system

Abstract

The system according to this embodiment aims to efficiently scrutinize the contents of a contract and detect risks. [Solution] The system according to the embodiment comprises a reading unit, a storage unit, a review unit, a risk detection unit, and a proposal unit. The reading unit reads past contracts. The storage unit stores the contents of the contracts read by the reading unit in a database. The review unit reviews the contents of the contracts stored by the storage unit by comparing them with the new contracts. The risk detection unit detects risks based on the contents of the contracts reviewed by the review unit. The proposal unit provides points for contract negotiation and improvements based on the risks detected by the risk detection unit.

Description

Technical Field

[0006] ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the work of checking the content of a contract requires time and effort, and there is a risk of overlooking contradictions and risks with past contract contents.

[0005] The system according to the embodiment aims to efficiently examine the content of a contract and detect risks.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reading unit, a storage unit, a review unit, a risk detection unit, and a proposal unit. The reading unit reads past contracts. The storage unit stores the contents of the contracts read by the reading unit in a database. The review unit reviews the contents of the contracts stored by the storage unit by comparing them with the new contracts. The risk detection unit detects risks based on the contents of the contracts reviewed by the review unit. The proposal unit provides points for contract negotiation and areas for improvement based on the risks detected by the risk detection unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently scrutinize the contents of a contract and detect risks. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 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". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the 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. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The "ContractGuard" AI agent for checking contract content according to an embodiment of the present invention is a system designed to reduce the effort and risks involved when companies manage and conclude numerous contracts. ContractGuard reads past contracts concluded within the company, compares them with all contract contents, and then scrutinizes new contracts to identify all problems and clarify potential risks. ContractGuard frees everyone from the task of meticulously reading each item manually and comparing it with past contracts and internal regulations. For example, ContractGuard reads past contracts concluded within the company. At this time, the contents of past contracts are saved in a database and analyzed by AI. For example, clauses and conditions of the contract are extracted and registered in the database. This allows for centralized management of past contract contents. Next, ContractGuard scrutinizes new contracts. When a new contract is entered, the AI ​​analyzes it by comparing it with past contract contents. For example, it checks whether the clauses of the new contract contradict past contract contents and whether there are any risks. This prevents the risk of concluding contracts with similar problems again or concluding contracts that contradict past contract contents. Furthermore, ContractGuard detects risks hidden within contracts and assesses their importance and impact. For example, AI analyzes risks hidden in contract clauses and evaluates their importance and impact. This allows it to provide users with suggestions for risk mitigation. ContractGuard also provides points and areas for improvement in contract negotiations based on past contract history and current business conditions. For example, it analyzes past contract history and the AI ​​suggests points and areas for improvement in contract negotiations tailored to current business conditions. This improves the efficiency and accuracy of contract negotiations. Through this mechanism, ContractGuard frees everyone from the task of meticulously reading each item manually and comparing it with past contracts and internal regulations. For example, it can significantly reduce the time and effort spent checking contract content in companies with small legal departments or in large corporations managing many contracts. It is also a useful tool for companies working to minimize contract management and legal risks.This allows ContractGuard to significantly reduce the time and expertise required to review contract details.

[0029] The AI ​​agent "ContractGuard" for checking contract content according to this embodiment comprises a reading unit, a storage unit, a scrutiny unit, a risk detection unit, and a proposal unit. The reading unit reads past contracts. Past contracts include, but are not limited to, business contracts, employment contracts, service contracts, etc. The reading unit can, for example, digitize and read past contracts concluded within the company using scanning technology. The reading unit can also directly read contracts submitted in digital format. Furthermore, the reading unit can read printed contracts using OCR technology. For example, the reading unit scans a handwritten contract with a high-resolution scanner and converts it into text information using OCR technology. For digital contracts, it can directly read those submitted in a specific file format. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The storage unit stores the contents of the read contracts in a database. The database includes, but is not limited to, relational databases, NoSQL databases, etc. The storage unit extracts, for example, the clauses and conditions of a contract and registers them in a database. The storage unit can also optimize the database structure for centralized management of contract content. For example, the storage unit creates indexes to efficiently search for contract content. The review unit reviews the content of new contracts by comparing them with the content of contracts stored by the storage unit. Review is performed based on, for example, the degree of clause agreement or risk assessment criteria, but is not limited to these examples. For example, the review unit checks whether the clauses of a new contract contradict the content of past contracts. The review unit can also assess the risks inherent in a new contract. For example, the review unit analyzes the risks inherent in the contract clauses and assesses the importance and impact of those risks. The risk detection unit detects risks based on the content of contracts reviewed by the review unit. Risks include, for example, legal risks, financial risks, and operational risks, but are not limited to these examples. For example, the risk detection unit analyzes the risks inherent in the contract clauses and assesses the importance and impact of those risks. Furthermore, the risk detection unit can also evaluate the probability of a risk occurring and the scope of its impact.The proposal unit provides points and areas for improvement in contract negotiations based on the risks detected by the risk detection unit. Proposals are made, for example, based on proposed clause revisions or negotiation strategies, but are not limited to these examples. The proposal unit also provides points and areas for improvement in contract negotiations based, for example, on past contract history or current business conditions. Furthermore, the proposal unit can optimize the content of its proposals to improve the efficiency and accuracy of contract negotiations. For example, the proposal unit provides proposals that are easy for users to understand by specifically indicating points and areas for improvement in contract negotiations. As a result, the AI ​​agent "ContractGuard" for checking contract content according to this embodiment can significantly reduce the time and expertise required to check contract content.

[0030] The reading unit reads past contracts. These past contracts include, but are not limited to, business contracts, employment contracts, and service contracts. For example, the reading unit digitizes and reads past contracts concluded within the company using scanning technology. Specifically, it scans the contract using a high-resolution scanner and saves it as image data. Then, it uses OCR (Optical Character Recognition) technology to extract character information from the scanned image data and convert it into digital text. Because OCR technology can recognize not only printed characters but also handwritten characters with high accuracy, handwritten contracts can also be accurately digitized. Furthermore, the reading unit can also directly read contracts submitted in digital format. For example, it can read contracts in PDF or Word format as is and analyze their contents. This allows for efficient data collection regardless of the contract format. The reading unit can also use a combination of multiple OCR engines to accurately read the content of contracts. This allows it to handle different fonts and layouts and improve recognition accuracy. In addition, the reading unit can use natural language processing (NLP) technology to analyze the content of contracts. By using NLP technology, it is possible to understand the content of a contract in context and extract important information. For example, it is possible to automatically identify the clauses and conditions of a contract and register them in a database. This allows the reading unit to efficiently digitize the content of the contract and provide the data necessary for subsequent processing.

[0031] The storage unit saves the contents of the loaded contract to a database. The database may include, but is not limited to, relational databases or NoSQL databases. For example, the storage unit extracts the clauses and conditions of the contract and registers them in the database. Specifically, it saves each clause of the contract as a separate record in the database and creates indexes to facilitate searching and referencing. This allows for quick retrieval of specific clauses and conditions and acquisition of necessary information. The storage unit can also optimize the database structure for centralized management of contract contents. For example, it can design the database schema and create necessary indexes to efficiently search the contract contents. Furthermore, the storage unit can implement database access control and encryption to securely store the contract contents. This prevents unauthorized access to the contract contents and protects the confidentiality of the information. The storage unit can also regularly back up the contract contents to prepare for data loss or corruption. This allows for quick data recovery in the event of a failure. Additionally, the storage unit can perform version control of contracts, comparing past and current versions. This allows for tracking the contract's change history and reviewing the changes. This allows the storage unit to efficiently and securely manage the contents of contracts and provide necessary information quickly.

[0032] The Review Department scrutinizes the content of new contracts by comparing them with the content of contracts stored by the Archive Department. This scrutiny is based on, for example, the degree of clause consistency and risk assessment criteria, but is not limited to these examples. Specifically, the Review Department checks whether the clauses of the new contract are consistent with the content of past contracts. For example, it compares the clauses in past contracts with those in the new contract and evaluates the degree of consistency. This allows for confirmation that the new contract is consistent with the content of past contracts. The Review Department can also assess the risks inherent in the new contract. For example, it analyzes the risks inherent in the contract clauses and evaluates their importance and impact. Specifically, it analyzes the contract clauses to identify legal risks, financial risks, operational risks, etc., and evaluates the probability of occurrence and the scope of impact of each risk. The Review Department can use AI to analyze the content of contracts and assess risks. AI can learn from past contract data and identify risk patterns. This allows for the highly accurate identification and evaluation of risks inherent in new contracts. Furthermore, the review department can also use natural language processing (NLP) technology to analyze the content of contracts. By using NLP technology, the content of contracts can be understood in context and important information can be extracted. For example, it can automatically identify clauses and conditions in contracts and provide information necessary for risk assessment. This allows the review department to efficiently review the content of contracts and assess risks.

