provide an interface for the user to confirm and correct the contract. This allows the correction unit to create a more appropriate contract by allowing the user to confirm and correct the contract. Some or all of the above-mentioned processing in the correction unit may be performed, for example, using AI, or may be performed without using AI. For example, the correction unit can perform the correction using an AI model that corrects the contract using the user's correction content as input.

[0082] The analysis unit can evaluate legal risks, financial risks, and operational risks. The analysis unit evaluates legal risks, financial risks, and operational risks. For example, as a legal risk, it evaluates whether the contract contents violate laws and regulations. As a financial risk, it evaluates whether the contract contents are financially sound. As an operational risk, it evaluates whether the contract contents cause operational problems. In this way, the analysis unit can perform comprehensive risk management by evaluating various risks. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can evaluate risks using an AI model that inputs the contract contents and outputs risks.

[0083] The generation unit can automatically insert clauses for reducing risk. The generation unit automatically inserts clauses for reducing risk. For example, clauses regarding product quality assurance and clauses regarding delivery delays are automatically inserted. This allows the generation unit to automatically generate a contract that minimizes risk. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or may be performed without using AI. For example, the generation unit can generate a contract using an AI model that automatically inserts clauses for reducing risk.

[0084] The reception unit can estimate the user's emotion and adjust the input method of the contract contents and the minimum items of the period based on the estimated user's emotion. The reception unit estimates the user's emotion and adjusts the input method of the contract contents and the minimum items of the period based on the estimated user's emotion. For example, when the user is stressed, a simple interface is provided and the input procedure is minimized. When the user is relaxed, detailed input options are provided and a customizable input method is suggested. When the user is in a hurry, voice input is prioritized and the contract contents and the period can be input quickly. In this way, the reception unit improves input efficiency by providing an input method according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0085] The reception unit can analyze the user's past input history and propose the optimal input method. The reception unit analyzes the user's past input history and proposes the optimal input method. For example, the contract contents and periods frequently input by the user in the past are automatically displayed as candidates. The input method (voice, text, etc.) used by the user in the past is preferentially proposed. The contract contents and periods to be used in a specific time period are predicted and proposed from the user's past input history. As a result, the reception unit proposes the optimal input method based on the past input history, thereby improving input efficiency. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's past input history to the generation AI and cause the generation AI to execute the proposal of the optimal input method.

[0086] The reception unit can automatically acquire the user's current business situation when inputting the minimum items such as the contract contents and the period, and simplify the input. The reception unit automatically acquires the user's current business situation when inputting the minimum items such as the contract contents and the period, and simplifies the input. For example, when the user opens the app, the current business situation is automatically acquired and the contract contents and the period are set. When the user inputs the contract contents, the optimal candidate is suggested based on the current business situation. When the user changes the business situation, it is updated in real time and reflected in the contract contents and the period. As a result, the reception unit automatically acquires the current business situation, and the input work is simplified. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's business situation data to the generation AI and cause the generation AI to execute simplification of the input.

[0087] The reception unit can estimate the user's emotion and adjust the design of the input interface based on the estimated user's emotion. The reception unit estimates the user's emotion and adjusts the design of the input interface based on the estimated user's emotion. For example, when the user is nervous, an interface with calm colors is provided to reduce visual stress. When the user is having fun, an interface with bright colors is provided to make the input work enjoyable. When the user is tired, an interface with simple and high visibility is provided to make the input work easier. In this way, the reception unit provides an interface according to the user's emotion, making the input work comfortable. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI and cause the generation AI to execute the interface design adjustment.

[0088] The reception unit can automatically propose region-specific contract terms in consideration of the geographical location information of the user. The reception unit automatically proposes region-specific contract terms in consideration of the geographical location information of the user. For example, when the user is in a specific region, the reception unit proposes contract terms based on the laws and regulations of the region. When the user moves to a different region, the reception unit automatically updates the region-specific contract terms. When the user makes an international contract, the reception unit proposes contract terms based on the laws and regulations of each country. In this way, the reception unit can create a contract suitable for the region by automatically proposing region-specific contract terms. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's geographical location information to the generation AI and cause the generation AI to execute the proposal of region-specific contract terms.

[0089] The reception unit can analyze the social media activity of the user and propose relevant contract contents. The reception unit analyzes the social media activity of the user and proposes relevant contract contents. For example, the reception unit proposes contract contents based on business activities mentioned by the user on social media. The reception unit proposes relevant contract contents based on the user's social media followers and interests. The reception unit proposes contract contents based on events and projects shared by the user on social media. In this way, the reception unit can create a contract suitable for the user by proposing contract contents based on social media activities. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's social media activity data to the generation AI and cause the generation AI to execute the proposal of relevant contract contents.

