System

Abstract

A system is provided.SOLUTION: A system comprising: means for analyzing documents using generative artificial intelligence to extract risk factors and errors; means for prioritizing the extracted risk factors and errors; means for transmitting data for displaying the prioritized risk factors and errors on a user interface; means for receiving correction information from a user and updating a risk assessment; and means for integrating the updated risk assessment into an integrated document management system.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern companies, risk management and human error prevention related to document management and evaluation are important issues. When humans manually review large volumes of documents, there is a high possibility of oversights and mistakes, which can have a significant impact on the company. Traditional methods often result in the slow detection of risk factors and errors, leading to delayed response, so efficiency and accuracy are required. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for analyzing documents using generative AI to extract risk factors and errors, a means for prioritizing the extracted risk factors and errors, a means for transmitting data to display the prioritized risk factors and errors on a user interface, a means for receiving correction information from a user and updating the risk assessment, and a means for integrating the updated risk assessment into an integrated document management system. This system efficiently performs document risk assessment, reduces human error, and improves the accuracy of risk management. Furthermore, by providing a means for applying custom models to adapt to specific industries or business operations and performing risk analysis, and a means for periodically generating and sending risk assessment reports to users, more accurate and timely risk management is possible.

[0006] "Generative artificial intelligence" refers to advanced computing systems capable of generating text using natural language processing and machine learning techniques.

[0007] A "document" is an information recording medium that includes documents related to business or work, such as contracts, work procedures, and work schedules.

[0008] "Risk Factors" are elements or conditions present in a document that may cause potential danger or loss to a business or contract.

[0009] An "Error" is an incorrect, incomplete, or inaccurate statement in a document or procedure.

[0010] "Extraction" is the process by which generative AI analyzes documents to identify and extract risk factors and errors.

[0011] "Prioritization" is the process of determining the order of response based on the importance and urgency of the extracted risk factors and errors.

[0012] A "user interface" is a computer-based interface that provides a screen and controls for a user to interact with a system.

[0013] "Correction Information" means corrections or additional information regarding risk factors or errors that a User provides to the System.

[0014] "Risk assessment" is the process of evaluating the extracted risk factors and errors and measuring their significance.

[0015] An "integrated document management system" is a system that centrally manages various documents owned by a company, making it easy to access, edit, and store them.

[0016] A "custom model" is an AI algorithm or analysis method that is optimized to meet the needs of a specific industry or business.

[0017] "Periodic generation of risk assessment reports" refers to the process by which the system automatically compiles the results of risk assessments at pre-set intervals and creates reports. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The present invention is a system that uses generative artificial intelligence to automate and streamline document management and risk assessment in a company, and is specifically implemented as follows.

[0040] System configuration

[0041] Server: Plays the central role in the system, analyzing documents, extracting risk factors and errors, prioritizing them, transmitting data, updating risk assessments, and linking with the integrated document management system.

[0042] Terminal: Provides a user interface, allowing users to upload documents, review analysis results, and submit corrections.

[0043] User: Operates the system to upload documents, check analysis results, and provide correction information.

[0044] Program processing flow

[0045] 1. Document upload: A user uploads a document to the server using a terminal. For example, a user sends a contract to the server via the "Upload Document" button on the terminal.

[0046] 2. Document analysis: The server receives the uploaded document and uses generative AI to analyze it. During the analysis process, the server breaks down the document, identifies each section and paragraph, and extracts risk factors and errors.

[0047] 3. Prioritization of risks and errors: The server evaluates the importance and urgency of the extracted risk factors and errors, and then assigns them numerical values. After the evaluation, the server classifies the risks and errors into "high," "medium," or "low" priorities.

[0048] 4. Sending results to the user interface: The server sends the prioritized results to the terminal, and the terminal displays the analysis results on the user interface. For example, high-priority risk factors are displayed in red, medium-priority in yellow, and low-priority in blue.

[0049] 5. User confirmation and correction: The user checks the analysis results and adds correction information and comments as necessary. After completing the corrections, the user presses the "Confirmation Complete" button, and the device sends the correction information to the server.

[0050] 6. Risk assessment update: The server receives the correction information from the user and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results as needed.

[0051] 7. Integration into the Unified Document Management System: The server integrates the latest risk assessments into the Unified Document Management System, enabling centralized risk management across the enterprise.

[0052] 8. Risk assessment report generation: The server will automatically generate a risk assessment report based on the latest risk assessment at regular intervals and send it to the user, who can use it to strengthen regular risk management and countermeasures.

[0053] Specific examples

[0054] For example, suppose a user uploads a new contract to the system. The server receives the contract and analyzes it using generation AI, extracting risk factors such as "ambiguity in contract clauses" and "insufficient penalty for exceeding deadlines." These risk factors are each rated as high priority and sent to the terminal. The user checks these risk factors on the terminal and adds comments to amend the penalty clause. After the amendment information is sent to the server, the server updates the risk assessment and reflects it in the integrated document management system. The user receives the latest risk assessment for this contract in a risk assessment report that is generated periodically.

[0055] The above is a specific embodiment for carrying out the present invention. This system enables a company to efficiently and accurately manage documents and risks.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The user selects a document using the "upload document" button on the terminal and uploads it to the server.

[0059] Step 2:

[0060] The server receives the uploaded document and sends it to the Generative AI's analysis engine to analyze the document's content, where sections and paragraphs of the document are identified.

[0061] Step 3:

[0062] The server uses generative AI to extract risk factors and errors within the document, such as "ambiguous contract clauses" and "insufficient penalties for exceeding deadlines."

[0063] Step 4:

[0064] The server evaluates the severity and urgency of the extracted risk factors and errors and assigns a numerical score, which categorizes each risk and error as "high," "medium," or "low."

[0065] Step 5:

[0066] The server converts the prioritized risk factors and error results into JSON format and sends them to the terminal, which receives the results and displays the analysis results on the user interface.

[0067] Step 6:

[0068] The user checks the analysis results on the device. For example, high-priority risk factors are displayed in red, medium-priority in yellow, and low-priority in blue.

[0069] Step 7:

[0070] The user can add corrections or comments to the analysis results as needed. Once corrections are complete, the user clicks the "Confirm" button to submit the information.

[0071] Step 8:

[0072] The terminal sends the user's modified information to the server, which receives the modified information and updates the existing risk assessment database.

[0073] Step 9:

[0074] The server reflects the updated risk assessment in the integrated document management system, enabling centralized management.

[0075] Step 10:

[0076] The server automatically generates risk assessment reports on a regular basis and sends the reports to users via email or other means, providing them with the latest risk information.

[0077] Example 1

[0078] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0079] In modern companies, document management and risk assessment processes are extremely time-consuming and labor-intensive. In particular, efficiently analyzing large volumes of documents and extracting and assessing risk factors and errors based on the results is difficult to do manually, and the accuracy of the results is limited. Furthermore, because risk assessment is performed manually, delays in updating information and errors can occur. There is a need for a system that can resolve these issues and perform document management and risk assessment efficiently and accurately.

[0080] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0081] In this invention, the server includes means for uploading documents to an information processing device, means for analyzing documents using generative artificial intelligence and extracting risk factors and errors, means for prioritizing the extracted risk factors and errors based on them, means for transmitting data to display the prioritized risk factors and errors on an information display device, means for receiving correction information from a user and updating a risk assessment, means for integrating the updated risk assessment into an integrated file management system, means for a user to check the analysis results and add comments, means for saving the updated risk assessment results, and means for automatically generating and transmitting a risk assessment report. This makes it possible to efficiently and accurately automate the document management and risk assessment processes.

[0082] "Generative AI" is an AI technology that has the ability to learn from data and automatically generate information.

[0083] A "document" is a collection of information in electronic or printed form, including textual and / or graphical information.

[0084] "Risk Factors" refers to the content or conditions contained in the document that may cause problems or dangers.

[0085] "Error" means a mistake or defect in a document.

[0086] "Prioritization" is the process of ranking risk factors or errors based on their importance and urgency.

[0087] An "information display device" is a device that displays analysis results and the priorities of risk factors and errors to the user.

[0088] "Revision information" refers to the revisions and comments on the document provided by the user.

[0089] "Risk assessment" is the result of a comprehensive evaluation of the extracted risk factors and the impact and probability of errors.

[0090] An "integrated file management system" is a system for centrally managing documents across an entire company and sharing necessary information.

[0091] The "information processing device" is a computer device for uploading documents and displaying analysis results.

[0092] A "risk assessment report" is a report prepared based on the latest risk assessment and compiles information for risk management.

[0093] The present invention is a system that uses generative artificial intelligence to automate and streamline document management and risk assessment in a company. Specific embodiments of this system are described below.

[0094] This system consists of a server, terminals, and users.

[0095] server

[0096] The server is the central part of the system, receiving documents, analyzing them, extracting risk factors and errors, prioritizing them, transmitting data, updating risk assessments, and connecting with the integrated file management system. The server uses generative AI models to analyze uploaded documents. This analysis process breaks down documents, identifies individual sections and paragraphs, and extracts risk factors and errors.

[0097] Terminal

[0098] The terminal provides an interface to the user, who can use the terminal to upload documents, check the analysis results, and submit correction information.

[0099] User

[0100] The user operates the system, uploads a specific document to the terminal, checks the analysis results, and inputs correction information as necessary.

[0101] Specific names of hardware and software used

[0102] This system uses a generative AI model, an information display device, an information processing device, and an integrated file management system.

[0103] Specific examples

[0104] For example, suppose a user uploads a new contract to the system. The user sends the contract to the server via the "Upload Document" button on their device. The server receives the contract, analyzes it using a generative AI model, and extracts risk factors such as "ambiguity in contract clauses" and "insufficient penalty for overdue deadlines." These risk factors are each rated as high priority and sent to the device. The user reviews these risk factors on their device and adds comments to amend the penalty clauses. After the amendments are sent to the server, the server updates the risk assessment and reflects it in the integrated file management system. The user receives the latest risk assessment for this contract in a regularly generated risk assessment report. This process ensures efficient and accurate document management and risk management.

[0105] Prompt Sentence Examples

[0106] To get the generative AI model to parse a document, use a prompt like this:

[0107] Analyze the following contract and extract risk factors and errors:

[0108] Contract text

[0109] ---

[0110] [Contract details here]

[0111] The above is a specific embodiment for carrying out the present invention. This system enables a company to efficiently and accurately manage documents and risks.

[0112] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0113] Step 1: Upload your documents

[0114] The user clicks the "Upload Document" button on the device and selects the document file to upload.

[0115] The terminal transmits the selected document file to the server.

[0116] The server receives and stores the uploaded document.

[0117] Input: A document file selected by the user (e.g., contract.pdf)

[0118] Data processing: receiving and storing files

[0119] Output: Document file saved on the server

[0120] As a specific operation, the user selects a file called "contract.pdf" and clicks the "upload document" button.

[0121] Step 2: Parsing the document

[0122] The server passes the received document to the generative AI model.

[0123] A generative AI model analyzes the document and identifies each section and paragraph.

[0124] The server receives the risk factor and error extraction results from the generative AI model.

[0125] Input: Document file stored on the server

[0126] Data Computing: Generative AI models analyze documents, extract risk factors and errors

[0127] Output: A list of extracted risk factors and errors

[0128] Specifically, the generative AI model extracts risk factors such as "ambiguity in contract terms" and "insufficient penalties for exceeding deadlines."

[0129] Step 3: Prioritize risks and errors

[0130] The server quantifies the extracted risk factors and the importance and urgency of the errors.

[0131] The server classifies risk factors and errors into "high," "medium," and "low" priorities.

[0132] Input: List of extracted risk factors and errors

[0133] Data calculation: Prioritization of risk factors and errors (quantification and classification)

[0134] Output: A prioritized list of risk factors and errors

[0135] As a specific operation, the ambiguity of the penalty clause is evaluated as a high priority.

[0136] Step 4: Sending results to the user interface

[0137] The server sends the prioritized results to the terminal.

[0138] The device displays the analysis results in a user interface.

[0139] Input: A prioritized list of risk factors and errors

[0140] Data transmission: Sending a priority list to the device

[0141] Output: Analysis results displayed to the user

[0142] Specifically, high-priority risk factors are displayed in red, and unclear penalty clauses are displayed in red on the user's screen.

[0143] Step 5: User review and correction

[0144] The user checks the analysis results through the terminal.

[0145] The user adds correction information and comments and presses the "Confirm" button.

[0146] The terminal sends the correction information to the server.

[0147] Input: User corrections and comments

[0148] Data transmission: Sending correction information to the server

[0149] Output: Correction information sent to the server

[0150] As a specific operation, the user adds a comment saying, "You need to recheck the penalty clause."

[0151] Step 6: Update your risk assessment

[0152] The server receives the correction information from the user.

[0153] The server updates the risk assessment based on the latest information.

[0154] The updated risk assessment is saved in the database.

[0155] Input: Correction information from the user

[0156] Data calculation: Update risk assessment (recalculate and save)

[0157] Output: Updated risk assessment data

[0158] Specifically, the risk assessment is recalculated based on the corrected information and saved in the database.

[0159] Step 7: Integrate into an integrated file management system

[0160] The server sends the latest risk assessment to the integrated file management system and reflects it.

[0161] Input: Updated risk assessment data

[0162] Data submission: submission of risk assessments to an integrated file management system

[0163] Output: Risk assessment reflected in an integrated file management system

[0164] Specifically, the latest risk assessment is automatically added to the company's file management system.

[0165] Step 8: Generate a risk assessment report

[0166] The server automatically generates risk assessment reports on a regular basis.

[0167] The server sends the generated report to the user.

[0168] Input: Latest risk assessment data

[0169] Data calculations: Automatic generation of risk assessment reports

[0170] Data submission: Sending risk assessment reports to users

[0171] Output: Risk assessment report sent to user

[0172] Specifically, an automatically generated risk assessment report is sent to the user's email address once a month.

[0173] (Application example 1)

[0174] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0175] In conventional factories, document analysis of equipment and process management is often performed manually, which delays the detection of risk factors and errors and makes it difficult to implement timely improvements. Furthermore, this process is time-consuming and labor-intensive, resulting in reduced production efficiency and safety issues. There is a need to solve this issue and provide an automated risk management system.

[0176] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0177] In this invention, the server includes means for analyzing documents using generative AI and extracting risk factors and errors, means for prioritizing the extracted risk factors and errors, means for transmitting data to display the prioritized risk factors and errors on a user interface, means for receiving correction information from a user and updating risk assessments, means for integrating the updated risk assessments into an integrated data management system, and means for analyzing documents for equipment and process management in factories, detecting risk factors and errors, and proposing necessary improvements. This enables the automation and efficiency of document management and risk assessment, thereby improving productivity and safety.

[0178] "Generative AI" is an AI technology that generates knowledge based on given data and makes decisions and predictions.

[0179] "Document" means an electronic file or printed material containing written information.

[0180] "Risk factors" refer to events or conditions that have the potential to cause problems or trouble.

[0181] "Error" refers to an inaccurate description or operational error that occurs in a document or process.

[0182] "Prioritizing" refers to determining the order of extracted risk factors and errors based on their importance and urgency.

[0183] "User interface" refers to an interactive screen or display that allows a user to interact with a system.

[0184] "Transmitting data" refers to the electronic transfer of analysis results or risk information to another device or system.

[0185] "Correction information" refers to information provided by the user to correct or supplement extracted risk factors or errors.

[0186] "Risk assessment" refers to the evaluation values ​​and safety judgments for extracted risk factors and errors.

[0187] An "integrated data management system" refers to a system that centrally manages multiple data sets and integrates and processes the necessary information.

[0188] A "factory" refers to facilities and equipment used for manufacturing and production activities.

[0189] "Equipment" refers to machinery and equipment such as production lines and manufacturing devices used within a factory.

[0190] "Process control" refers to the planning, monitoring, and control of the production process in a factory.

[0191] "Document analysis" refers to the process of analyzing text data and extracting useful information and patterns.

[0192] "Improvements" refer to areas in the current process or design that require change or improvement.

[0193] The "Factory Document Risk Assessment Robot" refers to a robot system that analyzes documents used within a factory, automatically detects and evaluates risk factors and errors, and proposes necessary improvements.

[0194] The system embodying this invention automates document analysis and risk assessment in factories, providing efficient risk management. Specifically, it has the following configuration.

[0195] System configuration

[0196] Server: The central part of the system, which analyzes documents, extracts risk factors and errors, prioritizes them, transmits data, and updates risk assessments, and integrates the updated risk assessments into the integrated data management system.

[0197] Robot: Scans documents related to equipment and process control used in the factory and uploads them to a server, and also provides an interface for users to provide correction information.

[0198] User: Operates the system as a factory manager or worker, uploading documents, checking analysis results, and providing correction information.

[0199] Program processing flow

[0200] 1. Document upload: A user uses a robot to upload a document to the server, for example, a factory inspection list or equipment manual.

[0201] 2. Document analysis: The server receives the uploaded document and analyzes it using a generative AI model (e.g., OpenAI GPT-4). During the analysis process, the server breaks down the document, identifies each section and paragraph, and extracts risk factors and errors.

[0202] 3. Prioritization of risks and errors: The server evaluates the importance and urgency of the extracted risk factors and errors, quantifies them, and classifies them into "high," "medium," or "low" priorities.

[0203] 4. Sending results to the user interface: The server sends the prioritized results to the robot's interface, allowing the user to review the analysis results. For example, high-risk factors are displayed in red.

[0204] 5. User confirmation and correction: The user checks the analysis results on the interface and adds corrections or comments as necessary. Once corrections are complete, the user presses the "Confirmation Complete" button, and the robot sends the corrections to the server.

[0205] 6. Risk assessment update: The server receives the correction information from the user and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results as needed.

[0206] 7. Integration into the Integrated Data Management System: The server integrates the latest risk assessments into the integrated data management system, which provides a single source of risk management across the entire factory.

[0207] Specific examples

[0208] For example, a user uploads a new inspection list for a factory into the system. The inspection list contains the following:

[0209] 1. Machine A inspection: hydraulic pressure normal, sound abnormal

[0210] 2. Machine B inspection: High temperature, heavy wear

[0211] 3. Machine C inspection: normal operation, no vibration

[0212] The server receives the inspection list and analyzes it using a generative AI model, extracting "abnormal sound" and "high temperature" as risk factors. These are each rated as high priority and sent to the robot's interface. The user checks these risk factors and enters comments, such as adding an inspection to identify the cause of "abnormal sound." Corrections are sent to the server, and the risk assessment is updated. As a result, the user can always understand the latest risk assessment and take appropriate measures.

[0213] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0214] Step 1:

[0215] The user uploads documents to the server using a robot. At this time, the user has the robot scan factory documents such as work procedures and inspection lists. The documents are sent as electronic data to the server, which then receives the data.

[0216] Input: Document data scanned by the robot

[0217] Output: Document data stored on the server

[0218] Step 2:

[0219] The server receives the uploaded document and analyzes it using a generative AI model. During this process, the server passes the received document data to the generative AI, which creates prompts for decomposition and analysis. The generative AI model (e.g., OpenAI GPT-4) identifies each section and paragraph of the document and extracts risk factors and errors.

[0220] Input: Uploaded document data

[0221] Output: Risk factors and error extraction results

[0222] Step 3:

[0223] The server evaluates the importance and urgency of the extracted risk factors and errors, and quantifies them. After the evaluation, the risks and errors are classified into "high," "medium," and "low" priorities. In this process, a numerical evaluation is performed in comparison with pre-set evaluation criteria.

[0224] Input: Risk factors and error extraction results

[0225] Output: Prioritized risk factors and errors

[0226] Step 4:

[0227] The server sends the prioritized results to the robot's interface, allowing the user to check the analysis results. The user interface displays high-priority factors in red, medium-priority factors in yellow, and low-priority factors in blue. This allows the user to check important risk factors at a glance.

[0228] Input: Prioritized risk factors and errors

[0229] Output: The result displayed on the user interface

[0230] Step 5:

[0231] The user checks the analysis results on the interface and adds correction information or comments as necessary. For example, they can enter a comment to add an inspection to identify the cause of the "sound abnormality." Once the corrections are complete, the user presses the "Confirmation Complete" button, and the robot sends the correction information to the server.

[0232] Input: User corrections and comments on analysis results

[0233] Output: Analysis results with correction information added

[0234] Step 6:

[0235] The server receives the correction information from the user and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results as needed.

[0236] Input: Correction information submitted by the user

[0237] Output: Latest risk assessment

[0238] Step 7:

[0239] The server integrates the latest risk assessments into an integrated data management system, enabling centralized risk management across the entire factory. Periodic risk assessment reports are automatically generated and sent to users.

[0240] Input: Latest risk assessment

[0241] Output: Risk assessment and risk assessment report integrated into an integrated data management system

[0242] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0243] The present invention is a system that uses generative artificial intelligence to automate and streamline document management and risk assessment in companies, and by combining it with an emotion engine that recognizes user emotions, it achieves a more advanced user experience and precise risk management. This system is specifically implemented as follows.

[0244] System configuration

[0245] Server: The central part of the system, responsible for document analysis, risk factor and error extraction, prioritization, data transmission, risk assessment updates, emotion recognition, and integration of updates.

[0246] Terminal: Provides a user interface where users can upload documents, check analysis results, submit corrections, and provide emotion information.

