system

Abstract

We provide the system. [Solution] A means for analyzing a specified document and detecting errors and deficiencies in the document using a natural language processing model, A means for analyzing a specified document and detecting errors and deficiencies within the document using a natural language processing model, Means for generating correction suggestions based on detected errors and deficiencies, A means of notifying the user of the generated correction suggestions, Means for recording and evaluating change history, A means of conducting a risk assessment and proposing an action plan, A means to detect errors in contracts and terms of service in real time and propose corrections, A system that includes this.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Errors and deficiencies in design documents and fee specifications can directly affect the service quality for customers and may damage reliability. Also, in the manual confirmation process, human errors are likely to occur, requiring a great deal of time and effort. Automation and efficiency improvement of these processes are demanded.

Means for Solving the Problems

[0005] The present invention aims to solve these problems by providing a system that includes means for analyzing a specified document and detecting errors and deficiencies within the document using a natural language processing model, means for generating correction suggestions based on the detected errors and deficiencies, means for notifying the user of the generated correction suggestions, means for recording and evaluating the change history, and means for performing a risk assessment and proposing an action plan.

[0006] "Specified documents" refer to documents such as service design documents and pricing specifications that the user has provided to the system for analysis.

[0007] A "natural language processing model" refers to algorithms and technologies that mechanically analyze text data within a document to understand its meaning and context.

[0008] "Errors and deficiencies" is a general term for problems found in a document, such as inconsistencies, omissions, grammatical errors, and misspellings.

[0009] A "correction suggestion" is a specific instruction or proposal provided to improve an error or deficiency that has been detected.

[0010] "Means of notifying users" refers to mechanisms for communicating correction suggestions and error information to users.

[0011] "Means for recording and evaluating change history" refers to a process or function for recording the content of changes to a document and evaluating its impact and risks.

[0012] "Risk assessment" is the process of analyzing potential problems and hazards associated with a modified document and determining appropriate actions based on that assessment.

[0013] An "action plan" refers to specific actions or plans recommended to minimize risks and address any problems that are discovered. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0015] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a system that receives a specified document, automatically detects errors and deficiencies within it, and suggests appropriate corrections. This system consists of three components: a server, a terminal, and a user.

[0036] First, the user uploads necessary documents, such as design specifications and pricing documents, to the server using their device. The server analyzes the uploaded documents using a natural language processing model to detect errors such as grammatical mistakes, inconsistencies, and violations of regulations.

[0037] When an error is detected, the server generates specific correction suggestions based on it. These suggestions include points to maintain the overall consistency of the document and improvement proposals based on similar past cases. The generated suggestions are notified to the user's terminal as feedback.

[0038] Furthermore, the server tracks the impact and progress of user-initiated changes by recording all change history in a database. Based on this historical information, the server assesses the risks that the changes pose to the overall service and proposes an action plan as needed.

[0039] In actual operation, for example, when a pricing specification document for a new service is created, the user uploads it from their terminal to the server. The server immediately begins analysis, comparing it with past data to identify potential errors. As a result, the server sends specific feedback to the user, who can then revise and verify the document based on the suggestions. By repeating this process, the quality of the document improves and the reliability of the service is ensured.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user uses their terminal to upload document files, such as design specifications and pricing documents, to the server. Once the upload is complete, the server receives the files and prepares them for analysis.

[0043] Step 2:

[0044] The server passes the received document through a natural language processing model. The model analyzes the document sentence by sentence and initiates an analysis process to identify grammatical errors and inconsistencies.

[0045] Step 3:

[0046] The server applies machine learning algorithms and compares the results with similar historical data to detect potential error patterns. In this process, discrepancies in pricing and inappropriate descriptions are particularly highlighted.

[0047] Step 4:

[0048] If an error is detected, the server will generate specific correction suggestions based on it. These suggestions will include a description of the error and proposed corrections, or comparison information with relevant documents.

[0049] Step 5:

[0050] When revision suggestions are generated, the server notifies the user's terminal. The suggestions presented as feedback serve as a guide for the user when revising the document.

[0051] Step 6:

[0052] The user modifies the document based on feedback from the server. If necessary, it is uploaded back to the server and subjected to another analysis process to verify the validity of the modifications.

[0053] Step 7:

[0054] The server records the history of all document changes and performs an impact analysis on newly modified documents. If the impact is deemed significant, it presents the user with a risk assessment report and action plan.

[0055] Step 8:

[0056] The process is repeated until changes are finalized, ultimately resulting in a document with guaranteed accuracy. Through this process, document quality improves, and customer service reliability increases.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In information processing, efficiently detecting errors and deficiencies in documents and information, and proposing appropriate corrections based on these findings, is challenging. Especially in today's society, where vast amounts of information are constantly being generated, maintaining information consistency quickly and accurately is a crucial issue. Furthermore, there is a need for methods to effectively utilize past revision history, assess risks, and prevent future errors.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes means for receiving information from a user, means for analyzing the received information using a natural language processing system to detect errors and deficiencies, and means for generating correction suggestions based on the detected errors and deficiencies. This enables users to quickly and accurately correct errors in documents and maintain the integrity of the information. Furthermore, by utilizing a model that learns from past information and predicts error patterns, it is possible to mitigate future risks.

[0062] A "user" is an entity that uses an information processing system to input information and to verify its output.

[0063] "Information" refers to documents and data that users input into the system, and is the subject of analysis.

[0064] A "natural language processing system" refers to the technology or program used by computers to understand, analyze, and generate human language.

[0065] "Analysis" is the process of identifying the content contained in received information and extracting information according to the purpose.

[0066] "Errors and deficiencies" refer to grammatical errors, factual inconsistencies, and deviations from established rules present in the information.

[0067] A "proposal for correction" refers to a specific plan for improvement to correct errors and deficiencies.

[0068] "History of modification work" refers to a record of modifications made by the user in the past, making it possible to track changes in the information.

[0069] "Assessing the impact" means analyzing and judging the effects that corrective actions will have on the information and the entire system.

[0070] "Risk assessment" involves analyzing potential problems associated with information processing and developing plans to mitigate those risks.

[0071] An "improvement plan" refers to specific steps and methods proposed to reduce risks and improve the quality of information processing.

[0072] A "predictive model" refers to a mathematical or statistical method used to predict future outcomes based on past information.

[0073] "Verification of consistency and coherence" is the process of confirming whether information is presented in a consistent and unified manner without contradictions.

[0074] This invention is a technology that uses an information processing system to efficiently detect errors and deficiencies in documents and generate correction suggestions. Specific embodiments for carrying out the invention are described below.

[0075] The user prepares the documents to be analyzed using a terminal and uploads them to the server. The documents must be in a commonly used electronic document format such as PDF or DOCX. Once the upload is complete, the server immediately processes the received information.

[0076] The server uses a natural language processing system to analyze documents. This system utilizes, for example, a generative AI model, specifically OpenAI® models or equivalent technologies. The system generates prompt sentences to identify grammatical errors and inconsistencies within the document, instructing the model to perform the analysis.

[0077] For example, a prompt might be text like, "Detect grammatical errors in this document and suggest corrections." The server inputs this prompt into the AI ​​model and receives the model's output.

[0078] Based on these results, the server generates specific correction suggestions. These suggestions are presented in a user-friendly format and are notified to the user in real time via their device. These notifications could be delivered through various methods, such as web applications or email.

[0079] Furthermore, the server has a function to record historical information in a database. This history is used for future improvements and risk assessments, and is an important element for ensuring the security of the information while maintaining its integrity.

[0080] In this way, the invention provides users with an efficient and accurate document management method, and makes it possible to improve the quality and reliability of information.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] Users prepare documents requiring analysis using their terminals and upload them to the server. Input documents are digital documents in PDF or DOCX format. Users select the target documents using the terminal's file selection function and send them to the server via a dedicated web interface or application. This securely uploads the documents to the server, allowing the process to proceed to the next analysis step.

[0084] Step 2:

[0085] The server first preprocesses the received document data. The files received as input are converted into text data. The server uses text extraction libraries such as Apache® Tika and textract to extract readable text from PDF and DOCX files and prepare the data in a structure that allows for analysis. The converted text data is generated and proceeds to the next analysis step.

[0086] Step 3:

[0087] The server analyzes the document using a natural language processing system. The input for this step is the text data converted in the previous step. The server uses a generative AI model to detect grammatical errors, inconsistencies, and deficiencies in this text. For this analysis, the server generates prompt sentences such as "Detect grammatical errors in this document and suggest corrections" and inputs them into the AI ​​model. The AI ​​model outputs analysis results, which include the identified errors and their explanations.

[0088] Step 4:

[0089] The server generates correction suggestions based on the output results from the AI ​​model. The input is the analysis results. The server formats the suggestions in a user-friendly format and creates written correction suggestions and proposals to be presented. The correction suggestions generated at this stage include, as concrete actions, the locations of the identified errors and specific methods for correcting them.

[0090] Step 5:

[0091] The server notifies the user's terminal of the generated correction suggestions. The input is a formatted correction suggestion. The server uses real-time notification technology to send the correction suggestions to the user's terminal. This output displays the suggested content on the terminal's user interface, allowing the user to review the content and point out any issues.

[0092] Step 6:

[0093] The server records user correction results and feedback, and saves all correction work as historical information in the database. As input, the user's correction information is sent to the server. The server then analyzes this historical information and records it for use in future analyses. Based on this historical data, it becomes possible to perform future risk assessments. This promotes improvements in information security and quality.

[0094] (Application Example 1)

[0095] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0096] In modern times, deficiencies and errors in contracts and transaction documents can lead to legal troubles and a decline in trust. Contracts and terms of service, in particular, are crucial for electronic payment services, and because errors are difficult to detect, they carry the risk of damaging the trust of business partners. Therefore, there is a need for a system that can detect potential errors and deficiencies in contracts and terms of service in real time and promptly propose corrections.

[0097] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0098] In this invention, the server includes means for analyzing a specified document and detecting errors and deficiencies within the document using a natural language processing model; means for generating correction suggestions based on the detected errors and deficiencies; and means for detecting errors in contracts and terms of service in real time and providing correction suggestions. This makes it possible to identify errors contained in documents in a timely manner and enable safe and reliable transactions through the rapid provision of correction suggestions.

[0099] A "specified document" refers to a document or text file that a user uploads for a specific purpose.

[0100] "Analysis" is the process of breaking down the information contained in a document and understanding its structure and content in detail.

[0101] A "natural language processing model" is an algorithm or machine learning model that enables computers to understand and generate natural language used by humans.

[0102] "Errors and deficiencies" refer to grammatical errors or substantive flaws present in a document.

[0103] A "proposal for correction" is a suggestion for improvement or correction to an error or deficiency that has been detected.

[0104] "Means of notifying the user" refers to communication or display means by which the system presents detection results or correction suggestions to the user.

[0105] "Means for recording and evaluating change history" refers to a system that tracks changes made to a document and analyzes the results and impacts of those changes.

[0106] "A means of conducting a risk assessment and proposing an action plan" refers to a method of analyzing the potential risks that may arise from revising a document and presenting specific action plans to mitigate them.

[0107] "A means of detecting errors in contracts and terms of service in real time and proposing corrections" refers to a mechanism that immediately recognizes errors in contract-related documents and immediately provides proposed corrections.

[0108] In this invention, three entities—a server, a terminal, and a user—play crucial roles in implementing a system for analyzing a specified document, detecting errors and deficiencies, and suggesting corrections. The following describes specific embodiments of this system.

[0109] The server analyzes uploaded documents using natural language processing models. The server detects grammatical errors and content deficiencies using AI algorithms and generates specific correction suggestions based on these findings. The natural language processing models used are widely known generative AI models such as GPT and BERT. The server also has the ability to predict error patterns by learning from past data, thereby improving the accuracy of document analysis.

[0110] The terminal provides an interface for users to upload contracts and terms of service. Analysis results and suggested revisions are notified to the user through the terminal. The terminal's software, as the user interface, is either a web application or a native application that provides real-time feedback.

[0111] Users upload documents from their devices and receive feedback from the server. Based on this feedback, users can revise their documents, enabling them to proceed with reliable contracts and transactions.

[0112] As a concrete example, suppose a company is launching a new electronic payment service and has created terms of service. When these terms of service are uploaded to the system from a terminal, the server immediately analyzes the document and identifies errors by comparing it with past cases. For example, it might point out the ambiguity of the term "penalties" in the document and suggest a revision such as, "This agreement is serious, and legal proceedings will be applied in case of violation. Specifically, (enter specific details)."

[0113] An example of a prompt message is as follows:

[0114] "Please analyze the following document, identify any errors, and propose corrections: Document Content"

[0115] This configuration allows the system to quickly detect errors in contracts and terms of service and provide users with useful correction suggestions. This helps prevent business problems and improves reliability.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] Users use a terminal to specify the documents they wish to analyze, such as contracts and terms of service, and upload them to the system. The input is a document file, and the output is digital data sent to the server. This process involves file selection and uploading through a user interface.

