system

Abstract

The system according to this embodiment aims to automatically detect inconsistencies and misconfigurations in documents related to agency agreements, and to quickly identify and resolve problems. [Solution] The system according to the embodiment comprises an analysis unit, a detection unit, and a report generation unit. The analysis unit analyzes a document. The detection unit detects inconsistencies and misconfigurations from the data analyzed by the analysis unit. The report generation unit generates a visual report based on the inconsistencies and misconfigurations detected by the detection unit.

Description

Technical Field

[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, and includes 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, it is difficult to manually detect inconsistencies and misconfigurations in documents related to agency contracts, and there is a problem that it takes time and effort.

[0005] The system according to the embodiment aims to automatically detect inconsistencies and misconfigurations in documents related to agency contracts and quickly identify and solve problems.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a detection unit, and a report generation unit. The analysis unit analyzes a document. The detection unit detects inconsistencies and misconfigurations from the data analyzed by the analysis unit. The report generation unit generates a visual report based on the inconsistencies and misconfigurations detected by the detection unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically detect inconsistencies and misconfigurations in documents related to agency agreements, and quickly identify and resolve problems. [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 applicable 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 / F26. 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 / F26 are connected to the bus 34. The communication I / F26 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 receiving 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 receiving 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 contract management system according to an embodiment of the present invention is a system that analyzes documents related to agency agreements using multimodal AI and automatically detects inconsistencies and misconfigurations. The contract management system analyzes documents related to agency agreements, detects inconsistencies and misconfigurations, and generates a visually easy-to-understand report. For example, the contract management system analyzes documents such as contracts, commission details, and incentive setting documents. In this process, the AI ​​analyzes the contents of the documents in detail and understands the content of each item. For example, it analyzes the clauses of the contract, the amounts in the commission details, and the incentive setting conditions. This allows for an accurate understanding of the document's content. Next, the contract management system automatically detects inconsistencies and misconfigurations from the analyzed data. Based on the analyzed data, the AI ​​checks the contract details, commission calculations, incentive setting conditions, etc. For example, it checks whether the clauses of the contract and the amounts in the commission details match, and whether the incentive setting conditions are accurately reflected. This allows for the automatic detection of inconsistencies and misconfigurations. Finally, the contract management system generates a visually easy-to-understand report. The AI ​​generates a visually easy-to-understand report based on the detected inconsistencies and misconfigurations. For example, outliers and discrepancies can be displayed in graphs and dashboards, allowing personnel to quickly identify problems. This enables agency personnel to quickly understand and resolve issues. This reduces the risk of incorrect or unpaid commissions and alleviates the burden of verification work. It also makes it easier to grasp the overall picture, which can be scattered, and improves operational efficiency. For example, personnel in the agency management department who are spending a lot of time on commission calculations and contract management can improve the efficiency of their work by using this system. Furthermore, with the advancement of digital transformation, the demand for contract management and automation tools is increasing, making this system extremely useful. For example, thousands of professionals in a domestic telecommunications carrier and its agency network can improve operational efficiency by using this system. In this way, the contract content analysis service utilizing multimodal AI reduces the risk of incorrect or unpaid commissions in agency management, alleviates the burden of verification work, and improves operational efficiency.This allows the contract management system to analyze documents related to agency agreements, detect inconsistencies and misconfigurations, and generate visually easy-to-understand reports.

[0029] The contract management system according to this embodiment comprises an analysis unit, a detection unit, and a report generation unit. The analysis unit analyzes documents. The analysis unit analyzes documents such as contracts, fee statements, and incentive setting documents. The analysis unit analyzes the contents of the documents in detail and understands the contents of each item. For example, the analysis unit analyzes the clauses of the contract, the amounts in the fee statements, and the incentive setting conditions. This allows for an accurate understanding of the contents of the documents. The detection unit detects inconsistencies and misconfigurations from the data analyzed by the analysis unit. The detection unit checks, for example, the contract details, fee calculations, and incentive setting conditions. For example, the detection unit verifies whether the clauses of the contract and the amounts in the fee statements match, and whether the incentive setting conditions are accurately reflected. This allows for the automatic detection of inconsistencies and misconfigurations. The report generation unit generates a visual report based on the inconsistencies and misconfigurations detected by the detection unit. The report generation unit displays anomalies and inconsistencies, for example, in graphs and dashboards. The report generation unit generates a visual report so that the person in charge can quickly identify the problem. This enables the contract management system to analyze documents, detect inconsistencies and misconfigurations, and generate visual reports. Some or all of the above processes in the analysis unit, detection unit, and report generation unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input documents such as contracts, fee statements, and incentive setting documents into the generation AI and have the generation AI perform analysis of the document content. The detection unit can input the data analyzed by the analysis unit into the generation AI and have the generation AI perform detection of inconsistencies and misconfigurations. The report generation unit can have the generation AI generate a visual report based on the inconsistencies and misconfigurations detected by the detection unit.

[0030] The analysis unit analyzes documents. For example, it analyzes documents such as contracts, fee statements, and incentive setting documents. The analysis unit analyzes the document content in detail, understanding the content of each item. Specifically, the analysis unit uses natural language processing technology to analyze the document text and extract contract clauses, fee statement amounts, and incentive setting conditions. For example, regarding contract clauses, it identifies the headings and content of each clause and understands the relationships between clauses. Regarding fee statements, it analyzes the amounts and calculation methods of each item to perform accurate fee calculations. Regarding incentive setting documents, it analyzes the setting conditions, target recipients, and payment amounts to clarify the conditions for applying incentives. This allows the analysis unit to accurately understand the document content and provide the data necessary for subsequent processing. Furthermore, the analysis unit can improve analysis accuracy by utilizing past document data as training data. For example, by analyzing past contracts and fee statements and learning common patterns and outliers, it can improve the analysis accuracy of new documents. Furthermore, the analysis unit is independent of the document format and language, and can handle multilingual documents and documents in different formats. This allows the analysis unit to efficiently analyze various types of documents, improving the overall flexibility and versatility of the system.