[0247] User: Operates the system to upload documents, check analysis results, provide corrections, and express emotions to provide feedback through the emotion engine.

[0248] Program processing flow

[0249] 1. Document upload: A user uploads a document to the server using a terminal. For example, a user sends a contract to the server via the "Upload Document" button on the terminal.

[0250] 2. Document analysis: The server receives the uploaded document and analyzes it using generative AI. During the analysis process, the server breaks down the document, identifies each section and paragraph, and extracts risk factors and errors.

[0251] 3. Prioritization of risks and errors: The server evaluates the importance and urgency of the extracted risk factors and errors, and then assigns them numerical values. After the evaluation, the server classifies the risks and errors into "high," "medium," or "low" priorities.

[0252] 4. Sending results to the user interface: The server converts the prioritized risk factors and error results into JSON format and sends them to the terminal. The terminal receives the results and displays the analysis results on the user interface.

[0253] 5. User emotion detection and feedback: The emotion engine recognizes the user's emotions using emotion information provided by the user, such as a camera or microphone. For example, the user analyzes facial expressions and tone of voice based on the analysis results, and the emotion engine processes them.

[0254] 6. Emotion-based priority adjustment: The emotion engine readjusts the priority of risk factors and errors based on the user's emotions. For example, risk factors that the user expresses discomfort with will be given a higher priority.

[0255] 7. User confirmation and correction: The user checks the analysis results on the device and adds correction information and comments as necessary. After completing the corrections, click the "Confirmation Complete" button to submit the information.

[0256] 8. Risk Assessment Update: The server receives the user's revised information and updates the risk assessment based on the latest information. The updated risk assessment is stored in the database and can be compared with past assessment results as needed.

[0257] 9. Integration into Unified Document Management System: The server integrates the latest risk assessments into the Unified Document Management System, enabling centralized risk management across the enterprise.

[0258] 10. Risk assessment report generation: The server will automatically generate risk assessment reports periodically and send them to users, who can use them to strengthen their regular risk management and countermeasures.

[0259] Specific examples

[0260] For example, consider what happens when a user uploads a new contract to the system. The server receives the contract and analyzes it using a generation AI, extracting risk factors such as "ambiguous contract terms" and "insufficient penalties for overdue documents." Each of these risk factors is rated as high priority and sent to the device. While the user is reviewing the results on the device, the emotion engine recognizes the user's facial expressions and detects that the user is expressing displeasure. As a result, the emotion engine sets the priority of the relevant risk factor even higher and displays the results to the user again. The user can then add corrections based on this, and the server updates the risk assessment. Finally, the updated risk assessment is reflected in the integrated document management system and sent to the user as a regular risk assessment report.

[0261] The above is a specific embodiment for carrying out the present invention. This system allows companies to manage documents and risks efficiently and accurately, and by incorporating feedback based on user emotions, more precise risk assessment and improvement can be achieved.

[0262] The processing flow will be explained below.

[0263] Step 1:

[0264] The user uses the "Document Upload" button on the device to select a document and upload it to the server. For example, when a user uploads a contract, they select the file and click the button to send it.

[0265] Step 2:

[0266] The server receives the uploaded document and sends it to the Generative AI's analysis engine for analysis, where the document is parsed and each section or paragraph is identified, such as the "Terms" and "Terms" sections in a contract.

[0267] Step 3:

[0268] The server uses generative AI to analyze the contents of the document and extract risk factors and errors, such as "risk of expiration" and "ambiguous contract terms."

[0269] Step 4:

[0270] The server evaluates the importance and urgency of the extracted risk factors and errors and assigns a numerical score. For example, the "risk of expiration" is evaluated as 9 out of 10.

[0271] Step 5:

[0272] The server converts the prioritized risk factors and error results into JSON format and sends it to the terminal. The terminal receives the results and displays the analysis results on the user interface. For example, high-priority risk factors are displayed in red.

[0273] Step 6:

[0274] While checking the analysis results, the user provides real-time emotions using the device's camera and microphone. For example, if the user feels dissatisfied, the emotion engine will recognize facial expressions and analyze the tone of voice.

[0275] Step 7:

[0276] The emotion engine processes the user's emotion information and reflects the user's dissatisfaction or surprise in the priority of risk factors. For example, a risk factor that the user expresses discomfort with is given a higher priority.

[0277] Step 8:

[0278] The server displays the adjusted risk factors and error priorities again in the user interface, and the user reviews the results and adds corrections or comments as needed.

[0279] Step 9:

[0280] After the user has completed inputting the correction information, he / she clicks the "Confirmation Complete" button to send the information from the terminal to the server. For example, he / she may enter correction comments that specifically indicate the "ambiguous contract terms."

[0281] Step 10:

[0282] The server receives the user's modified information and updates the existing risk assessment database, which is used for future document analysis and risk assessment processes.

[0283] Step 11:

[0284] The server updates the integrated document management system with the latest risk assessments, enabling centralized risk management and updating the risk database available across the entire company.

[0285] Step 12:

[0286] The server automatically generates a risk assessment report periodically and transmits the report to the user. For example, the server generates a monthly risk assessment report and transmits it to the user by email.

[0287] With this detailed processing flow, the present invention enables document management and risk assessment to be carried out efficiently and accurately, and by incorporating feedback based on the user's emotions, more precise risk assessment can be achieved.

[0288] Example 2

[0289] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0290] Conventional document management and risk assessment systems have issues such as difficulty in centralized management and inability to perform efficient risk assessment and correction. Furthermore, the accuracy of risk assessment that takes user emotions into account has not been sufficiently improved, and an improved user experience is required. As a result, risks can be overlooked or it can be difficult to respond quickly, making it difficult to optimize risk management across the entire company, requiring a lot of time and effort.

[0291] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0292] In this invention, the server includes: means for analyzing documents using generative artificial intelligence and extracting risk factors and errors; means for prioritizing the extracted risk factors and errors; means for transmitting data to display the prioritized risk factors and errors on a user interface; means for recognizing a user's emotions and readjusting the priorities of the risk factors and errors based on the emotions; means for receiving correction information from the user and updating the risk assessment; and means for integrating the updated risk assessment into an integrated document management system. This enables centralized and efficient performance of processes from document analysis to risk assessment, correction, and integrated management. Furthermore, a more accurate risk assessment that reflects the user's emotions can be achieved, improving the user experience.

[0293] "Generative AI" is a general term for AI technologies that have the ability to generate new information or results based on data.

[0294] A "document" refers to a file or data that contains information expressed as text data.

[0295] A "risk factor" is an element of potential negative consequence or danger that a particular event or action may cause.

[0296] An "Error" is any mistake or defect in a document that prevents accurate and proper processing or interpretation.

[0297] "User interface" refers to the display screen and input means that allow a user to interact with a system.

[0298] "Means for recognizing emotions" refers to processes or technologies that detect emotional expressions such as facial expressions and voice of a user and identify that emotional state.

[0299] "Measures for readjusting priorities" refers to the process of reevaluating and resetting the importance of risk factors and errors that have been set based on new information such as user sentiment.

[0300] "Correction information" refers to information including corrections and opinions provided by users, with the aim of improving documents and evaluation results.

[0301] "Updating" refers to the process of modifying, adding, or deleting existing data or assessment results based on new information.

[0302] An "integrated document management system" is a system for centrally managing, storing, and accessing multiple documents and data.

[0303] The present invention is a system that uses generative AI models to automate and streamline document management and risk assessment in companies. Furthermore, by combining it with an emotion engine that recognizes user emotions, it achieves a more advanced user experience and precise risk management. This system is specifically implemented as follows:

[0304] System configuration

[0305] server:

[0306] The server plays a central role in the system and has the following functions:

[0307] Document Analysis

[0308] Identifying risk factors and errors

[0309] Prioritization

[0310] Data transmission

[0311] Risk Assessment Updates

[0312] emotion recognition

[0313] Integration of update information

[0314] The server uses Python-based natural language processing libraries (e.g., NLTK, spaCy), machine learning techniques such as decision tree algorithms, and TensorFlow models for emotion recognition.

[0315] Device:

[0316] It provides the user interface and the means by which the user operates the system. The terminal has the following functions:

[0317] Document upload

[0318] Checking the analysis results

[0319] Submitting correction information

[0320] Providing emotional information

[0321] The device uses JavaScript-based front-end frameworks (e.g., React, Vue.js) to build the user interface.

[0322] User:

[0323] Users operate the system to upload documents, check analysis results, provide correction information, and express emotions to provide feedback through the emotion engine.

[0324] Specific examples

[0325] For example, let's consider what happens when a user uploads a new contract to the system. The user uploads the contract using a terminal. They click the "Upload Document" button on the terminal, select the contract file, and send it to the server. In this process, the file data is transferred to the server via an HTTP request.

[0326] The server uses a generative AI model to analyze the received contract. Specifically, it uses a Python-based natural language processing library (e.g., NLTK, spaCy) to break down the document and identify each section and paragraph. It then extracts risk factors and errors. Once this step is complete, it uses a decision tree algorithm to prioritize the extracted risk factors and errors.

[0327] Once the prioritization is complete, the server converts the results into JSON format and sends them to the device, where the analysis results are displayed in a user interface using a JavaScript-based front-end framework (e.g., React, Vue.js). The user can then view the analysis results displayed on the device.

[0328] As the user reviews the analysis results, their emotional information is sent to the emotion engine via the device's camera and microphone. The emotion engine then uses a TensorFlow model to analyze the user's emotions and automatically readjust the priority of risk factors that cause discomfort.

[0329] The user can add corrections or comments as needed and click the "Confirm" button to send the information to the server. Based on this information, the server updates the risk assessment and saves the latest assessment in the database. At the same time, the updated risk assessment is integrated into the integrated document management system.

[0330] Finally, the server automatically generates and sends risk assessment reports periodically to users, who can use the reports to strengthen their regular risk management and countermeasures.

[0331] Example prompts to input to the generative AI model

[0332] Analyze the contents of the contract below and extract the risk factors.

[0333] "Contract details:..."

[0334] The above is a specific embodiment for carrying out the present invention. This system allows companies to manage documents and risks efficiently and accurately, and by incorporating feedback based on user emotions, more precise risk assessment and improvement can be achieved.

[0335] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0336] Step 1:

[0337] Document upload

[0338] Subject: User

[0339] Specific operation: The user clicks the "Upload Document" button on the terminal, selects the contract file, and sends it to the server. At this time, the file data is sent using an HTTP request.

[0340] Input: A document file selected by the user

[0341] Output: Document file uploaded to the server

[0342] Step 2:

[0343] Document Analysis

[0344] Subject: Server

[0345] Specific operation: The server analyzes the received document file using a Python-based natural language processing library (e.g., NLTK, spaCy), breaking down the document into sections and paragraphs, and extracting risk factors and errors.

[0346] Input: Uploaded document file

[0347] Output: A list of extracted risk factors and errors

[0348] Step 3:

[0349] Prioritizing risks and errors

[0350] Subject: Server

[0351] What it does: The server uses a decision tree algorithm to evaluate the importance and urgency of the extracted risk factors and errors, and classifies them into "high," "medium," or "low" priorities.

[0352] Input: List of extracted risk factors and errors

[0353] Output: A prioritized list of risk factors and errors

[0354] Step 4:

[0355] Sending results to the user interface

[0356] Subject: Server

[0357] Specific operation: Converts the prioritized list of risk factors and errors into JSON format and sends it to the device.

[0358] Input: List of prioritized risk factors and errors

[0359] Output: The result as JSON data sent to the terminal.

[0360] Step 5:

[0361] Displaying analysis results

[0362] Subject: Terminal

[0363] Specific operation: The device uses the JSON data received and displays the analysis results on the user interface using a JavaScript-based front-end framework.

[0364] Input: Parsed result in JSON data format

[0365] Output: Analysis results displayed on the terminal

[0366] Step 6:

[0367] User emotion detection and feedback

[0368] Subject: User

[0369] How it works: While checking the analysis results, the user provides emotion information via the device's camera or microphone. The emotion engine then uses a TensorFlow model to analyze the emotion and identify the user's emotional state.

[0370] Input: User facial and voice data

[0371] Output: The user's emotional state as analyzed by the emotion engine.

[0372] Step 7:

[0373] Adjusting priorities based on emotions

[0374] Subject: Server

[0375] What it does: The server receives data from the emotion engine and re-prioritizes risk factors and errors based on the user's emotions.

[0376] Input: The user's emotional state as analyzed by the emotion engine

[0377] Output: A list of rescaled risk factors and errors

[0378] Step 8:

[0379] User confirmation and correction

[0380] Subject: User

[0381] Specific operation: The user checks the analysis results on their device and adds corrections or comments as necessary. They then click the "Confirm" button to send the information to the server. The corrections are sent in JSON format.

[0382] Input: User-added corrections and comments

[0383] Output: Correction information sent to the server

[0384] Step 9:

[0385] Risk Assessment Updates

[0386] Subject: Server

[0387] Specific operation: The server updates the risk assessment based on the latest information received from the correction information, and saves the updated assessment results in the database.

[0388] Input: User-submitted correction information

[0389] Output: Updated risk assessment results

[0390] Step 10:

[0391] Integration into an integrated document management system

[0392] Subject: Server

[0393] What it does: The server uploads the latest risk assessment results to an integrated document management system for centralized management across the enterprise.

[0394] Input: Updated risk assessment results

[0395] Output: Evaluation results stored in an integrated document management system

[0396] Step 11:

[0397] Generate a risk assessment report

[0398] Subject: Server

[0399] Specific operation: The server automatically generates a risk assessment report on a regular basis and sends it to the user in PDF format or other format.

[0400] Input: Latest risk assessment results

[0401] Output: Risk assessment report sent to user

[0402] (Application example 2)

[0403] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0404] In conventional document management systems, risk factor extraction and prioritization are performed manually, making efficient risk assessment difficult. Furthermore, risk assessment does not reflect user sentiment, preventing an improved user experience. Furthermore, rapid document analysis and real-time risk management are required in workplaces such as factory robots, but the lack of a system that meets these requirements has been an issue.

[0405] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0406] In this invention, the server includes: means for analyzing documents using generative artificial intelligence to extract risk factors and errors; means for prioritizing the extracted risk factors and errors; and means for transmitting data to display the prioritized risk factors and errors on a user interface. This enables rapid analysis of documents and automatic extraction of risk factors. The server also includes means for recognizing a user's emotional information and reevaluating the priority of risk factors and errors based on the emotional information, and means for acquiring the user's emotional information using an emotional recognition engine and providing feedback based on the emotional information. This improves the user experience and enables precise risk assessment.

[0407] "Generative AI" is an AI technology that analyzes documents and automatically extracts risk factors and errors.

[0408] "Risk factors" refer to potential problems or dangers inherent in a document.

[0409] "Error" means any mistake or inaccuracy in a Document.

[0410] "Prioritization" means ranking the extracted risk factors and errors based on their importance and urgency.

[0411] A "user interface" is an interface that provides a screen and operating means for a user to interact with a system.

[0412] "Correction information" refers to corrections or additional information to the document content provided by the user.

[0413] "Risk assessment" is the process of evaluating the impact of extracted risk factors and errors, and determining countermeasures based on that information.

[0414] An "integrated document management system" is a system that centrally manages documents and their risk assessment information.

[0415] "Emotional information" is data that represents the user's emotional state, and is acquired from facial expressions, tone of voice, and the like.

[0416] An "emotion recognition engine" is a technology that recognizes emotions by analyzing data obtained from the user's camera or microphone.

[0417] "Feedback" is the process of dynamically correcting the assessment results of risk factors and errors based on the user's emotional information.

[0418] This invention relates to a smart document analysis and risk assessment system for factory robots. The system consists of three main components: a server, a terminal, and a user.

[0419] Server Roles

[0420] The server plays a central role in the system and performs the following main processes:

[0421] 1. Document Analysis:

[0422] It uses generative artificial intelligence (AI) to analyze uploaded documents and extract risk factors and errors. The generative AI model is provided by the OpenAI API or a similar service.

[0423] 2. Prioritize risks and errors:

[0424] The identified risk factors and errors are evaluated and prioritized based on their importance. This evaluation is quantified and classified into categories of "high," "medium," or "low" according to the urgency of the risk or error.

[0425] 3. Recognition and feedback of emotional information:

[0426] An emotion recognition engine (e.g., DeepFace) is used to obtain user emotion information, and risk factors and error priorities are reassessed based on the results.

[0427] 4. Risk Assessment Update:

[0428] Receives corrections from users and updates the risk assessment based on the latest information. Updated risk assessments are integrated into the integrated document management system.

[0429] 5. Report Generation:

[0430] A risk assessment report is automatically generated periodically based on the updated risk assessment and sent to the user.

[0431] Device Role

[0432] The terminal provides a user interface for users to interact with the system. Specifically, it has the following functions:

[0433] 1. Upload your documents:

[0434] A factory manager uploads a document to the server using a smartphone or tablet, for example, by clicking the "Upload Document" button in the UI.

[0435] 2. Check the analysis results:

[0436] The analysis results sent from the server are displayed in real time, including a list of extracted risk factors and errors, and their priorities.

[0437] 3. Submitting Corrections:

[0438] The administrator will review the analysis results and submit corrections or additional comments as necessary.

[0439] User Roles

[0440] The users are mainly factory managers and perform the following operations:

[0441] 1. Upload your documents:

[0442] Documents used within the factory, such as work procedures, manuals, and contracts, are uploaded from the terminal to the server.

[0443] 2. Check the analysis results:

[0444] The analysis results are displayed on the device and feedback is provided on any risk factors or errors found.

[0445] 3. Providing emotional information:

[0446] Emotional information is provided using a camera or microphone, which allows the system to identify emotions in real time through an emotion recognition engine and incorporate them into risk assessment.

[0447] Specific examples

[0448] For example, when a factory manager uploads a new work procedure manual to the system, the following process takes place: The server analyzes the procedure manual and extracts risk factors and errors in the work process. Risk factors such as "ambiguous process procedures" and "insufficient safety measures" are extracted, rated as high priority, and sent to the terminal. While the manager is checking the results, a camera recognizes the manager's facial expressions, and if anxiety or discomfort is detected, the priority of that risk factor is set even higher. Finally, the manager adds any corrections, and the server recalculates the latest risk assessment. The risk assessment report generated by the system is useful for continuous risk management and strengthening countermeasures.

[0449] Generative AI model prompt example

[0450] Analyze the following factory operating procedures to identify risk factors and errors. Pay particular attention to the safety measures and procedure sequence when analyzing the following statements.

[0451] In this way, the present invention contributes to improving the work efficiency and safety of factories, and also has the effect of reducing the burden on managers.

[0452] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0453] Step 1:

[0454] Document upload

[0455] A user uses a terminal to upload a document to the server. Specifically, a factory manager presses the "upload document" button on a smartphone or tablet, selects and sends a document file such as a work procedure manual, manual, or contract. The terminal receives the document file and transfers the data to the server. The input is the document file, and the output is the transfer of the document file to the server.

[0456] Step 2:

[0457] Document Analysis

[0458] The server analyzes the received document file. Specifically, the server uses a generative AI model to break down the document content into sections and paragraphs and extract risk factors and errors. At this time, the prompt for the generative AI model (e.g., OpenAI API) is, "Analyze the following factory work procedure manual and extract risk factors and errors. Please analyze the following sentence, paying particular attention to safety measures and the order of procedures." The input is the document content, and the output is a list of extracted risk factors and errors.

[0459] Step 3:

[0460] Prioritizing risks and errors

[0461] The server evaluates the extracted risk factors and errors and sets priorities based on their importance and urgency. Specifically, it quantifies the evaluation results and categorizes the risks and errors into "high," "medium," and "low" categories. The input is a list of risk factors and errors, and the output is a prioritized list of risk factors and errors.

[0462] Step 4:

[0463] Sending and viewing analysis results

[0464] The server converts the prioritized risk factors and error results into JSON format and sends it to the terminal. The terminal receives the results and displays the analysis results on the user interface. Specifically, the risk factors and errors are displayed in list format by priority, making it easy for the user to check. The input is the list of prioritized risk factors and errors, and the output is the analysis results displayed on the terminal.

[0465] Step 5:

[0466] Recognition and feedback of emotional information

[0467] The device's camera and microphone are used to obtain the user's emotional information. The server uses an emotion recognition engine (e.g., DeepFace) to recognize emotions from the user's facial expressions and tone of voice, and based on the results, re-evaluates the priority of risk factors and errors. Specifically, risk factors that the user expresses discomfort with are given a higher priority. The input is the user's emotional information, and the output is a list of risk factors and errors with re-evaluated priorities.

[0468] Step 6:

[0469] Providing and sending correction information

[0470] The user checks the analysis results and adds any necessary corrections or comments. The device then sends the corrections to the server. Specifically, the user enters corrections for each item in the analysis results and clicks the "Confirm" button to send the results. The input is the user's corrections, and the output is the corrections sent to the server.

[0471] Step 7:

[0472] Risk Assessment Updates

[0473] The server receives the user's revised information and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results. The input is the user's revised information, and the output is the updated risk assessment.