[0033] The risk detection unit detects risks based on the content of the contract, which has been scrutinized by the review unit. Risks include, but are not limited to, legal risks, financial risks, and operational risks. Specifically, the risk detection unit analyzes the risks inherent in the contract clauses and evaluates their importance and impact. For example, if a contract clause is legally problematic, it evaluates the importance and impact of that risk and proposes appropriate countermeasures. The risk detection unit can also evaluate the probability of a risk occurring and the scope of its impact. For example, if a contract clause is financially risky, it evaluates the probability of that risk occurring and the scope of its impact and proposes appropriate countermeasures. The risk detection unit can use AI to analyze the content of the contract and evaluate risks. The AI ​​can learn from past contract data and identify risk patterns. This allows it to identify and evaluate risks inherent in new contracts with high accuracy. Furthermore, the risk detection unit can also use natural language processing (NLP) technology to analyze the content of the contract. By using NLP technology, it can understand the content of the contract in context and extract important information. For example, it can automatically identify clauses and conditions in a contract and provide the information necessary for risk assessment. This allows the risk detection unit to efficiently analyze the contents of the contract and assess the risks.

[0034] The proposal department provides points and areas for improvement in contract negotiations based on risks detected by the risk detection department. Proposals may include, but are not limited to, suggested clause revisions or negotiation strategies. Specifically, the proposal department provides points and areas for improvement in contract negotiations based on past contract history and current business conditions. For example, it may propose revisions to clauses in the current contract based on past contracts. The proposal department can also optimize the content of its proposals to improve the efficiency and accuracy of contract negotiations. For example, it can provide user-friendly proposals by clearly outlining points and areas for improvement in contract negotiations. The proposal department can use AI to analyze the content of contracts and provide optimal proposals. The AI ​​can learn from past contract data and generate optimal proposals. This allows the proposal department to improve the efficiency and accuracy of contract negotiations. Furthermore, the proposal department can use natural language processing (NLP) technology to analyze the content of contracts. NLP technology allows for contextual understanding of contract content and extraction of important information. For example, it can automatically identify clauses and conditions in contracts and provide optimal proposals. This allows the proposal department to efficiently analyze the contents of the contract and make the most appropriate proposal.

[0035] The reading unit can read past contracts concluded within the company. For example, the reading unit can scan past contracts concluded within the company and save them as image data. Then, the reading unit uses OCR technology to convert the image data into text data. The reading unit can also directly read past contracts concluded within the company in digital format. For example, the reading unit can directly read digital contracts submitted in a specific file format. Furthermore, the reading unit can store past contracts concluded within the company in a database for centralized management. This allows for efficient reading of past contracts. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input image data obtained by scanning past contracts concluded within the company into a generating AI, and have the generating AI generate text data from the image data.

[0036] The storage unit can save the contents of the loaded contract to a database. For example, the storage unit can save the contents of the loaded contract to a relational database. Alternatively, the storage unit can save the contents of the loaded contract to a NoSQL database. For example, the storage unit can extract the clauses and conditions of the contract and register them in the database. Furthermore, the storage unit can optimize the database structure to centrally manage the contents of the contracts. For example, the storage unit can create indexes to efficiently search the contents of the contracts. This enables centralized management of the contents of the contracts. Some or all of the above processes in the storage unit may be performed using AI, for example, or not using AI. For example, the storage unit can input the contents of the loaded contract to a generating AI and have the generating AI perform the saving to the database.

[0037] The review department can check whether the clauses of a new contract are consistent with or unaffected by past contracts. For example, the review department can check whether the clauses of a new contract are consistent with past contracts. The review department can also assess the risks inherent in a new contract. For example, the review department can analyze the risks inherent in the contract clauses and assess the importance and impact of those risks. Furthermore, the review department can check whether the clauses of a new contract are consistent with past contracts. For example, the review department can assess the degree of consistency of the contract clauses and evaluate the probability of risk occurrence and the scope of its impact. This allows for efficient checking of risks in a new contract. Some or all of the above processes in the review department may be performed using AI, for example, or not. For example, the review department can input the clauses of a new contract into a generating AI and have the generating AI perform a comparison with past contracts.

[0038] The risk detection unit can detect risks hidden within the clauses of a contract and evaluate their importance and impact. For example, the risk detection unit can analyze the risks hidden within the clauses of a contract and evaluate their importance and impact. The risk detection unit can also evaluate the probability of a risk occurring and the scope of its impact. For example, the risk detection unit can evaluate the degree of agreement between the clauses of a contract and evaluate the probability of a risk occurring and the scope of its impact. Furthermore, the risk detection unit can classify the risks hidden within the clauses of a contract and evaluate their importance and impact. For example, the risk detection unit can classify risks such as legal risks, financial risks, and operational risks and evaluate the importance and impact of each risk. This allows for the efficient detection and evaluation of risks in a contract. Some or all of the above processing in the risk detection unit may be performed using AI, for example, or without AI. For example, the risk detection unit can input the clauses of a contract into a generating AI and have the generating AI perform risk detection and evaluation.

[0039] The proposal department can provide points and areas for improvement in contract negotiations based on past contract history and current business conditions. For example, the proposal department can analyze past contract history and provide points and areas for improvement in contract negotiations tailored to current business conditions. The proposal department can also optimize the content of proposals to improve the efficiency and accuracy of contract negotiations. For example, the proposal department can provide proposals that are easy for users to understand by specifically outlining points and areas for improvement in contract negotiations. Furthermore, the proposal department can provide points and areas for improvement in contract negotiations in real time. For example, the proposal department can provide points and areas for improvement in contract negotiations in real time based on past contract history and current business conditions. This can improve the efficiency and accuracy of contract negotiations. Some or all of the above processing in the proposal department may be performed using AI, or not. For example, the proposal department can input past contract history and current business conditions into a generating AI and have the generating AI provide points and areas for improvement in contract negotiations.

[0040] The reading unit can determine the reading priority based on the type and importance of past contracts. For example, the reading unit can prioritize reading contracts of high importance. The reading unit can also change the reading order depending on the type of contract. Furthermore, the reading unit can prioritize reading urgent contracts. This allows for efficient reading based on the type and importance of contracts. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input data on the type and importance of contracts into a generating AI and have the generating AI determine the reading priority.

[0041] The reading unit can apply different reading algorithms depending on the format and language of the contract when reading it. For example, the reading unit can apply an English-specific reading algorithm to an English contract. It can also apply a PDF-specific reading algorithm to a PDF contract. Furthermore, the reading unit can apply a handwriting recognition algorithm to a handwritten contract. This allows for efficient reading according to the format and language of the contract. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input data on the format and language of the contract into a generating AI and have the generating AI execute the application of the reading algorithm.

[0042] The reading unit can read contracts while considering the attribute information of the contract's creator and signatories. For example, the reading unit can prioritize reading contracts with important business partners. It can also prioritize reading contracts with many signatories. Furthermore, the reading unit can change the reading order according to the creator's position. This allows for efficient reading while considering the attribute information of the contract's creator and signatories. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input the attribute information of the contract's creator and signatories into a generating AI and have the generating AI determine the reading order.

[0043] The reading unit can simultaneously read related documents and reference materials when reading a contract. For example, the reading unit can simultaneously read legal documents related to the contract. It can also simultaneously read past contracts related to the contract. Furthermore, the reading unit can simultaneously read reference materials related to the contract. This enables efficient reading by simultaneously reading related documents and reference materials for the contract. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input data on related documents and reference materials for the contract into a generating AI and have the generating AI perform the processing of simultaneous reading.

[0044] The storage unit can determine the priority of saved data based on the importance and risk assessment of the contracts during the saving process. For example, the storage unit can prioritize saving contracts of high importance. It can also prioritize saving contracts with high risk assessments. Furthermore, it can prioritize saving urgent contracts. This allows for efficient saving based on the importance and risk assessment of contracts. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input data on the importance and risk assessment of contracts into a generating AI and have the generating AI determine the priority of the saved data.

[0045] The storage unit can apply different storage algorithms depending on the format and language of the contract during storage. For example, the storage unit can apply an English-specific storage algorithm to English contracts. It can also apply a PDF-specific storage algorithm to PDF contracts. Furthermore, the storage unit can apply a handwriting recognition algorithm to handwritten contracts. This allows for efficient storage according to the format and language of the contract. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input data on the format and language of the contract into a generating AI and have the generating AI execute the application of the storage algorithm.