[0090] The analysis unit can estimate the user's emotion and adjust the risk assessment criteria based on the estimated user's emotion. The analysis unit estimates the user's emotion and adjusts the risk assessment criteria based on the estimated user's emotion. For example, when the user is relaxed, a detailed risk assessment is performed. When the user is in a hurry, a simplified risk assessment is performed. When the user is anxious, the result of the risk assessment is displayed in an easy-to-understand manner. This allows the analysis unit to perform a risk assessment according to the user's emotion, thereby enabling a more appropriate risk assessment. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to execute the risk assessment criterion adjustment.

[0091] The analysis unit can evaluate environmental and social risks in addition to legal, financial, and operational risks. The analysis unit evaluates environmental and social risks in addition to legal, financial, and operational risks. For example, as environmental risks, it evaluates the impact of the contract contents on the environment. As social risks, it evaluates the impact of the contract contents on society. In addition to legal, financial, and operational risks, it comprehensively evaluates environmental and social risks. This enables the analysis unit to evaluate various risks and perform comprehensive risk management. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can evaluate risks using an AI model that inputs the contract contents and outputs risks.

[0092] The analysis unit can apply different analysis algorithms depending on the complexity of the contract contents. The analysis unit applies different analysis algorithms depending on the complexity of the contract contents. For example, a simple analysis algorithm is applied to simple contract contents. A detailed analysis algorithm is applied to complex contract contents. An appropriate analysis algorithm is selected depending on the complexity of the contract contents. This allows the analysis unit to perform an analysis according to the complexity of the contract contents, thereby enabling more appropriate risk assessment. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can assess risk using an AI model that inputs the contract contents and outputs risk.

[0093] The analysis unit can estimate the user's emotion and adjust the order in which the results of the risk assessment are displayed based on the estimated user's emotion. The analysis unit estimates the user's emotion and adjusts the order in which the results of the risk assessment are displayed based on the estimated user's emotion. For example, if the user is nervous, the most important risk is displayed first. If the user is relaxed, detailed risk assessment results are displayed in an orderly manner. If the user is in a hurry, risk assessment results with the main points are displayed first. In this way, the analysis unit provides a display order according to the user's emotion, thereby deepening understanding of the risk assessment results. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display order of the results of the risk assessment.

[0094] The analysis unit can perform risk assessment taking into account the geographical distribution of the contract contents. The analysis unit performs risk assessment taking into account the geographical distribution of the contract contents. For example, if the contract contents relate to a specific region, the risk assessment is performed based on the laws and regulations of that region. If the contract contents relate to multiple regions, the risk assessment is performed based on the laws and regulations of each region. A comprehensive risk assessment is performed taking into account the geographical distribution of the contract contents. As a result, the analysis unit performs risk assessment taking into account the geographical distribution, thereby enabling risk management appropriate for the region. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input geographical distribution data of the contract contents to the generation AI and cause the generation AI to perform risk assessment.

[0095] The analysis unit can automatically refer to relevant laws and regulations and reflect them in the risk assessment. The analysis unit automatically refers to relevant laws and regulations and reflects them in the risk assessment. For example, the analysis unit automatically refers to laws and regulations related to the contract contents and reflects them in the risk assessment. When laws and regulations are changed, they are automatically reflected in the risk assessment. The analysis unit always refers to the latest laws and regulations related to the contract contents and reflects them in the risk assessment. This enables the analysis unit to perform risk assessment that reflects the latest laws and regulations. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input legal and regulatory data to the generation AI and have the generation AI reflect the data in the risk assessment.

[0096] The generation unit can estimate the user's emotion and adjust the contract expression method based on the estimated user's emotion. The generation unit estimates the user's emotion and adjusts the contract expression method based on the estimated user's emotion. For example, if the user is relaxed, a detailed contract is generated. If the user is in a hurry, a concise contract is generated. If the user is anxious, a contract using easy-to-understand expressions is generated. In this way, the generation unit provides a contract expression method according to the user's emotion, thereby deepening understanding of the contract. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the contract expression method.

[0097] The generation unit can automatically reflect region-specific laws and regulations when generating a contract. The generation unit automatically reflects region-specific laws and regulations when generating a contract. For example, the generation unit automatically reflects the laws and regulations of a specific region when generating a contract. The generation unit automatically reflects the laws and regulations of a plurality of regions when generating a contract. The generation unit automatically reflects the latest laws and regulations when generating a contract. This allows the generation unit to generate a contract that reflects region-specific laws and regulations. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input region-specific laws and regulations data into a generation AI and reflect them when generating a contract.

[0098] The generation unit can automatically refer to the related contract contents when generating a contract. The generation unit automatically refers to the related contract contents when generating a contract. For example, similar contracts in the past are automatically referred to when generating a contract. The related contract contents are automatically referred to when generating a contract. When generating a contract, optimal clauses are proposed based on the related contract contents when generating a contract. In this way, the generation unit can generate a more appropriate contract by referring to the related contract contents. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input related contract content data to the generation AI and have it referred to when generating a contract.