[0474] Step 8:

[0475] Generate and submit risk assessment reports

[0476] The server automatically generates risk assessment reports periodically and sends them to the user. Specifically, it creates reports based on updated risk assessment data and sends them to the user's terminal. The input is the updated risk assessment data, and the output is the risk assessment report sent to the user.

[0477] As described above, the present invention is a system that can efficiently and accurately manage documents and assess risks, and realizes precise risk assessment that reflects the user's feelings.

[0478] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0479] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0480] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0481] [Second embodiment]

[0482] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0483] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0484] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0485] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0486] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0487] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0488] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0489] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0490] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0491] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0492] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0493] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0494] The present invention is a system that uses generative artificial intelligence to automate and streamline document management and risk assessment in a company, and is specifically implemented as follows.

[0495] System configuration

[0496] Server: Plays the central role in the system, analyzing documents, extracting risk factors and errors, prioritizing them, transmitting data, updating risk assessments, and linking with the integrated document management system.

[0497] Terminal: Provides a user interface, allowing users to upload documents, review analysis results, and submit corrections.

[0498] User: Operates the system to upload documents, check analysis results, and provide correction information.

[0499] Program processing flow

[0500] 1. Document upload: A user uploads a document to the server using a terminal. For example, a user sends a contract to the server via the "Upload Document" button on the terminal.

[0501] 2. Document analysis: The server receives the uploaded document and uses generative AI to analyze it. During the analysis process, the server breaks down the document, identifies each section and paragraph, and extracts risk factors and errors.

[0502] 3. Prioritization of risks and errors: The server evaluates the importance and urgency of the extracted risk factors and errors, and then assigns them numerical values. After the evaluation, the server classifies the risks and errors into "high," "medium," or "low" priorities.

[0503] 4. Sending results to the user interface: The server sends the prioritized results to the terminal, and the terminal displays the analysis results on the user interface. For example, high-priority risk factors are displayed in red, medium-priority in yellow, and low-priority in blue.

[0504] 5. User confirmation and correction: The user checks the analysis results and adds correction information and comments as necessary. After completing the corrections, the user presses the "Confirmation Complete" button, and the device sends the correction information to the server.

[0505] 6. Risk assessment update: The server receives the correction information from the user and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results as needed.

[0506] 7. Integration into the Unified Document Management System: The server integrates the latest risk assessments into the Unified Document Management System, enabling centralized risk management across the enterprise.

[0507] 8. Risk assessment report generation: The server will automatically generate a risk assessment report based on the latest risk assessment at regular intervals and send it to the user, who can use it to strengthen regular risk management and countermeasures.

[0508] Specific examples

[0509] For example, suppose a user uploads a new contract to the system. The server receives the contract and analyzes it using generation AI, extracting risk factors such as "ambiguity in contract clauses" and "insufficient penalty for exceeding deadlines." These risk factors are each rated as high priority and sent to the terminal. The user checks these risk factors on the terminal and adds comments to amend the penalty clause. After the amendment information is sent to the server, the server updates the risk assessment and reflects it in the integrated document management system. The user receives the latest risk assessment for this contract in a risk assessment report that is generated periodically.

[0510] The above is a specific embodiment for carrying out the present invention. This system enables a company to efficiently and accurately manage documents and risks.

[0511] The processing flow will be explained below.

[0512] Step 1:

[0513] The user selects a document using the "upload document" button on the terminal and uploads it to the server.

[0514] Step 2:

[0515] The server receives the uploaded document and sends it to the Generative AI's analysis engine to analyze the document's content, where sections and paragraphs of the document are identified.

[0516] Step 3:

[0517] The server uses generative AI to extract risk factors and errors within the document, such as "ambiguous contract clauses" and "insufficient penalties for exceeding deadlines."

[0518] Step 4:

[0519] The server evaluates the severity and urgency of the extracted risk factors and errors and assigns a numerical score, which categorizes each risk and error as "high," "medium," or "low."

[0520] Step 5:

[0521] The server converts the prioritized risk factors and error results into JSON format and sends them to the terminal, which receives the results and displays the analysis results on the user interface.

[0522] Step 6:

[0523] The user checks the analysis results on the device. For example, high-priority risk factors are displayed in red, medium-priority in yellow, and low-priority in blue.

[0524] Step 7:

[0525] The user can add corrections or comments to the analysis results as needed. Once corrections are complete, the user clicks the "Confirm" button to submit the information.

[0526] Step 8:

[0527] The terminal sends the user's modified information to the server, which receives the modified information and updates the existing risk assessment database.

[0528] Step 9:

[0529] The server reflects the updated risk assessment in the integrated document management system, enabling centralized management.

[0530] Step 10:

[0531] The server automatically generates risk assessment reports on a regular basis and sends the reports to users via email or other means, providing them with the latest risk information.

[0532] Example 1

[0533] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0534] In modern companies, document management and risk assessment processes are extremely time-consuming and labor-intensive. In particular, efficiently analyzing large volumes of documents and extracting and assessing risk factors and errors based on the results is difficult to do manually, and the accuracy of the results is limited. Furthermore, because risk assessment is performed manually, delays in updating information and errors can occur. There is a need for a system that can resolve these issues and perform document management and risk assessment efficiently and accurately.

[0535] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0536] In this invention, the server includes means for uploading documents to an information processing device, means for analyzing documents using generative artificial intelligence and extracting risk factors and errors, means for prioritizing the extracted risk factors and errors based on them, means for transmitting data to display the prioritized risk factors and errors on an information display device, means for receiving correction information from a user and updating a risk assessment, means for integrating the updated risk assessment into an integrated file management system, means for a user to check the analysis results and add comments, means for saving the updated risk assessment results, and means for automatically generating and transmitting a risk assessment report. This makes it possible to efficiently and accurately automate the document management and risk assessment processes.

[0537] "Generative AI" is an AI technology that has the ability to learn from data and automatically generate information.

[0538] A "document" is a collection of information in electronic or printed form, including textual and / or graphical information.

[0539] "Risk Factors" refers to the content or conditions contained in the document that may cause problems or dangers.

[0540] "Error" means a mistake or defect in a document.

[0541] "Prioritization" is the process of ranking risk factors or errors based on their importance and urgency.

[0542] An "information display device" is a device that displays analysis results and the priorities of risk factors and errors to the user.

[0543] "Revision information" refers to the revisions and comments on the document provided by the user.

[0544] "Risk assessment" is the result of a comprehensive evaluation of the extracted risk factors and the impact and probability of errors.

[0545] An "integrated file management system" is a system for centrally managing documents across an entire company and sharing necessary information.

[0546] The "information processing device" is a computer device for uploading documents and displaying analysis results.

[0547] A "risk assessment report" is a report prepared based on the latest risk assessment and compiles information for risk management.

[0548] The present invention is a system that uses generative artificial intelligence to automate and streamline document management and risk assessment in a company. Specific embodiments of this system are described below.

[0549] This system consists of a server, terminals, and users.

[0550] server

[0551] The server is the central part of the system, receiving documents, analyzing them, extracting risk factors and errors, prioritizing them, transmitting data, updating risk assessments, and connecting with the integrated file management system. The server uses generative AI models to analyze uploaded documents. This analysis process breaks down documents, identifies individual sections and paragraphs, and extracts risk factors and errors.

[0552] Terminal

[0553] The terminal provides an interface to the user, who can use the terminal to upload documents, check the analysis results, and submit correction information.

[0554] User

[0555] The user operates the system, uploads a specific document to the terminal, checks the analysis results, and inputs correction information as necessary.

[0556] Specific names of hardware and software used

[0557] This system uses a generative AI model, an information display device, an information processing device, and an integrated file management system.

[0558] Specific examples

[0559] For example, suppose a user uploads a new contract to the system. The user sends the contract to the server via the "Upload Document" button on their device. The server receives the contract, analyzes it using a generative AI model, and extracts risk factors such as "ambiguity in contract clauses" and "insufficient penalty for overdue deadlines." These risk factors are each rated as high priority and sent to the device. The user reviews these risk factors on their device and adds comments to amend the penalty clauses. After the amendments are sent to the server, the server updates the risk assessment and reflects it in the integrated file management system. The user receives the latest risk assessment for this contract in a regularly generated risk assessment report. This process ensures efficient and accurate document management and risk management.

[0560] Prompt Sentence Examples

[0561] To get the generative AI model to parse a document, use a prompt like this:

[0562] Analyze the following contract and extract risk factors and errors:

[0563] Contract text

[0564] ---

[0565] [Contract details here]

[0566] The above is a specific embodiment for carrying out the present invention. This system enables a company to efficiently and accurately manage documents and risks.

[0567] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0568] Step 1: Upload your documents

[0569] The user clicks the "Upload Document" button on the device and selects the document file to upload.

[0570] The terminal transmits the selected document file to the server.

[0571] The server receives and stores the uploaded document.

[0572] Input: A document file selected by the user (e.g., contract.pdf)

[0573] Data processing: receiving and storing files

[0574] Output: Document file saved on the server

[0575] As a specific operation, the user selects a file called "contract.pdf" and clicks the "upload document" button.

[0576] Step 2: Parsing the document

[0577] The server passes the received document to the generative AI model.

[0578] A generative AI model analyzes the document and identifies each section and paragraph.

[0579] The server receives the risk factor and error extraction results from the generative AI model.

[0580] Input: Document file stored on the server

[0581] Data Computing: Generative AI models analyze documents, extract risk factors and errors

[0582] Output: A list of extracted risk factors and errors

[0583] Specifically, the generative AI model extracts risk factors such as "ambiguity in contract terms" and "insufficient penalties for exceeding deadlines."

[0584] Step 3: Prioritize risks and errors

[0585] The server quantifies the extracted risk factors and the importance and urgency of the errors.

[0586] The server classifies risk factors and errors into "high," "medium," and "low" priorities.

[0587] Input: List of extracted risk factors and errors

[0588] Data calculation: Prioritization of risk factors and errors (quantification and classification)

[0589] Output: A prioritized list of risk factors and errors

[0590] As a specific operation, the ambiguity of the penalty clause is evaluated as a high priority.

[0591] Step 4: Sending results to the user interface

[0592] The server sends the prioritized results to the terminal.

[0593] The device displays the analysis results in a user interface.

[0594] Input: A prioritized list of risk factors and errors

[0595] Data transmission: Sending a priority list to the device

[0596] Output: Analysis results displayed to the user

[0597] Specifically, high-priority risk factors are displayed in red, and unclear penalty clauses are displayed in red on the user's screen.

[0598] Step 5: User review and correction

[0599] The user checks the analysis results through the terminal.

[0600] The user adds correction information and comments and presses the "Confirm" button.

[0601] The terminal sends the correction information to the server.

[0602] Input: User corrections and comments

[0603] Data transmission: Sending correction information to the server

[0604] Output: Correction information sent to the server

[0605] As a specific operation, the user adds a comment saying, "You need to recheck the penalty clause."

[0606] Step 6: Update your risk assessment

[0607] The server receives the correction information from the user.

[0608] The server updates the risk assessment based on the latest information.

[0609] The updated risk assessment is saved in the database.

[0610] Input: Correction information from the user

[0611] Data calculation: Update risk assessment (recalculate and save)

[0612] Output: Updated risk assessment data

[0613] Specifically, the risk assessment is recalculated based on the corrected information and saved in the database.

[0614] Step 7: Integrate into an integrated file management system

[0615] The server sends the latest risk assessment to the integrated file management system and reflects it.

[0616] Input: Updated risk assessment data

[0617] Data submission: submission of risk assessments to an integrated file management system

[0618] Output: Risk assessment reflected in an integrated file management system

[0619] Specifically, the latest risk assessment is automatically added to the company's file management system.

[0620] Step 8: Generate a risk assessment report

[0621] The server automatically generates risk assessment reports on a regular basis.

[0622] The server sends the generated report to the user.

[0623] Input: Latest risk assessment data

[0624] Data calculations: Automatic generation of risk assessment reports

[0625] Data submission: Sending risk assessment reports to users

[0626] Output: Risk assessment report sent to user

[0627] Specifically, an automatically generated risk assessment report is sent to the user's email address once a month.

[0628] (Application example 1)

[0629] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0630] In conventional factories, document analysis of equipment and process management is often performed manually, which delays the detection of risk factors and errors and makes it difficult to implement timely improvements. Furthermore, this process is time-consuming and labor-intensive, resulting in reduced production efficiency and safety issues. There is a need to solve this issue and provide an automated risk management system.

[0631] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0632] In this invention, the server includes means for analyzing documents using generative AI and extracting risk factors and errors, means for prioritizing the extracted risk factors and errors, means for transmitting data to display the prioritized risk factors and errors on a user interface, means for receiving correction information from a user and updating risk assessments, means for integrating the updated risk assessments into an integrated data management system, and means for analyzing documents for equipment and process management in factories, detecting risk factors and errors, and proposing necessary improvements. This enables the automation and efficiency of document management and risk assessment, thereby improving productivity and safety.

[0633] "Generative AI" is an AI technology that generates knowledge based on given data and makes decisions and predictions.

[0634] "Document" means an electronic file or printed material containing written information.

[0635] "Risk factors" refer to events or conditions that have the potential to cause problems or trouble.

[0636] "Error" refers to an inaccurate description or operational error that occurs in a document or process.

[0637] "Prioritizing" refers to determining the order of extracted risk factors and errors based on their importance and urgency.

[0638] "User interface" refers to an interactive screen or display that allows a user to interact with a system.

[0639] "Transmitting data" refers to the electronic transfer of analysis results or risk information to another device or system.

[0640] "Correction information" refers to information provided by the user to correct or supplement extracted risk factors or errors.

[0641] "Risk assessment" refers to the evaluation values ​​and safety judgments for extracted risk factors and errors.

[0642] An "integrated data management system" refers to a system that centrally manages multiple data sets and integrates and processes the necessary information.

[0643] A "factory" refers to facilities and equipment used for manufacturing and production activities.

[0644] "Equipment" refers to machinery and equipment such as production lines and manufacturing devices used within a factory.

[0645] "Process control" refers to the planning, monitoring, and control of the production process in a factory.

[0646] "Document analysis" refers to the process of analyzing text data and extracting useful information and patterns.

[0647] "Improvements" refer to areas in the current process or design that require change or improvement.

[0648] The "Factory Document Risk Assessment Robot" refers to a robot system that analyzes documents used within a factory, automatically detects and evaluates risk factors and errors, and proposes necessary improvements.

[0649] The system embodying this invention automates document analysis and risk assessment in factories, providing efficient risk management. Specifically, it has the following configuration.

[0650] System configuration

[0651] Server: The central part of the system, which analyzes documents, extracts risk factors and errors, prioritizes them, transmits data, and updates risk assessments, and integrates the updated risk assessments into the integrated data management system.

[0652] Robot: Scans documents related to equipment and process control used in the factory and uploads them to a server, and also provides an interface for users to provide correction information.

[0653] User: Operates the system as a factory manager or worker, uploading documents, checking analysis results, and providing correction information.

[0654] Program processing flow

[0655] 1. Document upload: A user uses a robot to upload a document to the server, for example, a factory inspection list or equipment manual.

[0656] 2. Document analysis: The server receives the uploaded document and analyzes it using a generative AI model (e.g., OpenAI GPT-4). During the analysis process, the server breaks down the document, identifies each section and paragraph, and extracts risk factors and errors.

[0657] 3. Prioritization of risks and errors: The server evaluates the importance and urgency of the extracted risk factors and errors, quantifies them, and classifies them into "high," "medium," or "low" priorities.

[0658] 4. Sending results to the user interface: The server sends the prioritized results to the robot's interface, allowing the user to review the analysis results. For example, high-risk factors are displayed in red.

[0659] 5. User confirmation and correction: The user checks the analysis results on the interface and adds corrections or comments as necessary. Once corrections are complete, the user presses the "Confirmation Complete" button, and the robot sends the corrections to the server.

[0660] 6. Risk assessment update: The server receives the correction information from the user and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results as needed.

[0661] 7. Integration into the Integrated Data Management System: The server integrates the latest risk assessments into the integrated data management system, which provides a single source of risk management across the entire factory.

[0662] Specific examples

[0663] For example, a user uploads a new inspection list for a factory into the system. The inspection list contains the following:

[0664] 1. Machine A inspection: hydraulic pressure normal, sound abnormal

[0665] 2. Machine B inspection: High temperature, heavy wear

[0666] 3. Machine C inspection: normal operation, no vibration

[0667] The server receives the inspection list and analyzes it using a generative AI model, extracting "abnormal sound" and "high temperature" as risk factors. These are each rated as high priority and sent to the robot's interface. The user checks these risk factors and enters comments, such as adding an inspection to identify the cause of "abnormal sound." Corrections are sent to the server, and the risk assessment is updated. As a result, the user can always understand the latest risk assessment and take appropriate measures.

[0668] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0669] Step 1:

[0670] The user uploads documents to the server using a robot. At this time, the user has the robot scan factory documents such as work procedures and inspection lists. The documents are sent as electronic data to the server, which then receives the data.

[0671] Input: Document data scanned by the robot

[0672] Output: Document data stored on the server

[0673] Step 2:

[0674] The server receives the uploaded document and analyzes it using a generative AI model. During this process, the server passes the received document data to the generative AI, which creates prompts for decomposition and analysis. The generative AI model (e.g., OpenAI GPT-4) identifies each section and paragraph of the document and extracts risk factors and errors.

[0675] Input: Uploaded document data

[0676] Output: Risk factors and error extraction results

[0677] Step 3:

[0678] The server evaluates the importance and urgency of the extracted risk factors and errors, and quantifies them. After the evaluation, the risks and errors are classified into "high," "medium," and "low" priorities. In this process, a numerical evaluation is performed in comparison with pre-set evaluation criteria.

[0679] Input: Risk factors and error extraction results

[0680] Output: Prioritized risk factors and errors

[0681] Step 4:

[0682] The server sends the prioritized results to the robot's interface, allowing the user to check the analysis results. The user interface displays high-priority factors in red, medium-priority factors in yellow, and low-priority factors in blue. This allows the user to check important risk factors at a glance.

[0683] Input: Prioritized risk factors and errors

[0684] Output: The result displayed on the user interface

[0685] Step 5:

[0686] The user checks the analysis results on the interface and adds correction information or comments as necessary. For example, they can enter a comment to add an inspection to identify the cause of the "sound abnormality." Once the corrections are complete, the user presses the "Confirmation Complete" button, and the robot sends the correction information to the server.

[0687] Input: User corrections and comments on analysis results

[0688] Output: Analysis results with correction information added

[0689] Step 6:

[0690] The server receives the correction information from the user and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results as needed.

[0691] Input: Correction information submitted by the user

[0692] Output: Latest risk assessment

[0693] Step 7:

[0694] The server integrates the latest risk assessments into an integrated data management system, enabling centralized risk management across the entire factory. Periodic risk assessment reports are automatically generated and sent to users.

[0695] Input: Latest risk assessment

[0696] Output: Risk assessment and risk assessment report integrated into an integrated data management system

[0697] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0698] The present invention is a system that uses generative artificial intelligence to automate and streamline document management and risk assessment in companies, and by combining it with an emotion engine that recognizes user emotions, it achieves a more advanced user experience and precise risk management. This system is specifically implemented as follows.

[0699] System configuration

[0700] Server: The central part of the system, responsible for document analysis, risk factor and error extraction, prioritization, data transmission, risk assessment updates, emotion recognition, and integration of updates.

[0701] Terminal: Provides a user interface where users can upload documents, check analysis results, submit corrections, and provide emotion information.

[0702] User: Operates the system to upload documents, check analysis results, provide corrections, and express emotions to provide feedback through the emotion engine.

[0703] Program processing flow

[0704] 1. Document upload: A user uploads a document to the server using a terminal. For example, a user sends a contract to the server via the "Upload Document" button on the terminal.

[0705] 2. Document analysis: The server receives the uploaded document and analyzes it using generative AI. During the analysis process, the server breaks down the document, identifies each section and paragraph, and extracts risk factors and errors.

[0706] 3. Prioritization of risks and errors: The server evaluates the importance and urgency of the extracted risk factors and errors, and then assigns them numerical values. After the evaluation, the server classifies the risks and errors into "high," "medium," or "low" priorities.

[0707] 4. Sending results to the user interface: The server converts the prioritized risk factors and error results into JSON format and sends them to the terminal. The terminal receives the results and displays the analysis results on the user interface.

[0708] 5. User emotion detection and feedback: The emotion engine recognizes the user's emotions using emotion information provided by the user, such as a camera or microphone. For example, the user analyzes facial expressions and tone of voice based on the analysis results, and the emotion engine processes them.

[0709] 6. Emotion-based priority adjustment: The emotion engine readjusts the priority of risk factors and errors based on the user's emotions. For example, risk factors that the user expresses discomfort with will be given a higher priority.

[0710] 7. User confirmation and correction: The user checks the analysis results on the device and adds correction information and comments as necessary. After completing the corrections, click the "Confirmation Complete" button to submit the information.

[0711] 8. Risk Assessment Update: The server receives the user's revised information and updates the risk assessment based on the latest information. The updated risk assessment is stored in the database and can be compared with past assessment results as needed.

[0712] 9. Integration into Unified Document Management System: The server integrates the latest risk assessments into the Unified Document Management System, enabling centralized risk management across the enterprise.

[0713] 10. Risk assessment report generation: The server will automatically generate risk assessment reports periodically and send them to users, who can use them to strengthen their regular risk management and countermeasures.