[0031] The detection unit detects inconsistencies and misconfigurations from the data analyzed by the analysis unit. For example, the detection unit checks contract details, fee calculations, and incentive setting conditions. Specifically, it verifies whether the contract clauses and fee details match, and whether the incentive setting conditions are accurately reflected. For instance, it verifies whether the fee rate stated in the contract clauses matches the amount stated in the fee details, and issues a warning if they differ. It also verifies whether the incentive setting conditions described in the setting documents accurately reflect the actual data, and reports any discrepancies. By automating these checks, the detection unit prevents manual errors and efficiently detects inconsistencies and misconfigurations. Furthermore, the detection unit utilizes AI-based anomaly detection algorithms to detect unusual patterns and abnormal data. For example, it learns normal patterns based on past data and detects abnormal values ​​in new data. The detection unit also monitors data in real time and can immediately notify if an anomaly occurs. This allows the detection unit to quickly and accurately detect inconsistencies and misconfigurations, improving the overall reliability and security of the system.

[0032] The report generation unit generates visual reports based on the inconsistencies and misconfigurations detected by the detection unit. For example, the report generation unit displays anomalies and inconsistencies using graphs and dashboards. Specifically, the report generation unit uses various graph formats such as bar graphs, pie charts, and heatmaps to visually display detected inconsistencies and misconfigurations in an easy-to-understand manner. For example, inconsistencies between contract clauses and fee details are displayed using a bar graph, allowing users to see at a glance which items are inconsistent. Similarly, for misconfigurations of incentive setting conditions, a pie chart is used to visually display the application status of each condition, identifying problematic conditions. Furthermore, the report generation unit uses a dashboard to consolidate multiple graphs and charts onto a single screen, enabling users to quickly identify problems. The dashboard displays data updated in real time, allowing users to always stay informed of the latest situation. By generating these visual reports, the report generation unit provides users with the information necessary to quickly identify problems and take appropriate action. Additionally, the report generation unit has a function to export generated reports in formats such as PDF and Excel, making it easy for users to share and save reports. This allows the report generation unit to improve the overall transparency and efficiency of the system through visual reports.

[0033] The analysis unit can analyze documents such as contracts, fee statements, and incentive setting documents. For example, the analysis unit analyzes documents such as contracts, fee statements, and incentive setting documents. The analysis unit analyzes the content of the documents in detail and understands the content of each item. For example, the analysis unit analyzes the clauses of the contract, the amounts in the fee statements, and the conditions for setting incentives. This allows for an accurate understanding of the document's content. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input documents such as contracts, fee statements, and incentive setting documents into a generating AI and have the generating AI perform the analysis of the document's content.

[0034] The detection unit can check contract details, fee calculations, incentive setting conditions, etc. For example, the detection unit checks contract details, fee calculations, incentive setting conditions, etc. The detection unit verifies whether the contract clauses and the fee details match, and whether the incentive setting conditions are accurately reflected. This allows for the automatic detection of discrepancies and missettings. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input data analyzed by the analysis unit into a generation AI, and have the generation AI perform the detection of discrepancies and missettings.

[0035] The report generation unit can display anomalies and inconsistencies in graphs and dashboards. For example, the report generation unit displays anomalies and inconsistencies in graphs and dashboards. The report generation unit generates visual reports to enable personnel to quickly identify problems. This allows anomalies and inconsistencies to be displayed in graphs and dashboards. Some or all of the above-described processes in the report generation unit may be performed using AI, for example, or without AI. For example, the report generation unit can have a generating AI generate a visual report based on inconsistencies and misconfigurations detected by the detection unit.

[0036] The report generation unit can generate visual reports to enable personnel to quickly identify problems. For example, the report generation unit can generate visual reports to enable personnel to quickly identify problems. The report generation unit displays anomalies and inconsistencies in graphs and dashboards. This enables the generation of visual reports to enable personnel to quickly identify problems. Some or all of the above-described processes in the report generation unit may be performed using AI, for example, or without AI. For example, the report generation unit can cause a generating AI to generate a visual report based on inconsistencies and misconfigurations detected by the detection unit.

[0037] The analysis unit can analyze the contents of a document in detail and understand the content of each item. For example, the analysis unit can analyze the contents of a document in detail and understand the content of each item. The analysis unit analyzes the clauses of a contract, the amounts of fee details, the conditions for setting incentives, etc. This allows for an accurate understanding of the contents of the document. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input documents such as contracts, fee details, and incentive setting documents into a generating AI and have the generating AI perform the analysis of the document contents.

[0038] The analysis unit can optimize the analysis algorithm by referring to past analysis results. For example, the analysis unit adjusts the analysis algorithm for a specific document format based on past analysis results. The analysis unit learns frequently occurring errors from past analysis results and improves the algorithm. The analysis unit analyzes past analysis results and improves the analysis accuracy for specific patterns. This allows the analysis algorithm to be optimized by referring to past analysis results. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past analysis results into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0039] The analysis unit can apply different analysis methods depending on the type of document. For example, the analysis unit applies a clause analysis algorithm to contracts. For fee details, it applies a numerical analysis algorithm. For incentive setting documents, it applies a condition analysis algorithm. This allows different analysis methods to be applied depending on the type of document. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can have a generating AI execute different analysis methods depending on the type of document.

[0040] The analysis unit can adjust the order of analysis based on the submission date of the documents. For example, the analysis unit may prioritize the analysis of recently submitted documents. The analysis unit may prioritize the analysis of documents with approaching submission deadlines. The analysis unit may postpone the analysis of older documents. This allows the order of analysis to be adjusted based on the submission date of the documents. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit may have a generating AI execute the analysis order based on the submission date of the documents.