[0046] The storage unit can save contracts while considering the attribute information of the creator and signatories. For example, the storage unit can prioritize saving contracts of important business partners. It can also prioritize saving contracts with many signatories. Furthermore, the storage unit can change the saving order according to the creator's position. This allows for efficient saving while considering the attribute information of the creator and signatories of contracts. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input the attribute information of the creator and signatories of contracts into a generating AI and have the generating AI determine the saving order.

[0047] The storage unit can simultaneously store related documents and reference materials for a contract at the time of storage. For example, the storage unit can simultaneously store legal documents related to the contract. The storage unit can also simultaneously store past contracts related to the contract. Furthermore, the storage unit can simultaneously store reference materials related to the contract. This enables efficient storage by simultaneously storing related documents and reference materials for the contract. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input data on related documents and reference materials for the contract into a generating AI and have the generating AI perform the process of simultaneously storing the data.

[0048] The review department can determine the priority of the review based on the importance and risk assessment of the contract clauses during the review process. For example, the review department may prioritize reviewing clauses of high importance. It may also prioritize reviewing clauses with high risk assessments. Furthermore, it may prioritize reviewing clauses of urgency. This allows for efficient review based on the importance and risk assessment of the contract clauses. Some or all of the above processes in the review department may be performed using AI, for example, or not. For example, the review department can input data on the importance and risk assessment of the contract clauses into a generating AI and have the generating AI determine the review priority.

[0049] The review unit can apply different review algorithms depending on the format and language of the contract during the review process. For example, the review unit can apply an English-specific review algorithm to English-language contracts. It can also apply a PDF-specific review algorithm to PDF-formatted contracts. Furthermore, the review unit can apply a handwriting recognition algorithm to handwritten contracts. This allows for efficient review according to the format and language of the contract. Some or all of the above processes in the review unit may be performed using AI, for example, or without AI. For example, the review unit can input data on the format and language of the contract into a generating AI and have the generating AI execute the application of the review algorithm.

[0050] The review unit can perform its review while considering the attribute information of the contract's creator and signatories. For example, the review unit can prioritize reviewing contracts with important business partners. It can also prioritize reviewing contracts with a large number of signatories. Furthermore, the review unit can change the review order according to the creator's position. This allows for efficient review while considering the attribute information of the contract's creator and signatories. Some or all of the above processes in the review unit may be performed using AI, for example, or not using AI. For example, the review unit can input the attribute information of the contract's creator and signatories into a generating AI and have the generating AI determine the review order.

[0051] The review unit can improve the accuracy of its review by referring to relevant documents and reference materials related to the contract during the review process. For example, the review unit may refer to legal documents related to the contract during the review. The review unit may also refer to past contracts related to the contract during the review. Furthermore, the review unit may also refer to reference materials related to the contract during the review. This improves the accuracy of the review by referring to relevant documents and reference materials related to the contract during the review. Some or all of the above processes in the review unit may be performed using AI, for example, or not using AI. For example, the review unit may input data on relevant documents and reference materials related to the contract into a generating AI and have the generating AI perform the task of improving the accuracy of the review.

[0052] The risk detection unit can determine the priority of risks based on the importance of the contract clauses and the risk assessment when detecting risks. For example, the risk detection unit can prioritize the detection of risks with high importance. It can also prioritize the detection of risks with high risk assessments. Furthermore, the risk detection unit can prioritize the detection of urgent risks. This allows for efficient risk detection based on the importance of the contract clauses and the risk assessment. Some or all of the above processing in the risk detection unit may be performed using AI, for example, or without AI. For example, the risk detection unit can input data on the importance of the contract clauses and the risk assessment into a generating AI and have the generating AI perform the determination of risk priorities.

[0053] The risk detection unit can apply different risk detection algorithms depending on the format and language of the contract when detecting a risk. For example, the risk detection unit can apply an English-specific risk detection algorithm to an English-language contract. It can also apply a PDF-specific risk detection algorithm to a PDF-formatted contract. Furthermore, it can apply a handwriting recognition algorithm to a handwritten contract. This allows for efficient risk detection according to the format and language of the contract. Some or all of the above-described processes in the risk detection unit may be performed using AI, for example, or without AI. For example, the risk detection unit can input data on the contract format and language into a generating AI and have the generating AI execute the application of the risk detection algorithm.

[0054] The risk detection unit can detect risks by considering the attribute information of the contract's creator and signatories. For example, the risk detection unit can prioritize detecting risks in contracts with important business partners. It can also prioritize detecting risks in contracts with many signatories. Furthermore, the risk detection unit can change the order of risk detection according to the creator's position. This allows for efficient risk detection by considering the attribute information of the contract's creator and signatories. Some or all of the above processing in the risk detection unit may be performed using AI, for example, or without AI. For example, the risk detection unit can input the attribute information of the contract's creator and signatories into a generating AI and have the generating AI perform risk detection.

[0055] The risk detection unit can improve the accuracy of risk detection by referring to relevant documents and reference materials related to the contract when detecting risks. For example, the risk detection unit can detect risks by referring to legal documents related to the contract. The risk detection unit can also detect risks by referring to past contracts related to the contract. Furthermore, the risk detection unit can detect risks by referring to reference materials related to the contract. This improves the accuracy of risk detection by referring to relevant documents and reference materials related to the contract. Some or all of the above processing in the risk detection unit may be performed using AI, for example, or without AI. For example, the risk detection unit can input data on relevant documents and reference materials related to the contract into a generating AI and have the generating AI perform the risk accuracy improvement.

[0056] The proposal department can determine the priority of proposals based on the importance and risk assessment of the contract clauses when making a proposal. For example, the proposal department may prioritize proposals concerning clauses of high importance. It may also prioritize proposals concerning clauses with high risk assessments. Furthermore, it may prioritize proposals concerning clauses of urgency. This allows for efficient proposals based on the importance and risk assessment of the contract clauses. Some or all of the above processes in the proposal department may be performed using AI, for example, or not. For example, the proposal department can input data on the importance and risk assessment of contract clauses into a generating AI and have the generating AI determine the priority of proposals.

[0057] The proposal unit can apply different proposal algorithms depending on the format and language of the contract when making a proposal. For example, the proposal unit can apply an English-specific proposal algorithm to an English contract. It can also apply a PDF-specific proposal algorithm to a PDF contract. Furthermore, the proposal unit can apply a handwriting recognition algorithm to a handwritten contract. This allows for efficient proposal generation according to the format and language of the contract. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input data on the format and language of the contract into a generating AI and have the generating AI execute the application of the proposal algorithm.

[0058] The proposal department can make proposals while considering the attribute information of the contract's creators and signatories. For example, the proposal department can prioritize proposals for contracts with important business partners. It can also prioritize proposals for contracts with many signatories. Furthermore, the proposal department can change the order of proposals according to the creator's position. This allows for efficient proposals while considering the attribute information of the contract's creators and signatories. Some or all of the above processing in the proposal department may be performed using AI, for example, or not. For example, the proposal department can input the attribute information of the contract's creators and signatories into a generating AI and have the generating AI determine the order of proposals.

[0059] The proposal department can improve the accuracy of its proposals by referring to relevant documents and reference materials related to the contract. For example, the proposal department can make proposals by referring to legal documents related to the contract. It can also make proposals by referring to past contracts related to the contract. Furthermore, the proposal department can make proposals by referring to reference materials related to the contract. This improves the accuracy of proposals by referring to relevant documents and reference materials related to the contract. Some or all of the above processing in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input data on relevant documents and reference materials related to the contract into a generating AI and have the generating AI perform the improvement of proposal accuracy.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] ContractGuard allows you to prioritize the review of contract clauses based on their importance and risk assessment. For example, it can prioritize reviewing clauses with high importance, clauses with high risk, and clauses with high urgency. This enables efficient review based on the importance and risk assessment of each clause.

[0062] ContractGuard can apply different reading algorithms depending on the format and language of the contract when reading it. For example, it can apply an English-specific reading algorithm to English contracts, a PDF-specific reading algorithm to PDF contracts, and a handwriting recognition algorithm to handwritten contracts. This allows for efficient reading of contracts according to their format and language.

[0063] ContractGuard can prioritize the storage of contract data based on the importance and risk assessment of each contract. For example, it can prioritize the storage of contracts with high importance. It can also prioritize the storage of contracts with high risk assessments. Furthermore, it can prioritize the storage of urgent contracts. This allows for efficient storage based on the importance and risk assessment of each contract.