[0714] Specific examples

[0715] For example, consider what happens when a user uploads a new contract to the system. The server receives the contract and analyzes it using a generation AI, extracting risk factors such as "ambiguous contract terms" and "insufficient penalties for overdue documents." Each of these risk factors is rated as high priority and sent to the device. While the user is reviewing the results on the device, the emotion engine recognizes the user's facial expressions and detects that the user is expressing displeasure. As a result, the emotion engine sets the priority of the relevant risk factor even higher and displays the results to the user again. The user can then add corrections based on this, and the server updates the risk assessment. Finally, the updated risk assessment is reflected in the integrated document management system and sent to the user as a regular risk assessment report.

[0716] The above is a specific embodiment for carrying out the present invention. This system allows companies to manage documents and risks efficiently and accurately, and by incorporating feedback based on user emotions, more precise risk assessment and improvement can be achieved.

[0717] The processing flow will be explained below.

[0718] Step 1:

[0719] The user uses the "Document Upload" button on the device to select a document and upload it to the server. For example, when a user uploads a contract, they select the file and click the button to send it.

[0720] Step 2:

[0721] The server receives the uploaded document and sends it to the Generative AI's analysis engine for analysis, where the document is parsed and each section or paragraph is identified, such as the "Terms" and "Terms" sections in a contract.

[0722] Step 3:

[0723] The server uses generative AI to analyze the contents of the document and extract risk factors and errors, such as "risk of expiration" and "ambiguous contract terms."

[0724] Step 4:

[0725] The server evaluates the importance and urgency of the extracted risk factors and errors and assigns a numerical score. For example, the "risk of expiration" is evaluated as 9 out of 10.

[0726] Step 5:

[0727] The server converts the prioritized risk factors and error results into JSON format and sends it to the terminal. The terminal receives the results and displays the analysis results on the user interface. For example, high-priority risk factors are displayed in red.

[0728] Step 6:

[0729] While checking the analysis results, the user provides real-time emotions using the device's camera and microphone. For example, if the user feels dissatisfied, the emotion engine will recognize facial expressions and analyze the tone of voice.

[0730] Step 7:

[0731] The emotion engine processes the user's emotion information and reflects the user's dissatisfaction or surprise in the priority of risk factors. For example, a risk factor that the user expresses discomfort with is given a higher priority.

[0732] Step 8:

[0733] The server displays the adjusted risk factors and error priorities again in the user interface, and the user reviews the results and adds corrections or comments as needed.

[0734] Step 9:

[0735] After the user has completed inputting the correction information, he / she clicks the "Confirmation Complete" button to send the information from the terminal to the server. For example, he / she may enter correction comments that specifically indicate the "ambiguous contract terms."

[0736] Step 10:

[0737] The server receives the user's modified information and updates the existing risk assessment database, which is used for future document analysis and risk assessment processes.

[0738] Step 11:

[0739] The server updates the integrated document management system with the latest risk assessments, enabling centralized risk management and updating the risk database available across the entire company.

[0740] Step 12:

[0741] The server automatically generates a risk assessment report periodically and transmits the report to the user. For example, the server generates a monthly risk assessment report and transmits it to the user by email.

[0742] With this detailed processing flow, the present invention enables document management and risk assessment to be carried out efficiently and accurately, and by incorporating feedback based on the user's emotions, more precise risk assessment can be achieved.

[0743] Example 2

[0744] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0745] Conventional document management and risk assessment systems have issues such as difficulty in centralized management and inability to perform efficient risk assessment and correction. Furthermore, the accuracy of risk assessment that takes user emotions into account has not been sufficiently improved, and an improved user experience is required. As a result, risks can be overlooked or it can be difficult to respond quickly, making it difficult to optimize risk management across the entire company, requiring a lot of time and effort.

[0746] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0747] In this invention, the server includes: means for analyzing documents using generative artificial intelligence and extracting risk factors and errors; means for prioritizing the extracted risk factors and errors; means for transmitting data to display the prioritized risk factors and errors on a user interface; means for recognizing a user's emotions and readjusting the priorities of the risk factors and errors based on the emotions; means for receiving correction information from the user and updating the risk assessment; and means for integrating the updated risk assessment into an integrated document management system. This enables centralized and efficient performance of processes from document analysis to risk assessment, correction, and integrated management. Furthermore, a more accurate risk assessment that reflects the user's emotions can be achieved, improving the user experience.

[0748] "Generative AI" is a general term for AI technologies that have the ability to generate new information or results based on data.

[0749] A "document" refers to a file or data that contains information expressed as text data.

[0750] A "risk factor" is an element of potential negative consequence or danger that a particular event or action may cause.

[0751] An "Error" is any mistake or defect in a document that prevents accurate and proper processing or interpretation.

[0752] "User interface" refers to the display screen and input means that allow a user to interact with a system.

[0753] "Means for recognizing emotions" refers to processes or technologies that detect emotional expressions such as facial expressions and voice of a user and identify that emotional state.

[0754] "Measures for readjusting priorities" refers to the process of reevaluating and resetting the importance of risk factors and errors that have been set based on new information such as user sentiment.

[0755] "Correction information" refers to information including corrections and opinions provided by users, with the aim of improving documents and evaluation results.

[0756] "Updating" refers to the process of modifying, adding, or deleting existing data or assessment results based on new information.

[0757] An "integrated document management system" is a system for centrally managing, storing, and accessing multiple documents and data.

[0758] The present invention is a system that uses generative AI models to automate and streamline document management and risk assessment in companies. Furthermore, by combining it with an emotion engine that recognizes user emotions, it achieves a more advanced user experience and precise risk management. This system is specifically implemented as follows:

[0759] System configuration

[0760] server:

[0761] The server plays a central role in the system and has the following functions:

[0762] Document Analysis

[0763] Identifying risk factors and errors

[0764] Prioritization

[0765] Data transmission

[0766] Risk Assessment Updates

[0767] emotion recognition

[0768] Integration of update information

[0769] The server uses Python-based natural language processing libraries (e.g., NLTK, spaCy), machine learning techniques such as decision tree algorithms, and TensorFlow models for emotion recognition.

[0770] Device:

[0771] It provides the user interface and the means by which the user operates the system. The terminal has the following functions:

[0772] Document upload

[0773] Checking the analysis results

[0774] Submitting correction information

[0775] Providing emotional information

[0776] The device uses JavaScript-based front-end frameworks (e.g., React, Vue.js) to build the user interface.

[0777] User:

[0778] Users operate the system to upload documents, check analysis results, provide correction information, and express emotions to provide feedback through the emotion engine.

[0779] Specific examples

[0780] For example, let's consider what happens when a user uploads a new contract to the system. The user uploads the contract using a terminal. They click the "Upload Document" button on the terminal, select the contract file, and send it to the server. In this process, the file data is transferred to the server via an HTTP request.

[0781] The server uses a generative AI model to analyze the received contract. Specifically, it uses a Python-based natural language processing library (e.g., NLTK, spaCy) to break down the document and identify each section and paragraph. It then extracts risk factors and errors. Once this step is complete, it uses a decision tree algorithm to prioritize the extracted risk factors and errors.

[0782] Once the prioritization is complete, the server converts the results into JSON format and sends them to the device, where the analysis results are displayed in a user interface using a JavaScript-based front-end framework (e.g., React, Vue.js). The user can then view the analysis results displayed on the device.

[0783] As the user reviews the analysis results, their emotional information is sent to the emotion engine via the device's camera and microphone. The emotion engine then uses a TensorFlow model to analyze the user's emotions and automatically readjust the priority of risk factors that cause discomfort.

[0784] The user can add corrections or comments as needed and click the "Confirm" button to send the information to the server. Based on this information, the server updates the risk assessment and saves the latest assessment in the database. At the same time, the updated risk assessment is integrated into the integrated document management system.

[0785] Finally, the server automatically generates and sends risk assessment reports periodically to users, who can use the reports to strengthen their regular risk management and countermeasures.

[0786] Example prompts to input to the generative AI model

[0787] Analyze the contents of the contract below and extract the risk factors.

[0788] "Contract details:..."

[0789] The above is a specific embodiment for carrying out the present invention. This system allows companies to manage documents and risks efficiently and accurately, and by incorporating feedback based on user emotions, more precise risk assessment and improvement can be achieved.

[0790] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0791] Step 1:

[0792] Document upload

[0793] Subject: User

[0794] Specific operation: The user clicks the "Upload Document" button on the terminal, selects the contract file, and sends it to the server. At this time, the file data is sent using an HTTP request.

[0795] Input: A document file selected by the user

[0796] Output: Document file uploaded to the server

[0797] Step 2:

[0798] Document Analysis

[0799] Subject: Server

[0800] Specific operation: The server analyzes the received document file using a Python-based natural language processing library (e.g., NLTK, spaCy), breaking down the document into sections and paragraphs, and extracting risk factors and errors.

[0801] Input: Uploaded document file

[0802] Output: A list of extracted risk factors and errors

[0803] Step 3:

[0804] Prioritizing risks and errors

[0805] Subject: Server

[0806] What it does: The server uses a decision tree algorithm to evaluate the importance and urgency of the extracted risk factors and errors, and classifies them into "high," "medium," or "low" priorities.

[0807] Input: List of extracted risk factors and errors

[0808] Output: A prioritized list of risk factors and errors

[0809] Step 4:

[0810] Sending results to the user interface

[0811] Subject: Server

[0812] Specific operation: Converts the prioritized list of risk factors and errors into JSON format and sends it to the device.

[0813] Input: List of prioritized risk factors and errors

[0814] Output: The result as JSON data sent to the terminal.

[0815] Step 5:

[0816] Displaying analysis results

[0817] Subject: Terminal

[0818] Specific operation: The device uses the JSON data received and displays the analysis results on the user interface using a JavaScript-based front-end framework.

[0819] Input: Parsed result in JSON data format

[0820] Output: Analysis results displayed on the terminal

[0821] Step 6:

[0822] User emotion detection and feedback

[0823] Subject: User

[0824] How it works: While checking the analysis results, the user provides emotion information via the device's camera or microphone. The emotion engine then uses a TensorFlow model to analyze the emotion and identify the user's emotional state.

[0825] Input: User facial and voice data

[0826] Output: The user's emotional state as analyzed by the emotion engine.

[0827] Step 7:

[0828] Adjusting priorities based on emotions

[0829] Subject: Server

[0830] What it does: The server receives data from the emotion engine and re-prioritizes risk factors and errors based on the user's emotions.

[0831] Input: The user's emotional state as analyzed by the emotion engine

[0832] Output: A list of rescaled risk factors and errors

[0833] Step 8:

[0834] User confirmation and correction

[0835] Subject: User

[0836] Specific operation: The user checks the analysis results on their device and adds corrections or comments as necessary. They then click the "Confirm" button to send the information to the server. The corrections are sent in JSON format.

[0837] Input: User-added corrections and comments

[0838] Output: Correction information sent to the server

[0839] Step 9:

[0840] Risk Assessment Updates

[0841] Subject: Server

[0842] Specific operation: The server updates the risk assessment based on the latest information received from the correction information, and saves the updated assessment results in the database.

[0843] Input: User-submitted correction information

[0844] Output: Updated risk assessment results

[0845] Step 10:

[0846] Integration into an integrated document management system

[0847] Subject: Server

[0848] What it does: The server uploads the latest risk assessment results to an integrated document management system for centralized management across the enterprise.

[0849] Input: Updated risk assessment results

[0850] Output: Evaluation results stored in an integrated document management system

[0851] Step 11:

[0852] Generate a risk assessment report

[0853] Subject: Server

[0854] Specific operation: The server automatically generates a risk assessment report on a regular basis and sends it to the user in PDF format or other format.

[0855] Input: Latest risk assessment results

[0856] Output: Risk assessment report sent to user

[0857] (Application example 2)

[0858] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0859] In conventional document management systems, risk factor extraction and prioritization are performed manually, making efficient risk assessment difficult. Furthermore, risk assessment does not reflect user sentiment, preventing an improved user experience. Furthermore, rapid document analysis and real-time risk management are required in workplaces such as factory robots, but the lack of a system that meets these requirements has been an issue.

[0860] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0861] In this invention, the server includes: means for analyzing documents using generative artificial intelligence to extract risk factors and errors; means for prioritizing the extracted risk factors and errors; and means for transmitting data to display the prioritized risk factors and errors on a user interface. This enables rapid analysis of documents and automatic extraction of risk factors. The server also includes means for recognizing a user's emotional information and reevaluating the priority of risk factors and errors based on the emotional information, and means for acquiring the user's emotional information using an emotional recognition engine and providing feedback based on the emotional information. This improves the user experience and enables precise risk assessment.

[0862] "Generative AI" is an AI technology that analyzes documents and automatically extracts risk factors and errors.

[0863] "Risk factors" refer to potential problems or dangers inherent in a document.

[0864] "Error" means any mistake or inaccuracy in a Document.

[0865] "Prioritization" means ranking the extracted risk factors and errors based on their importance and urgency.

[0866] A "user interface" is an interface that provides a screen and operating means for a user to interact with a system.

[0867] "Correction information" refers to corrections or additional information to the document content provided by the user.

[0868] "Risk assessment" is the process of evaluating the impact of extracted risk factors and errors, and determining countermeasures based on that information.

[0869] An "integrated document management system" is a system that centrally manages documents and their risk assessment information.

[0870] "Emotional information" is data that represents the user's emotional state, and is acquired from facial expressions, tone of voice, and the like.

[0871] An "emotion recognition engine" is a technology that recognizes emotions by analyzing data obtained from the user's camera or microphone.

[0872] "Feedback" is the process of dynamically correcting the assessment results of risk factors and errors based on the user's emotional information.

[0873] This invention relates to a smart document analysis and risk assessment system for factory robots. The system consists of three main components: a server, a terminal, and a user.

[0874] Server Roles

[0875] The server plays a central role in the system and performs the following main processes:

[0876] 1. Document Analysis:

[0877] It uses generative artificial intelligence (AI) to analyze uploaded documents and extract risk factors and errors. The generative AI model is provided by the OpenAI API or a similar service.

[0878] 2. Prioritize risks and errors:

[0879] The identified risk factors and errors are evaluated and prioritized based on their importance. This evaluation is quantified and classified into categories of "high," "medium," or "low" according to the urgency of the risk or error.

[0880] 3. Recognition and feedback of emotional information:

[0881] An emotion recognition engine (e.g., DeepFace) is used to obtain user emotion information, and risk factors and error priorities are reassessed based on the results.

[0882] 4. Risk Assessment Update:

[0883] Receives corrections from users and updates the risk assessment based on the latest information. Updated risk assessments are integrated into the integrated document management system.

[0884] 5. Report Generation:

[0885] A risk assessment report is automatically generated periodically based on the updated risk assessment and sent to the user.

[0886] Device Role

[0887] The terminal provides a user interface for users to interact with the system. Specifically, it has the following functions:

[0888] 1. Upload your documents:

[0889] A factory manager uploads a document to the server using a smartphone or tablet, for example, by clicking the "Upload Document" button in the UI.

[0890] 2. Check the analysis results:

[0891] The analysis results sent from the server are displayed in real time, including a list of extracted risk factors and errors, and their priorities.

[0892] 3. Submitting Corrections:

[0893] The administrator will review the analysis results and submit corrections or additional comments as necessary.

[0894] User Roles

[0895] The users are mainly factory managers and perform the following operations:

[0896] 1. Upload your documents:

[0897] Documents used within the factory, such as work procedures, manuals, and contracts, are uploaded from the terminal to the server.

[0898] 2. Check the analysis results:

[0899] The analysis results are displayed on the device and feedback is provided on any risk factors or errors found.

[0900] 3. Providing emotional information:

[0901] Emotional information is provided using a camera or microphone, which allows the system to identify emotions in real time through an emotion recognition engine and incorporate them into risk assessment.

[0902] Specific examples

[0903] For example, when a factory manager uploads a new work procedure manual to the system, the following process takes place: The server analyzes the procedure manual and extracts risk factors and errors in the work process. Risk factors such as "ambiguous process procedures" and "insufficient safety measures" are extracted, rated as high priority, and sent to the terminal. While the manager is checking the results, a camera recognizes the manager's facial expressions, and if anxiety or discomfort is detected, the priority of that risk factor is set even higher. Finally, the manager adds any corrections, and the server recalculates the latest risk assessment. The risk assessment report generated by the system is useful for continuous risk management and strengthening countermeasures.

[0904] Generative AI model prompt example

[0905] Analyze the following factory operating procedures to identify risk factors and errors. Pay particular attention to the safety measures and procedure sequence when analyzing the following statements.

[0906] In this way, the present invention contributes to improving the work efficiency and safety of factories, and also has the effect of reducing the burden on managers.

[0907] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0908] Step 1:

[0909] Document upload

[0910] A user uses a terminal to upload a document to the server. Specifically, a factory manager presses the "upload document" button on a smartphone or tablet, selects and sends a document file such as a work procedure manual, manual, or contract. The terminal receives the document file and transfers the data to the server. The input is the document file, and the output is the transfer of the document file to the server.

[0911] Step 2:

[0912] Document Analysis

[0913] The server analyzes the received document file. Specifically, the server uses a generative AI model to break down the document content into sections and paragraphs and extract risk factors and errors. At this time, the prompt for the generative AI model (e.g., OpenAI API) is, "Analyze the following factory work procedure manual and extract risk factors and errors. Please analyze the following sentence, paying particular attention to safety measures and the order of procedures." The input is the document content, and the output is a list of extracted risk factors and errors.

[0914] Step 3:

[0915] Prioritizing risks and errors

[0916] The server evaluates the extracted risk factors and errors and sets priorities based on their importance and urgency. Specifically, it quantifies the evaluation results and categorizes the risks and errors into "high," "medium," and "low" categories. The input is a list of risk factors and errors, and the output is a prioritized list of risk factors and errors.

[0917] Step 4:

[0918] Sending and viewing analysis results

[0919] The server converts the prioritized risk factors and error results into JSON format and sends it to the terminal. The terminal receives the results and displays the analysis results on the user interface. Specifically, the risk factors and errors are displayed in list format by priority, making it easy for the user to check. The input is the list of prioritized risk factors and errors, and the output is the analysis results displayed on the terminal.

[0920] Step 5:

[0921] Recognition and feedback of emotional information

[0922] The device's camera and microphone are used to obtain the user's emotional information. The server uses an emotion recognition engine (e.g., DeepFace) to recognize emotions from the user's facial expressions and tone of voice, and based on the results, re-evaluates the priority of risk factors and errors. Specifically, risk factors that the user expresses discomfort with are given a higher priority. The input is the user's emotional information, and the output is a list of risk factors and errors with re-evaluated priorities.

[0923] Step 6:

[0924] Providing and sending correction information

[0925] The user checks the analysis results and adds any necessary corrections or comments. The device then sends the corrections to the server. Specifically, the user enters corrections for each item in the analysis results and clicks the "Confirm" button to send the results. The input is the user's corrections, and the output is the corrections sent to the server.

[0926] Step 7:

[0927] Risk Assessment Updates

[0928] The server receives the user's revised information and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results. The input is the user's revised information, and the output is the updated risk assessment.

[0929] Step 8:

[0930] Generate and submit risk assessment reports

[0931] The server automatically generates risk assessment reports periodically and sends them to the user. Specifically, it creates reports based on updated risk assessment data and sends them to the user's terminal. The input is the updated risk assessment data, and the output is the risk assessment report sent to the user.

[0932] As described above, the present invention is a system that can efficiently and accurately manage documents and assess risks, and realizes precise risk assessment that reflects the user's feelings.

[0933] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0934] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0935] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0936] [Third embodiment]

[0937] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0938] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0939] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0940] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0941] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0942] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0943] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0944] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0945] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0946] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0947] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0948] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0949] The present invention is a system that uses generative artificial intelligence to automate and streamline document management and risk assessment in a company, and is specifically implemented as follows.

[0950] System configuration

[0951] Server: Plays the central role in the system, analyzing documents, extracting risk factors and errors, prioritizing them, transmitting data, updating risk assessments, and linking with the integrated document management system.

[0952] Terminal: Provides a user interface, allowing users to upload documents, review analysis results, and submit corrections.

[0953] User: Operates the system to upload documents, check analysis results, and provide correction information.

[0954] Program processing flow

[0955] 1. Document upload: A user uploads a document to the server using a terminal. For example, a user sends a contract to the server via the "Upload Document" button on the terminal.

[0956] 2. Document analysis: The server receives the uploaded document and uses generative AI to analyze it. During the analysis process, the server breaks down the document, identifies each section and paragraph, and extracts risk factors and errors.

[0957] 3. Prioritization of risks and errors: The server evaluates the importance and urgency of the extracted risk factors and errors, and then assigns them numerical values. After the evaluation, the server classifies the risks and errors into "high," "medium," or "low" priorities.

[0958] 4. Sending results to the user interface: The server sends the prioritized results to the terminal, and the terminal displays the analysis results on the user interface. For example, high-priority risk factors are displayed in red, medium-priority in yellow, and low-priority in blue.

[0959] 5. User confirmation and correction: The user checks the analysis results and adds correction information and comments as necessary. After completing the corrections, the user presses the "Confirmation Complete" button, and the device sends the correction information to the server.