[0099] The providing unit can estimate the user's emotion and adjust the method of providing the contract based on the estimated user's emotion. The providing unit estimates the user's emotion and adjusts the method of providing the contract based on the estimated user's emotion. For example, when the user is relaxed, a providing method including a detailed explanation is selected. When the user is in a hurry, a providing method including a concise explanation is selected. When the user is anxious, a providing method that gives a sense of security is selected. In this way, the providing unit provides a providing method according to the user's emotion, thereby deepening understanding of the contract. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the providing method.

[0100] The provision unit can select the optimal provision method by referring to the user's past confirmation history when providing the contract. The provision unit selects the optimal provision method by referring to the user's past confirmation history when providing the contract. For example, the optimal provision method is selected based on the provision method used by the user in the past. The most efficient provision method is selected from the user's past confirmation history. The user's past confirmation history is analyzed and the optimal provision method is proposed. As a result, the provision unit selects the optimal provision method based on the past confirmation history, thereby making the provision of the contract more efficient. Part or all of the above-mentioned processing in the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the provision unit can input the user's past confirmation history data to the generation AI and cause the generation AI to select the provision method.

[0101] The provision unit can propose the optimal timing of provision in consideration of the user's work schedule when providing the contract. The provision unit proposes the optimal timing of provision in consideration of the user's work schedule when providing the contract. For example, the provision unit refers to the user's work schedule and proposes the optimal timing of provision. The provision unit adjusts the timing of provision of the contract based on the user's work schedule. The provision unit selects the optimal timing of provision in consideration of the user's work schedule. As a result, the provision unit proposes the timing of provision in consideration of the work schedule, thereby making the provision of the contract more efficient. Part or all of the above-mentioned processing in the provision unit may be performed, for example, using AI, or may be performed without using AI. For example, the provision unit can input the user's work schedule data to the generation AI and cause the generation AI to execute the proposal of the timing of provision.

[0102] The providing unit can estimate the user's emotion and adjust the interface for providing the contract based on the estimated user's emotion. The providing unit estimates the user's emotion and adjusts the interface for providing the contract based on the estimated user's emotion. For example, when the user is nervous, an interface with calm colors is provided to reduce visual stress. When the user is having fun, an interface with bright colors is provided to make the providing work enjoyable. When the user is tired, an interface with simple and high visibility is provided to make the providing work easier. Thereby, the providing unit provides an interface according to the user's emotion, making the provision of the contract comfortable. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the providing unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the interface for providing.

[0103] The provision unit can analyze the social media activity of the user and provide related information when providing the contract. The provision unit analyzes the social media activity of the user and provides related information when providing the contract. For example, the provision unit provides related information based on business activities mentioned by the user on social media. The provision unit provides related information based on the user's social media followers and interests. The provision unit provides related information based on events and projects shared by the user on social media. As a result, the provision unit provides related information based on social media activities, thereby deepening understanding of the contract. Part or all of the above-mentioned processing in the provision unit may be performed, for example, using AI or may be performed without using AI. For example, the provision unit can input the user's social media activity data to the generation AI and cause the generation AI to provide related information.

[0104] The providing unit can select the optimal providing method in consideration of the device information of the user when providing the contract. The providing unit selects the optimal providing method in consideration of the device information of the user when providing the contract. For example, when the user is using a smartphone, a providing method according to the screen size is provided. When the user is using a tablet, a providing method optimized for a large screen is provided. When the user is using a smartwatch, a providing method that is simple and highly visible is provided. As a result, the providing unit provides a providing method that takes device information into consideration, thereby making the provision of the contract more efficient. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the device information of the user to the generating AI and cause the generating AI to select the providing method.

[0105] The risk identification unit can estimate the user's emotion and adjust the display method of the risk based on the estimated user's emotion. The risk identification unit estimates the user's emotion and adjusts the display method of the risk based on the estimated user's emotion. For example, if the user is nervous, a simple and highly visible display method is provided. If the user is relaxed, a display method including detailed information is provided. If the user is in a hurry, a display method that focuses on the main points is provided. In this way, the risk identification unit provides a display method according to the user's emotion, thereby deepening the understanding of the risk. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the risk identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the risk identification unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display method of the risk.

[0106] The risk identification unit can identify environmental and social risks in addition to legal, financial, and operational risks. The risk identification unit identifies environmental and social risks in addition to legal, financial, and operational risks. For example, as environmental risks, it identifies the impact of the contract contents on the environment. As social risks, it identifies the impact of the contract contents on society. In addition to legal, financial, and operational risks, it also comprehensively identifies environmental and social risks. This enables the risk identification unit to identify various risks and perform comprehensive risk management. Some or all of the above-mentioned processing in the risk identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the risk identification unit can identify risks using an AI model that inputs the contract contents and outputs risks.