[0064] ContractGuard can improve the accuracy of contract scrutiny by referring to relevant literature and reference materials. For example, it can refer to relevant legal documents during the scrutiny process. It can also refer to relevant past contracts. Furthermore, it can refer to relevant reference materials during the scrutiny process. As a result, the accuracy of the scrutiny process is improved by referring to relevant literature and reference materials.

[0065] ContractGuard can prioritize risks in contracts based on the importance of the contract clauses and the risk assessment. For example, it can prioritize detecting high-importance risks. It can also prioritize detecting risks with high risk assessments. Furthermore, it can prioritize detecting urgent risks. This allows for efficient risk detection based on the importance of the contract clauses and the risk assessment.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The reading unit reads past contracts. Past contracts include business contracts, employment contracts, service contracts, etc. The reading unit digitizes and reads past contracts concluded within the company using scanning technology. It can also directly read contracts submitted in digital format. Furthermore, it can read printed contracts using OCR technology. For example, a handwritten contract can be scanned with a high-resolution scanner and converted into text information using OCR technology. Digital contracts can be directly read if they are submitted in a specific file format. OCR technology recognizes printed characters with high accuracy and converts them into digital text. Step 2: The storage unit saves the contents of the loaded contract to a database. The database can include relational databases, NoSQL databases, etc. The storage unit extracts the clauses and conditions of the contract and registers them in the database. It can also optimize the database structure to centrally manage the contents of contracts. For example, it can create indexes to efficiently search for the contents of contracts. Step 3: The review department reviews the new contract by comparing its contents with those of the contract stored by the archiving department. The review is conducted based on criteria for the degree of clause agreement and risk assessment. For example, it checks whether the clauses of the new contract are consistent with the contents of the previous contract. It can also assess the risks inherent in the new contract. For example, it analyzes the risks inherent in the contract clauses and assesses the importance and impact of those risks. Step 4: The risk detection unit detects risks based on the content of the contract reviewed by the scrutiny unit. Risks include legal risks, financial risks, and operational risks. The risk detection unit analyzes the risks hidden in the contract clauses and evaluates the importance and impact of the risks. It can also evaluate the probability of the risks occurring and the scope of their impact. Step 5: The proposal team provides points and areas for improvement in contract negotiations based on the risks detected by the risk detection team. Proposals are based on suggested clause revisions and negotiation strategies. For example, they provide points and areas for improvement in contract negotiations based on past contract history and current business conditions. Furthermore, the content of the proposals can be optimized to improve the efficiency and accuracy of contract negotiations. For example, by specifically outlining points and areas for improvement in contract negotiations, the proposals can be made easy for users to understand.

[0068] (Example of form 2) The "ContractGuard" AI agent for checking contract content according to an embodiment of the present invention is a system designed to reduce the effort and risks involved when companies manage and conclude numerous contracts. ContractGuard reads past contracts concluded within the company, compares them with all contract contents, and then scrutinizes new contracts to identify all problems and clarify potential risks. ContractGuard frees everyone from the task of meticulously reading each item manually and comparing it with past contracts and internal regulations. For example, ContractGuard reads past contracts concluded within the company. At this time, the contents of past contracts are saved in a database and analyzed by AI. For example, clauses and conditions of the contract are extracted and registered in the database. This allows for centralized management of past contract contents. Next, ContractGuard scrutinizes new contracts. When a new contract is entered, the AI ​​analyzes it by comparing it with past contract contents. For example, it checks whether the clauses of the new contract contradict past contract contents and whether there are any risks. This prevents the risk of concluding contracts with similar problems again or concluding contracts that contradict past contract contents. Furthermore, ContractGuard detects risks hidden within contracts and assesses their importance and impact. For example, AI analyzes risks hidden in contract clauses and evaluates their importance and impact. This allows it to provide users with suggestions for risk mitigation. ContractGuard also provides points and areas for improvement in contract negotiations based on past contract history and current business conditions. For example, it analyzes past contract history and the AI ​​suggests points and areas for improvement in contract negotiations tailored to current business conditions. This improves the efficiency and accuracy of contract negotiations. Through this mechanism, ContractGuard frees everyone from the task of meticulously reading each item manually and comparing it with past contracts and internal regulations. For example, it can significantly reduce the time and effort spent checking contract content in companies with small legal departments or in large corporations managing many contracts. It is also a useful tool for companies working to minimize contract management and legal risks.This allows ContractGuard to significantly reduce the time and expertise required to review contract details.

[0069] The AI ​​agent "ContractGuard" for checking contract content according to this embodiment comprises a reading unit, a storage unit, a scrutiny unit, a risk detection unit, and a proposal unit. The reading unit reads past contracts. Past contracts include, but are not limited to, business contracts, employment contracts, service contracts, etc. The reading unit can, for example, digitize and read past contracts concluded within the company using scanning technology. The reading unit can also directly read contracts submitted in digital format. Furthermore, the reading unit can read printed contracts using OCR technology. For example, the reading unit scans a handwritten contract with a high-resolution scanner and converts it into text information using OCR technology. For digital contracts, it can directly read those submitted in a specific file format. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The storage unit stores the contents of the read contracts in a database. The database includes, but is not limited to, relational databases, NoSQL databases, etc. The storage unit extracts, for example, the clauses and conditions of a contract and registers them in a database. The storage unit can also optimize the database structure for centralized management of contract content. For example, the storage unit creates indexes to efficiently search for contract content. The review unit reviews the content of new contracts by comparing them with the content of contracts stored by the storage unit. Review is performed based on, for example, the degree of clause agreement or risk assessment criteria, but is not limited to these examples. For example, the review unit checks whether the clauses of a new contract contradict the content of past contracts. The review unit can also assess the risks inherent in a new contract. For example, the review unit analyzes the risks inherent in the contract clauses and assesses the importance and impact of those risks. The risk detection unit detects risks based on the content of contracts reviewed by the review unit. Risks include, for example, legal risks, financial risks, and operational risks, but are not limited to these examples. For example, the risk detection unit analyzes the risks inherent in the contract clauses and assesses the importance and impact of those risks. Furthermore, the risk detection unit can also evaluate the probability of a risk occurring and the scope of its impact.The proposal unit provides points and areas for improvement in contract negotiations based on the risks detected by the risk detection unit. Proposals are made, for example, based on proposed clause revisions or negotiation strategies, but are not limited to these examples. The proposal unit also provides points and areas for improvement in contract negotiations based, for example, on past contract history or current business conditions. Furthermore, the proposal unit can optimize the content of its proposals to improve the efficiency and accuracy of contract negotiations. For example, the proposal unit provides proposals that are easy for users to understand by specifically indicating points and areas for improvement in contract negotiations. As a result, the AI ​​agent "ContractGuard" for checking contract content according to this embodiment can significantly reduce the time and expertise required to check contract content.

[0070] The reading unit reads past contracts. These past contracts include, but are not limited to, business contracts, employment contracts, and service contracts. For example, the reading unit digitizes and reads past contracts concluded within the company using scanning technology. Specifically, it scans the contract using a high-resolution scanner and saves it as image data. Then, it uses OCR (Optical Character Recognition) technology to extract character information from the scanned image data and convert it into digital text. Because OCR technology can recognize not only printed characters but also handwritten characters with high accuracy, handwritten contracts can also be accurately digitized. Furthermore, the reading unit can also directly read contracts submitted in digital format. For example, it can read contracts in PDF or Word format as is and analyze their contents. This allows for efficient data collection regardless of the contract format. The reading unit can also use a combination of multiple OCR engines to accurately read the content of contracts. This allows it to handle different fonts and layouts and improve recognition accuracy. In addition, the reading unit can use natural language processing (NLP) technology to analyze the content of contracts. By using NLP technology, it is possible to understand the content of a contract in context and extract important information. For example, it is possible to automatically identify the clauses and conditions of a contract and register them in a database. This allows the reading unit to efficiently digitize the content of the contract and provide the data necessary for subsequent processing.

[0071] The storage unit saves the contents of the loaded contract to a database. The database may include, but is not limited to, relational databases or NoSQL databases. For example, the storage unit extracts the clauses and conditions of the contract and registers them in the database. Specifically, it saves each clause of the contract as a separate record in the database and creates indexes to facilitate searching and referencing. This allows for quick retrieval of specific clauses and conditions and acquisition of necessary information. The storage unit can also optimize the database structure for centralized management of contract contents. For example, it can design the database schema and create necessary indexes to efficiently search the contract contents. Furthermore, the storage unit can implement database access control and encryption to securely store the contract contents. This prevents unauthorized access to the contract contents and protects the confidentiality of the information. The storage unit can also regularly back up the contract contents to prepare for data loss or corruption. This allows for quick data recovery in the event of a failure. Additionally, the storage unit can perform version control of contracts, comparing past and current versions. This allows for tracking the contract's change history and reviewing the changes. This allows the storage unit to efficiently and securely manage the contents of contracts and provide necessary information quickly.