[0041] The analysis unit can adjust the level of detail of the analysis based on the relevance of the documents. For example, the analysis unit will analyze important contracts in detail. The analysis unit will analyze fee details at a normal level of detail. The analysis unit will analyze incentive setting documents in a simplified manner. This allows the level of detail of the analysis to be adjusted based on the relevance of the documents. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can have a generating AI perform the level of detail of the analysis based on the relevance of the documents.

[0042] The detection unit can optimize its detection algorithm by referring to past detection results. For example, the detection unit can learn specific error patterns based on past detection results and improve its algorithm. The detection unit can identify frequently occurring discrepancies from past detection results and improve detection accuracy. The detection unit can analyze past detection results and improve detection accuracy under specific conditions. This allows the detection algorithm to be optimized by referring to past detection results. Some or all of the above processes in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input past detection results into a generating AI and have the generating AI perform the optimization of the detection algorithm.

[0043] The detection unit can apply different detection methods depending on the type of document. For example, the detection unit applies a method to detect clause matches to contracts. For fee statements, it applies a method to detect numerical matches. For incentive setting documents, it applies a method to detect condition matches. This allows different detection methods to be applied depending on the type of document. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can cause a generating AI to execute different detection methods depending on the type of document.

[0044] The detection unit can determine the detection priority based on the submission date of the documents. For example, the detection unit prioritizes detecting discrepancies in recently submitted documents. The detection unit prioritizes detecting discrepancies in documents with approaching submission deadlines. The detection unit postpones detecting discrepancies in older documents. This allows the detection priority to be determined based on the submission date of the documents. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can have a generating AI perform detection prioritization based on the submission date of the documents.

[0045] The detection unit can adjust the level of detail of the detection based on the relevance of the documents. For example, the detection unit will detect inconsistencies in important contracts with detail. The detection unit will detect inconsistencies in fee details with normal detail. The detection unit will detect inconsistencies in incentive setting documents with simplified detail. This allows the level of detail of the detection to be adjusted based on the relevance of the documents. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can have a generating AI perform the level of detail of the detection based on the relevance of the documents.

[0046] The report generation unit can optimize its report generation algorithm by referring to past report results. For example, the report generation unit adjusts the generation algorithm for a specific format based on past report results. The report generation unit learns frequently occurring errors from past report results and improves the algorithm. The report generation unit analyzes past report results and improves the generation accuracy for specific patterns. This allows the report generation algorithm to be optimized by referring to past report results. Some or all of the above processes in the report generation unit may be performed using AI, for example, or without AI. For example, the report generation unit can input past report results into a generation AI and have the generation AI perform the optimization of the report generation algorithm.

[0047] The report generation unit can apply different report generation methods depending on the type of document. For example, the report generation unit can generate a report that emphasizes the matching of clauses for contracts, a report that emphasizes the matching of numerical values ​​for fee details, and a report that emphasizes the matching of conditions for incentive setting documents. This allows for the application of different report generation methods depending on the type of document. Some or all of the above-described processes in the report generation unit may be performed using AI, for example, or without AI. For example, the report generation unit can cause the generating AI to execute different report generation methods depending on the type of document.

[0048] The report generation unit can adjust the order of reports based on the submission date of the documents. For example, the report generation unit prioritizes reporting discrepancies in recently submitted documents. The report generation unit prioritizes reporting discrepancies in documents with approaching submission deadlines. The report generation unit postpones reporting discrepancies in older documents. This allows the order of reports to be adjusted based on the submission date of the documents. Some or all of the above processing in the report generation unit may be performed using AI, for example, or without AI. For example, the report generation unit can have a generation AI execute the order of reports based on the submission date of the documents.

[0049] The report generation unit can adjust the level of detail in the report based on the relevance of the documents. For example, the report generation unit will report in detail discrepancies in important contracts. The report generation unit will report inconsistencies in fee details with normal detail. The report generation unit will report inconsistencies in incentive setting documents with simplified detail. This allows the level of detail in the report to be adjusted based on the relevance of the documents. Some or all of the above processing in the report generation unit may be performed using AI, for example, or not using AI. For example, the report generation unit can have the generating AI adjust the level of detail in the report based on the relevance of the documents.

[0050] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0051] The contract management system can also include a notification unit. The notification unit can provide real-time notifications to responsible personnel based on inconsistencies or misconfigurations detected by the detection unit. For example, the notification unit can instantly send alerts to responsible personnel via email, SMS, or in-app notifications, allowing them to address issues quickly. The notification unit can also prioritize notifications, providing immediate notifications for high-priority issues and periodic reports for lower-priority issues. Furthermore, the notification unit can save a history of notifications, allowing personnel to review past issues and implement preventative measures.

[0052] The contract management system can also include a learning unit. The learning unit can learn to improve the overall accuracy of the system based on the processing results of the analysis and detection units. For example, the learning unit analyzes past analysis and detection results to learn patterns of frequently occurring errors and discrepancies. This optimizes the algorithms of the analysis and detection units, improving the accuracy of future analysis and detection. The learning unit can also incorporate user feedback to improve the system. Furthermore, the learning unit can be customized to accommodate different industries and document formats. This allows the contract management system to be used for a wider range of applications.

[0053] The contract management system can also include a forecasting unit. Based on data from the analysis and detection units, the forecasting unit can predict the occurrence of future risks and problems. For example, the forecasting unit can analyze historical data and calculate the probability of a risk occurring under specific conditions. This allows personnel to understand risks in advance and take appropriate measures. The forecasting unit can also simulate the impact of changes to contract terms or new contracts to assess future risks. Furthermore, the forecasting unit can offer suggestions to prevent risks from occurring. This allows the contract management system to improve the accuracy of risk management.