[0107] The risk identification unit can improve the accuracy of risk identification by referring to past contract data. The risk identification unit improves the accuracy of risk identification by referring to past contract data. For example, the risk identification unit identifies risks in similar contracts by referring to past contract data. The risk identification unit analyzes past contract data and improves the accuracy of risk identification. The risk identification algorithm is optimized based on the past contract data. As a result, the risk identification unit improves the accuracy of risk identification by referring to past data. Some or all of the above-mentioned processing in the risk identification unit may be performed using AI, for example, or may be performed without using AI. For example, the risk identification unit can input past contract data to a generation AI and cause the generation AI to improve the accuracy of risk identification.

[0108] The risk identification unit can estimate the user's emotion and adjust the importance of the risk based on the estimated user's emotion. The risk identification unit estimates the user's emotion and adjusts the importance of the risk based on the estimated user's emotion. For example, if the user is nervous, the most important risk is displayed first. If the user is relaxed, detailed risk information is displayed in an orderly manner. If the user is in a hurry, risk information with the main points is displayed first. In this way, the risk identification unit provides the importance of the risk according to the user's emotion, thereby deepening the understanding of the risk. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the risk identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the risk identification unit can input the user's emotion data to the generation AI and cause the generation AI to execute the risk importance adjustment.

[0109] The risk identification unit can perform risk identification in consideration of the geographical distribution of the contract contents. The risk identification unit performs risk identification in consideration of the geographical distribution of the contract contents. For example, if the contract contents relate to a specific region, risk identification is performed based on the laws and regulations of that region. If the contract contents relate to multiple regions, risk identification is performed based on the laws and regulations of each region. Comprehensive risk identification is performed in consideration of the geographical distribution of the contract contents. As a result, the risk identification unit performs risk identification in consideration of the geographical distribution, thereby enabling risk management appropriate for the region. Part or all of the above-mentioned processing in the risk identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the risk identification unit can input geographical distribution data of the contract contents to the generation AI and cause the generation AI to execute risk identification.

[0110] The risk identification unit can automatically refer to relevant laws and regulations and reflect them in risk identification. The risk identification unit automatically refers to relevant laws and regulations and reflects them in risk identification. For example, the risk identification unit automatically refers to laws and regulations related to the contract contents and reflects them in risk identification. When laws and regulations are changed, they are automatically reflected in risk identification. The latest laws and regulations related to the contract contents are always referred to and reflected in risk identification. This enables the risk identification unit to identify risks that reflect the latest laws and regulations. Some or all of the above-mentioned processing in the risk identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the risk identification unit can input legal and regulatory data to the generation AI and have the generation AI reflect the data in the risk identification.

[0111] The learning unit can estimate the user's emotion and select learning data based on the estimated user's emotion. The learning unit estimates the user's emotion and selects learning data based on the estimated user's emotion. For example, when the user is relaxed, detailed learning data is selected. When the user is in a hurry, simplified learning data is selected. When the user is anxious, easy-to-understand learning data is selected. In this way, the learning unit selects learning data according to the user's emotion, thereby improving the efficiency of learning. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's emotion data to the generation AI and cause the generation AI to select the learning data.

[0112] The learning unit can learn from past contract data and improve the accuracy of risk assessment and contract generation. The learning unit learns from past contract data and improves the accuracy of risk assessment and contract generation. For example, the learning unit learns from past contract data and improves the accuracy of risk assessment in similar contracts. The learning unit analyzes past contract data and improves the accuracy of contract generation. The algorithms for risk assessment and contract generation are optimized based on the past contract data. As a result, the learning unit improves the accuracy of risk assessment and contract generation by learning from past data. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input past contract data to the generation AI and cause the generation AI to perform improvement in the accuracy of risk assessment and contract generation.

[0113] The learning unit can optimize the learning algorithm by referring to the change history of the contract content during learning. The learning unit optimizes the learning algorithm by referring to the change history of the contract content during learning. For example, the learning algorithm is optimized by referring to the change history of the contract content. The change history of the contract content is analyzed to improve the accuracy of the learning algorithm. The learning algorithm is optimized based on the change history of the contract content. As a result, the learning unit improves the accuracy of the learning algorithm by referring to the change history. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the change history data of the contract content to the generation AI and cause the generation AI to optimize the learning algorithm.

[0114] The learning unit can estimate the user's emotion and adjust the learning frequency based on the estimated user's emotion. The learning unit estimates the user's emotion and adjusts the learning frequency based on the estimated user's emotion. For example, when the user is relaxed, the learning is performed frequently. When the user is in a hurry, the learning frequency is reduced. When the user is anxious, the learning is performed at a moderate frequency. In this way, the learning unit provides a learning frequency according to the user's emotion, thereby improving the efficiency of learning. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the learning frequency.

[0115] The learning unit can select learning data in consideration of the geographical distribution of the contract contents during learning. The learning unit selects learning data in consideration of the geographical distribution of the contract contents during learning. For example, if the contract contents relate to a specific region, data for that region is preferentially learned. If the contract contents relate to multiple regions, data for each region is learned in a balanced manner. Optimal learning data is selected in consideration of the geographical distribution of the contract contents. As a result, the learning unit selects learning data in consideration of the geographical distribution, thereby improving the efficiency of learning. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input geographical distribution data of the contract contents to the generation AI and cause the generation AI to select the learning data.