[0072] The Review Department scrutinizes the content of new contracts by comparing them with the content of contracts stored by the Archive Department. This scrutiny is based on, for example, the degree of clause consistency and risk assessment criteria, but is not limited to these examples. Specifically, the Review Department checks whether the clauses of the new contract are consistent with the content of past contracts. For example, it compares the clauses in past contracts with those in the new contract and evaluates the degree of consistency. This allows for confirmation that the new contract is consistent with the content of past contracts. The Review Department can also assess the risks inherent in the new contract. For example, it analyzes the risks inherent in the contract clauses and evaluates their importance and impact. Specifically, it analyzes the contract clauses to identify legal risks, financial risks, operational risks, etc., and evaluates the probability of occurrence and the scope of impact of each risk. The Review Department can use AI to analyze the content of contracts and assess risks. AI can learn from past contract data and identify risk patterns. This allows for the highly accurate identification and evaluation of risks inherent in new contracts. Furthermore, the review department can also use natural language processing (NLP) technology to analyze the content of contracts. By using NLP technology, the content of contracts can be understood in context and important information can be extracted. For example, it can automatically identify clauses and conditions in contracts and provide information necessary for risk assessment. This allows the review department to efficiently review the content of contracts and assess risks.

[0073] The risk detection unit detects risks based on the content of the contract, which has been scrutinized by the review unit. Risks include, but are not limited to, legal risks, financial risks, and operational risks. Specifically, the risk detection unit analyzes the risks inherent in the contract clauses and evaluates their importance and impact. For example, if a contract clause is legally problematic, it evaluates the importance and impact of that risk and proposes appropriate countermeasures. The risk detection unit can also evaluate the probability of a risk occurring and the scope of its impact. For example, if a contract clause is financially risky, it evaluates the probability of that risk occurring and the scope of its impact and proposes appropriate countermeasures. The risk detection unit can use AI to analyze the content of the contract and evaluate risks. The AI ​​can learn from past contract data and identify risk patterns. This allows it to identify and evaluate risks inherent in new contracts with high accuracy. Furthermore, the risk detection unit can also use natural language processing (NLP) technology to analyze the content of the contract. By using NLP technology, it can understand the content of the contract in context and extract important information. For example, it can automatically identify clauses and conditions in a contract and provide the information necessary for risk assessment. This allows the risk detection unit to efficiently analyze the contents of the contract and assess the risks.

[0074] The proposal department provides points and areas for improvement in contract negotiations based on risks detected by the risk detection department. Proposals may include, but are not limited to, suggested clause revisions or negotiation strategies. Specifically, the proposal department provides points and areas for improvement in contract negotiations based on past contract history and current business conditions. For example, it may propose revisions to clauses in the current contract based on past contracts. The proposal department can also optimize the content of its proposals to improve the efficiency and accuracy of contract negotiations. For example, it can provide user-friendly proposals by clearly outlining points and areas for improvement in contract negotiations. The proposal department can use AI to analyze the content of contracts and provide optimal proposals. The AI ​​can learn from past contract data and generate optimal proposals. This allows the proposal department to improve the efficiency and accuracy of contract negotiations. Furthermore, the proposal department can use natural language processing (NLP) technology to analyze the content of contracts. NLP technology allows for contextual understanding of contract content and extraction of important information. For example, it can automatically identify clauses and conditions in contracts and provide optimal proposals. This allows the proposal department to efficiently analyze the contents of the contract and make the most appropriate proposal.

[0075] The reading unit can read past contracts concluded within the company. For example, the reading unit can scan past contracts concluded within the company and save them as image data. Then, the reading unit uses OCR technology to convert the image data into text data. The reading unit can also directly read past contracts concluded within the company in digital format. For example, the reading unit can directly read digital contracts submitted in a specific file format. Furthermore, the reading unit can store past contracts concluded within the company in a database for centralized management. This allows for efficient reading of past contracts. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input image data obtained by scanning past contracts concluded within the company into a generating AI, and have the generating AI generate text data from the image data.

[0076] The storage unit can save the contents of the loaded contract to a database. For example, the storage unit can save the contents of the loaded contract to a relational database. Alternatively, the storage unit can save the contents of the loaded contract to a NoSQL database. For example, the storage unit can extract the clauses and conditions of the contract and register them in the database. Furthermore, the storage unit can optimize the database structure to centrally manage the contents of the contracts. For example, the storage unit can create indexes to efficiently search the contents of the contracts. This enables centralized management of the contents of the contracts. Some or all of the above processes in the storage unit may be performed using AI, for example, or not using AI. For example, the storage unit can input the contents of the loaded contract to a generating AI and have the generating AI perform the saving to the database.

[0077] The review department can check whether the clauses of a new contract are consistent with or unaffected by past contracts. For example, the review department can check whether the clauses of a new contract are consistent with past contracts. The review department can also assess the risks inherent in a new contract. For example, the review department can analyze the risks inherent in the contract clauses and assess the importance and impact of those risks. Furthermore, the review department can check whether the clauses of a new contract are consistent with past contracts. For example, the review department can assess the degree of consistency of the contract clauses and evaluate the probability of risk occurrence and the scope of its impact. This allows for efficient checking of risks in a new contract. Some or all of the above processes in the review department may be performed using AI, for example, or not. For example, the review department can input the clauses of a new contract into a generating AI and have the generating AI perform a comparison with past contracts.

[0078] The risk detection unit can detect risks hidden within the clauses of a contract and evaluate their importance and impact. For example, the risk detection unit can analyze the risks hidden within the clauses of a contract and evaluate their importance and impact. The risk detection unit can also evaluate the probability of a risk occurring and the scope of its impact. For example, the risk detection unit can evaluate the degree of agreement between the clauses of a contract and evaluate the probability of a risk occurring and the scope of its impact. Furthermore, the risk detection unit can classify the risks hidden within the clauses of a contract and evaluate their importance and impact. For example, the risk detection unit can classify risks such as legal risks, financial risks, and operational risks and evaluate the importance and impact of each risk. This allows for the efficient detection and evaluation of risks in a contract. Some or all of the above processing in the risk detection unit may be performed using AI, for example, or without AI. For example, the risk detection unit can input the clauses of a contract into a generating AI and have the generating AI perform risk detection and evaluation.

[0079] The proposal department can provide points and areas for improvement in contract negotiations based on past contract history and current business conditions. For example, the proposal department can analyze past contract history and provide points and areas for improvement in contract negotiations tailored to current business conditions. The proposal department can also optimize the content of proposals to improve the efficiency and accuracy of contract negotiations. For example, the proposal department can provide proposals that are easy for users to understand by specifically outlining points and areas for improvement in contract negotiations. Furthermore, the proposal department can provide points and areas for improvement in contract negotiations in real time. For example, the proposal department can provide points and areas for improvement in contract negotiations in real time based on past contract history and current business conditions. This can improve the efficiency and accuracy of contract negotiations. Some or all of the above processing in the proposal department may be performed using AI, or not. For example, the proposal department can input past contract history and current business conditions into a generating AI and have the generating AI provide points and areas for improvement in contract negotiations.

[0080] The reading unit can estimate the user's emotions and adjust the timing of contract reading based on the estimated emotions. For example, if the user is stressed, the reading unit can delay the reading of the contract to allow the user to read it in a relaxed state. Conversely, if the user is focused, the reading unit can read the contract immediately. Furthermore, if the user is tired, the reading unit can postpone the reading of the contract until the next day. This allows for efficient reading by adjusting the timing of contract reading according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reading unit may be performed using AI or not. For example, the reading unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation and adjustment of reading timing.

[0081] The reading unit can determine the reading priority based on the type and importance of past contracts. For example, the reading unit can prioritize reading contracts of high importance. The reading unit can also change the reading order depending on the type of contract. Furthermore, the reading unit can prioritize reading urgent contracts. This allows for efficient reading based on the type and importance of contracts. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input data on the type and importance of contracts into a generating AI and have the generating AI determine the reading priority.

[0082] The reading unit can apply different reading algorithms depending on the format and language of the contract when reading it. For example, the reading unit can apply an English-specific reading algorithm to an English contract. It can also apply a PDF-specific reading algorithm to a PDF contract. Furthermore, the reading unit can apply a handwriting recognition algorithm to a handwritten contract. This allows for efficient reading according to the format and language of the contract. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input data on the format and language of the contract into a generating AI and have the generating AI execute the application of the reading algorithm.