[0054] The contract management system can also include a dashboard. The dashboard visually displays data from the analysis and detection sections, allowing personnel to grasp the situation at a glance. For example, the dashboard can display contract progress, the number of detected discrepancies, and important alerts in graphs and charts. This allows personnel to quickly identify problems and take corrective action. The dashboard can also provide customizable widgets, allowing personnel to freely arrange the information they need. Furthermore, the dashboard can update data in real time, providing the latest information. This allows the contract management system to improve the work efficiency of personnel.

[0055] The contract management system can also include an archiving section. This section stores past contract documents, analysis results, and discrepancy detection history, making them accessible as needed. For example, the archiving section digitally stores past contracts, fee statements, and incentive setting documents. This allows personnel to quickly search and refer to past documents. Furthermore, the archiving section can access past analysis results and detection history based on the stored data. In addition, the archiving section includes a data backup function to prevent data loss or corruption. This improves the data integrity of the contract management system.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The analysis unit analyzes the documents. The analysis unit analyzes documents such as contracts, fee statements, and incentive setting documents, and analyzes the contents of the documents in detail. For example, it analyzes the clauses of the contract, the amounts in the fee statements, and the conditions for setting incentives. Step 2: The detection unit detects inconsistencies and misconfigurations from the data analyzed by the analysis unit. The detection unit checks the contract details, fee calculations, and incentive setting conditions to confirm that the contract clauses and fee amounts match and that the incentive setting conditions are accurately reflected. Step 3: The report generation unit generates a visual report based on the inconsistencies and misconfigurations detected by the detection unit. The report generation unit displays anomalies and inconsistencies in graphs and dashboards, generating a visual report that allows the person in charge to quickly identify the problem.

[0058] (Example of form 2) The contract management system according to an embodiment of the present invention is a system that analyzes documents related to agency agreements using multimodal AI and automatically detects inconsistencies and misconfigurations. The contract management system analyzes documents related to agency agreements, detects inconsistencies and misconfigurations, and generates a visually easy-to-understand report. For example, the contract management system analyzes documents such as contracts, commission details, and incentive setting documents. In this process, the AI ​​analyzes the contents of the documents in detail and understands the content of each item. For example, it analyzes the clauses of the contract, the amounts in the commission details, and the incentive setting conditions. This allows for an accurate understanding of the document's content. Next, the contract management system automatically detects inconsistencies and misconfigurations from the analyzed data. Based on the analyzed data, the AI ​​checks the contract details, commission calculations, incentive setting conditions, etc. For example, it checks whether the clauses of the contract and the amounts in the commission details match, and whether the incentive setting conditions are accurately reflected. This allows for the automatic detection of inconsistencies and misconfigurations. Finally, the contract management system generates a visually easy-to-understand report. The AI ​​generates a visually easy-to-understand report based on the detected inconsistencies and misconfigurations. For example, outliers and discrepancies can be displayed in graphs and dashboards, allowing personnel to quickly identify problems. This enables agency personnel to quickly understand and resolve issues. This reduces the risk of incorrect or unpaid commissions and alleviates the burden of verification work. It also makes it easier to grasp the overall picture, which can be scattered, and improves operational efficiency. For example, personnel in the agency management department who are spending a lot of time on commission calculations and contract management can improve the efficiency of their work by using this system. Furthermore, with the advancement of digital transformation, the demand for contract management and automation tools is increasing, making this system extremely useful. For example, thousands of professionals in a domestic telecommunications carrier and its agency network can improve operational efficiency by using this system. In this way, the contract content analysis service utilizing multimodal AI reduces the risk of incorrect or unpaid commissions in agency management, alleviates the burden of verification work, and improves operational efficiency.This allows the contract management system to analyze documents related to agency agreements, detect inconsistencies and misconfigurations, and generate visually easy-to-understand reports.

[0059] The contract management system according to this embodiment comprises an analysis unit, a detection unit, and a report generation unit. The analysis unit analyzes documents. The analysis unit analyzes documents such as contracts, fee statements, and incentive setting documents. The analysis unit analyzes the contents of the documents in detail and understands the contents of each item. For example, the analysis unit analyzes the clauses of the contract, the amounts in the fee statements, and the incentive setting conditions. This allows for an accurate understanding of the contents of the documents. The detection unit detects inconsistencies and misconfigurations from the data analyzed by the analysis unit. The detection unit checks, for example, the contract details, fee calculations, and incentive setting conditions. For example, the detection unit verifies whether the clauses of the contract and the amounts in the fee statements match, and whether the incentive setting conditions are accurately reflected. This allows for the automatic detection of inconsistencies and misconfigurations. The report generation unit generates a visual report based on the inconsistencies and misconfigurations detected by the detection unit. The report generation unit displays anomalies and inconsistencies, for example, in graphs and dashboards. The report generation unit generates a visual report so that the person in charge can quickly identify the problem. This enables the contract management system to analyze documents, detect inconsistencies and misconfigurations, and generate visual reports. Some or all of the above processes in the analysis unit, detection unit, and report generation unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input documents such as contracts, fee statements, and incentive setting documents into the generation AI and have the generation AI perform analysis of the document content. The detection unit can input the data analyzed by the analysis unit into the generation AI and have the generation AI perform detection of inconsistencies and misconfigurations. The report generation unit can have the generation AI generate a visual report based on the inconsistencies and misconfigurations detected by the detection unit.