[0119] Step 2:

[0120] The server receives the uploaded document and analyzes its content using a natural language processing model. The input is the document data received from the user, and the output is a list of errors and deficiencies in the document. In this step, a generative AI model analyzes the document text and processes the data to detect grammatical errors and content deficiencies.

[0121] Step 3:

[0122] The server generates correction suggestions based on the errors detected. The input is a list of errors and deficiencies in the document, and the output is feedback data containing correction suggestions. At this stage, a database of past cases is referenced, and specific improvement plans are created based on similar cases.

[0123] Step 4:

[0124] The generated correction suggestions are notified from the server to the user's terminal. The input is the correction suggestion data, and the output is a notification message on the terminal. In this process, the suggested content is displayed on the user's interface through the user notification function.

[0125] Step 5:

[0126] The user reviews the feedback presented from the terminal and revises the document as needed. The input is the suggested feedback received from the server, and the output is the revised document data. At this stage, the user makes the necessary edits based on the suggestions to improve the quality of the document.

[0127] Step 6:

[0128] The server records the change history and assesses the impact and risks of each modification. The input is user modification history data, and the output is a risk assessment and necessary action plan. In this final processing stage, long-term document compliance is checked based on the stored historical data, and necessary countermeasures are developed.

[0129] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0130] This invention is a system that not only analyzes documents and detects errors, but also recognizes user emotions and dynamically adjusts the interface. The system consists of three entities: a server, a terminal, and a user, in addition to incorporating an emotion engine.

[0131] Users upload design documents and pricing specifications to the server using their devices. Upon receiving the documents, the server begins analysis using a natural language processing model to identify grammatical errors and inconsistencies.

[0132] Based on the analysis results, the server generates suggested revisions. This is where the emotion engine comes into play. The server understands the user's emotional state and adjusts the wording and expression of the suggested revisions accordingly. For example, if the user is feeling frustrated, the server will tailor the suggestions to use more approachable language.

[0133] Furthermore, user sentiment data can be used to improve the system. The server accumulates user feedback and sentiment states and uses them to improve the long-term user experience. In this process, data is collected on improvements in the accuracy of suggestions and the adaptability of the interface.

[0134] As a concrete example, suppose a user uploads the pricing specifications for a new service plan when it is announced. The server immediately analyzes the document and detects potential errors. If the user feels uneasy or suspicious while interacting with the system, the emotion engine recognizes this state and provides appropriate feedback. This allows the user to review and correct the document with confidence, improving the overall efficiency of the verification process.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] The user uses a terminal to upload document files such as design specifications and pricing specifications to the server. The server receives these files and completes the preparation for analysis.

[0138] Step 2:

[0139] The server begins analyzing the received document by running it through a natural language processing model. The analysis identifies grammatical errors, inconsistencies, and deficiencies in the document.

[0140] Step 3:

[0141] While the analysis is in progress, the server activates the emotion engine and monitors the user's emotions through an interface on the user's device. It collects emotion data from voice and text.

[0142] Step 4:

[0143] The server generates correction suggestions for errors detected based on the analysis results. In doing so, it adjusts the way the suggestions are expressed, taking into account the user's emotional state as recognized by the emotion engine.

[0144] Step 5:

[0145] If the server determines that the user's emotions are negative, it will change the suggested fix to polite and friendly language to reduce the burden on the user.

[0146] Step 6:

[0147] The generated revision suggestions are notified to the user's device and presented to the user. The user then revises the document based on this feedback.

[0148] Step 7:

[0149] After the user modifies the document, they can upload it to the server again if necessary to perform another analysis process to verify the validity of the modifications.

[0150] Step 8:

[0151] The server records user sentiment data along with the change history of all documents. This data will be used to improve the system in the future and enhance the user experience.

[0152] (Example 2)

[0153] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0154] In today's world, there is a demand for the ability to efficiently detect errors and deficiencies in specified information. However, conventional technologies lacked the ability to provide feedback that considered user emotions, posing challenges to improving the user experience. Furthermore, they were unable to effectively handle users' emotional reactions to error detection results, limiting the system's adaptability. As a result, error correction suggestions did not adapt to the user's emotional state, leading to problems such as decreased efficiency and satisfaction with the correction process.

[0155] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0156] In this invention, the server includes means for analyzing specified information and detecting errors and deficiencies in the information using a machine learning model; means for analyzing the user's emotional state and adjusting the expression of correction suggestions according to the emotion; and means for accumulating emotion data and building a model to improve the system's adaptability. This makes it possible to accurately detect errors in information, make suggestions that align with the user's emotions, improve the user experience, and perform correction work efficiently.

[0157] "Specified information" refers to documents and data, such as design documents and specifications, provided by the user for analysis.

[0158] A "machine learning model" is an artificial intelligence technique used to detect errors and inconsistencies in information, and includes algorithms specifically designed for natural language processing.

[0159] "Errors and deficiencies" refer to grammatical errors, logical inconsistencies, inconsistencies, or inappropriate expressions present in the specified information.

[0160] "User emotional state" refers to the user's psychological reaction and mood to the analysis results and suggested modifications of the specified information.

[0161] "Adjusting the wording of correction suggestions" refers to optimizing the tone and wording of feedback regarding the correction of errors and deficiencies, according to the user's emotional state.

[0162] "Emotional data" refers to data collected about a user's emotional state, which will be used for future system improvements and enhancements to the user experience.

[0163] A "model for improving adaptability" refers to an algorithm or mechanism that learns from user emotional data and feedback to continuously improve the overall functionality and services of the system.

[0164] Embodiments for carrying out this invention are described below.

[0165] This system consists of three components: a server, a terminal, and a user. The server receives the information to be analyzed and uses machine learning models to detect errors and defects. Specifically, natural language processing models such as BERT and GPT are used. Because these models operate on a cloud-based system, high-speed and efficient processing is possible.

[0166] Users upload documents via a terminal. The terminal is equipped with a graphical user interface (GUI) for selecting and uploading information. Users can provide specified information to the system with simple operations.

[0167] After performing the analysis, the server notifies the user's terminal of the suggested corrections. At this time, the server uses an emotion engine to analyze the user's emotional state and provides adjusted feedback accordingly. The emotion engine predicts emotional responses based on the user's input data and interface operation history, and modifies the wording of the corrections accordingly.

[0168] As a concrete example, suppose a user uploads a pricing specification for a new service to the system. The server immediately analyzes the specification and detects potential grammatical errors and inconsistencies. If the user is experiencing stress, the emotion engine detects this and provides user-friendly feedback such as, "Making corrections based on our suggestions will make the process smoother."

[0169] Examples of prompt statements to input into the generative AI model are as follows:

[0170] "Analyze the following document and identify grammatical errors and inconsistencies. Also, create appropriate revision suggestions based on the emotions the user is feeling."

[0171] In this way, the system can not only improve the accuracy of information but also provide feedback that takes user emotions into consideration, thereby improving the overall quality of the user experience.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The user selects a document file via the terminal and sends it to the server using the upload function. As input, the user specifies a document file and sends it to the server via the GUI. As output, the document file is received by the server.

[0175] Step 2:

[0176] The server inputs the received document files into a machine learning model and performs data processing to analyze grammatical errors and inconsistencies within the documents. Specifically, it uses BERT or GPT models to analyze the text data. The output is a list of grammatical errors and inconsistencies.

[0177] Step 3:

[0178] The server generates correction suggestions based on the analysis results. The input is the list of grammatical errors and deficiencies obtained in step 2. The server uses this data to perform calculations to create specific correction proposals. The output is a list of correction suggestions.

[0179] Step 4:

[0180] The server operates an emotion engine to understand the user's emotional state. The input consists of the user's operation history and response data from the device. The server analyzes this data to predict the user's current emotional state. The output is the user's emotional state.

[0181] Step 5:

[0182] The server adjusts the wording of the suggested revisions based on the user's emotional state. The inputs are the suggested revisions from step 3 and the emotional state from step 4. Based on this, the server modifies the suggested revisions to suit the user's needs. The output is the revised suggested revisions.

[0183] Step 6:

[0184] The server notifies the terminal of the adjusted correction proposal and allows the user to confirm it. The input is the adjusted correction proposal formed in step 5. The server sends this to the user terminal and displays it to the user through the terminal's GUI. As output, the user receives and can confirm the correction proposal.

[0185] (Application Example 2)

[0186] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0187] Modern information processing systems are required not only to point out errors and deficiencies in documents, but also to provide interfaces that understand and respond appropriately to user emotions. However, conventional systems have difficulty making dynamic adjustments based on user emotions, limiting the improvement of the user experience. Furthermore, there has been a lack of effective means to alleviate anxiety and doubt in situations such as payment procedures.

[0188] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0189] In this invention, the server includes means for analyzing specified information and detecting errors and deficiencies in the text using natural language processing technology; means for recognizing the user's emotional state and dynamically adjusting and notifying the content and expression of correction suggestions according to the emotion; and means for accumulating user emotion data and collecting and processing data useful for improving the experience. This makes it possible to detect errors in documents while providing an appropriate interface according to the user's emotions, thereby reducing user anxiety and doubt in payment procedures and other situations.

[0190] "Specified information" refers to the information that the system will analyze, and typically includes documents and data provided by the user.

[0191] "Natural language processing technology" refers to the technology that enables computers to understand and generate human language, and involves multiple processes including grammatical analysis and semantic analysis.

[0192] "Errors and deficiencies" refer to grammatical errors, inconsistencies in content, and inaccurate expressions contained in a document.

[0193] "User emotional state" refers to the user's psychological state and emotional condition, and typically includes emotions such as joy, anxiety, and frustration.

[0194] "Dynamic adjustment" means that the system changes the suggested content and interface display in real time according to the user's emotions and situation.

[0195] A "revision suggestion" refers to a specific proposal for improving a document based on any errors or deficiencies that have been detected.

[0196] "Improving the user experience" means enhancing the satisfaction and convenience that users experience when using a system.

[0197] To realize this invention, a server plays a central role. First, the server analyzes the specified information received from the user terminal. Specifically, it employs natural language processing technology for text analysis to detect errors and deficiencies in the information. Advanced natural language processing software, such as Google® Cloud Natural Language API, is utilized in this process.

[0198] Next, the server uses the Emotion API to analyze the user's emotional state. Based on this information, the server dynamically generates modification suggestions tailored to the user's current emotions and notifies the user through their device. These suggestions may include friendly language to alleviate frustration or information to stimulate purchasing intent.

[0199] Furthermore, user sentiment data and feedback are stored on the server and used to improve the long-term experience. Based on this data, the server analyzes the user experience and provides information that contributes to system improvements.

[0200] As a concrete example, let's assume a user is purchasing a product online. While the user is considering the purchase, the server analyzes the user's emotions in real time and dynamically provides information to assist in the purchase decision. For example, if the user is feeling anxious about the purchase, a suggestion such as "This product has very high ratings and offers great value for money" might be displayed.

[0201] Regarding the use of a generative AI model, one possible prompt message could be: "I'm considering making a payment, but I have some concerns. Please provide suggestions on how to make a purchase with confidence." Through this prompt, the system can provide the user with the most appropriate suggestions and information.

[0202] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0203] Step 1:

[0204] The server receives the specified information from the user's terminal. The input is text data sent by the user, which is passed to the server for analysis. The output indicates the completion of the process in which this data is prepared for analysis.

[0205] Step 2:

[0206] The server analyzes the information using natural language processing techniques. The input is the text data received in step 1. The server uses the Google Cloud Natural Language API to check for grammatical errors and content consistency. The output is processed as an analysis result, with errors and deficiencies identified.

[0207] Step 3:

[0208] The server uses the Emotion API to analyze the user's emotional state. Inputs include user interactions and pre-collected emotion-related data. At this stage, the server quantifies the user's emotional state, identifying frustration, anxiety, and other emotional states. The output is a report on the user's emotional state.

[0209] Step 4:

[0210] The server generates suggested modifications based on the analysis results and emotional state. The input is the output from steps 2 and 3. The server uses this information to generate suggestions tailored to the user's emotions. Dynamic feedback is created, including friendly language and specific purchase assistance information. The output is the suggested modifications, which are then notified to the user.

[0211] Step 5:

[0212] The terminal receives correction suggestions from the server and presents them to the user. The input is the correction suggestion generated in step 4. The terminal displays this suggestion on the user's screen and prompts the user for confirmation and further action. The output is the completion of displaying the suggestion to the user.