[0116] The learning unit can automatically refer to relevant laws and regulations during learning and reflect them in the learning data. The learning unit can automatically refer to relevant laws and regulations during learning and reflect them in the learning data. For example, the learning unit can automatically refer to laws and regulations related to the contract contents and reflect them in the learning data. When laws and regulations are changed, they are automatically reflected in the learning data. The learning unit can always refer to the latest laws and regulations related to the contract contents and reflect them in the learning data. As a result, the learning unit can provide learning data that reflects the latest laws and regulations, thereby improving the accuracy of learning. Some or all of the above-mentioned processing in the learning unit can be performed, for example, using AI or can be performed without using AI. For example, the learning unit can input legal and regulatory data to a generation AI and have the generation AI execute the reflection in the learning data.

[0117] The correction unit can estimate the user's emotion and adjust the display method of the correction interface based on the estimated user's emotion. The correction unit estimates the user's emotion and adjusts the display method of the correction interface based on the estimated user's emotion. For example, when the user is nervous, an interface with a calm color scheme is provided to reduce visual stress. When the user is having fun, an interface with a bright color scheme is provided to make the correction work enjoyable. When the user is tired, an interface with a simple and high visibility is provided to make the correction work easy. Thereby, the correction unit provides an interface according to the user's emotion, making the correction work comfortable. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the correction unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the correction unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display method of the correction interface.

[0118] The correction unit can suggest the optimal correction method by referring to the user's past correction history at the time of correction. The correction unit suggests the optimal correction method by referring to the user's past correction history at the time of correction. For example, the optimal correction method is suggested based on the correction contents made by the user in the past. Frequently made correction contents are automatically suggested from the user's past correction history. The user's past correction history is analyzed and the optimal correction method is suggested. As a result, the correction unit suggests the optimal correction method based on the past correction history, thereby making the correction work more efficient. Part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI, or may be performed without using AI. For example, the correction unit can input the user's past correction history data to the generation AI and have the generation AI execute the suggestion of the correction method.

[0119] The modification unit can track the change history of the contract contents at the time of modification and reflect it in the modification. The modification unit can track the change history of the contract contents at the time of modification and reflect it in the modification. For example, the modification unit refers to the change history of the contract contents and reflects it in the modification. The modification unit analyzes the change history of the contract contents and improves the accuracy of the modification. The modification unit optimizes the modification contents based on the change history of the contract contents. In this way, the modification unit improves the accuracy of the modification contents by tracking the change history. Some or all of the above-mentioned processing in the modification unit may be performed using, for example, AI, or may be performed without using AI. For example, the modification unit can input the change history data of the contract contents to the generation AI and cause the generation AI to reflect the modification contents.

[0120] The correction unit can estimate the user's emotion and determine the priority of correction based on the estimated user's emotion. The correction unit estimates the user's emotion and determines the priority of correction based on the estimated user's emotion. For example, if the user is nervous, the most important correction is made first. If the user is relaxed, detailed corrections are made in an orderly manner. If the user is in a hurry, corrections that focus on the main points are made first. In this way, the correction unit provides a priority according to the user's emotion, thereby making the correction work more efficient. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the correction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the correction unit can input the user's emotion data to the generation AI and cause the generation AI to execute the priority determination of corrections.

[0121] The correction unit can propose a correction method taking into consideration the geographical distribution of the contract contents at the time of correction. The correction unit proposes a correction method taking into consideration the geographical distribution of the contract contents at the time of correction. For example, if the contract contents relate to a specific region, the correction unit proposes a correction method based on the laws and regulations of the region. If the contract contents relate to multiple regions, the correction unit proposes a correction method based on the laws and regulations of each region. The correction unit proposes an optimal correction method taking into consideration the geographical distribution of the contract contents. As a result, the correction unit provides a correction method that takes into consideration the geographical distribution, thereby making the correction work more efficient. A part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI, or may be performed without using AI. For example, the correction unit can input geographical distribution data of the contract contents to the generation AI and cause the generation AI to execute the proposal of the correction method.

[0122] The correction unit can automatically refer to related laws and regulations at the time of correction and reflect them in the correction. The correction unit can automatically refer to related laws and regulations at the time of correction and reflect them in the correction. For example, the correction unit automatically refers to laws and regulations related to the contract content and reflects them in the correction content. If there is a change in laws or regulations, they are automatically reflected in the correction content. The latest laws and regulations related to the contract content are always referred to and reflected in the correction content. This enables the correction unit to make corrections that reflect the latest laws and regulations. A part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI, or may be performed without using AI. For example, the correction unit can input legal and regulatory data to the generation AI and have the generation AI execute the reflection in the correction content.