[0960] 6. Risk assessment update: The server receives the correction information from the user and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results as needed.

[0961] 7. Integration into the Unified Document Management System: The server integrates the latest risk assessments into the Unified Document Management System, enabling centralized risk management across the enterprise.

[0962] 8. Risk assessment report generation: The server will automatically generate a risk assessment report based on the latest risk assessment at regular intervals and send it to the user, who can use it to strengthen regular risk management and countermeasures.

[0963] Specific examples

[0964] For example, suppose a user uploads a new contract to the system. The server receives the contract and analyzes it using generation AI, extracting risk factors such as "ambiguity in contract clauses" and "insufficient penalty for exceeding deadlines." These risk factors are each rated as high priority and sent to the terminal. The user checks these risk factors on the terminal and adds comments to amend the penalty clause. After the amendment information is sent to the server, the server updates the risk assessment and reflects it in the integrated document management system. The user receives the latest risk assessment for this contract in a risk assessment report that is generated periodically.

[0965] The above is a specific embodiment for carrying out the present invention. This system enables a company to efficiently and accurately manage documents and risks.

[0966] The processing flow will be explained below.

[0967] Step 1:

[0968] The user selects a document using the "upload document" button on the terminal and uploads it to the server.

[0969] Step 2:

[0970] The server receives the uploaded document and sends it to the Generative AI's analysis engine to analyze the document's content, where sections and paragraphs of the document are identified.

[0971] Step 3:

[0972] The server uses generative AI to extract risk factors and errors within the document, such as "ambiguous contract clauses" and "insufficient penalties for exceeding deadlines."

[0973] Step 4:

[0974] The server evaluates the severity and urgency of the extracted risk factors and errors and assigns a numerical score, which categorizes each risk and error as "high," "medium," or "low."

[0975] Step 5:

[0976] The server converts the prioritized risk factors and error results into JSON format and sends them to the terminal, which receives the results and displays the analysis results on the user interface.

[0977] Step 6:

[0978] The user checks the analysis results on the device. For example, high-priority risk factors are displayed in red, medium-priority in yellow, and low-priority in blue.

[0979] Step 7:

[0980] The user can add corrections or comments to the analysis results as needed. Once corrections are complete, the user clicks the "Confirm" button to submit the information.

[0981] Step 8:

[0982] The terminal sends the user's modified information to the server, which receives the modified information and updates the existing risk assessment database.

[0983] Step 9:

[0984] The server reflects the updated risk assessment in the integrated document management system, enabling centralized management.

[0985] Step 10:

[0986] The server automatically generates risk assessment reports on a regular basis and sends the reports to users via email or other means, providing them with the latest risk information.

[0987] Example 1

[0988] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0989] In modern companies, document management and risk assessment processes are extremely time-consuming and labor-intensive. In particular, efficiently analyzing large volumes of documents and extracting and assessing risk factors and errors based on the results is difficult to do manually, and the accuracy of the results is limited. Furthermore, because risk assessment is performed manually, delays in updating information and errors can occur. There is a need for a system that can resolve these issues and perform document management and risk assessment efficiently and accurately.

[0990] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0991] In this invention, the server includes means for uploading documents to an information processing device, means for analyzing documents using generative artificial intelligence and extracting risk factors and errors, means for prioritizing the extracted risk factors and errors based on them, means for transmitting data to display the prioritized risk factors and errors on an information display device, means for receiving correction information from a user and updating a risk assessment, means for integrating the updated risk assessment into an integrated file management system, means for a user to check the analysis results and add comments, means for saving the updated risk assessment results, and means for automatically generating and transmitting a risk assessment report. This makes it possible to efficiently and accurately automate the document management and risk assessment processes.

[0992] "Generative AI" is an AI technology that has the ability to learn from data and automatically generate information.

[0993] A "document" is a collection of information in electronic or printed form, including textual and / or graphical information.

[0994] "Risk Factors" refers to the content or conditions contained in the document that may cause problems or dangers.

[0995] "Error" means a mistake or defect in a document.

[0996] "Prioritization" is the process of ranking risk factors or errors based on their importance and urgency.

[0997] An "information display device" is a device that displays analysis results and the priorities of risk factors and errors to the user.

[0998] "Revision information" refers to the revisions and comments on the document provided by the user.

[0999] "Risk assessment" is the result of a comprehensive evaluation of the extracted risk factors and the impact and probability of errors.

[1000] An "integrated file management system" is a system for centrally managing documents across an entire company and sharing necessary information.

[1001] The "information processing device" is a computer device for uploading documents and displaying analysis results.

[1002] A "risk assessment report" is a report prepared based on the latest risk assessment and compiles information for risk management.

[1003] The present invention is a system that uses generative artificial intelligence to automate and streamline document management and risk assessment in a company. Specific embodiments of this system are described below.

[1004] This system consists of a server, terminals, and users.

[1005] server

[1006] The server is the central part of the system, receiving documents, analyzing them, extracting risk factors and errors, prioritizing them, transmitting data, updating risk assessments, and connecting with the integrated file management system. The server uses generative AI models to analyze uploaded documents. This analysis process breaks down documents, identifies individual sections and paragraphs, and extracts risk factors and errors.

[1007] Terminal

[1008] The terminal provides an interface to the user, who can use the terminal to upload documents, check the analysis results, and submit correction information.

[1009] User

[1010] The user operates the system, uploads a specific document to the terminal, checks the analysis results, and inputs correction information as necessary.

[1011] Specific names of hardware and software used

[1012] This system uses a generative AI model, an information display device, an information processing device, and an integrated file management system.

[1013] Specific examples

[1014] For example, suppose a user uploads a new contract to the system. The user sends the contract to the server via the "Upload Document" button on their device. The server receives the contract, analyzes it using a generative AI model, and extracts risk factors such as "ambiguity in contract clauses" and "insufficient penalty for overdue deadlines." These risk factors are each rated as high priority and sent to the device. The user reviews these risk factors on their device and adds comments to amend the penalty clauses. After the amendments are sent to the server, the server updates the risk assessment and reflects it in the integrated file management system. The user receives the latest risk assessment for this contract in a regularly generated risk assessment report. This process ensures efficient and accurate document management and risk management.

[1015] Prompt Sentence Examples

[1016] To get the generative AI model to parse a document, use a prompt like this:

[1017] Analyze the following contract and extract risk factors and errors:

[1018] Contract text

[1019] ---

[1020] [Contract details here]

[1021] The above is a specific embodiment for carrying out the present invention. This system enables a company to efficiently and accurately manage documents and risks.

[1022] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1023] Step 1: Upload your documents

[1024] The user clicks the "Upload Document" button on the device and selects the document file to upload.

[1025] The terminal transmits the selected document file to the server.

[1026] The server receives and stores the uploaded document.

[1027] Input: A document file selected by the user (e.g., contract.pdf)

[1028] Data processing: receiving and storing files

[1029] Output: Document file saved on the server

[1030] As a specific operation, the user selects a file called "contract.pdf" and clicks the "upload document" button.

[1031] Step 2: Parsing the document

[1032] The server passes the received document to the generative AI model.

[1033] A generative AI model analyzes the document and identifies each section and paragraph.

[1034] The server receives the risk factor and error extraction results from the generative AI model.

[1035] Input: Document file stored on the server

[1036] Data Computing: Generative AI models analyze documents, extract risk factors and errors

[1037] Output: A list of extracted risk factors and errors

[1038] Specifically, the generative AI model extracts risk factors such as "ambiguity in contract terms" and "insufficient penalties for exceeding deadlines."

[1039] Step 3: Prioritize risks and errors

[1040] The server quantifies the extracted risk factors and the importance and urgency of the errors.

[1041] The server classifies risk factors and errors into "high," "medium," and "low" priorities.

[1042] Input: List of extracted risk factors and errors

[1043] Data calculation: Prioritization of risk factors and errors (quantification and classification)

[1044] Output: A prioritized list of risk factors and errors

[1045] As a specific operation, the ambiguity of the penalty clause is evaluated as a high priority.

[1046] Step 4: Sending results to the user interface

[1047] The server sends the prioritized results to the terminal.

[1048] The device displays the analysis results in a user interface.

[1049] Input: A prioritized list of risk factors and errors

[1050] Data transmission: Sending a priority list to the device

[1051] Output: Analysis results displayed to the user

[1052] Specifically, high-priority risk factors are displayed in red, and unclear penalty clauses are displayed in red on the user's screen.

[1053] Step 5: User review and correction

[1054] The user checks the analysis results through the terminal.

[1055] The user adds correction information and comments and presses the "Confirm" button.

[1056] The terminal sends the correction information to the server.

[1057] Input: User corrections and comments

[1058] Data transmission: Sending correction information to the server

[1059] Output: Correction information sent to the server

[1060] As a specific operation, the user adds a comment saying, "You need to recheck the penalty clause."

[1061] Step 6: Update your risk assessment

[1062] The server receives the correction information from the user.

[1063] The server updates the risk assessment based on the latest information.

[1064] The updated risk assessment is saved in the database.

[1065] Input: Correction information from the user

[1066] Data calculation: Update risk assessment (recalculate and save)

[1067] Output: Updated risk assessment data

[1068] Specifically, the risk assessment is recalculated based on the corrected information and saved in the database.

[1069] Step 7: Integrate into an integrated file management system

[1070] The server sends the latest risk assessment to the integrated file management system and reflects it.

[1071] Input: Updated risk assessment data

[1072] Data submission: submission of risk assessments to an integrated file management system

[1073] Output: Risk assessment reflected in an integrated file management system

[1074] Specifically, the latest risk assessment is automatically added to the company's file management system.

[1075] Step 8: Generate a risk assessment report

[1076] The server automatically generates risk assessment reports on a regular basis.

[1077] The server sends the generated report to the user.

[1078] Input: Latest risk assessment data

[1079] Data calculations: Automatic generation of risk assessment reports

[1080] Data submission: Sending risk assessment reports to users

[1081] Output: Risk assessment report sent to user

[1082] Specifically, an automatically generated risk assessment report is sent to the user's email address once a month.

[1083] (Application example 1)

[1084] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1085] In conventional factories, document analysis of equipment and process management is often performed manually, which delays the detection of risk factors and errors and makes it difficult to implement timely improvements. Furthermore, this process is time-consuming and labor-intensive, resulting in reduced production efficiency and safety issues. There is a need to solve this issue and provide an automated risk management system.

[1086] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1087] In this invention, the server includes means for analyzing documents using generative AI and extracting risk factors and errors, means for prioritizing the extracted risk factors and errors, means for transmitting data to display the prioritized risk factors and errors on a user interface, means for receiving correction information from a user and updating risk assessments, means for integrating the updated risk assessments into an integrated data management system, and means for analyzing documents for equipment and process management in factories, detecting risk factors and errors, and proposing necessary improvements. This enables the automation and efficiency of document management and risk assessment, thereby improving productivity and safety.

[1088] "Generative AI" is an AI technology that generates knowledge based on given data and makes decisions and predictions.

[1089] "Document" means an electronic file or printed material containing written information.

[1090] "Risk factors" refer to events or conditions that have the potential to cause problems or trouble.

[1091] "Error" refers to an inaccurate description or operational error that occurs in a document or process.

[1092] "Prioritizing" refers to determining the order of extracted risk factors and errors based on their importance and urgency.

[1093] "User interface" refers to an interactive screen or display that allows a user to interact with a system.

[1094] "Transmitting data" refers to the electronic transfer of analysis results or risk information to another device or system.

[1095] "Correction information" refers to information provided by the user to correct or supplement extracted risk factors or errors.

[1096] "Risk assessment" refers to the evaluation values ​​and safety judgments for extracted risk factors and errors.

[1097] An "integrated data management system" refers to a system that centrally manages multiple data sets and integrates and processes the necessary information.

[1098] A "factory" refers to facilities and equipment used for manufacturing and production activities.

[1099] "Equipment" refers to machinery and equipment such as production lines and manufacturing devices used within a factory.

[1100] "Process control" refers to the planning, monitoring, and control of the production process in a factory.

[1101] "Document analysis" refers to the process of analyzing text data and extracting useful information and patterns.

[1102] "Improvements" refer to areas in the current process or design that require change or improvement.

[1103] The "Factory Document Risk Assessment Robot" refers to a robot system that analyzes documents used within a factory, automatically detects and evaluates risk factors and errors, and proposes necessary improvements.

[1104] The system embodying this invention automates document analysis and risk assessment in factories, providing efficient risk management. Specifically, it has the following configuration.

[1105] System configuration

[1106] Server: The central part of the system, which analyzes documents, extracts risk factors and errors, prioritizes them, transmits data, and updates risk assessments, and integrates the updated risk assessments into the integrated data management system.

[1107] Robot: Scans documents related to equipment and process control used in the factory and uploads them to a server, and also provides an interface for users to provide correction information.

[1108] User: Operates the system as a factory manager or worker, uploading documents, checking analysis results, and providing correction information.

[1109] Program processing flow

[1110] 1. Document upload: A user uses a robot to upload a document to the server, for example, a factory inspection list or equipment manual.

[1111] 2. Document analysis: The server receives the uploaded document and analyzes it using a generative AI model (e.g., OpenAI GPT-4). During the analysis process, the server breaks down the document, identifies each section and paragraph, and extracts risk factors and errors.

[1112] 3. Prioritization of risks and errors: The server evaluates the importance and urgency of the extracted risk factors and errors, quantifies them, and classifies them into "high," "medium," or "low" priorities.

[1113] 4. Sending results to the user interface: The server sends the prioritized results to the robot's interface, allowing the user to review the analysis results. For example, high-risk factors are displayed in red.

[1114] 5. User confirmation and correction: The user checks the analysis results on the interface and adds corrections or comments as necessary. Once corrections are complete, the user presses the "Confirmation Complete" button, and the robot sends the corrections to the server.

[1115] 6. Risk assessment update: The server receives the correction information from the user and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results as needed.

[1116] 7. Integration into the Integrated Data Management System: The server integrates the latest risk assessments into the integrated data management system, which provides a single source of risk management across the entire factory.

[1117] Specific examples

[1118] For example, a user uploads a new inspection list for a factory into the system. The inspection list contains the following:

[1119] 1. Machine A inspection: hydraulic pressure normal, sound abnormal

[1120] 2. Machine B inspection: High temperature, heavy wear

[1121] 3. Machine C inspection: normal operation, no vibration

[1122] The server receives the inspection list and analyzes it using a generative AI model, extracting "abnormal sound" and "high temperature" as risk factors. These are each rated as high priority and sent to the robot's interface. The user checks these risk factors and enters comments, such as adding an inspection to identify the cause of "abnormal sound." Corrections are sent to the server, and the risk assessment is updated. As a result, the user can always understand the latest risk assessment and take appropriate measures.

[1123] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1124] Step 1:

[1125] The user uploads documents to the server using a robot. At this time, the user has the robot scan factory documents such as work procedures and inspection lists. The documents are sent as electronic data to the server, which then receives the data.

[1126] Input: Document data scanned by the robot

[1127] Output: Document data stored on the server

[1128] Step 2:

[1129] The server receives the uploaded document and analyzes it using a generative AI model. During this process, the server passes the received document data to the generative AI, which creates prompts for decomposition and analysis. The generative AI model (e.g., OpenAI GPT-4) identifies each section and paragraph of the document and extracts risk factors and errors.

[1130] Input: Uploaded document data

[1131] Output: Risk factors and error extraction results

[1132] Step 3:

[1133] The server evaluates the importance and urgency of the extracted risk factors and errors, and quantifies them. After the evaluation, the risks and errors are classified into "high," "medium," and "low" priorities. In this process, a numerical evaluation is performed in comparison with pre-set evaluation criteria.

[1134] Input: Risk factors and error extraction results

[1135] Output: Prioritized risk factors and errors

[1136] Step 4:

[1137] The server sends the prioritized results to the robot's interface, allowing the user to check the analysis results. The user interface displays high-priority factors in red, medium-priority factors in yellow, and low-priority factors in blue. This allows the user to check important risk factors at a glance.

[1138] Input: Prioritized risk factors and errors

[1139] Output: The result displayed on the user interface

[1140] Step 5:

[1141] The user checks the analysis results on the interface and adds correction information or comments as necessary. For example, they can enter a comment to add an inspection to identify the cause of the "sound abnormality." Once the corrections are complete, the user presses the "Confirmation Complete" button, and the robot sends the correction information to the server.

[1142] Input: User corrections and comments on analysis results

[1143] Output: Analysis results with correction information added

[1144] Step 6:

[1145] The server receives the correction information from the user and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results as needed.

[1146] Input: Correction information submitted by the user

[1147] Output: Latest risk assessment

[1148] Step 7:

[1149] The server integrates the latest risk assessments into an integrated data management system, enabling centralized risk management across the entire factory. Periodic risk assessment reports are automatically generated and sent to users.

[1150] Input: Latest risk assessment

[1151] Output: Risk assessment and risk assessment report integrated into an integrated data management system

[1152] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1153] The present invention is a system that uses generative artificial intelligence to automate and streamline document management and risk assessment in companies, and by combining it with an emotion engine that recognizes user emotions, it achieves a more advanced user experience and precise risk management. This system is specifically implemented as follows.

[1154] System configuration

[1155] Server: The central part of the system, responsible for document analysis, risk factor and error extraction, prioritization, data transmission, risk assessment updates, emotion recognition, and integration of updates.

[1156] Terminal: Provides a user interface where users can upload documents, check analysis results, submit corrections, and provide emotion information.

[1157] User: Operates the system to upload documents, check analysis results, provide corrections, and express emotions to provide feedback through the emotion engine.

[1158] Program processing flow

[1159] 1. Document upload: A user uploads a document to the server using a terminal. For example, a user sends a contract to the server via the "Upload Document" button on the terminal.

[1160] 2. Document analysis: The server receives the uploaded document and analyzes it using generative AI. During the analysis process, the server breaks down the document, identifies each section and paragraph, and extracts risk factors and errors.

[1161] 3. Prioritization of risks and errors: The server evaluates the importance and urgency of the extracted risk factors and errors, and then assigns them numerical values. After the evaluation, the server classifies the risks and errors into "high," "medium," or "low" priorities.

[1162] 4. Sending results to the user interface: The server converts the prioritized risk factors and error results into JSON format and sends them to the terminal. The terminal receives the results and displays the analysis results on the user interface.

[1163] 5. User emotion detection and feedback: The emotion engine recognizes the user's emotions using emotion information provided by the user, such as a camera or microphone. For example, the user analyzes facial expressions and tone of voice based on the analysis results, and the emotion engine processes them.

[1164] 6. Emotion-based priority adjustment: The emotion engine readjusts the priority of risk factors and errors based on the user's emotions. For example, risk factors that the user expresses discomfort with will be given a higher priority.

[1165] 7. User confirmation and correction: The user checks the analysis results on the device and adds correction information and comments as necessary. After completing the corrections, click the "Confirmation Complete" button to submit the information.

[1166] 8. Risk Assessment Update: The server receives the user's revised information and updates the risk assessment based on the latest information. The updated risk assessment is stored in the database and can be compared with past assessment results as needed.

[1167] 9. Integration into Unified Document Management System: The server integrates the latest risk assessments into the Unified Document Management System, enabling centralized risk management across the enterprise.

[1168] 10. Risk assessment report generation: The server will automatically generate risk assessment reports periodically and send them to users, who can use them to strengthen their regular risk management and countermeasures.

[1169] Specific examples

[1170] For example, consider what happens when a user uploads a new contract to the system. The server receives the contract and analyzes it using a generation AI, extracting risk factors such as "ambiguous contract terms" and "insufficient penalties for overdue documents." Each of these risk factors is rated as high priority and sent to the device. While the user is reviewing the results on the device, the emotion engine recognizes the user's facial expressions and detects that the user is expressing displeasure. As a result, the emotion engine sets the priority of the relevant risk factor even higher and displays the results to the user again. The user can then add corrections based on this, and the server updates the risk assessment. Finally, the updated risk assessment is reflected in the integrated document management system and sent to the user as a regular risk assessment report.

[1171] The above is a specific embodiment for carrying out the present invention. This system allows companies to manage documents and risks efficiently and accurately, and by incorporating feedback based on user emotions, more precise risk assessment and improvement can be achieved.

[1172] The processing flow will be explained below.

[1173] Step 1:

[1174] The user uses the "Document Upload" button on the device to select a document and upload it to the server. For example, when a user uploads a contract, they select the file and click the button to send it.

[1175] Step 2:

[1176] The server receives the uploaded document and sends it to the Generative AI's analysis engine for analysis, where the document is parsed and each section or paragraph is identified, such as the "Terms" and "Terms" sections in a contract.

[1177] Step 3:

[1178] The server uses generative AI to analyze the contents of the document and extract risk factors and errors, such as "risk of expiration" and "ambiguous contract terms."

[1179] Step 4:

[1180] The server evaluates the importance and urgency of the extracted risk factors and errors and assigns a numerical score. For example, the "risk of expiration" is evaluated as 9 out of 10.

[1181] Step 5:

[1182] The server converts the prioritized risk factors and error results into JSON format and sends it to the terminal. The terminal receives the results and displays the analysis results on the user interface. For example, high-priority risk factors are displayed in red.