[0213] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0214] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0215] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0216] [Second Embodiment]

[0217] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0218] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0219] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0220] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0221] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0222] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0223] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0224] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0225] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0226] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0227] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0228] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0229] This invention is a system that receives a specified document, automatically detects errors and deficiencies within it, and suggests appropriate corrections. This system consists of three components: a server, a terminal, and a user.

[0230] First, the user uploads necessary documents, such as design specifications and pricing documents, to the server using their device. The server analyzes the uploaded documents using a natural language processing model to detect errors such as grammatical mistakes, inconsistencies, and violations of regulations.

[0231] When an error is detected, the server generates specific correction suggestions based on it. These suggestions include points to maintain the overall consistency of the document and improvement proposals based on similar past cases. The generated suggestions are notified to the user's terminal as feedback.

[0232] Furthermore, the server tracks the impact and progress of user-initiated changes by recording all change history in a database. Based on this historical information, the server assesses the risks that the changes pose to the overall service and proposes an action plan as needed.

[0233] In actual operation, for example, when a pricing specification document for a new service is created, the user uploads it from their terminal to the server. The server immediately begins analysis, comparing it with past data to identify potential errors. As a result, the server sends specific feedback to the user, who can then revise and verify the document based on the suggestions. By repeating this process, the quality of the document improves and the reliability of the service is ensured.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] The user uses their terminal to upload document files, such as design specifications and pricing documents, to the server. Once the upload is complete, the server receives the files and prepares them for analysis.

[0237] Step 2:

[0238] The server passes the received document through a natural language processing model. The model analyzes the document sentence by sentence and initiates an analysis process to identify grammatical errors and inconsistencies.

[0239] Step 3:

[0240] The server applies machine learning algorithms and compares the results with similar historical data to detect potential error patterns. In this process, discrepancies in pricing and inappropriate descriptions are particularly highlighted.

[0241] Step 4:

[0242] If an error is detected, the server will generate specific correction suggestions based on it. These suggestions will include a description of the error and proposed corrections, or comparison information with relevant documents.

[0243] Step 5:

[0244] When revision suggestions are generated, the server notifies the user's terminal. The suggestions presented as feedback serve as a guide for the user when revising the document.

[0245] Step 6:

[0246] The user modifies the document based on feedback from the server. If necessary, it is uploaded back to the server and subjected to another analysis process to verify the validity of the modifications.

[0247] Step 7:

[0248] The server records the history of all document changes and performs an impact analysis on newly modified documents. If the impact is deemed significant, it presents the user with a risk assessment report and action plan.

[0249] Step 8:

[0250] The process is repeated until changes are finalized, ultimately resulting in a document with guaranteed accuracy. Through this process, document quality improves, and customer service reliability increases.

[0251] (Example 1)

[0252] Next, we will describe Example 1. 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".

[0253] In information processing, efficiently detecting errors and deficiencies in documents and information, and proposing appropriate corrections based on these findings, is challenging. Especially in today's society, where vast amounts of information are constantly being generated, maintaining information consistency quickly and accurately is a crucial issue. Furthermore, there is a need for methods to effectively utilize past revision history, assess risks, and prevent future errors.

[0254] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0255] In this invention, the server includes means for receiving information from a user, means for analyzing the received information using a natural language processing system to detect errors and deficiencies, and means for generating correction suggestions based on the detected errors and deficiencies. This enables users to quickly and accurately correct errors in documents and maintain the integrity of the information. Furthermore, by utilizing a model that learns from past information and predicts error patterns, it is possible to mitigate future risks.

[0256] A "user" is an entity that uses an information processing system to input information and to verify its output.

[0257] "Information" refers to documents and data that users input into the system, and is the subject of analysis.

[0258] A "natural language processing system" refers to the technology or program used by computers to understand, analyze, and generate human language.

[0259] "Analysis" is the process of identifying the content contained in received information and extracting information according to the purpose.

[0260] "Errors and deficiencies" refer to grammatical errors, factual inconsistencies, and deviations from established rules present in the information.

[0261] A "proposal for correction" refers to a specific plan for improvement to correct errors and deficiencies.

[0262] "History of modification work" refers to a record of modifications made by the user in the past, making it possible to track changes in the information.

[0263] "Assessing the impact" means analyzing and judging the effects that corrective actions will have on the information and the entire system.

[0264] "Risk assessment" involves analyzing potential problems associated with information processing and developing plans to mitigate those risks.

[0265] An "improvement plan" refers to specific steps and methods proposed to reduce risks and improve the quality of information processing.

[0266] A "predictive model" refers to a mathematical or statistical method used to predict future outcomes based on past information.

[0267] "Verification of consistency and coherence" is the process of confirming whether information is presented in a consistent and unified manner without contradictions.

[0268] This invention is a technology that uses an information processing system to efficiently detect errors and deficiencies in documents and generate correction suggestions. Specific embodiments for carrying out the invention are described below.

[0269] The user prepares the documents to be analyzed using a terminal and uploads them to the server. The documents must be in a commonly used electronic document format such as PDF or DOCX. Once the upload is complete, the server immediately processes the received information.

[0270] The server uses a natural language processing system to analyze documents. This system utilizes, for example, a generative AI model, specifically OpenAI models or equivalent technologies. The system generates prompt sentences to identify grammatical errors and inconsistencies within the document, instructing the model to perform the analysis.

[0271] For example, a prompt might be text like, "Detect grammatical errors in this document and suggest corrections." The server inputs this prompt into the AI ​​model and receives the model's output.

[0272] Based on these results, the server generates specific correction suggestions. These suggestions are presented in a user-friendly format and are notified to the user in real time via their device. These notifications could be delivered through various methods, such as web applications or email.

[0273] Furthermore, the server has a function to record historical information in a database. This history is used for future improvements and risk assessments, and is an important element for ensuring the security of the information while maintaining its integrity.

[0274] In this way, the invention provides users with an efficient and accurate document management method, and makes it possible to improve the quality and reliability of information.

[0275] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0276] Step 1:

[0277] Users prepare documents requiring analysis using their terminals and upload them to the server. Input documents are digital documents in PDF or DOCX format. Users select the target documents using the terminal's file selection function and send them to the server via a dedicated web interface or application. This securely uploads the documents to the server, allowing the process to proceed to the next analysis step.

[0278] Step 2:

[0279] The server first preprocesses the received document data. The file received as input is converted into text data. The server uses a text extraction library such as Apache Tika or textract to extract readable text from PDF or DOCX files and prepares the data in a structure that enables analysis. The converted text data is generated and proceeds to the next analysis step.

[0280] Step 3:

[0281] The server analyzes the document using a natural language processing system. The input for this step is the text data converted in the previous step. The server uses a generative AI model to detect grammar errors, content contradictions, and deficiencies in this text. The server generates a prompt sentence such as "Detect grammar errors contained in this document and present amendments" for this analysis and inputs it into the AI model. The analysis result output by the AI model is generated, which includes the identified errors and their explanations.

[0282] Step 4:

[0283] The server generates a correction proposal based on the output result from the AI model. The input is the analysis result. The server formats the proposal into an easy-to-understand form for the user and creates the amendments and proposals to be presented as text. The correction proposals generated at this stage include, as specific actions, the locations of the pointed-out mistakes and the specific methods for correcting them.

[0284] Step 5:

[0285] The server notifies the user's terminal of the generated modification proposals. The input is the formatted modification proposals. The server utilizes real-time notification technology to send the modification proposals to the user's terminal. With this output, the proposal content is displayed on the user interface of the terminal, and the user can confirm the content along with pointing out any issues.

[0286] Step 6:

[0287] The server records the modification results and feedback from the user and stores all modification operations in the database as historical information. As input, the modification information made by the user is sent to the server. Here, the server analyzes the historical information and records it for use in future analysis. Based on this historical data, it becomes possible to conduct future risk assessments. This promotes the improvement of information security and quality.

[0288] (Application Example 1)

[0289] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0290] In modern times, deficiencies and errors in documents in contracts and transactions have become a cause of legal troubles and a decline in reliability. Particularly, the contract documents and terms of use in electronic payment services are important, and due to the difficulty of detecting errors, there is a risk of damaging the trust of business partners. Therefore, there is a need for a system that can detect errors and deficiencies latent in contract documents and terms of use in real time and quickly make modification proposals.

[0291] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0292] In this invention, the server includes means for analyzing a specified document and detecting errors and deficiencies within the document using a natural language processing model; means for generating correction suggestions based on the detected errors and deficiencies; and means for detecting errors in contracts and terms of service in real time and providing correction suggestions. This makes it possible to identify errors contained in documents in a timely manner and enable safe and reliable transactions through the rapid provision of correction suggestions.

[0293] A "specified document" refers to a document or text file that a user uploads for a specific purpose.

[0294] "Analysis" is the process of breaking down the information contained in a document and understanding its structure and content in detail.

[0295] A "natural language processing model" is an algorithm or machine learning model that enables computers to understand and generate natural language used by humans.

[0296] "Errors and deficiencies" refer to grammatical errors or substantive flaws present in a document.

[0297] A "proposal for correction" is a suggestion for improvement or correction to an error or deficiency that has been detected.

[0298] "Means of notifying the user" refers to communication or display means by which the system presents detection results or correction suggestions to the user.

[0299] "Means for recording and evaluating change history" refers to a system that tracks changes made to a document and analyzes the results and impacts of those changes.

[0300] "A means of conducting a risk assessment and proposing an action plan" refers to a method of analyzing the potential risks that may arise from revising a document and presenting specific action plans to mitigate them.

[0301] "A means of detecting errors in contracts and terms of service in real time and proposing corrections" refers to a mechanism that immediately recognizes errors in contract-related documents and immediately provides proposed corrections.

[0302] In this invention, three entities—a server, a terminal, and a user—play crucial roles in implementing a system for analyzing a specified document, detecting errors and deficiencies, and suggesting corrections. The following describes specific embodiments of this system.

[0303] The server analyzes uploaded documents using natural language processing models. The server detects grammatical errors and content deficiencies using AI algorithms and generates specific correction suggestions based on these findings. The natural language processing models used are widely known generative AI models such as GPT and BERT. The server also has the ability to predict error patterns by learning from past data, thereby improving the accuracy of document analysis.

[0304] The terminal provides an interface for users to upload contracts and terms of service. Analysis results and suggested revisions are notified to the user through the terminal. The terminal's software, as the user interface, is either a web application or a native application that provides real-time feedback.

[0305] Users upload documents from their devices and receive feedback from the server. Based on this feedback, users can revise their documents, enabling them to proceed with reliable contracts and transactions.

[0306] As a specific example, suppose a company creates a terms of use when starting a new electronic payment service. When the terms of use are uploaded from a terminal to the system, the server immediately analyzes the document and identifies errors while comparing it with past cases. For example, it points out the ambiguity of the term "penalty" in the document and proposes a correction such as "This contract is important, and legal procedures will be applied in case of violation. Specifically, (input specific content)".

[0307] Examples of prompt sentences are as follows.

[0308] "Analyze the following document, identify errors in the document, and provide correction proposals: Document content"

[0309] In this form, the system can quickly detect errors in contracts and terms of use and provide useful correction proposals to users. This can prevent troubles in business and improve reliability.

[0310] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0311] Step 1:

[0312] The user uses the terminal to specify a document to be analyzed, such as a contract or terms of use, and uploads it to the system. The input is a document file, and the output is digital data passed to the server. In this process, file selection and upload operations are performed through the user interface.

[0313] Step 2:

[0314] The server receives the uploaded document and analyzes its content using a natural language processing model. The input is the document data received from the user, and the output is a list of errors and deficiencies in the document. In this step, the generative AI model analyzes the document text and performs data processing to detect grammatical errors and content deficiencies.

[0315] Step 3:

[0316] The server generates correction suggestions based on the errors detected. The input is a list of errors and deficiencies in the document, and the output is feedback data containing correction suggestions. At this stage, a database of past cases is referenced, and specific improvement plans are created based on similar cases.

[0317] Step 4:

[0318] The generated correction suggestions are notified from the server to the user's terminal. The input is the correction suggestion data, and the output is a notification message on the terminal. In this process, the suggested content is displayed on the user's interface through the user notification function.

[0319] Step 5:

[0320] The user reviews the feedback presented from the terminal and revises the document as needed. The input is the suggested feedback received from the server, and the output is the revised document data. At this stage, the user makes the necessary edits based on the suggestions to improve the quality of the document.

[0321] Step 6:

[0322] The server records the change history and assesses the impact and risks of each modification. The input is user modification history data, and the output is a risk assessment and necessary action plan. In this final processing stage, long-term document compliance is checked based on the stored historical data, and necessary countermeasures are developed.

[0323] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0324] This invention is a system that not only analyzes documents and detects errors, but also recognizes user emotions and dynamically adjusts the interface. The system consists of three entities: a server, a terminal, and a user, in addition to incorporating an emotion engine.