[0123] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0124] The contract creation system can analyze a user's past contract creation history and suggest optimal contract templates. For example, similar contract templates can be automatically suggested based on the content and format of contracts created by the user in the past. Clauses and formats frequently used by the user are preferentially displayed, improving the efficiency of contract creation. Furthermore, the system can learn the content of revisions made by the user in the past and automatically suggest them when similar revisions are necessary. This allows the contract creation system to create contracts more quickly and accurately by utilizing the user's past history.

[0125] The contract creation system can estimate the user's emotions and adjust the contents of the contract based on the estimated emotions. For example, if the user feels anxious, the contract creation system can explain risk clauses in detail and add reassuring content. If the user feels relaxed, the contract creation system can generate a concise contract that gets to the point. If the user is in a hurry, the contract creation system can highlight important clauses to enable quick confirmation. In this way, the contract creation system can provide a contract that corresponds to the user's emotions and improve user satisfaction.

[0126] The contract creation system can suggest the optimal timing for creating a contract, taking into account the user's work schedule. For example, by referencing the user's calendar, it can suggest creating a contract during a time when there is less work to do. If the user needs to create a contract before an important meeting or project, it can set a reminder to notify the user. It can suggest that the user create necessary contracts in advance before taking an extended vacation. In this way, the contract creation system can support efficient contract creation that matches the user's work schedule.

[0127] The contract creation system can estimate the user's emotions and suggest revisions to the contract based on the estimated emotions. For example, if the user is stressed, the parts that need revisions are briefly indicated, simplifying the revision procedure. If the user is relaxed, detailed revision suggestions are made, improving the quality of the contract. If the user is in a hurry, the most important revisions are suggested as a priority, allowing the revisions to be made quickly. In this way, the contract creation system can suggest revisions according to the user's emotions and improve the efficiency of the revision work.

[0128] The contract drafting system can automatically insert region-specific contract clauses by taking into account the user's geographic location. For example, if the user is signing a contract in a specific region, clauses based on the laws and regulations of that region will be automatically added. If the user moves to a different region, the contract clauses specific to that region will be automatically updated. If the user is signing an international contract, clauses based on the laws and regulations of each country will be suggested. This allows the contract drafting system to create contracts that are appropriate for the region.

[0129] The contract creation system can estimate the user's emotions and adjust the method of providing a contract based on the estimated emotions. For example, if the user is nervous, an interface with calm colors is provided to reduce visual stress. If the user is having fun, an interface with bright colors is provided to make the providing task more enjoyable. If the user is tired, a simple and highly visible interface is provided to make the providing task easier. In this way, the contract creation system makes providing a contract more comfortable by providing an interface according to the user's emotions.

[0130] The contract creation system can analyze the user's social media activity and suggest relevant contract content. For example, suggest contract content based on business activities mentioned by the user on social media; suggest relevant contract content based on the user's social media followers and interests; suggest contract content based on events or projects shared by the user on social media. In this way, the contract creation system can create a contract that is suitable for the user by suggesting contract content based on social media activity.

[0131] The contract creation system can estimate the user's emotions and adjust the way the contract is expressed based on the estimated emotions. For example, if the user is relaxed, a detailed contract is generated. If the user is in a hurry, a concise contract is generated. If the user is anxious, a contract using easy-to-understand expressions is generated. In this way, the contract creation system provides a contract expression method according to the user's emotions, thereby deepening the user's understanding of the contract.

[0132] The contract creation system can provide an optimal contract creation interface by taking into account the device information of the user. For example, if the user is using a smartphone, an interface that matches the screen size is provided. If the user is using a tablet, an interface optimized for a large screen is provided. If the user is using a smartwatch, an interface that is simple and highly visible is provided. In this way, the contract creation system provides an interface that takes into account device information, thereby making contract creation more efficient.

[0133] The contract creation system can estimate the user's emotions and adjust the timing of providing the contract based on the estimated emotions. For example, if the user is relaxed, a method of providing the contract that includes a detailed explanation is selected. If the user is in a hurry, a method of providing the contract that includes a concise explanation is selected. If the user is feeling anxious, a method of providing the contract that gives a sense of security is selected. In this way, the contract creation system can deepen the user's understanding of the contract by providing a method of providing the contract that corresponds to the user's emotions.

[0134] The process flow of the second embodiment will be briefly described below.

[0135] Step 1: The reception unit receives input of the contract contents or contract period. For example, the user can input information such as "contract contents: product sales" and "contract period: 1 year." The reception unit may include AI processing and provides an interface for receiving user input. Step 2: The analysis unit uses a large-scale language model (generative AI) to analyze the information entered by the reception unit and evaluate the risks. For example, if the contract content is product sales, it evaluates risks related to product quality assurance and delivery delays. Step 3: The generator uses a large-scale language model (generative AI) to generate a contract based on the risks assessed by the analyzer. The generator automatically inserts clauses to minimize risks and generates a contract. For example, clauses regarding product quality assurance and delivery delays are automatically inserted. Step 4: The provision unit provides the contract generated by the generation unit to the user. The provision unit may include AI processing and provides an interface for the user to confirm and modify the contract.