[1183] Step 6:

[1184] While checking the analysis results, the user provides real-time emotions using the device's camera and microphone. For example, if the user feels dissatisfied, the emotion engine will recognize facial expressions and analyze the tone of voice.

[1185] Step 7:

[1186] The emotion engine processes the user's emotion information and reflects the user's dissatisfaction or surprise in the priority of risk factors. For example, a risk factor that the user expresses discomfort with is given a higher priority.

[1187] Step 8:

[1188] The server displays the adjusted risk factors and error priorities again in the user interface, and the user reviews the results and adds corrections or comments as needed.

[1189] Step 9:

[1190] After the user has completed inputting the correction information, he / she clicks the "Confirmation Complete" button to send the information from the terminal to the server. For example, he / she may enter correction comments that specifically indicate the "ambiguous contract terms."

[1191] Step 10:

[1192] The server receives the user's modified information and updates the existing risk assessment database, which is used for future document analysis and risk assessment processes.

[1193] Step 11:

[1194] The server updates the integrated document management system with the latest risk assessments, enabling centralized risk management and updating the risk database available across the entire company.

[1195] Step 12:

[1196] The server automatically generates a risk assessment report periodically and transmits the report to the user. For example, the server generates a monthly risk assessment report and transmits it to the user by email.

[1197] With this detailed processing flow, the present invention enables document management and risk assessment to be carried out efficiently and accurately, and by incorporating feedback based on the user's emotions, more precise risk assessment can be achieved.

[1198] Example 2

[1199] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1200] Conventional document management and risk assessment systems have issues such as difficulty in centralized management and inability to perform efficient risk assessment and correction. Furthermore, the accuracy of risk assessment that takes user emotions into account has not been sufficiently improved, and an improved user experience is required. As a result, risks can be overlooked or it can be difficult to respond quickly, making it difficult to optimize risk management across the entire company, requiring a lot of time and effort.

[1201] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1202] In this invention, the server includes: means for analyzing documents using generative artificial intelligence and extracting risk factors and errors; means for prioritizing the extracted risk factors and errors; means for transmitting data to display the prioritized risk factors and errors on a user interface; means for recognizing a user's emotions and readjusting the priorities of the risk factors and errors based on the emotions; means for receiving correction information from the user and updating the risk assessment; and means for integrating the updated risk assessment into an integrated document management system. This enables centralized and efficient performance of processes from document analysis to risk assessment, correction, and integrated management. Furthermore, a more accurate risk assessment that reflects the user's emotions can be achieved, improving the user experience.

[1203] "Generative AI" is a general term for AI technologies that have the ability to generate new information or results based on data.

[1204] A "document" refers to a file or data that contains information expressed as text data.

[1205] A "risk factor" is an element of potential negative consequence or danger that a particular event or action may cause.

[1206] An "Error" is any mistake or defect in a document that prevents accurate and proper processing or interpretation.

[1207] "User interface" refers to the display screen and input means that allow a user to interact with a system.

[1208] "Means for recognizing emotions" refers to processes or technologies that detect emotional expressions such as facial expressions and voice of a user and identify that emotional state.

[1209] "Measures for readjusting priorities" refers to the process of reevaluating and resetting the importance of risk factors and errors that have been set based on new information such as user sentiment.

[1210] "Correction information" refers to information including corrections and opinions provided by users, with the aim of improving documents and evaluation results.

[1211] "Updating" refers to the process of modifying, adding, or deleting existing data or assessment results based on new information.

[1212] An "integrated document management system" is a system for centrally managing, storing, and accessing multiple documents and data.

[1213] The present invention is a system that uses generative AI models to automate and streamline document management and risk assessment in companies. Furthermore, by combining it with an emotion engine that recognizes user emotions, it achieves a more advanced user experience and precise risk management. This system is specifically implemented as follows:

[1214] System configuration

[1215] server:

[1216] The server plays a central role in the system and has the following functions:

[1217] Document Analysis

[1218] Identifying risk factors and errors

[1219] Prioritization

[1220] Data transmission

[1221] Risk Assessment Updates

[1222] emotion recognition

[1223] Integration of update information

[1224] The server uses Python-based natural language processing libraries (e.g., NLTK, spaCy), machine learning techniques such as decision tree algorithms, and TensorFlow models for emotion recognition.

[1225] Device:

[1226] It provides the user interface and the means by which the user operates the system. The terminal has the following functions:

[1227] Document upload

[1228] Checking the analysis results

[1229] Submitting correction information

[1230] Providing emotional information

[1231] The device uses JavaScript-based front-end frameworks (e.g., React, Vue.js) to build the user interface.

[1232] User:

[1233] Users operate the system to upload documents, check analysis results, provide correction information, and express emotions to provide feedback through the emotion engine.

[1234] Specific examples

[1235] For example, let's consider what happens when a user uploads a new contract to the system. The user uploads the contract using a terminal. They click the "Upload Document" button on the terminal, select the contract file, and send it to the server. In this process, the file data is transferred to the server via an HTTP request.

[1236] The server uses a generative AI model to analyze the received contract. Specifically, it uses a Python-based natural language processing library (e.g., NLTK, spaCy) to break down the document and identify each section and paragraph. It then extracts risk factors and errors. Once this step is complete, it uses a decision tree algorithm to prioritize the extracted risk factors and errors.

[1237] Once the prioritization is complete, the server converts the results into JSON format and sends them to the device, where the analysis results are displayed in a user interface using a JavaScript-based front-end framework (e.g., React, Vue.js). The user can then view the analysis results displayed on the device.

[1238] As the user reviews the analysis results, their emotional information is sent to the emotion engine via the device's camera and microphone. The emotion engine then uses a TensorFlow model to analyze the user's emotions and automatically readjust the priority of risk factors that cause discomfort.

[1239] The user can add corrections or comments as needed and click the "Confirm" button to send the information to the server. Based on this information, the server updates the risk assessment and saves the latest assessment in the database. At the same time, the updated risk assessment is integrated into the integrated document management system.

[1240] Finally, the server automatically generates and sends risk assessment reports periodically to users, who can use the reports to strengthen their regular risk management and countermeasures.

[1241] Example prompts to input to the generative AI model

[1242] Analyze the contents of the contract below and extract the risk factors.

[1243] "Contract details:..."

[1244] The above is a specific embodiment for carrying out the present invention. This system allows companies to manage documents and risks efficiently and accurately, and by incorporating feedback based on user emotions, more precise risk assessment and improvement can be achieved.

[1245] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1246] Step 1:

[1247] Document upload

[1248] Subject: User

[1249] Specific operation: The user clicks the "Upload Document" button on the terminal, selects the contract file, and sends it to the server. At this time, the file data is sent using an HTTP request.

[1250] Input: A document file selected by the user

[1251] Output: Document file uploaded to the server

[1252] Step 2:

[1253] Document Analysis

[1254] Subject: Server

[1255] Specific operation: The server analyzes the received document file using a Python-based natural language processing library (e.g., NLTK, spaCy), breaking down the document into sections and paragraphs, and extracting risk factors and errors.

[1256] Input: Uploaded document file

[1257] Output: A list of extracted risk factors and errors

[1258] Step 3:

[1259] Prioritizing risks and errors

[1260] Subject: Server

[1261] What it does: The server uses a decision tree algorithm to evaluate the importance and urgency of the extracted risk factors and errors, and classifies them into "high," "medium," or "low" priorities.

[1262] Input: List of extracted risk factors and errors

[1263] Output: A prioritized list of risk factors and errors

[1264] Step 4:

[1265] Sending results to the user interface

[1266] Subject: Server

[1267] Specific operation: Converts the prioritized list of risk factors and errors into JSON format and sends it to the device.

[1268] Input: List of prioritized risk factors and errors

[1269] Output: The result as JSON data sent to the terminal.

[1270] Step 5:

[1271] Displaying analysis results

[1272] Subject: Terminal

[1273] Specific operation: The device uses the JSON data received and displays the analysis results on the user interface using a JavaScript-based front-end framework.

[1274] Input: Parsed result in JSON data format

[1275] Output: Analysis results displayed on the terminal

[1276] Step 6:

[1277] User emotion detection and feedback

[1278] Subject: User

[1279] How it works: While checking the analysis results, the user provides emotion information via the device's camera or microphone. The emotion engine then uses a TensorFlow model to analyze the emotion and identify the user's emotional state.

[1280] Input: User facial and voice data

[1281] Output: The user's emotional state as analyzed by the emotion engine.

[1282] Step 7:

[1283] Adjusting priorities based on emotions

[1284] Subject: Server

[1285] What it does: The server receives data from the emotion engine and re-prioritizes risk factors and errors based on the user's emotions.

[1286] Input: The user's emotional state as analyzed by the emotion engine

[1287] Output: A list of rescaled risk factors and errors

[1288] Step 8:

[1289] User confirmation and correction

[1290] Subject: User

[1291] Specific operation: The user checks the analysis results on their device and adds corrections or comments as necessary. They then click the "Confirm" button to send the information to the server. The corrections are sent in JSON format.

[1292] Input: User-added corrections and comments

[1293] Output: Correction information sent to the server

[1294] Step 9:

[1295] Risk Assessment Updates

[1296] Subject: Server

[1297] Specific operation: The server updates the risk assessment based on the latest information received from the correction information, and saves the updated assessment results in the database.

[1298] Input: User-submitted correction information

[1299] Output: Updated risk assessment results

[1300] Step 10:

[1301] Integration into an integrated document management system

[1302] Subject: Server

[1303] What it does: The server uploads the latest risk assessment results to an integrated document management system for centralized management across the enterprise.

[1304] Input: Updated risk assessment results

[1305] Output: Evaluation results stored in an integrated document management system

[1306] Step 11:

[1307] Generate a risk assessment report

[1308] Subject: Server

[1309] Specific operation: The server automatically generates a risk assessment report on a regular basis and sends it to the user in PDF format or other format.

[1310] Input: Latest risk assessment results

[1311] Output: Risk assessment report sent to user

[1312] (Application example 2)

[1313] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1314] In conventional document management systems, risk factor extraction and prioritization are performed manually, making efficient risk assessment difficult. Furthermore, risk assessment does not reflect user sentiment, preventing an improved user experience. Furthermore, rapid document analysis and real-time risk management are required in workplaces such as factory robots, but the lack of a system that meets these requirements has been an issue.

[1315] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1316] In this invention, the server includes: means for analyzing documents using generative artificial intelligence to extract risk factors and errors; means for prioritizing the extracted risk factors and errors; and means for transmitting data to display the prioritized risk factors and errors on a user interface. This enables rapid analysis of documents and automatic extraction of risk factors. The server also includes means for recognizing a user's emotional information and reevaluating the priority of risk factors and errors based on the emotional information, and means for acquiring the user's emotional information using an emotional recognition engine and providing feedback based on the emotional information. This improves the user experience and enables precise risk assessment.

[1317] "Generative AI" is an AI technology that analyzes documents and automatically extracts risk factors and errors.

[1318] "Risk factors" refer to potential problems or dangers inherent in a document.

[1319] "Error" means any mistake or inaccuracy in a Document.

[1320] "Prioritization" means ranking the extracted risk factors and errors based on their importance and urgency.

[1321] A "user interface" is an interface that provides a screen and operating means for a user to interact with a system.

[1322] "Correction information" refers to corrections or additional information to the document content provided by the user.

[1323] "Risk assessment" is the process of evaluating the impact of extracted risk factors and errors, and determining countermeasures based on that information.

[1324] An "integrated document management system" is a system that centrally manages documents and their risk assessment information.

[1325] "Emotional information" is data that represents the user's emotional state, and is acquired from facial expressions, tone of voice, and the like.

[1326] An "emotion recognition engine" is a technology that recognizes emotions by analyzing data obtained from the user's camera or microphone.

[1327] "Feedback" is the process of dynamically correcting the assessment results of risk factors and errors based on the user's emotional information.

[1328] This invention relates to a smart document analysis and risk assessment system for factory robots. The system consists of three main components: a server, a terminal, and a user.

[1329] Server Roles

[1330] The server plays a central role in the system and performs the following main processes:

[1331] 1. Document Analysis:

[1332] It uses generative artificial intelligence (AI) to analyze uploaded documents and extract risk factors and errors. The generative AI model is provided by the OpenAI API or a similar service.

[1333] 2. Prioritize risks and errors:

[1334] The identified risk factors and errors are evaluated and prioritized based on their importance. This evaluation is quantified and classified into categories of "high," "medium," or "low" according to the urgency of the risk or error.

[1335] 3. Recognition and feedback of emotional information:

[1336] An emotion recognition engine (e.g., DeepFace) is used to obtain user emotion information, and risk factors and error priorities are reassessed based on the results.

[1337] 4. Risk Assessment Update:

[1338] Receives corrections from users and updates the risk assessment based on the latest information. Updated risk assessments are integrated into the integrated document management system.

[1339] 5. Report Generation:

[1340] A risk assessment report is automatically generated periodically based on the updated risk assessment and sent to the user.

[1341] Device Role

[1342] The terminal provides a user interface for users to interact with the system. Specifically, it has the following functions:

[1343] 1. Upload your documents:

[1344] A factory manager uploads a document to the server using a smartphone or tablet, for example, by clicking the "Upload Document" button in the UI.

[1345] 2. Check the analysis results:

[1346] The analysis results sent from the server are displayed in real time, including a list of extracted risk factors and errors, and their priorities.

[1347] 3. Submitting Corrections:

[1348] The administrator will review the analysis results and submit corrections or additional comments as necessary.

[1349] User Roles

[1350] The users are mainly factory managers and perform the following operations:

[1351] 1. Upload your documents:

[1352] Documents used within the factory, such as work procedures, manuals, and contracts, are uploaded from the terminal to the server.

[1353] 2. Check the analysis results:

[1354] The analysis results are displayed on the device and feedback is provided on any risk factors or errors found.

[1355] 3. Providing emotional information:

[1356] Emotional information is provided using a camera or microphone, which allows the system to identify emotions in real time through an emotion recognition engine and incorporate them into risk assessment.

[1357] Specific examples

[1358] For example, when a factory manager uploads a new work procedure manual to the system, the following process takes place: The server analyzes the procedure manual and extracts risk factors and errors in the work process. Risk factors such as "ambiguous process procedures" and "insufficient safety measures" are extracted, rated as high priority, and sent to the terminal. While the manager is checking the results, a camera recognizes the manager's facial expressions, and if anxiety or discomfort is detected, the priority of that risk factor is set even higher. Finally, the manager adds any corrections, and the server recalculates the latest risk assessment. The risk assessment report generated by the system is useful for continuous risk management and strengthening countermeasures.

[1359] Generative AI model prompt example

[1360] Analyze the following factory operating procedures to identify risk factors and errors. Pay particular attention to the safety measures and procedure sequence when analyzing the following statements.

[1361] In this way, the present invention contributes to improving the work efficiency and safety of factories, and also has the effect of reducing the burden on managers.

[1362] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1363] Step 1:

[1364] Document upload

[1365] A user uses a terminal to upload a document to the server. Specifically, a factory manager presses the "upload document" button on a smartphone or tablet, selects and sends a document file such as a work procedure manual, manual, or contract. The terminal receives the document file and transfers the data to the server. The input is the document file, and the output is the transfer of the document file to the server.

[1366] Step 2:

[1367] Document Analysis

[1368] The server analyzes the received document file. Specifically, the server uses a generative AI model to break down the document content into sections and paragraphs and extract risk factors and errors. At this time, the prompt for the generative AI model (e.g., OpenAI API) is, "Analyze the following factory work procedure manual and extract risk factors and errors. Please analyze the following sentence, paying particular attention to safety measures and the order of procedures." The input is the document content, and the output is a list of extracted risk factors and errors.

[1369] Step 3:

[1370] Prioritizing risks and errors

[1371] The server evaluates the extracted risk factors and errors and sets priorities based on their importance and urgency. Specifically, it quantifies the evaluation results and categorizes the risks and errors into "high," "medium," and "low" categories. The input is a list of risk factors and errors, and the output is a prioritized list of risk factors and errors.

[1372] Step 4:

[1373] Sending and viewing analysis results

[1374] The server converts the prioritized risk factors and error results into JSON format and sends it to the terminal. The terminal receives the results and displays the analysis results on the user interface. Specifically, the risk factors and errors are displayed in list format by priority, making it easy for the user to check. The input is the list of prioritized risk factors and errors, and the output is the analysis results displayed on the terminal.

[1375] Step 5:

[1376] Recognition and feedback of emotional information

[1377] The device's camera and microphone are used to obtain the user's emotional information. The server uses an emotion recognition engine (e.g., DeepFace) to recognize emotions from the user's facial expressions and tone of voice, and based on the results, re-evaluates the priority of risk factors and errors. Specifically, risk factors that the user expresses discomfort with are given a higher priority. The input is the user's emotional information, and the output is a list of risk factors and errors with re-evaluated priorities.

[1378] Step 6:

[1379] Providing and sending correction information

[1380] The user checks the analysis results and adds any necessary corrections or comments. The device then sends the corrections to the server. Specifically, the user enters corrections for each item in the analysis results and clicks the "Confirm" button to send the results. The input is the user's corrections, and the output is the corrections sent to the server.

[1381] Step 7:

[1382] Risk Assessment Updates

[1383] The server receives the user's revised information and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results. The input is the user's revised information, and the output is the updated risk assessment.

[1384] Step 8:

[1385] Generate and submit risk assessment reports

[1386] The server automatically generates risk assessment reports periodically and sends them to the user. Specifically, it creates reports based on updated risk assessment data and sends them to the user's terminal. The input is the updated risk assessment data, and the output is the risk assessment report sent to the user.

[1387] As described above, the present invention is a system that can efficiently and accurately manage documents and assess risks, and realizes precise risk assessment that reflects the user's feelings.

[1388] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1389] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1390] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1391] [Fourth embodiment]

[1392] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1393] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1394] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1395] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1396] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1397] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1398] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1399] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1400] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1401] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1402] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1403] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1404] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1405] The present invention is a system that uses generative artificial intelligence to automate and streamline document management and risk assessment in a company, and is specifically implemented as follows.

[1406] System configuration

[1407] Server: Plays the central role in the system, analyzing documents, extracting risk factors and errors, prioritizing them, transmitting data, updating risk assessments, and linking with the integrated document management system.

[1408] Terminal: Provides a user interface, allowing users to upload documents, review analysis results, and submit corrections.

[1409] User: Operates the system to upload documents, check analysis results, and provide correction information.

[1410] Program processing flow

[1411] 1. Document upload: A user uploads a document to the server using a terminal. For example, a user sends a contract to the server via the "Upload Document" button on the terminal.

[1412] 2. Document analysis: The server receives the uploaded document and uses generative AI to analyze it. During the analysis process, the server breaks down the document, identifies each section and paragraph, and extracts risk factors and errors.

[1413] 3. Prioritization of risks and errors: The server evaluates the importance and urgency of the extracted risk factors and errors, and then assigns them numerical values. After the evaluation, the server classifies the risks and errors into "high," "medium," or "low" priorities.

[1414] 4. Sending results to the user interface: The server sends the prioritized results to the terminal, and the terminal displays the analysis results on the user interface. For example, high-priority risk factors are displayed in red, medium-priority in yellow, and low-priority in blue.

[1415] 5. User confirmation and correction: The user checks the analysis results and adds correction information and comments as necessary. After completing the corrections, the user presses the "Confirmation Complete" button, and the device sends the correction information to the server.

[1416] 6. Risk assessment update: The server receives the correction information from the user and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results as needed.

[1417] 7. Integration into the Unified Document Management System: The server integrates the latest risk assessments into the Unified Document Management System, enabling centralized risk management across the enterprise.

[1418] 8. Risk assessment report generation: The server will automatically generate a risk assessment report based on the latest risk assessment at regular intervals and send it to the user, who can use it to strengthen regular risk management and countermeasures.

[1419] Specific examples

[1420] For example, suppose a user uploads a new contract to the system. The server receives the contract and analyzes it using generation AI, extracting risk factors such as "ambiguity in contract clauses" and "insufficient penalty for exceeding deadlines." These risk factors are each rated as high priority and sent to the terminal. The user checks these risk factors on the terminal and adds comments to amend the penalty clause. After the amendment information is sent to the server, the server updates the risk assessment and reflects it in the integrated document management system. The user receives the latest risk assessment for this contract in a risk assessment report that is generated periodically.

[1421] The above is a specific embodiment for carrying out the present invention. This system enables a company to efficiently and accurately manage documents and risks.

[1422] The processing flow will be explained below.

[1423] Step 1:

[1424] The user selects a document using the "upload document" button on the terminal and uploads it to the server.

[1425] Step 2:

[1426] The server receives the uploaded document and sends it to the Generative AI's analysis engine to analyze the document's content, where sections and paragraphs of the document are identified.

[1427] Step 3:

[1428] The server uses generative AI to extract risk factors and errors within the document, such as "ambiguous contract clauses" and "insufficient penalties for exceeding deadlines."

[1429] Step 4:

[1430] The server evaluates the severity and urgency of the extracted risk factors and errors and assigns a numerical score, which categorizes each risk and error as "high," "medium," or "low."

[1431] Step 5:

[1432] The server converts the prioritized risk factors and error results into JSON format and sends them to the terminal, which receives the results and displays the analysis results on the user interface.