[0060] The analysis unit analyzes documents. For example, it analyzes documents such as contracts, fee statements, and incentive setting documents. The analysis unit analyzes the document content in detail, understanding the content of each item. Specifically, the analysis unit uses natural language processing technology to analyze the document text and extract contract clauses, fee statement amounts, and incentive setting conditions. For example, regarding contract clauses, it identifies the headings and content of each clause and understands the relationships between clauses. Regarding fee statements, it analyzes the amounts and calculation methods of each item to perform accurate fee calculations. Regarding incentive setting documents, it analyzes the setting conditions, target recipients, and payment amounts to clarify the conditions for applying incentives. This allows the analysis unit to accurately understand the document content and provide the data necessary for subsequent processing. Furthermore, the analysis unit can improve analysis accuracy by utilizing past document data as training data. For example, by analyzing past contracts and fee statements and learning common patterns and outliers, it can improve the analysis accuracy of new documents. Furthermore, the analysis unit is independent of the document format and language, and can handle multilingual documents and documents in different formats. This allows the analysis unit to efficiently analyze various types of documents, improving the overall flexibility and versatility of the system.

[0061] The detection unit detects inconsistencies and misconfigurations from the data analyzed by the analysis unit. For example, the detection unit checks contract details, fee calculations, and incentive setting conditions. Specifically, it verifies whether the contract clauses and fee details match, and whether the incentive setting conditions are accurately reflected. For instance, it verifies whether the fee rate stated in the contract clauses matches the amount stated in the fee details, and issues a warning if they differ. It also verifies whether the incentive setting conditions described in the setting documents accurately reflect the actual data, and reports any discrepancies. By automating these checks, the detection unit prevents manual errors and efficiently detects inconsistencies and misconfigurations. Furthermore, the detection unit utilizes AI-based anomaly detection algorithms to detect unusual patterns and abnormal data. For example, it learns normal patterns based on past data and detects abnormal values ​​in new data. The detection unit also monitors data in real time and can immediately notify if an anomaly occurs. This allows the detection unit to quickly and accurately detect inconsistencies and misconfigurations, improving the overall reliability and security of the system.

[0062] The report generation unit generates visual reports based on the inconsistencies and misconfigurations detected by the detection unit. For example, the report generation unit displays anomalies and inconsistencies using graphs and dashboards. Specifically, the report generation unit uses various graph formats such as bar graphs, pie charts, and heatmaps to visually display detected inconsistencies and misconfigurations in an easy-to-understand manner. For example, inconsistencies between contract clauses and fee details are displayed using a bar graph, allowing users to see at a glance which items are inconsistent. Similarly, for misconfigurations of incentive setting conditions, a pie chart is used to visually display the application status of each condition, identifying problematic conditions. Furthermore, the report generation unit uses a dashboard to consolidate multiple graphs and charts onto a single screen, enabling users to quickly identify problems. The dashboard displays data updated in real time, allowing users to always stay informed of the latest situation. By generating these visual reports, the report generation unit provides users with the information necessary to quickly identify problems and take appropriate action. Additionally, the report generation unit has a function to export generated reports in formats such as PDF and Excel, making it easy for users to share and save reports. This allows the report generation unit to improve the overall transparency and efficiency of the system through visual reports.

[0063] The analysis unit can analyze documents such as contracts, fee statements, and incentive setting documents. For example, the analysis unit analyzes documents such as contracts, fee statements, and incentive setting documents. The analysis unit analyzes the content of the documents in detail and understands the content of each item. For example, the analysis unit analyzes the clauses of the contract, the amounts in the fee statements, and the conditions for setting incentives. This allows for an accurate understanding of the document's content. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input documents such as contracts, fee statements, and incentive setting documents into a generating AI and have the generating AI perform the analysis of the document's content.

[0064] The detection unit can check contract details, fee calculations, incentive setting conditions, etc. For example, the detection unit checks contract details, fee calculations, incentive setting conditions, etc. The detection unit verifies whether the contract clauses and the fee details match, and whether the incentive setting conditions are accurately reflected. This allows for the automatic detection of discrepancies and missettings. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input data analyzed by the analysis unit into a generation AI, and have the generation AI perform the detection of discrepancies and missettings.

[0065] The report generation unit can display anomalies and inconsistencies in graphs and dashboards. For example, the report generation unit displays anomalies and inconsistencies in graphs and dashboards. The report generation unit generates visual reports to enable personnel to quickly identify problems. This allows anomalies and inconsistencies to be displayed in graphs and dashboards. Some or all of the above-described processes in the report generation unit may be performed using AI, for example, or without AI. For example, the report generation unit can have a generating AI generate a visual report based on inconsistencies and misconfigurations detected by the detection unit.

[0066] The report generation unit can generate visual reports to enable personnel to quickly identify problems. For example, the report generation unit can generate visual reports to enable personnel to quickly identify problems. The report generation unit displays anomalies and inconsistencies in graphs and dashboards. This enables the generation of visual reports to enable personnel to quickly identify problems. Some or all of the above-described processes in the report generation unit may be performed using AI, for example, or without AI. For example, the report generation unit can cause a generating AI to generate a visual report based on inconsistencies and misconfigurations detected by the detection unit.

[0067] The analysis unit can analyze the contents of a document in detail and understand the content of each item. For example, the analysis unit can analyze the contents of a document in detail and understand the content of each item. The analysis unit analyzes the clauses of a contract, the amounts of fee details, the conditions for setting incentives, etc. This allows for an accurate understanding of the contents of the document. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input documents such as contracts, fee details, and incentive setting documents into a generating AI and have the generating AI perform the analysis of the document contents.

[0068] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the user is stressed, the analysis unit increases the accuracy of the analysis to reduce false positives. If the user is relaxed, the analysis unit maintains normal accuracy and prioritizes processing speed. If the user is in a hurry, the analysis unit slightly reduces the accuracy of the analysis to maximize processing speed. This allows the accuracy of the analysis to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0069] The analysis unit can optimize the analysis algorithm by referring to past analysis results. For example, the analysis unit adjusts the analysis algorithm for a specific document format based on past analysis results. The analysis unit learns frequently occurring errors from past analysis results and improves the algorithm. The analysis unit analyzes past analysis results and improves the analysis accuracy for specific patterns. This allows the analysis algorithm to be optimized by referring to past analysis results. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past analysis results into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0070] The analysis unit can apply different analysis methods depending on the type of document. For example, the analysis unit applies a clause analysis algorithm to contracts. For fee details, it applies a numerical analysis algorithm. For incentive setting documents, it applies a condition analysis algorithm. This allows different analysis methods to be applied depending on the type of document. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can have a generating AI execute different analysis methods depending on the type of document.