[0083] The reading unit can estimate the user's emotions and determine the priority of contracts to read based on the estimated emotions. For example, if the user is relaxed, the reading unit will prioritize reading contracts of high importance. If the user is stressed, the reading unit can also prioritize reading simpler contracts. Furthermore, if the user is focused, the reading unit can also prioritize reading more complex contracts. This enables efficient reading by prioritizing contracts according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reading unit may be performed using AI or not. For example, the reading unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation and priority determination.

[0084] The reading unit can read contracts while considering the attribute information of the contract's creator and signatories. For example, the reading unit can prioritize reading contracts with important business partners. It can also prioritize reading contracts with many signatories. Furthermore, the reading unit can change the reading order according to the creator's position. This allows for efficient reading while considering the attribute information of the contract's creator and signatories. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input the attribute information of the contract's creator and signatories into a generating AI and have the generating AI determine the reading order.

[0085] The reading unit can simultaneously read related documents and reference materials when reading a contract. For example, the reading unit can simultaneously read legal documents related to the contract. It can also simultaneously read past contracts related to the contract. Furthermore, the reading unit can simultaneously read reference materials related to the contract. This enables efficient reading by simultaneously reading related documents and reference materials for the contract. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input data on related documents and reference materials for the contract into a generating AI and have the generating AI perform the processing of simultaneous reading.

[0086] The storage unit can estimate the user's emotions and select data to save based on the estimated emotions. For example, if the user is relaxed, the storage unit will prioritize saving high-importance data. If the user is stressed, the storage unit can also prioritize saving simple data. Furthermore, if the user is focused, the storage unit can prioritize saving complex data. This allows for efficient storage by selecting data to save according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation and data selection for saving.

[0087] The storage unit can determine the priority of saved data based on the importance and risk assessment of the contracts during the saving process. For example, the storage unit can prioritize saving contracts of high importance. It can also prioritize saving contracts with high risk assessments. Furthermore, it can prioritize saving urgent contracts. This allows for efficient saving based on the importance and risk assessment of contracts. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input data on the importance and risk assessment of contracts into a generating AI and have the generating AI determine the priority of the saved data.

[0088] The storage unit can apply different storage algorithms depending on the format and language of the contract during storage. For example, the storage unit can apply an English-specific storage algorithm to English contracts. It can also apply a PDF-specific storage algorithm to PDF contracts. Furthermore, the storage unit can apply a handwriting recognition algorithm to handwritten contracts. This allows for efficient storage according to the format and language of the contract. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input data on the format and language of the contract into a generating AI and have the generating AI execute the application of the storage algorithm.

[0089] The storage unit can estimate the user's emotions and determine the priority of data to save based on the estimated emotions. For example, if the user is relaxed, the storage unit will prioritize saving high-importance data. If the user is stressed, the storage unit may also prioritize saving simple data. Furthermore, if the user is focused, the storage unit may prioritize saving complex data. This enables efficient storage by prioritizing data to save according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation and determine the priority of data to save.

[0090] The storage unit can save contracts while considering the attribute information of the creator and signatories. For example, the storage unit can prioritize saving contracts of important business partners. It can also prioritize saving contracts with many signatories. Furthermore, the storage unit can change the saving order according to the creator's position. This allows for efficient saving while considering the attribute information of the creator and signatories of contracts. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input the attribute information of the creator and signatories of contracts into a generating AI and have the generating AI determine the saving order.

[0091] The storage unit can simultaneously store related documents and reference materials for a contract at the time of storage. For example, the storage unit can simultaneously store legal documents related to the contract. The storage unit can also simultaneously store past contracts related to the contract. Furthermore, the storage unit can simultaneously store reference materials related to the contract. This enables efficient storage by simultaneously storing related documents and reference materials for the contract. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input data on related documents and reference materials for the contract into a generating AI and have the generating AI perform the process of simultaneously storing the data.

[0092] The review unit can estimate the user's emotions and adjust the review criteria based on the estimated emotions. For example, if the user is relaxed, the review unit can perform a detailed review. If the user is stressed, the review unit can perform a simpler review. Furthermore, if the user is focused, the review unit can prioritize reviewing complex contracts. This allows for efficient review by adjusting the review criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the review unit may be performed using AI or not. For example, the review unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation and adjustment of review criteria.

[0093] The review department can determine the priority of the review based on the importance and risk assessment of the contract clauses during the review process. For example, the review department may prioritize reviewing clauses of high importance. It may also prioritize reviewing clauses with high risk assessments. Furthermore, it may prioritize reviewing clauses of urgency. This allows for efficient review based on the importance and risk assessment of the contract clauses. Some or all of the above processes in the review department may be performed using AI, for example, or not. For example, the review department can input data on the importance and risk assessment of the contract clauses into a generating AI and have the generating AI determine the review priority.

[0094] The review unit can apply different review algorithms depending on the format and language of the contract during the review process. For example, the review unit can apply an English-specific review algorithm to English-language contracts. It can also apply a PDF-specific review algorithm to PDF-formatted contracts. Furthermore, the review unit can apply a handwriting recognition algorithm to handwritten contracts. This allows for efficient review according to the format and language of the contract. Some or all of the above processes in the review unit may be performed using AI, for example, or without AI. For example, the review unit can input data on the format and language of the contract into a generating AI and have the generating AI execute the application of the review algorithm.

[0095] The analysis unit can estimate the user's emotions and adjust the order in which the analysis results are displayed based on the estimated emotions. For example, if the user is relaxed, the analysis unit can prioritize displaying results of high importance. It can also prioritize displaying simpler results if the user is stressed. Furthermore, if the user is focused, it can prioritize displaying more complex results. This allows for efficient display of analysis results by adjusting the order in which the results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation and adjust the order in which the results are displayed.

[0096] The review unit can perform its review while considering the attribute information of the contract's creator and signatories. For example, the review unit can prioritize reviewing contracts with important business partners. It can also prioritize reviewing contracts with a large number of signatories. Furthermore, the review unit can change the review order according to the creator's position. This allows for efficient review while considering the attribute information of the contract's creator and signatories. Some or all of the above processes in the review unit may be performed using AI, for example, or not using AI. For example, the review unit can input the attribute information of the contract's creator and signatories into a generating AI and have the generating AI determine the review order.

[0097] The review unit can improve the accuracy of its review by referring to relevant documents and reference materials related to the contract during the review process. For example, the review unit may refer to legal documents related to the contract during the review. The review unit may also refer to past contracts related to the contract during the review. Furthermore, the review unit may also refer to reference materials related to the contract during the review. This improves the accuracy of the review by referring to relevant documents and reference materials related to the contract during the review. Some or all of the above processes in the review unit may be performed using AI, for example, or not using AI. For example, the review unit may input data on relevant documents and reference materials related to the contract into a generating AI and have the generating AI perform the task of improving the accuracy of the review.

[0098] The risk detection unit can estimate the user's emotions and adjust the risk detection criteria based on the estimated emotions. For example, if the user is relaxed, the risk detection unit can perform detailed risk detection. If the user is stressed, the risk detection unit can also perform simpler risk detection. Furthermore, if the user is focused, the risk detection unit can prioritize the detection of complex risks. This allows for efficient risk detection by adjusting the risk detection criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the risk detection unit may be performed using AI, or not using AI. For example, the risk detection unit can input user emotion data into the generative AI and have the generative AI perform emotion estimation and adjustment of risk detection criteria.

[0099] The risk detection unit can determine the priority of risks based on the importance of the contract clauses and the risk assessment when detecting risks. For example, the risk detection unit can prioritize the detection of risks with high importance. It can also prioritize the detection of risks with high risk assessments. Furthermore, the risk detection unit can prioritize the detection of urgent risks. This allows for efficient risk detection based on the importance of the contract clauses and the risk assessment. Some or all of the above processing in the risk detection unit may be performed using AI, for example, or without AI. For example, the risk detection unit can input data on the importance of the contract clauses and the risk assessment into a generating AI and have the generating AI perform the determination of risk priorities.

[0100] The risk detection unit can apply different risk detection algorithms depending on the format and language of the contract when detecting a risk. For example, the risk detection unit can apply an English-specific risk detection algorithm to an English-language contract. It can also apply a PDF-specific risk detection algorithm to a PDF-formatted contract. Furthermore, it can apply a handwriting recognition algorithm to a handwritten contract. This allows for efficient risk detection according to the format and language of the contract. Some or all of the above-described processes in the risk detection unit may be performed using AI, for example, or without AI. For example, the risk detection unit can input data on the contract format and language into a generating AI and have the generating AI execute the application of the risk detection algorithm.