[1433] Step 6:

[1434] The user checks the analysis results on the device. For example, high-priority risk factors are displayed in red, medium-priority in yellow, and low-priority in blue.

[1435] Step 7:

[1436] The user can add corrections or comments to the analysis results as needed. Once corrections are complete, the user clicks the "Confirm" button to submit the information.

[1437] Step 8:

[1438] The terminal sends the user's modified information to the server, which receives the modified information and updates the existing risk assessment database.

[1439] Step 9:

[1440] The server reflects the updated risk assessment in the integrated document management system, enabling centralized management.

[1441] Step 10:

[1442] The server automatically generates risk assessment reports on a regular basis and sends the reports to users via email or other means, providing them with the latest risk information.

[1443] Example 1

[1444] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1445] In modern companies, document management and risk assessment processes are extremely time-consuming and labor-intensive. In particular, efficiently analyzing large volumes of documents and extracting and assessing risk factors and errors based on the results is difficult to do manually, and the accuracy of the results is limited. Furthermore, because risk assessment is performed manually, delays in updating information and errors can occur. There is a need for a system that can resolve these issues and perform document management and risk assessment efficiently and accurately.

[1446] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1447] In this invention, the server includes means for uploading documents to an information processing device, means for analyzing documents using generative artificial intelligence and extracting risk factors and errors, means for prioritizing the extracted risk factors and errors based on them, means for transmitting data to display the prioritized risk factors and errors on an information display device, means for receiving correction information from a user and updating a risk assessment, means for integrating the updated risk assessment into an integrated file management system, means for a user to check the analysis results and add comments, means for saving the updated risk assessment results, and means for automatically generating and transmitting a risk assessment report. This makes it possible to efficiently and accurately automate the document management and risk assessment processes.

[1448] "Generative AI" is an AI technology that has the ability to learn from data and automatically generate information.

[1449] A "document" is a collection of information in electronic or printed form, including textual and / or graphical information.

[1450] "Risk Factors" refers to the content or conditions contained in the document that may cause problems or dangers.

[1451] "Error" means a mistake or defect in a document.

[1452] "Prioritization" is the process of ranking risk factors or errors based on their importance and urgency.

[1453] An "information display device" is a device that displays analysis results and the priorities of risk factors and errors to the user.

[1454] "Revision information" refers to the revisions and comments on the document provided by the user.

[1455] "Risk assessment" is the result of a comprehensive evaluation of the extracted risk factors and the impact and probability of errors.

[1456] An "integrated file management system" is a system for centrally managing documents across an entire company and sharing necessary information.

[1457] The "information processing device" is a computer device for uploading documents and displaying analysis results.

[1458] A "risk assessment report" is a report prepared based on the latest risk assessment and compiles information for risk management.

[1459] The present invention is a system that uses generative artificial intelligence to automate and streamline document management and risk assessment in a company. Specific embodiments of this system are described below.

[1460] This system consists of a server, terminals, and users.

[1461] server

[1462] The server is the central part of the system, receiving documents, analyzing them, extracting risk factors and errors, prioritizing them, transmitting data, updating risk assessments, and connecting with the integrated file management system. The server uses generative AI models to analyze uploaded documents. This analysis process breaks down documents, identifies individual sections and paragraphs, and extracts risk factors and errors.

[1463] Terminal

[1464] The terminal provides an interface to the user, who can use the terminal to upload documents, check the analysis results, and submit correction information.

[1465] User

[1466] The user operates the system, uploads a specific document to the terminal, checks the analysis results, and inputs correction information as necessary.

[1467] Specific names of hardware and software used

[1468] This system uses a generative AI model, an information display device, an information processing device, and an integrated file management system.

[1469] Specific examples

[1470] For example, suppose a user uploads a new contract to the system. The user sends the contract to the server via the "Upload Document" button on their device. The server receives the contract, analyzes it using a generative AI model, and extracts risk factors such as "ambiguity in contract clauses" and "insufficient penalty for overdue deadlines." These risk factors are each rated as high priority and sent to the device. The user reviews these risk factors on their device and adds comments to amend the penalty clauses. After the amendments are sent to the server, the server updates the risk assessment and reflects it in the integrated file management system. The user receives the latest risk assessment for this contract in a regularly generated risk assessment report. This process ensures efficient and accurate document management and risk management.

[1471] Prompt Sentence Examples

[1472] To get the generative AI model to parse a document, use a prompt like this:

[1473] Analyze the following contract and extract risk factors and errors:

[1474] Contract text

[1475] ---

[1476] [Contract details here]

[1477] The above is a specific embodiment for carrying out the present invention. This system enables a company to efficiently and accurately manage documents and risks.

[1478] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1479] Step 1: Upload your documents

[1480] The user clicks the "Upload Document" button on the device and selects the document file to upload.

[1481] The terminal transmits the selected document file to the server.

[1482] The server receives and stores the uploaded document.

[1483] Input: A document file selected by the user (e.g., contract.pdf)

[1484] Data processing: receiving and storing files

[1485] Output: Document file saved on the server

[1486] As a specific operation, the user selects a file called "contract.pdf" and clicks the "upload document" button.

[1487] Step 2: Parsing the document

[1488] The server passes the received document to the generative AI model.

[1489] A generative AI model analyzes the document and identifies each section and paragraph.

[1490] The server receives the risk factor and error extraction results from the generative AI model.

[1491] Input: Document file stored on the server

[1492] Data Computing: Generative AI models analyze documents, extract risk factors and errors

[1493] Output: A list of extracted risk factors and errors

[1494] Specifically, the generative AI model extracts risk factors such as "ambiguity in contract terms" and "insufficient penalties for exceeding deadlines."

[1495] Step 3: Prioritize risks and errors

[1496] The server quantifies the extracted risk factors and the importance and urgency of the errors.

[1497] The server classifies risk factors and errors into "high," "medium," and "low" priorities.

[1498] Input: List of extracted risk factors and errors

[1499] Data calculation: Prioritization of risk factors and errors (quantification and classification)

[1500] Output: A prioritized list of risk factors and errors

[1501] As a specific operation, the ambiguity of the penalty clause is evaluated as a high priority.

[1502] Step 4: Sending results to the user interface

[1503] The server sends the prioritized results to the terminal.

[1504] The device displays the analysis results in a user interface.

[1505] Input: A prioritized list of risk factors and errors

[1506] Data transmission: Sending a priority list to the device

[1507] Output: Analysis results displayed to the user

[1508] Specifically, high-priority risk factors are displayed in red, and unclear penalty clauses are displayed in red on the user's screen.

[1509] Step 5: User review and correction

[1510] The user checks the analysis results through the terminal.

[1511] The user adds correction information and comments and presses the "Confirm" button.

[1512] The terminal sends the correction information to the server.

[1513] Input: User corrections and comments

[1514] Data transmission: Sending correction information to the server

[1515] Output: Correction information sent to the server

[1516] As a specific operation, the user adds a comment saying, "You need to recheck the penalty clause."

[1517] Step 6: Update your risk assessment

[1518] The server receives the correction information from the user.

[1519] The server updates the risk assessment based on the latest information.

[1520] The updated risk assessment is saved in the database.

[1521] Input: Correction information from the user

[1522] Data calculation: Update risk assessment (recalculate and save)

[1523] Output: Updated risk assessment data

[1524] Specifically, the risk assessment is recalculated based on the corrected information and saved in the database.

[1525] Step 7: Integrate into an integrated file management system

[1526] The server sends the latest risk assessment to the integrated file management system and reflects it.

[1527] Input: Updated risk assessment data

[1528] Data submission: submission of risk assessments to an integrated file management system

[1529] Output: Risk assessment reflected in an integrated file management system

[1530] Specifically, the latest risk assessment is automatically added to the company's file management system.

[1531] Step 8: Generate a risk assessment report

[1532] The server automatically generates risk assessment reports on a regular basis.

[1533] The server sends the generated report to the user.

[1534] Input: Latest risk assessment data

[1535] Data calculations: Automatic generation of risk assessment reports

[1536] Data submission: Sending risk assessment reports to users

[1537] Output: Risk assessment report sent to user

[1538] Specifically, an automatically generated risk assessment report is sent to the user's email address once a month.

[1539] (Application example 1)

[1540] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1541] In conventional factories, document analysis of equipment and process management is often performed manually, which delays the detection of risk factors and errors and makes it difficult to implement timely improvements. Furthermore, this process is time-consuming and labor-intensive, resulting in reduced production efficiency and safety issues. There is a need to solve this issue and provide an automated risk management system.

[1542] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1543] In this invention, the server includes means for analyzing documents using generative AI and extracting risk factors and errors, means for prioritizing the extracted risk factors and errors, means for transmitting data to display the prioritized risk factors and errors on a user interface, means for receiving correction information from a user and updating risk assessments, means for integrating the updated risk assessments into an integrated data management system, and means for analyzing documents for equipment and process management in factories, detecting risk factors and errors, and proposing necessary improvements. This enables the automation and efficiency of document management and risk assessment, thereby improving productivity and safety.

[1544] "Generative AI" is an AI technology that generates knowledge based on given data and makes decisions and predictions.

[1545] "Document" means an electronic file or printed material containing written information.

[1546] "Risk factors" refer to events or conditions that have the potential to cause problems or trouble.

[1547] "Error" refers to an inaccurate description or operational error that occurs in a document or process.

[1548] "Prioritizing" refers to determining the order of extracted risk factors and errors based on their importance and urgency.

[1549] "User interface" refers to an interactive screen or display that allows a user to interact with a system.

[1550] "Transmitting data" refers to the electronic transfer of analysis results or risk information to another device or system.

[1551] "Correction information" refers to information provided by the user to correct or supplement extracted risk factors or errors.

[1552] "Risk assessment" refers to the evaluation values ​​and safety judgments for extracted risk factors and errors.

[1553] An "integrated data management system" refers to a system that centrally manages multiple data sets and integrates and processes the necessary information.

[1554] A "factory" refers to facilities and equipment used for manufacturing and production activities.

[1555] "Equipment" refers to machinery and equipment such as production lines and manufacturing devices used within a factory.

[1556] "Process control" refers to the planning, monitoring, and control of the production process in a factory.

[1557] "Document analysis" refers to the process of analyzing text data and extracting useful information and patterns.

[1558] "Improvements" refer to areas in the current process or design that require change or improvement.

[1559] The "Factory Document Risk Assessment Robot" refers to a robot system that analyzes documents used within a factory, automatically detects and evaluates risk factors and errors, and proposes necessary improvements.

[1560] The system embodying this invention automates document analysis and risk assessment in factories, providing efficient risk management. Specifically, it has the following configuration.

[1561] System configuration

[1562] Server: The central part of the system, which analyzes documents, extracts risk factors and errors, prioritizes them, transmits data, and updates risk assessments, and integrates the updated risk assessments into the integrated data management system.

[1563] Robot: Scans documents related to equipment and process control used in the factory and uploads them to a server, and also provides an interface for users to provide correction information.

[1564] User: Operates the system as a factory manager or worker, uploading documents, checking analysis results, and providing correction information.

[1565] Program processing flow

[1566] 1. Document upload: A user uses a robot to upload a document to the server, for example, a factory inspection list or equipment manual.

[1567] 2. Document analysis: The server receives the uploaded document and analyzes it using a generative AI model (e.g., OpenAI GPT-4). During the analysis process, the server breaks down the document, identifies each section and paragraph, and extracts risk factors and errors.

[1568] 3. Prioritization of risks and errors: The server evaluates the importance and urgency of the extracted risk factors and errors, quantifies them, and classifies them into "high," "medium," or "low" priorities.

[1569] 4. Sending results to the user interface: The server sends the prioritized results to the robot's interface, allowing the user to review the analysis results. For example, high-risk factors are displayed in red.

[1570] 5. User confirmation and correction: The user checks the analysis results on the interface and adds corrections or comments as necessary. Once corrections are complete, the user presses the "Confirmation Complete" button, and the robot sends the corrections to the server.

[1571] 6. Risk assessment update: The server receives the correction information from the user and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results as needed.

[1572] 7. Integration into the Integrated Data Management System: The server integrates the latest risk assessments into the integrated data management system, which provides a single source of risk management across the entire factory.

[1573] Specific examples

[1574] For example, a user uploads a new inspection list for a factory into the system. The inspection list contains the following:

[1575] 1. Machine A inspection: hydraulic pressure normal, sound abnormal

[1576] 2. Machine B inspection: High temperature, heavy wear

[1577] 3. Machine C inspection: normal operation, no vibration

[1578] The server receives the inspection list and analyzes it using a generative AI model, extracting "abnormal sound" and "high temperature" as risk factors. These are each rated as high priority and sent to the robot's interface. The user checks these risk factors and enters comments, such as adding an inspection to identify the cause of "abnormal sound." Corrections are sent to the server, and the risk assessment is updated. As a result, the user can always understand the latest risk assessment and take appropriate measures.

[1579] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1580] Step 1:

[1581] The user uploads documents to the server using a robot. At this time, the user has the robot scan factory documents such as work procedures and inspection lists. The documents are sent as electronic data to the server, which then receives the data.

[1582] Input: Document data scanned by the robot

[1583] Output: Document data stored on the server

[1584] Step 2:

[1585] The server receives the uploaded document and analyzes it using a generative AI model. During this process, the server passes the received document data to the generative AI, which creates prompts for decomposition and analysis. The generative AI model (e.g., OpenAI GPT-4) identifies each section and paragraph of the document and extracts risk factors and errors.

[1586] Input: Uploaded document data

[1587] Output: Risk factors and error extraction results

[1588] Step 3:

[1589] The server evaluates the importance and urgency of the extracted risk factors and errors, and quantifies them. After the evaluation, the risks and errors are classified into "high," "medium," and "low" priorities. In this process, a numerical evaluation is performed in comparison with pre-set evaluation criteria.

[1590] Input: Risk factors and error extraction results

[1591] Output: Prioritized risk factors and errors

[1592] Step 4:

[1593] The server sends the prioritized results to the robot's interface, allowing the user to check the analysis results. The user interface displays high-priority factors in red, medium-priority factors in yellow, and low-priority factors in blue. This allows the user to check important risk factors at a glance.

[1594] Input: Prioritized risk factors and errors

[1595] Output: The result displayed on the user interface

[1596] Step 5:

[1597] The user checks the analysis results on the interface and adds correction information or comments as necessary. For example, they can enter a comment to add an inspection to identify the cause of the "sound abnormality." Once the corrections are complete, the user presses the "Confirmation Complete" button, and the robot sends the correction information to the server.

[1598] Input: User corrections and comments on analysis results

[1599] Output: Analysis results with correction information added

[1600] Step 6:

[1601] The server receives the correction information from the user and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results as needed.

[1602] Input: Correction information submitted by the user

[1603] Output: Latest risk assessment

[1604] Step 7:

[1605] The server integrates the latest risk assessments into an integrated data management system, enabling centralized risk management across the entire factory. Periodic risk assessment reports are automatically generated and sent to users.

[1606] Input: Latest risk assessment

[1607] Output: Risk assessment and risk assessment report integrated into an integrated data management system

[1608] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1609] The present invention is a system that uses generative artificial intelligence to automate and streamline document management and risk assessment in companies, and by combining it with an emotion engine that recognizes user emotions, it achieves a more advanced user experience and precise risk management. This system is specifically implemented as follows.

[1610] System configuration

[1611] Server: The central part of the system, responsible for document analysis, risk factor and error extraction, prioritization, data transmission, risk assessment updates, emotion recognition, and integration of updates.

[1612] Terminal: Provides a user interface where users can upload documents, check analysis results, submit corrections, and provide emotion information.

[1613] User: Operates the system to upload documents, check analysis results, provide corrections, and express emotions to provide feedback through the emotion engine.

[1614] Program processing flow

[1615] 1. Document upload: A user uploads a document to the server using a terminal. For example, a user sends a contract to the server via the "Upload Document" button on the terminal.

[1616] 2. Document analysis: The server receives the uploaded document and analyzes it using generative AI. During the analysis process, the server breaks down the document, identifies each section and paragraph, and extracts risk factors and errors.

[1617] 3. Prioritization of risks and errors: The server evaluates the importance and urgency of the extracted risk factors and errors, and then assigns them numerical values. After the evaluation, the server classifies the risks and errors into "high," "medium," or "low" priorities.

[1618] 4. Sending results to the user interface: The server converts the prioritized risk factors and error results into JSON format and sends them to the terminal. The terminal receives the results and displays the analysis results on the user interface.

[1619] 5. User emotion detection and feedback: The emotion engine recognizes the user's emotions using emotion information provided by the user, such as a camera or microphone. For example, the user analyzes facial expressions and tone of voice based on the analysis results, and the emotion engine processes them.

[1620] 6. Emotion-based priority adjustment: The emotion engine readjusts the priority of risk factors and errors based on the user's emotions. For example, risk factors that the user expresses discomfort with will be given a higher priority.

[1621] 7. User confirmation and correction: The user checks the analysis results on the device and adds correction information and comments as necessary. After completing the corrections, click the "Confirmation Complete" button to submit the information.

[1622] 8. Risk Assessment Update: The server receives the user's revised information and updates the risk assessment based on the latest information. The updated risk assessment is stored in the database and can be compared with past assessment results as needed.

[1623] 9. Integration into Unified Document Management System: The server integrates the latest risk assessments into the Unified Document Management System, enabling centralized risk management across the enterprise.

[1624] 10. Risk assessment report generation: The server will automatically generate risk assessment reports periodically and send them to users, who can use them to strengthen their regular risk management and countermeasures.

[1625] Specific examples

[1626] For example, consider what happens when a user uploads a new contract to the system. The server receives the contract and analyzes it using a generation AI, extracting risk factors such as "ambiguous contract terms" and "insufficient penalties for overdue documents." Each of these risk factors is rated as high priority and sent to the device. While the user is reviewing the results on the device, the emotion engine recognizes the user's facial expressions and detects that the user is expressing displeasure. As a result, the emotion engine sets the priority of the relevant risk factor even higher and displays the results to the user again. The user can then add corrections based on this, and the server updates the risk assessment. Finally, the updated risk assessment is reflected in the integrated document management system and sent to the user as a regular risk assessment report.

[1627] The above is a specific embodiment for carrying out the present invention. This system allows companies to manage documents and risks efficiently and accurately, and by incorporating feedback based on user emotions, more precise risk assessment and improvement can be achieved.

[1628] The processing flow will be explained below.

[1629] Step 1:

[1630] The user uses the "Document Upload" button on the device to select a document and upload it to the server. For example, when a user uploads a contract, they select the file and click the button to send it.

[1631] Step 2:

[1632] The server receives the uploaded document and sends it to the Generative AI's analysis engine for analysis, where the document is parsed and each section or paragraph is identified, such as the "Terms" and "Terms" sections in a contract.

[1633] Step 3:

[1634] The server uses generative AI to analyze the contents of the document and extract risk factors and errors, such as "risk of expiration" and "ambiguous contract terms."

[1635] Step 4:

[1636] The server evaluates the importance and urgency of the extracted risk factors and errors and assigns a numerical score. For example, the "risk of expiration" is evaluated as 9 out of 10.

[1637] Step 5:

[1638] The server converts the prioritized risk factors and error results into JSON format and sends it to the terminal. The terminal receives the results and displays the analysis results on the user interface. For example, high-priority risk factors are displayed in red.

[1639] Step 6:

[1640] While checking the analysis results, the user provides real-time emotions using the device's camera and microphone. For example, if the user feels dissatisfied, the emotion engine will recognize facial expressions and analyze the tone of voice.

[1641] Step 7:

[1642] The emotion engine processes the user's emotion information and reflects the user's dissatisfaction or surprise in the priority of risk factors. For example, a risk factor that the user expresses discomfort with is given a higher priority.

[1643] Step 8:

[1644] The server displays the adjusted risk factors and error priorities again in the user interface, and the user reviews the results and adds corrections or comments as needed.

[1645] Step 9:

[1646] After the user has completed inputting the correction information, he / she clicks the "Confirmation Complete" button to send the information from the terminal to the server. For example, he / she may enter correction comments that specifically indicate the "ambiguous contract terms."

[1647] Step 10:

[1648] The server receives the user's modified information and updates the existing risk assessment database, which is used for future document analysis and risk assessment processes.

[1649] Step 11:

[1650] The server updates the integrated document management system with the latest risk assessments, enabling centralized risk management and updating the risk database available across the entire company.

[1651] Step 12:

[1652] The server automatically generates a risk assessment report periodically and transmits the report to the user. For example, the server generates a monthly risk assessment report and transmits it to the user by email.

[1653] With this detailed processing flow, the present invention enables document management and risk assessment to be carried out efficiently and accurately, and by incorporating feedback based on the user's emotions, more precise risk assessment can be achieved.

[1654] Example 2

[1655] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1656] Conventional document management and risk assessment systems have issues such as difficulty in centralized management and inability to perform efficient risk assessment and correction. Furthermore, the accuracy of risk assessment that takes user emotions into account has not been sufficiently improved, and an improved user experience is required. As a result, risks can be overlooked or it can be difficult to respond quickly, making it difficult to optimize risk management across the entire company, requiring a lot of time and effort.