[0325] Users upload design documents and pricing specifications to the server using their devices. Upon receiving the documents, the server begins analysis using a natural language processing model to identify grammatical errors and inconsistencies.

[0326] Based on the analysis results, the server generates suggested revisions. This is where the emotion engine comes into play. The server understands the user's emotional state and adjusts the wording and expression of the suggested revisions accordingly. For example, if the user is feeling frustrated, the server will tailor the suggestions to use more approachable language.

[0327] Furthermore, user sentiment data can be used to improve the system. The server accumulates user feedback and sentiment states and uses them to improve the long-term user experience. In this process, data is collected on improvements in the accuracy of suggestions and the adaptability of the interface.

[0328] As a concrete example, suppose a user uploads the pricing specifications for a new service plan when it is announced. The server immediately analyzes the document and detects potential errors. If the user feels uneasy or suspicious while interacting with the system, the emotion engine recognizes this state and provides appropriate feedback. This allows the user to review and correct the document with confidence, improving the overall efficiency of the verification process.

[0329] The following describes the processing flow.

[0330] Step 1:

[0331] The user uses a terminal to upload document files such as design specifications and pricing specifications to the server. The server receives these files and completes the preparation for analysis.

[0332] Step 2:

[0333] The server begins analyzing the received document by running it through a natural language processing model. The analysis identifies grammatical errors, inconsistencies, and deficiencies in the document.

[0334] Step 3:

[0335] While the analysis is in progress, the server activates the emotion engine and monitors the user's emotions through an interface on the user's device. It collects emotion data from voice and text.

[0336] Step 4:

[0337] The server generates correction suggestions for errors detected based on the analysis results. In doing so, it adjusts the way the suggestions are expressed, taking into account the user's emotional state as recognized by the emotion engine.

[0338] Step 5:

[0339] If the server determines that the user's emotions are negative, it will change the suggested fix to polite and friendly language to reduce the burden on the user.

[0340] Step 6:

[0341] The generated revision suggestions are notified to the user's device and presented to the user. The user then revises the document based on this feedback.

[0342] Step 7:

[0343] After the user modifies the document, they can upload it to the server again if necessary to perform another analysis process to verify the validity of the modifications.

[0344] Step 8:

[0345] The server records user sentiment data along with the change history of all documents. This data will be used to improve the system in the future and enhance the user experience.

[0346] (Example 2)

[0347] Next, we will describe Example 2. 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".

[0348] In today's world, there is a demand for the ability to efficiently detect errors and deficiencies in specified information. However, conventional technologies lacked the ability to provide feedback that considered user emotions, posing challenges to improving the user experience. Furthermore, they were unable to effectively handle users' emotional reactions to error detection results, limiting the system's adaptability. As a result, error correction suggestions did not adapt to the user's emotional state, leading to problems such as decreased efficiency and satisfaction with the correction process.

[0349] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0350] In this invention, the server includes means for analyzing specified information and detecting errors and deficiencies in the information using a machine learning model; means for analyzing the user's emotional state and adjusting the expression of correction suggestions according to the emotion; and means for accumulating emotion data and building a model to improve the system's adaptability. This makes it possible to accurately detect errors in information, make suggestions that align with the user's emotions, improve the user experience, and perform correction work efficiently.

[0351] "Specified information" refers to documents and data, such as design documents and specifications, provided by the user for analysis.

[0352] A "machine learning model" is an artificial intelligence technique used to detect errors and inconsistencies in information, and includes algorithms specifically designed for natural language processing.

[0353] "Errors and deficiencies" refer to grammatical errors, logical inconsistencies, inconsistencies, or inappropriate expressions present in the specified information.

[0354] "User emotional state" refers to the user's psychological reaction and mood to the analysis results and suggested modifications of the specified information.

[0355] "Adjusting the wording of correction suggestions" refers to optimizing the tone and wording of feedback regarding the correction of errors and deficiencies, depending on the user's emotional state.

[0356] "Emotional data" refers to data collected about a user's emotional state, which will be used for future system improvements and enhancements to the user experience.

[0357] A "model for improving adaptability" refers to an algorithm or mechanism that learns from user emotional data and feedback to continuously improve the overall functionality and services of the system.

[0358] Embodiments for carrying out this invention are described below.

[0359] This system consists of three components: a server, a terminal, and a user. The server receives the information to be analyzed and uses machine learning models to detect errors and defects. Specifically, natural language processing models such as BERT and GPT are used. Because these models operate on a cloud-based system, high-speed and efficient processing is possible.

[0360] Users upload documents via a terminal. The terminal is equipped with a graphical user interface (GUI) for selecting and uploading information. Users can provide specified information to the system with simple operations.

[0361] After performing the analysis, the server notifies the user's terminal of the suggested corrections. At this time, the server uses an emotion engine to analyze the user's emotional state and provides adjusted feedback accordingly. The emotion engine predicts emotional responses based on the user's input data and interface operation history, and modifies the wording of the corrections accordingly.

[0362] As a concrete example, suppose a user uploads a pricing specification for a new service to the system. The server immediately analyzes the specification and detects potential grammatical errors and inconsistencies. If the user is experiencing stress, the emotion engine detects this and provides user-friendly feedback such as, "Making corrections based on our suggestions will make the process smoother."

[0363] Examples of prompt statements to input into the generative AI model are as follows:

[0364] "Analyze the following document and identify grammatical errors and inconsistencies. Also, create appropriate revision suggestions based on the emotions the user is feeling."

[0365] In this way, the system can not only improve the accuracy of information but also provide feedback that takes user emotions into consideration, thereby improving the overall quality of the user experience.

[0366] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0367] Step 1:

[0368] The user selects a document file via the terminal and sends it to the server using the upload function. As input, the user specifies a document file and sends it to the server via the GUI. As output, the document file is received by the server.

[0369] Step 2:

[0370] The server inputs the received document files into a machine learning model and performs data processing to analyze grammatical errors and inconsistencies within the documents. Specifically, it uses BERT or GPT models to analyze the text data. The output is a list of grammatical errors and inconsistencies.

[0371] Step 3:

[0372] The server generates correction suggestions based on the analysis results. The input is the list of grammatical errors and deficiencies obtained in step 2. The server uses this data to perform calculations to create specific correction proposals. The output is a list of correction suggestions.

[0373] Step 4:

[0374] The server operates an emotion engine to understand the user's emotional state. The input consists of the user's operation history and device response data. The server analyzes this data to predict the user's current emotional state. The output is the user's emotional state.

[0375] Step 5:

[0376] The server adjusts the wording of the suggested revisions based on the user's emotional state. The inputs are the suggested revisions from step 3 and the emotional state from step 4. Based on this, the server modifies the suggested revisions to suit the user's needs. The output is the revised suggested revisions.

[0377] Step 6:

[0378] The server notifies the terminal of the adjusted correction proposal and allows the user to confirm it. The input is the adjusted correction proposal formed in step 5. The server sends this to the user terminal and displays it to the user through the terminal's GUI. As output, the user receives and can confirm the correction proposal.

[0379] (Application Example 2)

[0380] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0381] Modern information processing systems are required not only to point out errors and deficiencies in documents, but also to provide interfaces that understand and respond appropriately to user emotions. However, conventional systems have difficulty making dynamic adjustments based on user emotions, limiting the improvement of the user experience. Furthermore, there has been a lack of effective means to alleviate anxiety and doubt in situations such as payment procedures.

[0382] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0383] In this invention, the server includes means for analyzing specified information and detecting errors and deficiencies in the text using natural language processing technology; means for recognizing the user's emotional state and dynamically adjusting and notifying the content and expression of correction suggestions according to the emotion; and means for accumulating user emotion data and collecting and processing data useful for improving the experience. This makes it possible to detect errors in documents while providing an appropriate interface according to the user's emotions, thereby reducing user anxiety and doubt in payment procedures and other situations.

[0384] "Specified information" refers to the information that the system will analyze, and typically includes documents and data provided by the user.

[0385] "Natural language processing technology" refers to the technology that enables computers to understand and generate human language, and involves multiple processes including grammatical analysis and semantic analysis.

[0386] "Errors and deficiencies" refer to grammatical errors, inconsistencies in content, and inaccurate expressions contained in a document.

[0387] "User emotional state" refers to the user's psychological state and emotional condition, and typically includes emotions such as joy, anxiety, and frustration.

[0388] "Dynamic adjustment" means that the system changes the suggested content and interface display in real time according to the user's emotions and situation.

[0389] A "revision suggestion" refers to a specific proposal for improving a document based on any errors or deficiencies that have been detected.

[0390] "Improving the user experience" means enhancing the satisfaction and convenience that users experience when using a system.

[0391] To realize this invention, a server plays a central role. First, the server analyzes the specified information received from the user terminal. Specifically, it employs natural language processing technology for text analysis to detect errors and deficiencies in the information. Advanced natural language processing software, such as the Google Cloud Natural Language API, is utilized in this process.

[0392] Next, the server uses the Emotion API to analyze the user's emotional state. Based on this information, the server dynamically generates modification suggestions tailored to the user's current emotions and notifies the user through their device. These suggestions may include friendly language to alleviate frustration or information to stimulate purchasing intent.

[0393] Furthermore, user sentiment data and feedback are stored on the server and used to improve the long-term experience. Based on this data, the server analyzes the user experience and provides information that contributes to system improvements.

[0394] As a concrete example, let's assume a user is purchasing a product online. While the user is considering the purchase, the server analyzes the user's emotions in real time and dynamically provides information to assist in the purchase decision. For example, if the user is feeling anxious about the purchase, a suggestion such as "This product has very high ratings and offers great value for money" might be displayed.

[0395] Regarding the use of a generative AI model, one possible prompt message could be: "I'm considering making a payment, but I have some concerns. Please provide suggestions on how to make a purchase with confidence." Through this prompt, the system can provide the user with the most appropriate suggestions and information.

[0396] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0397] Step 1:

[0398] The server receives the specified information from the user's terminal. The input is text data sent by the user, which is passed to the server for analysis. The output indicates the completion of the process in which this data is prepared for analysis.

[0399] Step 2:

[0400] The server analyzes the information using natural language processing techniques. The input is the text data received in step 1. The server uses the Google Cloud Natural Language API to check for grammatical errors and content consistency. The output is processed as an analysis result, with errors and deficiencies identified.

[0401] Step 3:

[0402] The server uses the Emotion API to analyze the user's emotional state. Inputs include user interactions and pre-collected emotion-related data. At this stage, the server quantifies the user's emotional state, identifying frustration, anxiety, and other emotional states. The output is a report on the user's emotional state.

[0403] Step 4:

[0404] The server generates suggested modifications based on the analysis results and emotional state. The input is the output from steps 2 and 3. The server uses this information to generate suggestions tailored to the user's emotions. Dynamic feedback is created, including friendly language and specific purchase assistance information. The output is the suggested modifications, which are then notified to the user.

[0405] Step 5:

[0406] The terminal receives correction suggestions from the server and presents them to the user. The input is the correction suggestion generated in step 4. The terminal displays this suggestion on the user's screen and prompts the user for confirmation and further action. The output is the completion of displaying the suggestion to the user.

[0407] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0408] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0409] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0410] [Third Embodiment]

[0411] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0412] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0413] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0414] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0415] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0416] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0417] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0418] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0419] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0420] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0421] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0422] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0423] This invention is a system that receives a specified document, automatically detects errors and deficiencies within it, and suggests appropriate corrections. This system consists of three components: a server, a terminal, and a user.

[0424] First, the user uploads necessary documents, such as design specifications and pricing documents, to the server using their device. The server analyzes the uploaded documents using a natural language processing model to detect errors such as grammatical mistakes, inconsistencies, and violations of regulations.

[0425] When an error is detected, the server generates specific correction suggestions based on it. These suggestions include points to maintain the overall consistency of the document and improvement proposals based on similar past cases. The generated suggestions are notified to the user's terminal as feedback.

[0426] Furthermore, the server tracks the impact and progress of user-initiated changes by recording all change history in a database. Based on this historical information, the server assesses the risks that the changes pose to the overall service and proposes an action plan as needed.

[0427] In actual operation, for example, when a pricing specification document for a new service is created, the user uploads it from their terminal to the server. The server immediately begins analysis, comparing it with past data to identify potential errors. As a result, the server sends specific feedback to the user, who can then revise and verify the document based on the suggestions. By repeating this process, the quality of the document improves and the reliability of the service is ensured.

[0428] The following describes the processing flow.

[0429] Step 1:

[0430] The user uses their terminal to upload document files, such as design specifications and pricing documents, to the server. Once the upload is complete, the server receives the files and prepares them for analysis.