[0101] The risk detection unit can estimate the user's emotions and adjust the way risks are displayed based on the estimated emotions. For example, if the user is relaxed, the risk detection unit can display detailed risk information. If the user is stressed, the risk detection unit can also display simplified risk information. Furthermore, if the user is focused, the risk detection unit can prioritize displaying complex risk information. This allows for efficient risk display by adjusting the way risks are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the risk detection unit may be performed using AI, or not using AI. For example, the risk detection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation and adjustment of the risk display method.

[0102] The risk detection unit can detect risks by considering the attribute information of the contract's creator and signatories. For example, the risk detection unit can prioritize detecting risks in contracts with important business partners. It can also prioritize detecting risks in contracts with many signatories. Furthermore, the risk detection unit can change the order of risk detection according to the creator's position. This allows for efficient risk detection by considering the attribute information of the contract's creator and signatories. Some or all of the above processing in the risk detection unit may be performed using AI, for example, or without AI. For example, the risk detection unit can input the attribute information of the contract's creator and signatories into a generating AI and have the generating AI perform risk detection.

[0103] The risk detection unit can improve the accuracy of risk detection by referring to relevant documents and reference materials related to the contract when detecting risks. For example, the risk detection unit can detect risks by referring to legal documents related to the contract. The risk detection unit can also detect risks by referring to past contracts related to the contract. Furthermore, the risk detection unit can detect risks by referring to reference materials related to the contract. This improves the accuracy of risk detection by referring to relevant documents and reference materials related to the contract. Some or all of the above processing in the risk detection unit may be performed using AI, for example, or without AI. For example, the risk detection unit can input data on relevant documents and reference materials related to the contract into a generating AI and have the generating AI perform the risk accuracy improvement.

[0104] The suggestion unit can estimate the user's emotions and adjust the way suggestions are presented based on those emotions. For example, if the user is relaxed, the suggestion unit can provide detailed suggestions. If the user is stressed, the suggestion unit can provide simpler suggestions. Furthermore, if the user is focused, the suggestion unit can prioritize providing more complex suggestions. This allows for efficient suggestions by adjusting the presentation of suggestions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation and adjust the presentation of suggestions.

[0105] The proposal department can determine the priority of proposals based on the importance and risk assessment of the contract clauses when making a proposal. For example, the proposal department may prioritize proposals concerning clauses of high importance. It may also prioritize proposals concerning clauses with high risk assessments. Furthermore, it may prioritize proposals concerning clauses of urgency. This allows for efficient proposals based on the importance and risk assessment of the contract clauses. Some or all of the above processes in the proposal department may be performed using AI, for example, or not. For example, the proposal department can input data on the importance and risk assessment of contract clauses into a generating AI and have the generating AI determine the priority of proposals.

[0106] The proposal unit can apply different proposal algorithms depending on the format and language of the contract when making a proposal. For example, the proposal unit can apply an English-specific proposal algorithm to an English contract. It can also apply a PDF-specific proposal algorithm to a PDF contract. Furthermore, the proposal unit can apply a handwriting recognition algorithm to a handwritten contract. This allows for efficient proposal generation according to the format and language of the contract. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input data on the format and language of the contract into a generating AI and have the generating AI execute the application of the proposal algorithm.

[0107] The suggestion unit can estimate the user's emotions and adjust the length of suggestions based on the estimated emotions. For example, if the user is relaxed, the suggestion unit can provide detailed suggestions. If the user is stressed, the suggestion unit can provide simpler suggestions. Furthermore, if the user is focused, the suggestion unit can prioritize providing more complex suggestions. This allows for efficient suggestions by adjusting the length of suggestions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation and suggestion length adjustment.

[0108] The proposal department can make proposals while considering the attribute information of the contract's creators and signatories. For example, the proposal department can prioritize proposals for contracts with important business partners. It can also prioritize proposals for contracts with many signatories. Furthermore, the proposal department can change the order of proposals according to the creator's position. This allows for efficient proposals while considering the attribute information of the contract's creators and signatories. Some or all of the above processing in the proposal department may be performed using AI, for example, or not. For example, the proposal department can input the attribute information of the contract's creators and signatories into a generating AI and have the generating AI determine the order of proposals.

[0109] The proposal department can improve the accuracy of its proposals by referring to relevant documents and reference materials related to the contract. For example, the proposal department can make proposals by referring to legal documents related to the contract. It can also make proposals by referring to past contracts related to the contract. Furthermore, the proposal department can make proposals by referring to reference materials related to the contract. This improves the accuracy of proposals by referring to relevant documents and reference materials related to the contract. Some or all of the above processing in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input data on relevant documents and reference materials related to the contract into a generating AI and have the generating AI perform the improvement of proposal accuracy.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] ContractGuard allows you to prioritize the review of contract clauses based on their importance and risk assessment. For example, it can prioritize reviewing clauses with high importance, clauses with high risk, and clauses with high urgency. This enables efficient review based on the importance and risk assessment of each clause.

[0112] ContractGuard can apply different reading algorithms depending on the format and language of the contract when reading it. For example, it can apply an English-specific reading algorithm to English contracts, a PDF-specific reading algorithm to PDF contracts, and a handwriting recognition algorithm to handwritten contracts. This allows for efficient reading of contracts according to their format and language.

[0113] ContractGuard can prioritize the storage of contract data based on the importance and risk assessment of each contract. For example, it can prioritize the storage of contracts with high importance. It can also prioritize the storage of contracts with high risk assessments. Furthermore, it can prioritize the storage of urgent contracts. This allows for efficient storage based on the importance and risk assessment of each contract.

[0114] ContractGuard can improve the accuracy of contract scrutiny by referring to relevant literature and reference materials. For example, it can refer to relevant legal documents during the scrutiny process. It can also refer to relevant past contracts. Furthermore, it can refer to relevant reference materials during the scrutiny process. As a result, the accuracy of the scrutiny process is improved by referring to relevant literature and reference materials.

[0115] ContractGuard can prioritize risks in contracts based on the importance of the contract clauses and the risk assessment. For example, it can prioritize detecting high-importance risks. It can also prioritize detecting risks with high risk assessments. Furthermore, it can prioritize detecting urgent risks. This allows for efficient risk detection based on the importance of the contract clauses and the risk assessment.

[0116] ContractGuard can estimate the user's emotions and adjust the timing of contract reading based on those emotions. For example, if the user is stressed, the contract reading can be delayed so that they can read it in a relaxed state. Conversely, if the user is focused, the contract can be read immediately. Furthermore, if the user is tired, the contract reading can be postponed until the next day. This allows for more efficient contract reading by adjusting the timing of contract reading according to the user's emotions.

[0117] ContractGuard can estimate the user's emotions and prioritize which contracts to read based on those emotions. For example, if the user is relaxed, it can prioritize reading high-priority contracts. If the user is stressed, it can prioritize reading simpler contracts first. Furthermore, if the user is focused, it can prioritize reading more complex contracts. This allows for more efficient contract reading by prioritizing contracts according to the user's emotions.

[0118] ContractGuard can estimate a user's emotions and select which data to save based on those emotions. For example, if a user is relaxed, it can prioritize saving high-priority data. If a user is stressed, it can save simpler data first. Furthermore, if a user is focused, it can prioritize saving complex data. This allows for efficient data storage by selecting data to save according to the user's emotions.

[0119] ContractGuard can estimate the user's emotions and adjust the review criteria based on those emotions. For example, if the user is relaxed, a detailed review can be performed. If the user is stressed, a simpler review can be performed. Furthermore, if the user is focused, the review of complex contracts can be prioritized. This allows for more efficient review by adjusting the review criteria according to the user's emotions.