[0071] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, if the user is stressed, the analysis unit will prioritize the analysis of important documents. If the user is relaxed, the analysis unit will perform analysis with normal priorities. If the user is in a hurry, the analysis unit will prioritize the analysis of urgent documents. This allows the analysis priority to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0072] The analysis unit can adjust the order of analysis based on the submission date of the documents. For example, the analysis unit may prioritize the analysis of recently submitted documents. The analysis unit may prioritize the analysis of documents with approaching submission deadlines. The analysis unit may postpone the analysis of older documents. This allows the order of analysis to be adjusted based on the submission date of the documents. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit may have a generating AI execute the analysis order based on the submission date of the documents.

[0073] The analysis unit can adjust the level of detail of the analysis based on the relevance of the documents. For example, the analysis unit will analyze important contracts in detail. The analysis unit will analyze fee details at a normal level of detail. The analysis unit will analyze incentive setting documents in a simplified manner. This allows the level of detail of the analysis to be adjusted based on the relevance of the documents. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can have a generating AI perform the level of detail of the analysis based on the relevance of the documents.

[0074] The detection unit can estimate the user's emotions and adjust the detection criteria for mismatches and misconfigurations based on the estimated user emotions. For example, if the user is stressed, the detection unit applies strict detection criteria. If the user is relaxed, the detection unit applies normal detection criteria. If the user is in a hurry, the detection unit applies lenient detection criteria. This allows the detection criteria for mismatches and misconfigurations to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 detection unit may be performed using AI, for example, or not using AI. For example, the detection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0075] The detection unit can optimize its detection algorithm by referring to past detection results. For example, the detection unit can learn specific error patterns based on past detection results and improve its algorithm. The detection unit can identify frequently occurring discrepancies from past detection results and improve detection accuracy. The detection unit can analyze past detection results and improve detection accuracy under specific conditions. This allows the detection algorithm to be optimized by referring to past detection results. Some or all of the above processes in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input past detection results into a generating AI and have the generating AI perform the optimization of the detection algorithm.

[0076] The detection unit can apply different detection methods depending on the type of document. For example, the detection unit applies a method to detect clause matches to contracts. For fee statements, it applies a method to detect numerical matches. For incentive setting documents, it applies a method to detect condition matches. This allows different detection methods to be applied depending on the type of document. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can cause a generating AI to execute different detection methods depending on the type of document.

[0077] The detection unit can estimate the user's emotions and adjust the display order of the detection results based on the estimated user emotions. For example, if the user is stressed, the detection unit will prioritize displaying significant discrepancies. If the user is relaxed, the detection unit will display the results in the normal order. If the user is in a hurry, the detection unit will prioritize displaying highly urgent discrepancies. This allows the display order of the detection results to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 detection unit may be performed using AI, for example, or not using AI. For example, the detection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0078] The detection unit can determine the detection priority based on the submission date of the documents. For example, the detection unit prioritizes detecting discrepancies in recently submitted documents. The detection unit prioritizes detecting discrepancies in documents with approaching submission deadlines. The detection unit postpones detecting discrepancies in older documents. This allows the detection priority to be determined based on the submission date of the documents. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can have a generating AI perform detection prioritization based on the submission date of the documents.

[0079] The detection unit can adjust the level of detail of the detection based on the relevance of the documents. For example, the detection unit will detect inconsistencies in important contracts with detail. The detection unit will detect inconsistencies in fee details with normal detail. The detection unit will detect inconsistencies in incentive setting documents with simplified detail. This allows the level of detail of the detection to be adjusted based on the relevance of the documents. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can have a generating AI perform the level of detail of the detection based on the relevance of the documents.

[0080] The report generation unit can estimate the user's emotions and adjust the report display method based on the estimated user emotions. For example, if the user is tense, the report generation unit provides a simple and highly visible display method. If the user is relaxed, the report generation unit provides a display method that includes detailed information. If the user is in a hurry, the report generation unit provides a concise display method. This allows the report display method to be adjusted based on 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 report generation unit may be performed using AI, for example, or not using AI. For example, the report generation unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0081] The report generation unit can optimize its report generation algorithm by referring to past report results. For example, the report generation unit adjusts the generation algorithm for a specific format based on past report results. The report generation unit learns frequently occurring errors from past report results and improves the algorithm. The report generation unit analyzes past report results and improves the generation accuracy for specific patterns. This allows the report generation algorithm to be optimized by referring to past report results. Some or all of the above processes in the report generation unit may be performed using AI, for example, or without AI. For example, the report generation unit can input past report results into a generation AI and have the generation AI perform the optimization of the report generation algorithm.

[0082] The report generation unit can apply different report generation methods depending on the type of document. For example, the report generation unit can generate a report that emphasizes the matching of clauses for contracts, a report that emphasizes the matching of numerical values ​​for fee details, and a report that emphasizes the matching of conditions for incentive setting documents. This allows for the application of different report generation methods depending on the type of document. Some or all of the above-described processes in the report generation unit may be performed using AI, for example, or without AI. For example, the report generation unit can cause the generating AI to execute different report generation methods depending on the type of document.