[0431] Step 2:

[0432] The server passes the received document through a natural language processing model. The model analyzes the document sentence by sentence and initiates an analysis process to identify grammatical errors and inconsistencies.

[0433] Step 3:

[0434] The server applies machine learning algorithms and compares the results with similar historical data to detect potential error patterns. In this process, discrepancies in pricing and inappropriate descriptions are particularly highlighted.

[0435] Step 4:

[0436] If an error is detected, the server will generate specific correction suggestions based on it. These suggestions will include a description of the error and proposed corrections, or comparison information with relevant documents.

[0437] Step 5:

[0438] When revision suggestions are generated, the server notifies the user's terminal. The suggestions presented as feedback serve as a guide for the user when revising the document.

[0439] Step 6:

[0440] The user modifies the document based on feedback from the server. If necessary, it is uploaded back to the server and subjected to another analysis process to verify the validity of the modifications.

[0441] Step 7:

[0442] The server records the history of all document changes and performs an impact analysis on newly modified documents. If the impact is deemed significant, it presents the user with a risk assessment report and action plan.

[0443] Step 8:

[0444] The process is repeated until changes are finalized, ultimately resulting in a document with guaranteed accuracy. Through this process, document quality improves, and customer service reliability increases.

[0445] (Example 1)

[0446] Next, we will describe Example 1. 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."

[0447] In information processing, efficiently detecting errors and deficiencies in documents and information, and proposing appropriate corrections based on these findings, is challenging. Especially in today's society, where vast amounts of information are constantly being generated, maintaining information consistency quickly and accurately is a crucial issue. Furthermore, there is a need for methods to effectively utilize past revision history, assess risks, and prevent future errors.

[0448] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0449] In this invention, the server includes means for receiving information from a user, means for analyzing the received information using a natural language processing system to detect errors and deficiencies, and means for generating correction suggestions based on the detected errors and deficiencies. This enables users to quickly and accurately correct errors in documents and maintain the integrity of the information. Furthermore, by utilizing a model that learns from past information and predicts error patterns, it is possible to mitigate future risks.

[0450] A "user" is an entity that uses an information processing system to input information and to verify its output.

[0451] "Information" refers to documents and data that users input into the system, and is the subject of analysis.

[0452] A "natural language processing system" refers to the technology or program used by computers to understand, analyze, and generate human language.

[0453] "Analysis" is the process of identifying the content contained in received information and extracting information according to the purpose.

[0454] "Errors and deficiencies" refer to grammatical errors, factual inconsistencies, and deviations from established rules present in the information.

[0455] A "proposal for correction" refers to a specific plan for improvement to correct errors and deficiencies.

[0456] "History of modification work" refers to a record of modifications made by the user in the past, making it possible to track changes in the information.

[0457] "Assessing the impact" means analyzing and judging the effects that corrective actions will have on the information and the entire system.

[0458] "Risk assessment" involves analyzing potential problems associated with information processing and developing plans to mitigate those risks.

[0459] An "improvement plan" refers to specific steps and methods proposed to reduce risks and improve the quality of information processing.

[0460] A "predictive model" refers to a mathematical or statistical method used to predict future outcomes based on past information.

[0461] "Verification of consistency and coherence" is the process of confirming whether information is presented in a consistent and unified manner without contradictions.

[0462] This invention is a technology that uses an information processing system to efficiently detect errors and deficiencies in documents and generate correction suggestions. Specific embodiments for carrying out the invention are described below.

[0463] The user prepares the documents to be analyzed using a terminal and uploads them to the server. The documents must be in a commonly used electronic document format such as PDF or DOCX. Once the upload is complete, the server immediately processes the received information.

[0464] The server uses a natural language processing system to analyze documents. This system utilizes, for example, a generative AI model, specifically OpenAI models or equivalent technologies. The system generates prompt sentences to identify grammatical errors and inconsistencies within the document, instructing the model to perform the analysis.

[0465] For example, a prompt might be text like, "Detect grammatical errors in this document and suggest corrections." The server inputs this prompt into the AI ​​model and receives the model's output.

[0466] Based on these results, the server generates specific correction suggestions. These suggestions are presented in a user-friendly format and are notified to the user in real time via their device. These notifications could be delivered through various methods, such as web applications or email.

[0467] Furthermore, the server has a function to record historical information in a database. This history is used for future improvements and risk assessments, and is an important element for ensuring the security of the information while maintaining its integrity.

[0468] In this way, the invention provides users with an efficient and accurate document management method, and makes it possible to improve the quality and reliability of information.

[0469] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0470] Step 1:

[0471] Users prepare documents requiring analysis using their terminals and upload them to the server. Input documents are digital documents in PDF or DOCX format. Users select the target documents using the terminal's file selection function and send them to the server via a dedicated web interface or application. This securely uploads the documents to the server, allowing the process to proceed to the next analysis step.

[0472] Step 2:

[0473] The server first preprocesses the received document data. The files received as input are converted into text data. The server uses text extraction libraries such as Apache Tika and textract to extract readable text from PDF and DOCX files and prepare the data in a structure that allows for analysis. The converted text data is generated and proceeds to the next analysis step.

[0474] Step 3:

[0475] The server analyzes the document using a natural language processing system. The input for this step is the text data converted in the previous step. The server uses a generative AI model to detect grammatical errors, inconsistencies, and deficiencies in this text. For this analysis, the server generates prompt sentences such as "Detect grammatical errors in this document and suggest corrections" and inputs them into the AI ​​model. The AI ​​model outputs analysis results, which include the identified errors and their explanations.

[0476] Step 4:

[0477] The server generates correction suggestions based on the output results from the AI ​​model. The input is the analysis results. The server formats the suggestions in a user-friendly format and creates written correction suggestions and proposals to be presented. The correction suggestions generated at this stage include, as concrete actions, the locations of the identified errors and specific methods for correcting them.

[0478] Step 5:

[0479] The server notifies the user's terminal of the generated correction suggestions. The input is a formatted correction suggestion. The server uses real-time notification technology to send the correction suggestions to the user's terminal. This output displays the suggested content on the terminal's user interface, allowing the user to review the content and point out any issues.

[0480] Step 6:

[0481] The server records user correction results and feedback, and saves all correction work as historical information in the database. As input, the user's correction information is sent to the server. The server then analyzes this historical information and records it for use in future analyses. Based on this historical data, it becomes possible to perform future risk assessments. This promotes improvements in information security and quality.

[0482] (Application Example 1)

[0483] Next, we will explain Application Example 1. In the following explanation, 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."

[0484] In modern times, deficiencies and errors in contracts and transaction documents can lead to legal troubles and a decline in trust. Contracts and terms of service, in particular, are crucial for electronic payment services, and because errors are difficult to detect, they carry the risk of damaging the trust of business partners. Therefore, there is a need for a system that can detect potential errors and deficiencies in contracts and terms of service in real time and promptly propose corrections.

[0485] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0486] In this invention, the server includes means for analyzing a specified document and detecting errors and deficiencies within the document using a natural language processing model; means for generating correction suggestions based on the detected errors and deficiencies; and means for detecting errors in contracts and terms of service in real time and providing correction suggestions. This makes it possible to identify errors contained in documents in a timely manner and enable safe and reliable transactions through the rapid provision of correction suggestions.

[0487] A "specified document" refers to a document or text file that a user uploads for a specific purpose.

[0488] "Analysis" is the process of breaking down the information contained in a document and understanding its structure and content in detail.

[0489] A "natural language processing model" is an algorithm or machine learning model that enables computers to understand and generate natural language used by humans.

[0490] "Errors and deficiencies" refer to grammatical errors or substantive flaws present in a document.

[0491] A "proposal for correction" is a suggestion for improvement or correction to an error or deficiency that has been detected.

[0492] "Means of notifying the user" refers to communication or display means by which the system presents detection results or correction suggestions to the user.

[0493] "Means for recording and evaluating change history" refers to a system that tracks changes made to a document and analyzes the results and impacts of those changes.

[0494] "A means of conducting a risk assessment and proposing an action plan" refers to a method of analyzing the potential risks that may arise from revising a document and presenting specific action plans to mitigate them.

[0495] "A means of detecting errors in contracts and terms of service in real time and proposing corrections" refers to a mechanism that immediately recognizes errors in contract-related documents and immediately provides proposed corrections.

[0496] In this invention, three entities—a server, a terminal, and a user—play crucial roles in implementing a system for analyzing a specified document, detecting errors and deficiencies, and suggesting corrections. The following describes specific embodiments of this system.

[0497] The server analyzes uploaded documents using natural language processing models. The server detects grammatical errors and content deficiencies using AI algorithms and generates specific correction suggestions based on these findings. The natural language processing models used are widely known generative AI models such as GPT and BERT. The server also has the ability to predict error patterns by learning from past data, thereby improving the accuracy of document analysis.

[0498] The terminal provides an interface for users to upload contracts and terms of service. Analysis results and suggested revisions are notified to the user through the terminal. The terminal's software, as the user interface, is either a web application or a native application that provides real-time feedback.

[0499] Users upload documents from their devices and receive feedback from the server. Based on this feedback, users can revise their documents, enabling them to proceed with reliable contracts and transactions.

[0500] As a concrete example, suppose a company is launching a new electronic payment service and has created terms of service. When these terms of service are uploaded to the system from a terminal, the server immediately analyzes the document and identifies errors by comparing it with past cases. For example, it might point out the ambiguity of the term "penalties" in the document and suggest a revision such as, "This agreement is serious, and legal proceedings will be applied in case of violation. Specifically, (enter specific details)."

[0501] An example of a prompt message is as follows:

[0502] "Please analyze the following document, identify any errors, and propose corrections: Document Content"

[0503] This configuration allows the system to quickly detect errors in contracts and terms of service and provide users with useful correction suggestions. This helps prevent business problems and improves reliability.

[0504] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0505] Step 1:

[0506] Users use a terminal to specify the documents they wish to analyze, such as contracts and terms of service, and upload them to the system. The input is a document file, and the output is digital data sent to the server. This process involves file selection and uploading through a user interface.

[0507] Step 2:

[0508] The server receives the uploaded document and analyzes its content using a natural language processing model. The input is the document data received from the user, and the output is a list of errors and deficiencies in the document. In this step, a generative AI model analyzes the document text and processes the data to detect grammatical errors and content deficiencies.

[0509] Step 3:

[0510] The server generates correction suggestions based on the errors detected. The input is a list of errors and deficiencies in the document, and the output is feedback data containing correction suggestions. At this stage, a database of past cases is referenced, and specific improvement plans are created based on similar cases.

[0511] Step 4:

[0512] The generated correction suggestions are notified from the server to the user's terminal. The input is the correction suggestion data, and the output is a notification message on the terminal. In this process, the suggested content is displayed on the user's interface through the user notification function.

[0513] Step 5:

[0514] The user reviews the feedback presented from the terminal and revises the document as needed. The input is the suggested feedback received from the server, and the output is the revised document data. At this stage, the user makes the necessary edits based on the suggestions to improve the quality of the document.

[0515] Step 6:

[0516] The server records the change history and assesses the impact and risks of each modification. The input is user modification history data, and the output is a risk assessment and necessary action plan. In this final processing stage, long-term document compliance is checked based on the stored historical data, and necessary countermeasures are developed.

[0517] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0518] This invention is a system that not only analyzes documents and detects errors, but also recognizes user emotions and dynamically adjusts the interface. The system consists of three entities: a server, a terminal, and a user, in addition to incorporating an emotion engine.

[0519] Users upload design documents and pricing specifications to the server using their devices. Upon receiving the documents, the server begins analysis using a natural language processing model to identify grammatical errors and inconsistencies.

[0520] Based on the analysis results, the server generates suggested revisions. This is where the emotion engine comes into play. The server understands the user's emotional state and adjusts the wording and expression of the suggested revisions accordingly. For example, if the user is feeling frustrated, the server will tailor the suggestions to use more approachable language.

[0521] Furthermore, user sentiment data can be used to improve the system. The server accumulates user feedback and sentiment states and uses them to improve the long-term user experience. In this process, data is collected on improvements in the accuracy of suggestions and the adaptability of the interface.

[0522] As a concrete example, suppose a user uploads the pricing specifications for a new service plan when it is announced. The server immediately analyzes the document and detects potential errors. If the user feels uneasy or suspicious while interacting with the system, the emotion engine recognizes this state and provides appropriate feedback. This allows the user to review and correct the document with confidence, improving the overall efficiency of the verification process.

[0523] The following describes the processing flow.

[0524] Step 1:

[0525] The user uses a terminal to upload document files such as design specifications and pricing specifications to the server. The server receives these files and completes the preparation for analysis.

[0526] Step 2:

[0527] The server begins analyzing the received document by running it through a natural language processing model. The analysis identifies grammatical errors, inconsistencies, and deficiencies in the document.