[0136] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0137] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0138] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0139] For example, the reception unit receives user input via the reception device 38 of the smart device 14 or the communication I / F 26 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12, analyzes the input information, and evaluates the risk. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a contract by automatically inserting clauses for minimizing the risk. For example, the provision unit provides the generated contract to the user via the output device 40 of the smart device 14 or the communication I / F 26 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0140] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0141] 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.

[0142] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0143] The 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.

[0144] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0145] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0146] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0147] Fig. 4 shows an example of 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.

[0148] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0149] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0150] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0151] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0152] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0153] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0154] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0155] For example, the reception unit receives user input via the microphone 238 of the smart glasses 214 or the communication I / F 26 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12, analyzes the input information, and evaluates the risk. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a contract by automatically inserting clauses for minimizing the risk. For example, the provision unit provides the generated contract to the user via the speaker 240 of the smart glasses 214 or the communication I / F 26 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0156] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0157] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0158] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0159] The 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.

[0160] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0161] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0162] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0163] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0164] 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.

[0165] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0166] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 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.

[0167] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0168] 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 voice indicating a user input for 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.

[0169] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0170] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0171] For example, the reception unit receives user input via the microphone 238 of the headset type terminal 314 or the communication I / F 26 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12, analyzes the input information, and evaluates the risk. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a contract by automatically inserting clauses for minimizing the risk. For example, the provision unit provides the generated contract to the user via the display 343 of the headset type terminal 314 or the communication I / F 26 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0172] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0173] 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.

[0174] 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, the RAM 30, and the 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.

[0175] 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.

[0176] 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 the voice according to instructions from the processor 46.

[0177] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0178] 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 performed in a secure state.

[0179] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0180] 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.

[0181] 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.

[0182] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0183] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0184] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0185] 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 a voice indicating a user input for 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.

[0186] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0187] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0188] For example, the reception unit receives user input via the microphone 238 of the robot 414 or the communication I / F 26 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12, analyzes the input information, and evaluates the risk. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a contract by automatically inserting clauses for minimizing the risk. For example, the provision unit provides the generated contract to the user via the speaker 240 of the robot 414 or the communication I / F 26 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0189] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0190] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0191] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0192] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0193] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0194] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is 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 the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0195] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0196] 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.

[0197] 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 Universal Serial Bus (USB) 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.

[0198] In addition, 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 upon request from the data processing device 12.

[0199] 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.