[0083] The report generation unit can estimate the user's emotions and determine the priority of reports based on the estimated user emotions. For example, if the user is stressed, the report generation unit will prioritize reporting important discrepancies. If the user is relaxed, the report generation unit will report with normal priority. If the user is in a hurry, the report generation unit will prioritize reporting highly urgent discrepancies. This allows the report to be prioritized based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 report generation unit may be performed using AI or not using AI. For example, the report generation unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0084] The report generation unit can adjust the order of reports based on the submission date of the documents. For example, the report generation unit prioritizes reporting discrepancies in recently submitted documents. The report generation unit prioritizes reporting discrepancies in documents with approaching submission deadlines. The report generation unit postpones reporting discrepancies in older documents. This allows the order of reports to be adjusted based on the submission date of the documents. Some or all of the above processing in the report generation unit may be performed using AI, for example, or without AI. For example, the report generation unit can have a generation AI execute the order of reports based on the submission date of the documents.

[0085] The report generation unit can adjust the level of detail in the report based on the relevance of the documents. For example, the report generation unit will report in detail discrepancies in important contracts. The report generation unit will report inconsistencies in fee details with normal detail. The report generation unit will report inconsistencies in incentive setting documents with simplified detail. This allows the level of detail in the report to be adjusted based on the relevance of the documents. Some or all of the above processing in the report generation unit may be performed using AI, for example, or not using AI. For example, the report generation unit can have the generating AI adjust the level of detail in the report based on the relevance of the documents.

[0086] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0087] The contract management system can also include a notification unit. The notification unit can provide real-time notifications to responsible personnel based on inconsistencies or misconfigurations detected by the detection unit. For example, the notification unit can instantly send alerts to responsible personnel via email, SMS, or in-app notifications, allowing them to address issues quickly. The notification unit can also prioritize notifications, providing immediate notifications for high-priority issues and periodic reports for lower-priority issues. Furthermore, the notification unit can save a history of notifications, allowing personnel to review past issues and implement preventative measures.

[0088] The contract management system can also include a learning unit. The learning unit can learn to improve the overall accuracy of the system based on the processing results of the analysis and detection units. For example, the learning unit analyzes past analysis and detection results to learn patterns of frequently occurring errors and discrepancies. This optimizes the algorithms of the analysis and detection units, improving the accuracy of future analysis and detection. The learning unit can also incorporate user feedback to improve the system. Furthermore, the learning unit can be customized to accommodate different industries and document formats. This allows the contract management system to be used for a wider range of applications.

[0089] The contract management system can also include a forecasting unit. Based on data from the analysis and detection units, the forecasting unit can predict the occurrence of future risks and problems. For example, the forecasting unit can analyze historical data and calculate the probability of a risk occurring under specific conditions. This allows personnel to understand risks in advance and take appropriate measures. The forecasting unit can also simulate the impact of changes to contract terms or new contracts to assess future risks. Furthermore, the forecasting unit can offer suggestions to prevent risks from occurring. This allows the contract management system to improve the accuracy of risk management.

[0090] The contract management system can also include a dashboard. The dashboard visually displays data from the analysis and detection sections, allowing personnel to grasp the situation at a glance. For example, the dashboard can display contract progress, the number of detected discrepancies, and important alerts in graphs and charts. This allows personnel to quickly identify problems and take corrective action. The dashboard can also provide customizable widgets, allowing personnel to freely arrange the information they need. Furthermore, the dashboard can update data in real time, providing the latest information. This allows the contract management system to improve the work efficiency of personnel.

[0091] The contract management system can also include an archiving section. This section stores past contract documents, analysis results, and discrepancy detection history, making them accessible as needed. For example, the archiving section digitally stores past contracts, fee statements, and incentive setting documents. This allows personnel to quickly search and refer to past documents. Furthermore, the archiving section can access past analysis results and detection history based on the stored data. In addition, the archiving section includes a data backup function to prevent data loss or corruption. This improves the data integrity of the contract management system.

[0092] The contract management system allows the analysis unit to estimate the user's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the user is stressed, the analysis unit increases the accuracy of the analysis to reduce false positives. If the user is relaxed, the analysis unit maintains normal accuracy and prioritizes processing speed. If the user is in a hurry, the analysis unit slightly reduces the accuracy of the analysis to maximize processing speed. This allows the accuracy of the analysis to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 analysis unit may be performed using AI or not using AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0093] The contract management system has a detection unit that estimates the user's emotions and adjusts the detection criteria for discrepancies and misconfigurations based on the estimated user emotions. For example, the detection unit applies strict detection criteria when the user is stressed. The detection unit applies normal detection criteria when the user is relaxed. The detection unit applies lenient detection criteria when the user is in a hurry. This allows the detection criteria for discrepancies and misconfigurations to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 detection unit may be performed using AI or not using AI. For example, the detection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0094] The contract management system can have a report generation unit estimate the user's emotions and adjust the report display method based on the estimated emotions. For example, if the user is stressed, the report generation unit provides a simple and highly visible display method. If the user is relaxed, the report generation unit provides a display method that includes detailed information. If the user is in a hurry, the report generation unit provides a concise display method. This allows the report display method to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 report generation unit may be performed using AI, for example, or not using AI. For example, the report generation unit can input user emotion data into the generative AI and have the generative AI perform emotion estimation.

[0095] The contract management system allows the analysis unit to estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, if the user is stressed, the analysis unit prioritizes the analysis of important documents. If the user is relaxed, the analysis unit performs analysis with normal priorities. If the user is in a hurry, the analysis unit prioritizes the analysis of urgent documents. This allows the system to determine the priority of analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 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.

[0096] The contract management system allows the report generation unit to estimate the user's emotions and prioritize reports based on those emotions. For example, if the user is stressed, the report generation unit will prioritize reporting important discrepancies. If the user is relaxed, the report generation unit will report with normal priority. If the user is in a hurry, the report generation unit will prioritize reporting highly urgent discrepancies. This allows the report priority to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 report generation unit may be performed using AI or not. For example, the report generation unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0097] The following briefly describes the processing flow for example form 2.