[0528] Step 3:

[0529] While the analysis is in progress, the server activates the emotion engine and monitors the user's emotions through an interface on the user's device. It collects emotion data from voice and text.

[0530] Step 4:

[0531] The server generates correction suggestions for errors detected based on the analysis results. In doing so, it adjusts the way the suggestions are expressed, taking into account the user's emotional state as recognized by the emotion engine.

[0532] Step 5:

[0533] If the server determines that the user's emotions are negative, it will change the suggested fix to polite and friendly language to reduce the burden on the user.

[0534] Step 6:

[0535] The generated revision suggestions are notified to the user's device and presented to the user. The user then revises the document based on this feedback.

[0536] Step 7:

[0537] After the user modifies the document, they can upload it to the server again if necessary to perform another analysis process to verify the validity of the modifications.

[0538] Step 8:

[0539] The server records user sentiment data along with the change history of all documents. This data will be used to improve the system in the future and enhance the user experience.

[0540] (Example 2)

[0541] Next, we will describe Example 2. 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."

[0542] In today's world, there is a demand for the ability to efficiently detect errors and deficiencies in specified information. However, conventional technologies lacked the ability to provide feedback that considered user emotions, posing challenges to improving the user experience. Furthermore, they were unable to effectively handle users' emotional reactions to error detection results, limiting the system's adaptability. As a result, error correction suggestions did not adapt to the user's emotional state, leading to problems such as decreased efficiency and satisfaction with the correction process.

[0543] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0544] In this invention, the server includes means for analyzing specified information and detecting errors and deficiencies in the information using a machine learning model; means for analyzing the user's emotional state and adjusting the expression of correction suggestions according to the emotion; and means for accumulating emotion data and building a model to improve the system's adaptability. This makes it possible to accurately detect errors in information, make suggestions that align with the user's emotions, improve the user experience, and perform correction work efficiently.

[0545] "Specified information" refers to documents and data, such as design documents and specifications, provided by the user for analysis.

[0546] A "machine learning model" is an artificial intelligence technique used to detect errors and inconsistencies in information, and includes algorithms specifically designed for natural language processing.

[0547] "Errors and deficiencies" refer to grammatical errors, logical inconsistencies, inconsistencies, or inappropriate expressions present in the specified information.

[0548] "User emotional state" refers to the user's psychological reaction and mood to the analysis results and suggested modifications of the specified information.

[0549] "Adjusting the wording of correction suggestions" refers to optimizing the tone and wording of feedback regarding the correction of errors and deficiencies, depending on the user's emotional state.

[0550] "Emotional data" refers to data collected about a user's emotional state, which will be used for future system improvements and enhancements to the user experience.

[0551] A "model for improving adaptability" refers to an algorithm or mechanism that learns from user emotional data and feedback to continuously improve the overall functionality and services of the system.

[0552] Embodiments for carrying out this invention are described below.

[0553] This system consists of three components: a server, a terminal, and a user. The server receives the information to be analyzed and uses machine learning models to detect errors and defects. Specifically, natural language processing models such as BERT and GPT are used. Because these models operate on a cloud-based system, high-speed and efficient processing is possible.

[0554] Users upload documents via a terminal. The terminal is equipped with a graphical user interface (GUI) for selecting and uploading information. Users can provide specified information to the system with simple operations.

[0555] After performing the analysis, the server notifies the user's terminal of the suggested corrections. At this time, the server uses an emotion engine to analyze the user's emotional state and provides adjusted feedback accordingly. The emotion engine predicts emotional responses based on the user's input data and interface operation history, and modifies the wording of the corrections accordingly.

[0556] As a concrete example, suppose a user uploads a pricing specification for a new service to the system. The server immediately analyzes the specification and detects potential grammatical errors and inconsistencies. If the user is experiencing stress, the emotion engine detects this and provides user-friendly feedback such as, "Making corrections based on our suggestions will make the process smoother."

[0557] Examples of prompt statements to input into the generative AI model are as follows:

[0558] "Analyze the following document and identify grammatical errors and inconsistencies. Also, create appropriate revision suggestions based on the emotions the user is feeling."

[0559] In this way, the system can not only improve the accuracy of information but also provide feedback that takes user emotions into consideration, thereby improving the overall quality of the user experience.

[0560] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0561] Step 1:

[0562] The user selects a document file via the terminal and sends it to the server using the upload function. As input, the user specifies a document file and sends it to the server via the GUI. As output, the document file is received by the server.

[0563] Step 2:

[0564] The server inputs the received document files into a machine learning model and performs data processing to analyze grammatical errors and inconsistencies within the documents. Specifically, it uses BERT or GPT models to analyze the text data. The output is a list of grammatical errors and inconsistencies.

[0565] Step 3:

[0566] The server generates correction suggestions based on the analysis results. The input is the list of grammatical errors and deficiencies obtained in step 2. The server uses this data to perform calculations to create specific correction proposals. The output is a list of correction suggestions.

[0567] Step 4:

[0568] The server operates an emotion engine to understand the user's emotional state. The input consists of the user's operation history and device response data. The server analyzes this data to predict the user's current emotional state. The output is the user's emotional state.

[0569] Step 5:

[0570] The server adjusts the wording of the suggested revisions based on the user's emotional state. The inputs are the suggested revisions from step 3 and the emotional state from step 4. Based on this, the server modifies the suggested revisions to suit the user's needs. The output is the revised suggested revisions.

[0571] Step 6:

[0572] The server notifies the terminal of the adjusted correction proposal and allows the user to confirm it. The input is the adjusted correction proposal formed in step 5. The server sends this to the user terminal and displays it to the user through the terminal's GUI. As output, the user receives and can confirm the correction proposal.

[0573] (Application Example 2)

[0574] Next, we will explain application example 2. In the following explanation, 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."

[0575] Modern information processing systems are required not only to point out errors and deficiencies in documents, but also to provide interfaces that understand and respond appropriately to user emotions. However, conventional systems have difficulty making dynamic adjustments based on user emotions, limiting the improvement of the user experience. Furthermore, there has been a lack of effective means to alleviate anxiety and doubt in situations such as payment procedures.

[0576] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0577] In this invention, the server includes means for analyzing specified information and detecting errors and deficiencies in the text using natural language processing technology; means for recognizing the user's emotional state and dynamically adjusting and notifying the content and expression of correction suggestions according to the emotion; and means for accumulating user emotion data and collecting and processing data useful for improving the experience. This makes it possible to detect errors in documents while providing an appropriate interface according to the user's emotions, thereby reducing user anxiety and doubt in payment procedures and other situations.

[0578] "Specified information" refers to the information that the system will analyze, and typically includes documents and data provided by the user.

[0579] "Natural language processing technology" refers to the technology that enables computers to understand and generate human language, and involves multiple processes including grammatical analysis and semantic analysis.

[0580] "Errors and deficiencies" refer to grammatical errors, inconsistencies in content, and inaccurate expressions contained in a document.

[0581] "User emotional state" refers to the user's psychological state and emotional condition, and typically includes emotions such as joy, anxiety, and frustration.

[0582] "Dynamic adjustment" means that the system changes the suggested content and interface display in real time according to the user's emotions and situation.

[0583] A "revision suggestion" refers to a specific proposal for improving a document based on any errors or deficiencies that have been detected.

[0584] "Improving the user experience" means enhancing the satisfaction and convenience that users experience when using a system.

[0585] To realize this invention, a server plays a central role. First, the server analyzes the specified information received from the user terminal. Specifically, it employs natural language processing technology for text analysis to detect errors and deficiencies in the information. Advanced natural language processing software, such as the Google Cloud Natural Language API, is utilized in this process.

[0586] Next, the server uses the Emotion API to analyze the user's emotional state. Based on this information, the server dynamically generates modification suggestions tailored to the user's current emotions and notifies the user through their device. These suggestions may include friendly language to alleviate frustration or information to stimulate purchasing intent.

[0587] Furthermore, user sentiment data and feedback are stored on the server and used to improve the long-term experience. Based on this data, the server analyzes the user experience and provides information that contributes to system improvements.

[0588] As a concrete example, let's assume a user is purchasing a product online. While the user is considering the purchase, the server analyzes the user's emotions in real time and dynamically provides information to assist in the purchase decision. For example, if the user is feeling anxious about the purchase, a suggestion such as "This product has very high ratings and offers great value for money" might be displayed.

[0589] Regarding the use of a generative AI model, one possible prompt message could be: "I'm considering making a payment, but I have some concerns. Please provide suggestions on how to make a purchase with confidence." Through this prompt, the system can provide the user with the most appropriate suggestions and information.

[0590] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0591] Step 1:

[0592] The server receives the specified information from the user's terminal. The input is text data sent by the user, which is passed to the server for analysis. The output indicates the completion of the process in which this data is prepared for analysis.

[0593] Step 2:

[0594] The server analyzes the information using natural language processing techniques. The input is the text data received in step 1. The server uses the Google Cloud Natural Language API to check for grammatical errors and content consistency. The output is processed as an analysis result, with errors and deficiencies identified.

[0595] Step 3:

[0596] The server uses the Emotion API to analyze the user's emotional state. Inputs include user interactions and pre-collected emotion-related data. At this stage, the server quantifies the user's emotional state, identifying frustration, anxiety, and other emotional states. The output is a report on the user's emotional state.

[0597] Step 4:

[0598] The server generates suggested modifications based on the analysis results and emotional state. The input is the output from steps 2 and 3. The server uses this information to generate suggestions tailored to the user's emotions. Dynamic feedback is created, including friendly language and specific purchase assistance information. The output is the suggested modifications, which are then notified to the user.

[0599] Step 5:

[0600] The terminal receives correction suggestions from the server and presents them to the user. The input is the correction suggestion generated in step 4. The terminal displays this suggestion on the user's screen and prompts the user for confirmation and further action. The output is the completion of displaying the suggestion to the user.

[0601] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0602] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0603] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0604] [Fourth Embodiment]

[0605] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0606] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0607] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0608] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0609] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0610] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0611] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0612] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0613] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0614] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0615] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0616] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0617] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0618] This invention is a system that receives a specified document, automatically detects errors and deficiencies within it, and suggests appropriate corrections. This system consists of three components: a server, a terminal, and a user.

[0619] First, the user uploads necessary documents, such as design specifications and pricing documents, to the server using their device. The server analyzes the uploaded documents using a natural language processing model to detect errors such as grammatical mistakes, inconsistencies, and violations of regulations.

[0620] When an error is detected, the server generates specific correction suggestions based on it. These suggestions include points to maintain the overall consistency of the document and improvement proposals based on similar past cases. The generated suggestions are notified to the user's terminal as feedback.

[0621] Furthermore, the server tracks the impact and progress of user-initiated changes by recording all change history in a database. Based on this historical information, the server assesses the risks that the changes pose to the overall service and proposes an action plan as needed.

[0622] In actual operation, for example, when a pricing specification document for a new service is created, the user uploads it from their terminal to the server. The server immediately begins analysis, comparing it with past data to identify potential errors. As a result, the server sends specific feedback to the user, who can then revise and verify the document based on the suggestions. By repeating this process, the quality of the document improves and the reliability of the service is ensured.

[0623] The following describes the processing flow.

[0624] Step 1:

[0625] The user uses their terminal to upload document files, such as design specifications and pricing documents, to the server. Once the upload is complete, the server receives the files and prepares them for analysis.

[0626] Step 2:

[0627] The server passes the received document through a natural language processing model. The model analyzes the document sentence by sentence and initiates an analysis process to identify grammatical errors and inconsistencies.

[0628] Step 3:

[0629] The server applies machine learning algorithms and compares the results with similar historical data to detect potential error patterns. In this process, discrepancies in pricing and inappropriate descriptions are particularly highlighted.

[0630] Step 4:

[0631] If an error is detected, the server will generate specific correction suggestions based on it. These suggestions will include a description of the error and proposed corrections, or comparison information with relevant documents.

[0632] Step 5:

[0633] When revision suggestions are generated, the server notifies the user's terminal. The suggestions presented as feedback serve as a guide for the user when revising the document.

[0634] Step 6:

[0635] The user modifies the document based on feedback from the server. If necessary, it is uploaded back to the server and subjected to another analysis process to verify the validity of the modifications.

[0636] Step 7:

[0637] The server records the history of all document changes and performs an impact analysis on newly modified documents. If the impact is deemed significant, it presents the user with a risk assessment report and action plan.

[0638] Step 8:

[0639] The process is repeated until changes are finalized, ultimately resulting in a document with guaranteed accuracy. Through this process, document quality improves, and customer service reliability increases.

[0640] (Example 1)

[0641] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0642] In information processing, efficiently detecting errors and deficiencies in documents and information, and proposing appropriate corrections based on these findings, is challenging. Especially in today's society, where vast amounts of information are constantly being generated, maintaining information consistency quickly and accurately is a crucial issue. Furthermore, there is a need for methods to effectively utilize past revision history, assess risks, and prevent future errors.