[0200] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0201] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0202] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0203] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0204] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0205] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0206] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0207] (Appendix 1) a reception unit for receiving input of contract details or contract period; an analysis unit that analyzes the information input by the reception unit and evaluates a risk; a generation unit that generates a contract based on the risk evaluated by the analysis unit; a providing unit that provides the contract generated by the generating unit to a user. A system characterized by: (Appendix 2) Have a risk identification department that lists specific types of risks 2. The system of claim 1, (Appendix 3) Equipped with a learning module that learns from past contract data 2. The system of claim 1, (Appendix 4) Equipped with a modification section that allows users to check and modify the generated contract 2. The system of claim 1, (Appendix 5) The analysis unit is Assess legal, financial and operational risks 2. The system of claim 1, (Appendix 6) The generation unit is Automatically insert clauses to mitigate risk 2. The system of claim 1, (Appendix 7) The reception unit is Infer user sentiment and adjust the input method for contract details and minimum period items based on the inferred user sentiment 2. The system of claim 1, (Appendix 8) The reception unit is Analyze the user's past input history and suggest appropriate input methods 2. The system of claim 1, (Appendix 9) The reception unit is Simplify input by automatically acquiring the user's current business situation when entering contract details and minimum period items. 2. The system of claim 1, (Appendix 10) The reception unit is Estimating user emotions and adjusting the design of the input interface based on the estimated user emotions 2. The system of claim 1, (Appendix 11) The reception unit is Taking into account the user's geographic location, automatically suggesting region-specific contract terms 2. The system of claim 1, (Appendix 12) The reception unit is Analyze your social media activity and provide relevant subscription offers 2. The system of claim 1, (Appendix 13) The analysis unit is Inferring user emotions and adjusting risk assessment criteria based on the inferred user emotions 2. The system of claim 1, (Appendix 14) The analysis unit is Assess legal, financial, and operational risks, as well as environmental and social risks 2. The system of claim 1, (Appendix 15) The analysis unit is Apply different analysis algorithms depending on the complexity of the contract 2. The system of claim 1, (Appendix 16) The analysis unit is Inferring user sentiment and adjusting the order in which risk assessment results are displayed based on the inferred user sentiment 2. The system of claim 1, (Appendix 17) The analysis unit is Conduct risk assessment taking into account the geographical distribution of contract contents 2. The system of claim 1, (Appendix 18) The analysis unit is Automatically reference relevant laws and regulations and incorporate them into risk assessments 2. The system of claim 1, (Appendix 19) The generation unit is Infer user sentiment and adjust contract wording based on the inferred sentiment 2. The system of claim 1, (Appendix 20) The generation unit is Automatically reflect local laws and regulations when generating contracts 2. The system of claim 1, (Appendix 21) The generation unit is Automatically reference related agreement content when generating agreements 2. The system of claim 1, (Appendix 22) The providing unit is Inferring user sentiment and adjusting how the contract is delivered based on the inferred user sentiment 2. The system of claim 1, (Appendix 23) The providing unit is When providing a contract, the optimal method of providing the contract is selected by referring to the user's past confirmation history. 2. The system of claim 1, (Appendix 24) The providing unit is When providing a contract, the system will suggest the optimal timing to provide it, taking into account the user's work schedule. 2. The system of claim 1, (Appendix 25) The providing unit is A method for predicting a user's emotions and adjusting a contract presentation interface based on the user's emotions 2. The system of claim 1, (Appendix 26) The providing unit is Analyze your social media activity and provide you with relevant information when providing the contract 2. The system of claim 1, (Appendix 27) The providing unit is When providing a contract, select the optimal method of providing it by taking into account the user's device information 2. The system of claim 1, (Appendix 28) The risk identification unit includes: Infer user sentiment and adjust risk display based on the inferred user sentiment 2. The system of claim 1, (Appendix 29) The risk identification unit includes: Identify legal, financial and operational risks, as well as environmental and social risks 2. The system of claim 1, (Appendix 30) The risk identification unit includes: Referencing past contract data to improve the accuracy of risk identification 2. The system of claim 1, (Appendix 31) The risk identification unit includes: Infer user sentiment and adjust the importance of risks based on the inferred user sentiment 2. The system of claim 1, (Appendix 32) The risk identification unit includes: Identify risks by considering the geographic distribution of contract contents 2. The system of claim 1, (Appendix 33) The risk identification unit includes: Automatically reference relevant laws and regulations and incorporate them into risk identification 2. The system of claim 1, (Appendix 34) The learning unit is Estimate the user's emotions and select learning data based on the estimated user emotions. 2. The system of claim 1, (Appendix 35) The learning unit is Learn from past contract data to improve the accuracy of risk assessment and contract generation 2. The system of claim 1, (Appendix 36) The learning unit is During learning, the learning algorithm is optimized by referring to the contract content change history. 2. The system of claim 1, (Appendix 37) The learning unit is Infer user emotions and adjust the frequency of learning based on the estimated user emotions. 2. The system of claim 1, (Appendix 38) The learning unit is During training, training data is selected taking into account the geographic distribution of contract contents. 2. The system of claim 1, (Appendix 39) The learning unit is During learning, relevant laws and regulations are automatically referenced and reflected in the learning data 2. The system of claim 1, (Appendix 40) The correction unit is A user's emotion is estimated, and a display method of a modified interface is adjusted based on the estimated user's emotion. 2. The system of claim 1, (Appendix 41) The correction unit is When making corrections, the system refers to the user's past correction history and suggests the best way to correct the problem. 2. The system of claim 1, (Appendix 42) The correction unit is When making amendments, track the change history of the contract contents and reflect them in the amendments. 2. The system of claim 1, (Appendix 43) The correction unit is Inferring user sentiment and prioritizing modifications based on the estimated user sentiment 2. The system of claim 1, (Appendix 44) The correction unit is When making modifications, propose modifications taking into account the geographical distribution of the contract contents 2. The system of claim 1, (Appendix 45) The correction unit is When making revisions, automatically refer to relevant laws and regulations and reflect them in the revisions 2. The system of claim 1, [Explanation of symbols]

[0208] 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 reception unit for receiving input of contract details or contract period; an analysis unit that analyzes the information input by the reception unit and evaluates a risk; a generation unit that generates a contract based on the risk evaluated by the analysis unit; a providing unit that provides the contract generated by the generating unit to a user. A system characterized by:

2. Have a risk identification department that lists specific types of risks 2. The system of claim 1 .

3. Equipped with a learning module that learns from past contract data 2. The system of claim 1 .

4. Equipped with a modification section that allows users to check and modify the generated contract 2. The system of claim 1 .

5. The analysis unit is Assess legal, financial and operational risks 2. The system of claim 1 .

6. The generation unit is Automatically insert clauses to mitigate risk 2. The system of claim 1 .

7. The reception unit is Infer user sentiment and adjust the input method for contract details and minimum period items based on the inferred user sentiment 2. The system of claim 1 .

8. The reception unit is Analyze the user's past input history and suggest appropriate input methods 2. The system of claim 1 .

9. The reception unit is Simplify input by automatically acquiring the user's current business situation when entering contract details and minimum period items.

2. The system of claim 1 .

10. The reception unit is Estimating user emotions and adjusting the design of the input interface based on the estimated user emotions 2. The system of claim 1 .

Images