[0098] Step 1: The analysis unit analyzes the documents. The analysis unit analyzes documents such as contracts, fee statements, and incentive setting documents, and analyzes the contents of the documents in detail. For example, it analyzes the clauses of the contract, the amounts in the fee statements, and the conditions for setting incentives. Step 2: The detection unit detects inconsistencies and misconfigurations from the data analyzed by the analysis unit. The detection unit checks the contract details, fee calculations, and incentive setting conditions to confirm that the contract clauses and fee amounts match and that the incentive setting conditions are accurately reflected. Step 3: The report generation unit generates a visual report based on the inconsistencies and misconfigurations detected by the detection unit. The report generation unit displays anomalies and inconsistencies in graphs and dashboards, generating a visual report that allows the person in charge to quickly identify the problem.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] Each of the multiple elements described above, including the analysis unit, detection unit, and report generation unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 and analyzes documents such as contracts and fee statements. The detection unit is implemented by the identification processing unit 290 of the data processing device 12 and detects inconsistencies and misconfigurations from the analyzed data. The report generation unit is implemented by the control unit 46A of the smart device 14 and generates a report that is easy to understand visually. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0103] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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).

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.).

[0115] 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.

[0116] 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.

[0117] 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.

[0118] Each of the multiple elements described above, including the analysis unit, detection unit, and report generation unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 and analyzes documents such as contracts and fee statements. The detection unit is implemented by the identification processing unit 290 of the data processing device 12 and detects inconsistencies and misconfigurations from the analyzed data. The report generation unit is implemented by the control unit 46A of the smart glasses 214 and generates a report that is easy to understand visually. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0119] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] Each of the multiple elements described above, including the analysis unit, detection unit, and report generation unit, is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 and analyzes documents such as contracts and fee statements. The detection unit is implemented by the identification processing unit 290 of the data processing device 12 and detects inconsistencies and misconfigurations from the analyzed data. The report generation unit is implemented by the control unit 46A of the headset terminal 314 and generates a report that is easy to understand visually. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0135] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] Each of the multiple elements described above, including the analysis unit, detection unit, and report generation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the robot 414 and analyzes documents such as contracts and fee statements. The detection unit is implemented by the identification processing unit 290 of the data processing unit 12 and detects inconsistencies and misconfigurations from the analyzed data. The report generation unit is implemented by the control unit 46A of the robot 414 and generates a report that is easy to understand visually. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] (Note 1) The analysis unit analyzes the document, A detection unit that detects inconsistencies or misconfigurations from the data analyzed by the aforementioned analysis unit, The system includes a report generation unit that generates a visual report based on the discrepancies and misconfigurations detected by the detection unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Analyze documents such as contracts, fee statements, and incentive setting documents. The system described in Appendix 1, characterized by the features described herein. (Note 3) The detection unit is Check the contract details, fee calculations, incentive setting conditions, etc. The system described in Appendix 1, characterized by the features described herein. (Note 4) The report generation unit, Display outliers and discrepancies in graphs and dashboards. The system described in Appendix 1, characterized by the features described herein. (Note 5) The report generation unit, Generate visual reports so that the person in charge can quickly identify the problem. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, Analyze the document's contents in detail and understand the content of each item. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, Optimize the analysis algorithm by referring to past analysis results. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, Apply different analysis methods depending on the type of document. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, The system estimates the user's emotions and determines the priority of analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, The order of analysis will be adjusted based on the submission date of the documents. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, Adjust the level of detail of the analysis based on the relevance of the documents. The system described in Appendix 1, characterized by the features described herein. (Note 13) The detection unit is It estimates the user's sentiment and adjusts the criteria for detecting inconsistencies and misconfigurations based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The detection unit is Optimize the detection algorithm by referring to past detection results. The system described in Appendix 1, characterized by the features described herein. (Note 15) The detection unit is Apply different detection methods depending on the type of document. The system described in Appendix 1, characterized by the features described herein. (Note 16) The detection unit is It estimates the user's emotions and adjusts the display order of the detection results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The detection unit is Prioritize detection based on when the documents were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The detection unit is Adjust the level of detail of the detection based on the relevance of the documents. The system described in Appendix 1, characterized by the features described herein. (Note 19) The report generation unit, It estimates user sentiment and adjusts how reports are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The report generation unit, Optimize the report generation algorithm by referring to past report results. The system described in Appendix 1, characterized by the features described herein. (Note 21) The report generation unit, Apply different report generation methods depending on the type of document. The system described in Appendix 1, characterized by the features described herein. (Note 22) The report generation unit, It estimates user sentiment and prioritizes reports based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The report generation unit, Adjust the order of reports based on when the documents are submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The report generation unit, Adjust the level of detail in the report based on the relevance of the documents. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0171] 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. The analysis unit analyzes the document, A detection unit that detects inconsistencies or misconfigurations from the data analyzed by the aforementioned analysis unit, The system includes a report generation unit that generates a visual report based on the discrepancies and misconfigurations detected by the detection unit. A system characterized by the following features.

2. The aforementioned analysis unit, Analyze documents such as contracts, fee statements, and incentive setting documents. The system according to feature 1.

3. The detection unit is Check the contract details, fee calculations, incentive setting conditions, etc. The system according to feature 1.

4. The report generation unit, Display outliers and discrepancies in graphs and dashboards. The system according to feature 1.

5. The report generation unit, Generate visual reports so that the person in charge can quickly identify the problem. The system according to feature 1.

6. The aforementioned analysis unit, Analyze the document's contents in detail and understand the content of each item. The system according to feature 1.

7. The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The system according to feature 1.

8. The aforementioned analysis unit, Optimize the analysis algorithm by referring to past analysis results. The system according to feature 1.

Images