[0643] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0644] In this invention, the server includes means for receiving information from a user, means for analyzing the received information using a natural language processing system to detect errors and deficiencies, and means for generating correction suggestions based on the detected errors and deficiencies. This enables users to quickly and accurately correct errors in documents and maintain the integrity of the information. Furthermore, by utilizing a model that learns from past information and predicts error patterns, it is possible to mitigate future risks.

[0645] A "user" is an entity that uses an information processing system to input information and to verify its output.

[0646] "Information" refers to documents and data that users input into the system, and is the subject of analysis.

[0647] A "natural language processing system" refers to the technology or program used by computers to understand, analyze, and generate human language.

[0648] "Analysis" is the process of identifying the content contained in received information and extracting information according to the purpose.

[0649] "Errors and deficiencies" refer to grammatical errors, factual inconsistencies, and deviations from established rules present in the information.

[0650] A "proposal for correction" refers to a specific plan for improvement to correct errors and deficiencies.

[0651] "History of modification work" refers to a record of modifications made by the user in the past, making it possible to track changes in the information.

[0652] "Assessing the impact" means analyzing and judging the effects that corrective actions will have on the information and the entire system.

[0653] "Risk assessment" involves analyzing potential problems associated with information processing and developing plans to mitigate those risks.

[0654] An "improvement plan" refers to specific steps and methods proposed to reduce risks and improve the quality of information processing.

[0655] A "predictive model" refers to a mathematical or statistical method used to predict future outcomes based on past information.

[0656] "Verification of consistency and coherence" is the process of confirming whether information is presented in a consistent and unified manner without contradictions.

[0657] This invention is a technology that uses an information processing system to efficiently detect errors and deficiencies in documents and generate correction suggestions. Specific embodiments for carrying out the invention are described below.

[0658] The user prepares the documents to be analyzed using a terminal and uploads them to the server. The documents must be in a commonly used electronic document format such as PDF or DOCX. Once the upload is complete, the server immediately processes the received information.

[0659] The server uses a natural language processing system to analyze documents. This system utilizes, for example, a generative AI model, specifically OpenAI models or equivalent technologies. The system generates prompt sentences to identify grammatical errors and inconsistencies within the document, instructing the model to perform the analysis.

[0660] For example, a prompt might be text like, "Detect grammatical errors in this document and suggest corrections." The server inputs this prompt into the AI ​​model and receives the model's output.

[0661] Based on these results, the server generates specific correction suggestions. These suggestions are presented in a user-friendly format and are notified to the user in real time via their device. These notifications could be delivered through various methods, such as web applications or email.

[0662] Furthermore, the server has a function to record historical information in a database. This history is used for future improvements and risk assessments, and is an important element for ensuring the security of the information while maintaining its integrity.

[0663] In this way, the invention provides users with an efficient and accurate document management method, and makes it possible to improve the quality and reliability of information.

[0664] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0665] Step 1:

[0666] Users prepare documents requiring analysis using their terminals and upload them to the server. Input documents are digital documents in PDF or DOCX format. Users select the target documents using the terminal's file selection function and send them to the server via a dedicated web interface or application. This securely uploads the documents to the server, allowing the process to proceed to the next analysis step.

[0667] Step 2:

[0668] The server first preprocesses the received document data. The files received as input are converted into text data. The server uses text extraction libraries such as Apache Tika and textract to extract readable text from PDF and DOCX files and prepare the data in a structure that allows for analysis. The converted text data is generated and proceeds to the next analysis step.

[0669] Step 3:

[0670] The server analyzes the document using a natural language processing system. The input for this step is the text data converted in the previous step. The server uses a generative AI model to detect grammatical errors, inconsistencies, and deficiencies in this text. For this analysis, the server generates prompt sentences such as "Detect grammatical errors in this document and suggest corrections" and inputs them into the AI ​​model. The AI ​​model outputs analysis results, which include the identified errors and their explanations.

[0671] Step 4:

[0672] The server generates correction suggestions based on the output results from the AI ​​model. The input is the analysis results. The server formats the suggestions in a user-friendly format and creates written correction suggestions and proposals to be presented. The correction suggestions generated at this stage include, as concrete actions, the locations of the identified errors and specific methods for correcting them.

[0673] Step 5:

[0674] The server notifies the user's terminal of the generated correction suggestions. The input is a formatted correction suggestion. The server uses real-time notification technology to send the correction suggestions to the user's terminal. This output displays the suggested content on the terminal's user interface, allowing the user to review the content and point out any issues.

[0675] Step 6:

[0676] The server records user correction results and feedback, and saves all correction work as historical information in the database. As input, the user's correction information is sent to the server. The server then analyzes this historical information and records it for use in future analyses. Based on this historical data, it becomes possible to perform future risk assessments. This promotes improvements in information security and quality.

[0677] (Application Example 1)

[0678] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0679] In modern times, deficiencies and errors in contracts and transaction documents can lead to legal troubles and a decline in trust. Contracts and terms of service, in particular, are crucial for electronic payment services, and because errors are difficult to detect, they carry the risk of damaging the trust of business partners. Therefore, there is a need for a system that can detect potential errors and deficiencies in contracts and terms of service in real time and promptly propose corrections.

[0680] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0681] In this invention, the server includes means for analyzing a specified document and detecting errors and deficiencies within the document using a natural language processing model; means for generating correction suggestions based on the detected errors and deficiencies; and means for detecting errors in contracts and terms of service in real time and providing correction suggestions. This makes it possible to identify errors contained in documents in a timely manner and enable safe and reliable transactions through the rapid provision of correction suggestions.

[0682] A "specified document" refers to a document or text file that a user uploads for a specific purpose.

[0683] "Analysis" is the process of breaking down the information contained in a document and understanding its structure and content in detail.

[0684] A "natural language processing model" is an algorithm or machine learning model that enables computers to understand and generate natural language used by humans.

[0685] "Errors and deficiencies" refer to grammatical errors or substantive flaws present in a document.

[0686] A "proposal for correction" is a suggestion for improvement or correction to an error or deficiency that has been detected.

[0687] "Means of notifying the user" refers to communication or display means by which the system presents detection results or correction suggestions to the user.

[0688] "Means for recording and evaluating change history" refers to a system that tracks changes made to a document and analyzes the results and impacts of those changes.

[0689] "A means of conducting a risk assessment and proposing an action plan" refers to a method of analyzing the potential risks that may arise from revising a document and presenting specific action plans to mitigate them.

[0690] "A means of detecting errors in contracts and terms of service in real time and proposing corrections" refers to a mechanism that immediately recognizes errors in contract-related documents and immediately provides proposed corrections.

[0691] In this invention, three entities—a server, a terminal, and a user—play crucial roles in implementing a system for analyzing a specified document, detecting errors and deficiencies, and suggesting corrections. The following describes specific embodiments of this system.

[0692] The server analyzes uploaded documents using natural language processing models. The server detects grammatical errors and content deficiencies using AI algorithms and generates specific correction suggestions based on these findings. The natural language processing models used are widely known generative AI models such as GPT and BERT. The server also has the ability to predict error patterns by learning from past data, thereby improving the accuracy of document analysis.

[0693] The terminal provides an interface for users to upload contracts and terms of service. Analysis results and suggested revisions are notified to the user through the terminal. The terminal's software, as the user interface, is either a web application or a native application that provides real-time feedback.

[0694] Users upload documents from their devices and receive feedback from the server. Based on this feedback, users can revise their documents, enabling them to proceed with reliable contracts and transactions.

[0695] As a concrete example, suppose a company is launching a new electronic payment service and has created terms of service. When these terms of service are uploaded to the system from a terminal, the server immediately analyzes the document and identifies errors by comparing it with past cases. For example, it might point out the ambiguity of the term "penalties" in the document and suggest a revision such as, "This agreement is serious, and legal proceedings will be applied in case of violation. Specifically, (enter specific details)."

[0696] An example of a prompt message is as follows:

[0697] "Please analyze the following document, identify any errors, and propose corrections: Document Content"

[0698] This configuration allows the system to quickly detect errors in contracts and terms of service and provide users with useful correction suggestions. This helps prevent business problems and improves reliability.

[0699] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0700] Step 1:

[0701] Users use a terminal to specify the documents they wish to analyze, such as contracts and terms of service, and upload them to the system. The input is a document file, and the output is digital data sent to the server. This process involves file selection and uploading through a user interface.

[0702] Step 2:

[0703] The server receives the uploaded document and analyzes its content using a natural language processing model. The input is the document data received from the user, and the output is a list of errors and deficiencies in the document. In this step, a generative AI model analyzes the document text and processes the data to detect grammatical errors and content deficiencies.

[0704] Step 3:

[0705] The server generates correction suggestions based on the errors detected. The input is a list of errors and deficiencies in the document, and the output is feedback data containing correction suggestions. At this stage, a database of past cases is referenced, and specific improvement plans are created based on similar cases.

[0706] Step 4:

[0707] The generated correction suggestions are notified from the server to the user's terminal. The input is the correction suggestion data, and the output is a notification message on the terminal. In this process, the suggested content is displayed on the user's interface through the user notification function.

[0708] Step 5:

[0709] The user reviews the feedback presented from the terminal and revises the document as needed. The input is the suggested feedback received from the server, and the output is the revised document data. At this stage, the user makes the necessary edits based on the suggestions to improve the quality of the document.

[0710] Step 6:

[0711] The server records the change history and assesses the impact and risks of each modification. The input is user modification history data, and the output is a risk assessment and necessary action plan. In this final processing stage, long-term document compliance is checked based on the stored historical data, and necessary countermeasures are developed.

[0712] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0713] This invention is a system that not only analyzes documents and detects errors, but also recognizes user emotions and dynamically adjusts the interface. The system consists of three entities: a server, a terminal, and a user, in addition to incorporating an emotion engine.

[0714] Users upload design documents and pricing specifications to the server using their devices. Upon receiving the documents, the server begins analysis using a natural language processing model to identify grammatical errors and inconsistencies.

[0715] Based on the analysis results, the server generates suggested revisions. This is where the emotion engine comes into play. The server understands the user's emotional state and adjusts the wording and expression of the suggested revisions accordingly. For example, if the user is feeling frustrated, the server will tailor the suggestions to use more approachable language.

[0716] Furthermore, user sentiment data can be used to improve the system. The server accumulates user feedback and sentiment states and uses them to improve the long-term user experience. In this process, data is collected on improvements in the accuracy of suggestions and the adaptability of the interface.

[0717] As a concrete example, suppose a user uploads the pricing specifications for a new service plan when it is announced. The server immediately analyzes the document and detects potential errors. If the user feels uneasy or suspicious while interacting with the system, the emotion engine recognizes this state and provides appropriate feedback. This allows the user to review and correct the document with confidence, improving the overall efficiency of the verification process.

[0718] The following describes the processing flow.

[0719] Step 1:

[0720] The user uses a terminal to upload document files such as design specifications and pricing specifications to the server. The server receives these files and completes the preparation for analysis.

[0721] Step 2:

[0722] The server begins analyzing the received document by running it through a natural language processing model. The analysis identifies grammatical errors, inconsistencies, and deficiencies in the document.

[0723] Step 3:

[0724] While the analysis is in progress, the server activates the emotion engine and monitors the user's emotions through an interface on the user's device. It collects emotion data from voice and text.

[0725] Step 4:

[0726] The server generates correction suggestions for errors detected based on the analysis results. In doing so, it adjusts the way the suggestions are expressed, taking into account the user's emotional state as recognized by the emotion engine.

[0727] Step 5:

[0728] If the server determines that the user's emotions are negative, it will change the suggested fix to polite and friendly language to reduce the burden on the user.

[0729] Step 6:

[0730] The generated revision suggestions are notified to the user's device and presented to the user. The user then revises the document based on this feedback.

[0731] Step 7:

[0732] After the user modifies the document, they can upload it to the server again if necessary to perform another analysis process to verify the validity of the modifications.

[0733] Step 8:

[0734] The server records user sentiment data along with the change history of all documents. This data will be used to improve the system in the future and enhance the user experience.

[0735] (Example 2)

[0736] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0737] In today's world, there is a demand for the ability to efficiently detect errors and deficiencies in specified information. However, conventional technologies lacked the ability to provide feedback that considered user emotions, posing challenges to improving the user experience. Furthermore, they were unable to effectively handle users' emotional reactions to error detection results, limiting the system's adaptability. As a result, error correction suggestions did not adapt to the user's emotional state, leading to problems such as decreased efficiency and satisfaction with the correction process.