[0120] ContractGuard can estimate a user's emotions and adjust risk detection criteria based on those emotions. For example, if a user is relaxed, it can perform detailed risk detection. If a user is stressed, it can perform simpler risk detection. Furthermore, if a user is focused, it can prioritize the detection of complex risks. This allows for efficient risk detection by adjusting risk detection criteria according to the user's emotions.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The reading unit reads past contracts. Past contracts include business contracts, employment contracts, service contracts, etc. The reading unit digitizes and reads past contracts concluded within the company using scanning technology. It can also directly read contracts submitted in digital format. Furthermore, it can read printed contracts using OCR technology. For example, a handwritten contract can be scanned with a high-resolution scanner and converted into text information using OCR technology. Digital contracts can be directly read if they are submitted in a specific file format. OCR technology recognizes printed characters with high accuracy and converts them into digital text. Step 2: The storage unit saves the contents of the loaded contract to a database. The database can include relational databases, NoSQL databases, etc. The storage unit extracts the clauses and conditions of the contract and registers them in the database. It can also optimize the database structure to centrally manage the contents of contracts. For example, it can create indexes to efficiently search for the contents of contracts. Step 3: The review department reviews the new contract by comparing its contents with those of the contract stored by the archiving department. The review is conducted based on criteria for the degree of clause agreement and risk assessment. For example, it checks whether the clauses of the new contract are consistent with the contents of the previous contract. It can also assess the risks inherent in the new contract. For example, it analyzes the risks inherent in the contract clauses and assesses the importance and impact of those risks. Step 4: The risk detection unit detects risks based on the content of the contract reviewed by the scrutiny unit. Risks include legal risks, financial risks, and operational risks. The risk detection unit analyzes the risks hidden in the contract clauses and evaluates the importance and impact of the risks. It can also evaluate the probability of the risks occurring and the scope of their impact. Step 5: The proposal team provides points and areas for improvement in contract negotiations based on the risks detected by the risk detection team. Proposals are based on suggested clause revisions and negotiation strategies. For example, they provide points and areas for improvement in contract negotiations based on past contract history and current business conditions. Furthermore, the content of the proposals can be optimized to improve the efficiency and accuracy of contract negotiations. For example, by specifically outlining points and areas for improvement in contract negotiations, the proposals can be made easy for users to understand.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the reading unit, storage unit, review unit, risk detection unit, and proposal unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the reading unit can read past contracts using the scanner or OCR technology of the smart device 14. The storage unit stores the contents of the read contracts in the database 24. The review unit reviews the contents of the contracts stored by the storage unit by comparing them with the new contracts. The risk detection unit detects risks based on the contents of the contracts reviewed by the review unit. The proposal unit provides points for contract negotiation and improvements based on the risks detected by the risk detection unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed 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 necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the reading unit, storage unit, review unit, risk detection unit, and proposal unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reading unit can read past contracts using the camera and OCR technology of the smart glasses 214. The storage unit stores the contents of the read contracts in the database 24. The review unit reviews the contents of the contracts stored by the storage unit by comparing them with the new contracts. The risk detection unit detects risks based on the contents of the contracts reviewed by the review unit. The proposal unit provides points for contract negotiation and improvements based on the risks detected by the risk detection unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, 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 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the reading unit, storage unit, review unit, risk detection unit, and proposal unit, is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the reading unit can read past contracts using the camera and OCR technology of the headset terminal 314. The storage unit stores the contents of the read contracts in the database 24. The review unit reviews the contents of the contracts stored by the storage unit by comparing them with the new contracts. The risk detection unit detects risks based on the contents of the contracts reviewed by the review unit. The proposal unit provides points for contract negotiation and improvements based on the risks detected by the risk detection unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 7, the 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.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed 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 necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the reading unit, storage unit, review unit, risk detection unit, and proposal unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the reading unit can read past contracts using the camera and OCR technology of the robot 414. The storage unit stores the contents of the read contracts in the database 24. The review unit reviews the contents of the contracts stored by the storage unit by comparing them with the new contracts. The risk detection unit detects risks based on the contents of the contracts reviewed by the review unit. The proposal unit provides points for contract negotiation and improvements based on the risks detected by the risk detection unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in 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 the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it 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 emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0186] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) A reading unit that reads past contracts, A storage unit that stores the contents of the contract read by the aforementioned reading unit in a database, A review unit that compares the contents of the contract stored by the aforementioned storage unit with the new contract and examines them, A risk detection unit that detects risks based on the contents of the contract examined by the aforementioned examination unit, The system includes a proposal unit that provides points for contract negotiation and areas for improvement based on the risks detected by the risk detection unit. A system characterized by the following features. (Note 2) The aforementioned reading unit, Review past contracts concluded within the company. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned storage unit is The contents of the loaded contract are saved to the database. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned inspection unit, Check whether the clauses in the new contract contradict the terms of the previous contract and whether there are any risks. The system described in Appendix 1, characterized by the features described herein. (Note 5) The risk detection unit, We detect risks hidden within contract clauses and assess the importance and impact of those risks. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned proposal section is, Based on past contract history and current business conditions, we provide key points and areas for improvement in contract negotiations. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reading unit, The system estimates the user's emotions and adjusts the timing of contract reading based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reading unit, When reviewing past contracts, prioritize them based on their type and importance. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reading unit, When reading contracts, different reading algorithms are applied depending on the format and language of the contract. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reading unit, It estimates the user's emotions and determines the priority of contracts to read based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reading unit, When reading contracts, the system takes into account the attribute information of the contract's creator and signatories. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reading unit, When reading a contract, simultaneously read related documents and reference materials. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned storage unit is The system estimates the user's emotions and selects data to store based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned storage unit is When saving data, the priority of the saved data is determined based on the importance and risk assessment of the contract. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned storage unit is When saving, different saving algorithms are applied depending on the format and language of the contract. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned storage unit is It estimates the user's emotions and determines the priority of data to store based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned storage unit is When saving, the system takes into account the attribute information of the contract's creator and signatories. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned storage unit is When saving, save related documents and reference materials for the contract at the same time. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned inspection unit, We estimate the user's emotions and adjust the scrutiny criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned inspection unit, During the review process, we determine the priority of the review based on the importance of the contract clauses and the risk assessment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned inspection unit, During the review process, different review algorithms are applied depending on the format and language of the contract. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned inspection unit, It estimates the user's sentiment and adjusts the order in which the analysis results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned inspection unit, During the review process, the attribute information of the contract's creator and signatories will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned inspection unit, During the review process, we improve the accuracy of the review by referring to relevant documents and reference materials related to the contract. The system described in Appendix 1, characterized by the features described herein. (Note 25) The risk detection unit, We estimate user sentiment and adjust risk detection criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The risk detection unit, When a risk is detected, the priority of the risk is determined based on the importance of the contract clauses and the risk assessment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The risk detection unit, When detecting risks, different risk detection algorithms are applied depending on the format and language of the contract. The system described in Appendix 1, characterized by the features described herein. (Note 28) The risk detection unit, It estimates the user's sentiment and adjusts how risks are displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The risk detection unit, When detecting risks, the attribute information of the contract's creators and signatories is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 30) The risk detection unit, When detecting risks, we improve the accuracy of risk detection by referring to relevant documents and reference materials in the contract. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned proposal section is, It estimates the user's emotions and adjusts the way suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned proposal section is, When making proposals, we determine the priority of each proposal based on the importance of the contract clauses and the risk assessment. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned proposal section is, When making a proposal, different proposal algorithms are applied depending on the contract format and language. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned proposal section is, It estimates the user's emotions and adjusts the length of the suggestion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned proposal section is, When making a proposal, we will take into account the attribute information of the contract's creator and signatories. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned proposal section is, When making a proposal, we will improve its accuracy by referring to relevant documents and reference materials related to the contract. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reading unit that reads past contracts, A storage unit that stores the contents of the contract read by the aforementioned reading unit in a database, A review unit that compares the contents of the contract stored by the aforementioned storage unit with the new contract and examines them, A risk detection unit that detects risks based on the contents of the contract examined by the aforementioned examination unit, The system includes a proposal unit that provides points for contract negotiation and areas for improvement based on the risks detected by the risk detection unit. A system characterized by the following features.

2. The aforementioned reading unit, Review past contracts concluded within the company. The system according to feature 1.

3. The aforementioned storage unit is The contents of the loaded contract are saved to the database. The system according to feature 1.

4. The aforementioned inspection unit, Check whether the clauses in the new contract contradict the terms of the previous contract and whether there are any risks. The system according to feature 1.

5. The risk detection unit, We detect risks hidden within contract clauses and assess the importance and impact of those risks. The system according to feature 1.

6. The aforementioned proposal section is, Based on past contract history and current business conditions, we provide key points and areas for improvement in contract negotiations. The system according to feature 1.

7. The aforementioned reading unit, The system estimates the user's emotions and adjusts the timing of contract reading based on those estimated emotions. The system according to feature 1.

8. The aforementioned reading unit, When reviewing past contracts, prioritize them based on their type and importance. The system according to feature 1.

9. The aforementioned reading unit, When reading contracts, different reading algorithms are applied depending on the format and language of the contract. The system according to feature 1.

10. The aforementioned reading unit, It estimates the user's emotions and determines the priority of contracts to read based on those estimated emotions. The system according to feature 1.

Images