[1657] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1658] In this invention, the server includes: means for analyzing documents using generative artificial intelligence and extracting risk factors and errors; means for prioritizing the extracted risk factors and errors; means for transmitting data to display the prioritized risk factors and errors on a user interface; means for recognizing a user's emotions and readjusting the priorities of the risk factors and errors based on the emotions; means for receiving correction information from the user and updating the risk assessment; and means for integrating the updated risk assessment into an integrated document management system. This enables centralized and efficient performance of processes from document analysis to risk assessment, correction, and integrated management. Furthermore, a more accurate risk assessment that reflects the user's emotions can be achieved, improving the user experience.

[1659] "Generative AI" is a general term for AI technologies that have the ability to generate new information or results based on data.

[1660] A "document" refers to a file or data that contains information expressed as text data.

[1661] A "risk factor" is an element of potential negative consequence or danger that a particular event or action may cause.

[1662] An "Error" is any mistake or defect in a document that prevents accurate and proper processing or interpretation.

[1663] "User interface" refers to the display screen and input means that allow a user to interact with a system.

[1664] "Means for recognizing emotions" refers to processes or technologies that detect emotional expressions such as facial expressions and voice of a user and identify that emotional state.

[1665] "Measures for readjusting priorities" refers to the process of reevaluating and resetting the importance of risk factors and errors that have been set based on new information such as user sentiment.

[1666] "Correction information" refers to information including corrections and opinions provided by users, with the aim of improving documents and evaluation results.

[1667] "Updating" refers to the process of modifying, adding, or deleting existing data or assessment results based on new information.

[1668] An "integrated document management system" is a system for centrally managing, storing, and accessing multiple documents and data.

[1669] The present invention is a system that uses generative AI models to automate and streamline document management and risk assessment in companies. Furthermore, by combining it with an emotion engine that recognizes user emotions, it achieves a more advanced user experience and precise risk management. This system is specifically implemented as follows:

[1670] System configuration

[1671] server:

[1672] The server plays a central role in the system and has the following functions:

[1673] Document Analysis

[1674] Identifying risk factors and errors

[1675] Prioritization

[1676] Data transmission

[1677] Risk Assessment Updates

[1678] emotion recognition

[1679] Integration of update information

[1680] The server uses Python-based natural language processing libraries (e.g., NLTK, spaCy), machine learning techniques such as decision tree algorithms, and TensorFlow models for emotion recognition.

[1681] Device:

[1682] It provides the user interface and the means by which the user operates the system. The terminal has the following functions:

[1683] Document upload

[1684] Checking the analysis results

[1685] Submitting correction information

[1686] Providing emotional information

[1687] The device uses JavaScript-based front-end frameworks (e.g., React, Vue.js) to build the user interface.

[1688] User:

[1689] Users operate the system to upload documents, check analysis results, provide correction information, and express emotions to provide feedback through the emotion engine.

[1690] Specific examples

[1691] For example, let's consider what happens when a user uploads a new contract to the system. The user uploads the contract using a terminal. They click the "Upload Document" button on the terminal, select the contract file, and send it to the server. In this process, the file data is transferred to the server via an HTTP request.

[1692] The server uses a generative AI model to analyze the received contract. Specifically, it uses a Python-based natural language processing library (e.g., NLTK, spaCy) to break down the document and identify each section and paragraph. It then extracts risk factors and errors. Once this step is complete, it uses a decision tree algorithm to prioritize the extracted risk factors and errors.

[1693] Once the prioritization is complete, the server converts the results into JSON format and sends them to the device, where the analysis results are displayed in a user interface using a JavaScript-based front-end framework (e.g., React, Vue.js). The user can then view the analysis results displayed on the device.

[1694] As the user reviews the analysis results, their emotional information is sent to the emotion engine via the device's camera and microphone. The emotion engine then uses a TensorFlow model to analyze the user's emotions and automatically readjust the priority of risk factors that cause discomfort.

[1695] The user can add corrections or comments as needed and click the "Confirm" button to send the information to the server. Based on this information, the server updates the risk assessment and saves the latest assessment in the database. At the same time, the updated risk assessment is integrated into the integrated document management system.

[1696] Finally, the server automatically generates and sends risk assessment reports periodically to users, who can use the reports to strengthen their regular risk management and countermeasures.

[1697] Example prompts to input to the generative AI model

[1698] Analyze the contents of the contract below and extract the risk factors.

[1699] "Contract details:..."

[1700] The above is a specific embodiment for carrying out the present invention. This system allows companies to manage documents and risks efficiently and accurately, and by incorporating feedback based on user emotions, more precise risk assessment and improvement can be achieved.

[1701] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1702] Step 1:

[1703] Document upload

[1704] Subject: User

[1705] Specific operation: The user clicks the "Upload Document" button on the terminal, selects the contract file, and sends it to the server. At this time, the file data is sent using an HTTP request.

[1706] Input: A document file selected by the user

[1707] Output: Document file uploaded to the server

[1708] Step 2:

[1709] Document Analysis

[1710] Subject: Server

[1711] Specific operation: The server analyzes the received document file using a Python-based natural language processing library (e.g., NLTK, spaCy), breaking down the document into sections and paragraphs, and extracting risk factors and errors.

[1712] Input: Uploaded document file

[1713] Output: A list of extracted risk factors and errors

[1714] Step 3:

[1715] Prioritizing risks and errors

[1716] Subject: Server

[1717] What it does: The server uses a decision tree algorithm to evaluate the importance and urgency of the extracted risk factors and errors, and classifies them into "high," "medium," or "low" priorities.

[1718] Input: List of extracted risk factors and errors

[1719] Output: A prioritized list of risk factors and errors

[1720] Step 4:

[1721] Sending results to the user interface

[1722] Subject: Server

[1723] Specific operation: Converts the prioritized list of risk factors and errors into JSON format and sends it to the device.

[1724] Input: List of prioritized risk factors and errors

[1725] Output: The result as JSON data sent to the terminal.

[1726] Step 5:

[1727] Displaying analysis results

[1728] Subject: Terminal

[1729] Specific operation: The device uses the JSON data received and displays the analysis results on the user interface using a JavaScript-based front-end framework.

[1730] Input: Parsed result in JSON data format

[1731] Output: Analysis results displayed on the terminal

[1732] Step 6:

[1733] User emotion detection and feedback

[1734] Subject: User

[1735] How it works: While checking the analysis results, the user provides emotion information via the device's camera or microphone. The emotion engine then uses a TensorFlow model to analyze the emotion and identify the user's emotional state.

[1736] Input: User facial and voice data

[1737] Output: The user's emotional state as analyzed by the emotion engine.

[1738] Step 7:

[1739] Adjusting priorities based on emotions

[1740] Subject: Server

[1741] What it does: The server receives data from the emotion engine and re-prioritizes risk factors and errors based on the user's emotions.

[1742] Input: The user's emotional state as analyzed by the emotion engine

[1743] Output: A list of rescaled risk factors and errors

[1744] Step 8:

[1745] User confirmation and correction

[1746] Subject: User

[1747] Specific operation: The user checks the analysis results on their device and adds corrections or comments as necessary. They then click the "Confirm" button to send the information to the server. The corrections are sent in JSON format.

[1748] Input: User-added corrections and comments

[1749] Output: Correction information sent to the server

[1750] Step 9:

[1751] Risk Assessment Updates

[1752] Subject: Server

[1753] Specific operation: The server updates the risk assessment based on the latest information received from the correction information, and saves the updated assessment results in the database.

[1754] Input: User-submitted correction information

[1755] Output: Updated risk assessment results

[1756] Step 10:

[1757] Integration into an integrated document management system

[1758] Subject: Server

[1759] What it does: The server uploads the latest risk assessment results to an integrated document management system for centralized management across the enterprise.

[1760] Input: Updated risk assessment results

[1761] Output: Evaluation results stored in an integrated document management system

[1762] Step 11:

[1763] Generate a risk assessment report

[1764] Subject: Server

[1765] Specific operation: The server automatically generates a risk assessment report on a regular basis and sends it to the user in PDF format or other format.

[1766] Input: Latest risk assessment results

[1767] Output: Risk assessment report sent to user

[1768] (Application example 2)

[1769] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1770] In conventional document management systems, risk factor extraction and prioritization are performed manually, making efficient risk assessment difficult. Furthermore, risk assessment does not reflect user sentiment, preventing an improved user experience. Furthermore, rapid document analysis and real-time risk management are required in workplaces such as factory robots, but the lack of a system that meets these requirements has been an issue.

[1771] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1772] In this invention, the server includes: means for analyzing documents using generative artificial intelligence to extract risk factors and errors; means for prioritizing the extracted risk factors and errors; and means for transmitting data to display the prioritized risk factors and errors on a user interface. This enables rapid analysis of documents and automatic extraction of risk factors. The server also includes means for recognizing a user's emotional information and reevaluating the priority of risk factors and errors based on the emotional information, and means for acquiring the user's emotional information using an emotional recognition engine and providing feedback based on the emotional information. This improves the user experience and enables precise risk assessment.

[1773] "Generative AI" is an AI technology that analyzes documents and automatically extracts risk factors and errors.

[1774] "Risk factors" refer to potential problems or dangers inherent in a document.

[1775] "Error" means any mistake or inaccuracy in a Document.

[1776] "Prioritization" means ranking the extracted risk factors and errors based on their importance and urgency.

[1777] A "user interface" is an interface that provides a screen and operating means for a user to interact with a system.

[1778] "Correction information" refers to corrections or additional information to the document content provided by the user.

[1779] "Risk assessment" is the process of evaluating the impact of extracted risk factors and errors, and determining countermeasures based on that information.

[1780] An "integrated document management system" is a system that centrally manages documents and their risk assessment information.

[1781] "Emotional information" is data that represents the user's emotional state, and is acquired from facial expressions, tone of voice, and the like.

[1782] An "emotion recognition engine" is a technology that recognizes emotions by analyzing data obtained from the user's camera or microphone.

[1783] "Feedback" is the process of dynamically correcting the assessment results of risk factors and errors based on the user's emotional information.

[1784] This invention relates to a smart document analysis and risk assessment system for factory robots. The system consists of three main components: a server, a terminal, and a user.

[1785] Server Roles

[1786] The server plays a central role in the system and performs the following main processes:

[1787] 1. Document Analysis:

[1788] It uses generative artificial intelligence (AI) to analyze uploaded documents and extract risk factors and errors. The generative AI model is provided by the OpenAI API or a similar service.

[1789] 2. Prioritize risks and errors:

[1790] The identified risk factors and errors are evaluated and prioritized based on their importance. This evaluation is quantified and classified into categories of "high," "medium," or "low" according to the urgency of the risk or error.

[1791] 3. Recognition and feedback of emotional information:

[1792] An emotion recognition engine (e.g., DeepFace) is used to obtain user emotion information, and risk factors and error priorities are reassessed based on the results.

[1793] 4. Risk Assessment Update:

[1794] Receives corrections from users and updates the risk assessment based on the latest information. Updated risk assessments are integrated into the integrated document management system.

[1795] 5. Report Generation:

[1796] A risk assessment report is automatically generated periodically based on the updated risk assessment and sent to the user.

[1797] Device Role

[1798] The terminal provides a user interface for users to interact with the system. Specifically, it has the following functions:

[1799] 1. Upload your documents:

[1800] A factory manager uploads a document to the server using a smartphone or tablet, for example, by clicking the "Upload Document" button in the UI.

[1801] 2. Check the analysis results:

[1802] The analysis results sent from the server are displayed in real time, including a list of extracted risk factors and errors, and their priorities.

[1803] 3. Submitting Corrections:

[1804] The administrator will review the analysis results and submit corrections or additional comments as necessary.

[1805] User Roles

[1806] The users are mainly factory managers and perform the following operations:

[1807] 1. Upload your documents:

[1808] Documents used within the factory, such as work procedures, manuals, and contracts, are uploaded from the terminal to the server.

[1809] 2. Check the analysis results:

[1810] The analysis results are displayed on the device and feedback is provided on any risk factors or errors found.

[1811] 3. Providing emotional information:

[1812] Emotional information is provided using a camera or microphone, which allows the system to identify emotions in real time through an emotion recognition engine and incorporate them into risk assessment.

[1813] Specific examples

[1814] For example, when a factory manager uploads a new work procedure manual to the system, the following process takes place: The server analyzes the procedure manual and extracts risk factors and errors in the work process. Risk factors such as "ambiguous process procedures" and "insufficient safety measures" are extracted, rated as high priority, and sent to the terminal. While the manager is checking the results, a camera recognizes the manager's facial expressions, and if anxiety or discomfort is detected, the priority of that risk factor is set even higher. Finally, the manager adds any corrections, and the server recalculates the latest risk assessment. The risk assessment report generated by the system is useful for continuous risk management and strengthening countermeasures.

[1815] Generative AI model prompt example

[1816] Analyze the following factory operating procedures to identify risk factors and errors. Pay particular attention to the safety measures and procedure sequence when analyzing the following statements.

[1817] In this way, the present invention contributes to improving the work efficiency and safety of factories, and also has the effect of reducing the burden on managers.

[1818] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1819] Step 1:

[1820] Document upload

[1821] A user uses a terminal to upload a document to the server. Specifically, a factory manager presses the "upload document" button on a smartphone or tablet, selects and sends a document file such as a work procedure manual, manual, or contract. The terminal receives the document file and transfers the data to the server. The input is the document file, and the output is the transfer of the document file to the server.

[1822] Step 2:

[1823] Document Analysis

[1824] The server analyzes the received document file. Specifically, the server uses a generative AI model to break down the document content into sections and paragraphs and extract risk factors and errors. At this time, the prompt for the generative AI model (e.g., OpenAI API) is, "Analyze the following factory work procedure manual and extract risk factors and errors. Please analyze the following sentence, paying particular attention to safety measures and the order of procedures." The input is the document content, and the output is a list of extracted risk factors and errors.

[1825] Step 3:

[1826] Prioritizing risks and errors

[1827] The server evaluates the extracted risk factors and errors and sets priorities based on their importance and urgency. Specifically, it quantifies the evaluation results and categorizes the risks and errors into "high," "medium," and "low" categories. The input is a list of risk factors and errors, and the output is a prioritized list of risk factors and errors.

[1828] Step 4:

[1829] Sending and viewing analysis results

[1830] The server converts the prioritized risk factors and error results into JSON format and sends it to the terminal. The terminal receives the results and displays the analysis results on the user interface. Specifically, the risk factors and errors are displayed in list format by priority, making it easy for the user to check. The input is the list of prioritized risk factors and errors, and the output is the analysis results displayed on the terminal.

[1831] Step 5:

[1832] Recognition and feedback of emotional information

[1833] The device's camera and microphone are used to obtain the user's emotional information. The server uses an emotion recognition engine (e.g., DeepFace) to recognize emotions from the user's facial expressions and tone of voice, and based on the results, re-evaluates the priority of risk factors and errors. Specifically, risk factors that the user expresses discomfort with are given a higher priority. The input is the user's emotional information, and the output is a list of risk factors and errors with re-evaluated priorities.

[1834] Step 6:

[1835] Providing and sending correction information

[1836] The user checks the analysis results and adds any necessary corrections or comments. The device then sends the corrections to the server. Specifically, the user enters corrections for each item in the analysis results and clicks the "Confirm" button to send the results. The input is the user's corrections, and the output is the corrections sent to the server.

[1837] Step 7:

[1838] Risk Assessment Updates

[1839] The server receives the user's revised information and updates the risk assessment based on the latest information. The updated risk assessment is saved in the database and can be compared with past assessment results. The input is the user's revised information, and the output is the updated risk assessment.

[1840] Step 8:

[1841] Generate and submit risk assessment reports

[1842] The server automatically generates risk assessment reports periodically and sends them to the user. Specifically, it creates reports based on updated risk assessment data and sends them to the user's terminal. The input is the updated risk assessment data, and the output is the risk assessment report sent to the user.

[1843] As described above, the present invention is a system that can efficiently and accurately manage documents and assess risks, and realizes precise risk assessment that reflects the user's feelings.

[1844] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1845] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1846] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1847] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1848] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1849] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1850] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1851] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, motorcycles, and other devices, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1852] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1853] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1854] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1855] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1856] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1857] 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.

[1858] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1859] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1860] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1861] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1862] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1863] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1864] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1865] The following is further disclosed regarding the above embodiment.

[1866] (Claim 1)

[1867] A means for analyzing documents using generative artificial intelligence to extract risk factors and errors;

[1868] A means of prioritizing the risk factors and errors based on the identified risks and errors;

[1869] means for transmitting the prioritized risk factors and errors for display on a user interface;

[1870] means for receiving corrective information from the user and updating the risk assessment;

[1871] a means of integrating the updated risk assessment into an integrated document management system;

[1872] A system including:

[1873] (Claim 2)

[1874] 10. The system of claim 1, further comprising means for applying a custom model to perform risk analysis to suit a particular industry or business.

[1875] (Claim 3)

[1876] 10. The system according to claim 1, further comprising means for periodically generating a risk assessment report based on the updated risk assessment and transmitting the report to the user.

[1877] "Example 1"

[1878] (Claim 1)

[1879] A means for analyzing documents using generative artificial intelligence to extract risk factors and errors;

[1880] A means of prioritizing the risk factors and errors based on the identified risks and errors;

[1881] means for transmitting data for displaying the prioritized risk factors and errors on an information display device;

[1882] means for receiving corrective information from the user and updating the risk assessment;

[1883] a means of integrating the updated risk assessment into an integrated file management system;

[1884] means for uploading a document to an information processing device;

[1885] A means for users to review the analysis results and add comments;

[1886] a means for storing updated risk assessments;

[1887] a means for automatically generating and transmitting risk assessment reports;

[1888] A system including:

[1889] (Claim 2)

[1890] 10. The system of claim 1, further comprising means for applying a custom model to adapt to a particular field or business to perform risk analysis.

[1891] (Claim 3)

[1892] 10. The system according to claim 1, further comprising means for periodically generating a risk assessment report based on the updated risk assessment and transmitting the report to the user.

[1893] "Application Example 1"

[1894] (Claim 1)

[1895] A means for analyzing documents using generative artificial intelligence to extract risk factors and errors;

[1896] A means of prioritizing the risk factors and errors based on the identified risks and errors;

[1897] means for transmitting the prioritized risk factors and errors for display on a user interface;

[1898] means for receiving corrective information from the user and updating the risk assessment;

[1899] a means of integrating the updated risk assessment into an integrated data management system;

[1900] A method to analyze factory equipment and process control documents, detect risk factors and errors, and propose necessary improvements.

[1901] A system including:

[1902] (Claim 2)

[1903] 10. The system of claim 1, further comprising means for applying a custom model to perform risk analysis to suit a particular industry or business.

[1904] (Claim 3)

[1905] 10. The system according to claim 1, further comprising means for periodically generating a risk assessment report based on the updated risk assessment and transmitting the report to the user.

[1906] "Example 2: Combining Emotion Engines"

[1907] (Claim 1)

[1908] A means for analyzing documents using generative artificial intelligence to extract risk factors and errors;

[1909] A means of prioritizing the risk factors and errors based on the identified risks and errors;

[1910] means for transmitting the prioritized risk factors and errors for display on a user interface;

[1911] means for recognizing a user's emotions and re-prioritizing risk factors and errors based on the emotions;

[1912] means for receiving corrective information from the user and updating the risk assessment;

[1913] a means of integrating the updated risk assessment into an integrated document management system;

[1914] A system including:

[1915] (Claim 2)

[1916] 10. The system of claim 1, further comprising means for applying a custom model to perform risk analysis to suit a particular industry or business.

[1917] (Claim 3)

[1918] 10. The system according to claim 1, further comprising means for periodically generating a risk assessment report based on the updated risk assessment and transmitting the report to the user.

[1919] "Application example 2 when combining emotion engines"

[1920] (Claim 1)

[1921] A means for analyzing documents using generative artificial intelligence to extract risk factors and errors;

[1922] A means of prioritizing the risk factors and errors based on the identified risks and errors;

[1923] means for transmitting the prioritized risk factors and errors for display on a user interface;

[1924] means for receiving corrective information from the user and updating the risk assessment;

[1925] a means for integrating the updated risk assessment into an integrated document management system;

[1926] means for recognizing the user's emotional information and reassessing the priority of risk factors and errors based on the emotional information;

[1927] a means for acquiring the user's emotions using an emotion recognition engine and providing feedback based on the emotions;

[1928] A system including:

[1929] (Claim 2)

[1930] 10. The system of claim 1, further comprising means for applying a custom model to perform risk analysis to suit a particular industry or business.

[1931] (Claim 3)

[1932] 10. The system according to claim 1, further comprising means for periodically generating a risk assessment report based on the updated risk assessment and transmitting the report to the user. [Explanation of symbols]

[1933] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for analyzing documents using generative artificial intelligence to extract risk factors and errors; A means of prioritizing the risk factors and errors based on the identified risks and errors; means for transmitting the prioritized risk factors and errors for display on a user interface; means for receiving corrective information from the user and updating the risk assessment; a means of integrating the updated risk assessment into an integrated document management system; A system including:

2. 10. The system of claim 1, further comprising means for applying a custom model to adapt to a particular industry or business to perform risk analysis.

3. 2. The system according to claim 1, further comprising means for periodically generating a risk assessment report based on the updated risk assessment and transmitting the report to the user.

Images