[0738] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0739] In this invention, the server includes means for analyzing specified information and detecting errors and deficiencies in the information using a machine learning model; means for analyzing the user's emotional state and adjusting the expression of correction suggestions according to the emotion; and means for accumulating emotion data and building a model to improve the system's adaptability. This makes it possible to accurately detect errors in information, make suggestions that align with the user's emotions, improve the user experience, and perform correction work efficiently.

[0740] "Specified information" refers to documents and data, such as design documents and specifications, provided by the user for analysis.

[0741] A "machine learning model" is an artificial intelligence technique used to detect errors and inconsistencies in information, and includes algorithms specifically designed for natural language processing.

[0742] "Errors and deficiencies" refer to grammatical errors, logical inconsistencies, inconsistencies, or inappropriate expressions present in the specified information.

[0743] "User emotional state" refers to the user's psychological reaction and mood to the analysis results and suggested modifications of the specified information.

[0744] "Adjusting the wording of correction suggestions" refers to optimizing the tone and wording of feedback regarding the correction of errors and deficiencies, depending on the user's emotional state.

[0745] "Emotional data" refers to data collected about a user's emotional state, which will be used for future system improvements and enhancements to the user experience.

[0746] A "model for improving adaptability" refers to an algorithm or mechanism that learns from user emotional data and feedback to continuously improve the overall functionality and services of the system.

[0747] Embodiments for carrying out this invention are described below.

[0748] This system consists of three components: a server, a terminal, and a user. The server receives the information to be analyzed and uses machine learning models to detect errors and defects. Specifically, natural language processing models such as BERT and GPT are used. Because these models operate on a cloud-based system, high-speed and efficient processing is possible.

[0749] Users upload documents via a terminal. The terminal is equipped with a graphical user interface (GUI) for selecting and uploading information. Users can provide specified information to the system with simple operations.

[0750] After performing the analysis, the server notifies the user's terminal of the suggested corrections. At this time, the server uses an emotion engine to analyze the user's emotional state and provides adjusted feedback accordingly. The emotion engine predicts emotional responses based on the user's input data and interface operation history, and modifies the wording of the corrections accordingly.

[0751] As a concrete example, suppose a user uploads a pricing specification for a new service to the system. The server immediately analyzes the specification and detects potential grammatical errors and inconsistencies. If the user is experiencing stress, the emotion engine detects this and provides user-friendly feedback such as, "Making corrections based on our suggestions will make the process smoother."

[0752] Examples of prompt statements to input into the generative AI model are as follows:

[0753] "Analyze the following document and identify grammatical errors and inconsistencies. Also, create appropriate revision suggestions based on the emotions the user is feeling."

[0754] In this way, the system can not only improve the accuracy of information but also provide feedback that takes user emotions into consideration, thereby improving the overall quality of the user experience.

[0755] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0756] Step 1:

[0757] The user selects a document file via the terminal and sends it to the server using the upload function. As input, the user specifies a document file and sends it to the server via the GUI. As output, the document file is received by the server.

[0758] Step 2:

[0759] The server inputs the received document files into a machine learning model and performs data processing to analyze grammatical errors and inconsistencies within the documents. Specifically, it uses BERT or GPT models to analyze the text data. The output is a list of grammatical errors and inconsistencies.

[0760] Step 3:

[0761] The server generates correction suggestions based on the analysis results. The input is the list of grammatical errors and deficiencies obtained in step 2. The server uses this data to perform calculations to create specific correction proposals. The output is a list of correction suggestions.

[0762] Step 4:

[0763] The server operates an emotion engine to understand the user's emotional state. The input consists of the user's operation history and device response data. The server analyzes this data to predict the user's current emotional state. The output is the user's emotional state.

[0764] Step 5:

[0765] The server adjusts the wording of the suggested revisions based on the user's emotional state. The inputs are the suggested revisions from step 3 and the emotional state from step 4. Based on this, the server modifies the suggested revisions to suit the user's needs. The output is the revised suggested revisions.

[0766] Step 6:

[0767] The server notifies the terminal of the adjusted correction proposal and allows the user to confirm it. The input is the adjusted correction proposal formed in step 5. The server sends this to the user terminal and displays it to the user through the terminal's GUI. As output, the user receives and can confirm the correction proposal.

[0768] (Application Example 2)

[0769] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0770] Modern information processing systems are required not only to point out errors and deficiencies in documents, but also to provide interfaces that understand and respond appropriately to user emotions. However, conventional systems have difficulty making dynamic adjustments based on user emotions, limiting the improvement of the user experience. Furthermore, there has been a lack of effective means to alleviate anxiety and doubt in situations such as payment procedures.

[0771] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0772] In this invention, the server includes means for analyzing specified information and detecting errors and deficiencies in the text using natural language processing technology; means for recognizing the user's emotional state and dynamically adjusting and notifying the content and expression of correction suggestions according to the emotion; and means for accumulating user emotion data and collecting and processing data useful for improving the experience. This makes it possible to detect errors in documents while providing an appropriate interface according to the user's emotions, thereby reducing user anxiety and doubt in payment procedures and other situations.

[0773] "Specified information" refers to the information that the system will analyze, and typically includes documents and data provided by the user.

[0774] "Natural language processing technology" refers to the technology that enables computers to understand and generate human language, and involves multiple processes including grammatical analysis and semantic analysis.

[0775] "Errors and deficiencies" refer to grammatical errors, inconsistencies in content, and inaccurate expressions contained in a document.

[0776] "User emotional state" refers to the user's psychological state and emotional condition, and typically includes emotions such as joy, anxiety, and frustration.

[0777] "Dynamic adjustment" means that the system changes the suggested content and interface display in real time according to the user's emotions and situation.

[0778] A "revision suggestion" refers to a specific proposal for improving a document based on any errors or deficiencies that have been detected.

[0779] "Improving the user experience" means enhancing the satisfaction and convenience that users experience when using a system.

[0780] To realize this invention, a server plays a central role. First, the server analyzes the specified information received from the user terminal. Specifically, it employs natural language processing technology for text analysis to detect errors and deficiencies in the information. Advanced natural language processing software, such as the Google Cloud Natural Language API, is utilized in this process.

[0781] Next, the server uses the Emotion API to analyze the user's emotional state. Based on this information, the server dynamically generates modification suggestions tailored to the user's current emotions and notifies the user through their device. These suggestions may include friendly language to alleviate frustration or information to stimulate purchasing intent.

[0782] Furthermore, user sentiment data and feedback are stored on the server and used to improve the long-term experience. Based on this data, the server analyzes the user experience and provides information that contributes to system improvements.

[0783] As a concrete example, let's assume a user is purchasing a product online. While the user is considering the purchase, the server analyzes the user's emotions in real time and dynamically provides information to assist in the purchase decision. For example, if the user is feeling anxious about the purchase, a suggestion such as "This product has very high ratings and offers great value for money" might be displayed.

[0784] Regarding the use of a generative AI model, one possible prompt message could be: "I'm considering making a payment, but I have some concerns. Please provide suggestions on how to make a purchase with confidence." Through this prompt, the system can provide the user with the most appropriate suggestions and information.

[0785] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0786] Step 1:

[0787] The server receives the specified information from the user's terminal. The input is text data sent by the user, which is passed to the server for analysis. The output indicates the completion of the process in which this data is prepared for analysis.

[0788] Step 2:

[0789] The server analyzes the information using natural language processing techniques. The input is the text data received in step 1. The server uses the Google Cloud Natural Language API to check for grammatical errors and content consistency. The output is processed as an analysis result, with errors and deficiencies identified.

[0790] Step 3:

[0791] The server uses the Emotion API to analyze the user's emotional state. Inputs include user interactions and pre-collected emotion-related data. At this stage, the server quantifies the user's emotional state, identifying frustration, anxiety, and other emotional states. The output is a report on the user's emotional state.

[0792] Step 4:

[0793] The server generates suggested modifications based on the analysis results and emotional state. The input is the output from steps 2 and 3. The server uses this information to generate suggestions tailored to the user's emotions. Dynamic feedback is created, including friendly language and specific purchase assistance information. The output is the suggested modifications, which are then notified to the user.

[0794] Step 5:

[0795] The terminal receives correction suggestions from the server and presents them to the user. The input is the correction suggestion generated in step 4. The terminal displays this suggestion on the user's screen and prompts the user for confirmation and further action. The output is the completion of displaying the suggestion to the user.

[0796] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0797] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0798] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0799] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0800] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0801] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0802] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0803] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0804] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0805] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0806] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0807] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0808] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0809] 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.

[0810] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0811] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0812] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0813] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0814] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0815] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0816] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0817] The following is further disclosed regarding the embodiments described above.

[0818] (Claim 1)

[0819] A means for analyzing a specified document and detecting errors and deficiencies within the document using a natural language processing model,

[0820] Means for generating correction suggestions based on detected errors and deficiencies,

[0821] A means of notifying the user of the generated correction suggestions,

[0822] Means for recording and evaluating change history,

[0823] A means of conducting a risk assessment and proposing an action plan,

[0824] A system that includes this.

[0825] (Claim 2)

[0826] The system according to claim 1, comprising means for building a model that learns from past data and predicts error patterns.

[0827] (Claim 3)

[0828] The system according to claim 1, comprising means for checking the integrity and consistency of notation of a document.

[0829] "Example 1"

[0830] (Claim 1)

[0831] Means of receiving information from users,

[0832] A means for analyzing received information using a natural language processing system and detecting errors and deficiencies,

[0833] Means for generating correction suggestions based on detected errors and deficiencies,

[0834] A means of notifying the user's device of the generated correction suggestions,

[0835] A means of recording the history of correction work and evaluating its impact based on this information,

[0836] A means of conducting a risk assessment and presenting an improvement plan,

[0837] An information processing system that includes this.

[0838] (Claim 2)

[0839] The information processing system according to claim 1, comprising means for constructing a predictive model that learns past information and predicts error patterns.

[0840] (Claim 3)

[0841] The information processing system according to claim 1, comprising means for verifying the integrity and consistency of information.

[0842] "Application Example 1"

[0843] (Claim 1)

[0844] A means for analyzing a specified document and detecting errors and deficiencies within the document using a natural language processing model,

[0845] Means for generating correction suggestions based on detected errors and deficiencies,

[0846] A means of notifying the user of the generated correction suggestions,

[0847] Means for recording and evaluating change history,

[0848] A means of conducting a risk assessment and proposing an action plan,

[0849] A means to detect errors in contracts and terms of service in real time and propose corrections,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, comprising means for building a model that learns from past data and predicts error patterns.

[0853] (Claim 3)

[0854] The system according to claim 1, comprising means for checking the integrity and consistency of notation of a document.

[0855] "Example 2 of combining an emotion engine"

[0856] (Claim 1)

[0857] A means for analyzing specified information and detecting errors and deficiencies in the information using a machine learning model,

[0858] Means for generating correction suggestions based on detected errors and deficiencies,

[0859] A means of analyzing the user's emotional state and adjusting the wording of the correction suggestion according to that emotion,

[0860] A means of notifying users of the generated correction suggestions,

[0861] A means for recording and evaluating user feedback,

[0862] A means of accumulating emotional data and building a model to improve the system's adaptability,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, comprising means for building a model that learns past information and predicts error patterns.

[0866] (Claim 3)

[0867] The system according to claim 1, comprising means for checking the integrity of information and the consistency of notation.

[0868] "Application example 2 when combining with an emotional engine"

[0869] (Claim 1)

[0870] A device that analyzes specified information and detects errors and deficiencies in the text using natural language processing technology,

[0871] A device that generates correction suggestions based on detected errors and deficiencies,

[0872] A device that recognizes the user's emotional state and dynamically adjusts and notifies the user of the content and expression of suggested modifications according to that emotion.

[0873] A device that accumulates user emotional data and collects and processes data useful for improving the user experience,

[0874] A device for recording and evaluating change history,

[0875] A device that performs risk assessment and proposes an action plan,

[0876] A system that includes this.

[0877] (Claim 2)

[0878] The system according to claim 1, which learns from past data, builds a model to predict error patterns, and provides support for payment procedures based on user sentiment.

[0879] (Claim 3)

[0880] The system according to claim 1, which checks the integrity and consistency of information and provides suggestions that take into account the user's feelings. [Explanation of Symbols]

[0881] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for analyzing a specified document and detecting errors and deficiencies within the document using a natural language processing model, Means for generating correction suggestions based on detected errors and deficiencies, A means of notifying the user of the generated correction suggestions, Means for recording and evaluating change history, A means of conducting a risk assessment and proposing an action plan, A means to detect errors in contracts and terms of service in real time and propose corrections, A system that includes this.

2. The system according to claim 1, comprising means for building a model that learns from past data and predicts error patterns.

3. The system according to claim 1, comprising means for checking the integrity and consistency of notation of a document.

Images