System

Abstract

A system is provided.SOLUTION: A system comprising: means for obtaining a report file; means for analyzing contents of the report; means for generating an improvement proposal based on an analysis result; means for displaying the generated improvement proposal; and means for obtaining feedback from a user and performing self-learning.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Describe the "problem that the invention aims to solve" and the "means for solving the problem."

[0005] ---

[0006] In today's business environment, data-driven decision-making is essential. However, despite the need for accurate information and rapid decision-making, many challenges exist when creating and sharing reports. These challenges include a lack of purposeful organization and presentation of information, uncertainty in content, and misunderstandings by readers. Furthermore, there are few opportunities to receive appropriate feedback, which hinders progress in improving reports. As a result, decision-making within companies becomes slower and less efficient. [Means for solving the problem]

[0007] In order to solve these problems, the present invention provides a system called "Report Master AI", which includes the following means:

[0008] 1. How to obtain the report file

[0009] 2. A way to analyze the report content

[0010] 3. A means of generating improvement suggestions based on the analysis results

[0011] 4. A means to display generated improvement suggestions

[0012] 5. A means of obtaining user feedback and self-learning

[0013] Furthermore, by using natural language processing technology to analyze report content and supporting a variety of report file formats without any restrictions, users can create and improve reports effectively, thereby improving the quality of reports and supporting companies in making quick and accurate decisions.

[0014] ---

[0015] "Report files" refer to document files created by users and uploaded to the system in a variety of formats, including Excel, PowerPoint, spreadsheets, and BI dashboards.

[0016] "Means for analyzing the content of the report" refers to the process by which the system uses natural language processing technology and data analysis technology to understand and evaluate the meaning of the text and data in the report.

[0017] "Means for generating improvement proposals based on analysis results" refers to the function of the system to automatically create improvement proposals for the structure and content of a report based on the results of analysis of the report.

[0018] "Means for displaying improvement suggestions" refers to an interface that visually presents the improvement suggestions generated by the system to the user, including highlighting and annotations.

[0019] "Means for obtaining feedback" refers to the process by which the system receives user evaluations and opinions and stores them as data. This feedback is used for the system's self-learning.

[0020] "Means for self-learning" refers to the process of improving the algorithm based on user feedback obtained by the system, thereby improving the accuracy of analysis and proposals from the next time onwards.

[0021] "Natural language processing technology" is a general term for technology that enables computers to understand, analyze, and generate human language. This technology is used for text analysis, grammar checking, keyword extraction, etc.

[0022] "Various formats" refers to the fact that there are no specific restrictions on the format of report files, and that multiple different formats are supported, including Excel, PowerPoint, spreadsheets, and BI dashboards. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0024] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0025] First, the terms used in the following description will be explained.

[0026] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0027] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0028] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0029] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0030] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0031] [First embodiment]

[0032] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0033] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0034] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0035] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0036] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0037] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0038] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0039] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0041] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0042] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0043] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0044] ---

[0045] This invention provides a method for automatically analyzing reports and making improvement suggestions using a system called "Report Master AI." This system analyzes the contents of reports based on report files uploaded by users, generates improvement suggestions, and provides feedback to users.

[0046] Specifically, the system operates as follows.

[0047] 1. Uploading a report: The user selects a report file from the terminal and uploads it to the system, which then transfers the file to the server using the HTTP protocol.

[0048] 2. Receiving and saving reports: The server saves the received report files in temporary storage, which is optimized for smooth subsequent analysis.

[0049] 3. Report preprocessing: The server reads the report file using a specific library (e.g., Pandas library) and converts the data into an appropriate format. For example, if it is an Excel file, it parses the sheet information and cell data and converts it into a data frame.

[0050] 4. Text and Data Analysis: The server uses a natural language processing (NLP) engine to analyze the text in the report, including grammar checks, keyword extraction, and summary generation, as well as correlation and trend analysis of numerical data.

[0051] 5. Generating peer review results: The server integrates the results of the text and data analysis and generates recommendations for improving the structure and content of the report, such as "The introduction to the report lacks background information."

[0052] 6. Providing feedback: The server creates an HTML feedback report based on the generated improvement suggestions and sends it to the user's device. Through this feedback, the user can visually confirm the improvements made to the report.

[0053] 7. Re-upload revised report (optional): The user can revise the report based on the feedback and re-upload it to the system. The server will receive the new report, compare it with the previous feedback and make further improvement suggestions.

[0054] 8. Self-learning function: The server collects and analyzes user feedback and uses that data to update the self-learning algorithm, allowing the system to improve the accuracy of its analysis and improvement suggestions in future sessions.

[0055] The following explains this with specific examples.

[0056] The user uploads an Excel file called "Monthly Sales Report.xlsx" from their device. This file contains sales data and analysis details for each store. The server receives this file and saves it in temporary storage. Next, the PANDAS library reads the Excel file and converts the data in each sheet into a data frame.

[0057] The server uses a natural language processing engine to analyze the text and extract keywords such as "causes of sales decline." At the same time, it performs trend and correlation analysis on the numerical data. Based on the results, the server realizes that "sales have declined compared to the previous year, but the reasons for this have not been specifically stated," and suggests adding specific market and competitive situations.

[0058] These improvement suggestions are sent to the user's device in HTML format, where the user can review the improvements and modify the report. When the modified report is uploaded again, the server compares the differences with the previous version and makes further improvement suggestions. Furthermore, based on user feedback, the self-learning algorithm is improved to improve the accuracy of future analyses.

[0059] In this way, "Report Master AI" effectively supports users in creating and improving reports, helping companies make quick and accurate decisions.

[0060] The processing flow will be explained below.

[0061] ---

[0062] Step 1:

[0063] The user selects a report file (e.g., an Excel file) from the terminal and clicks the upload button. The terminal sends the selected report file to the server via an HTTP POST request.

[0064] Step 2:

[0065] The server parses the received HTTP POST request, retrieves the attached report file, saves the report file in a temporary folder, and records the file path.

[0066] Step 3:

[0067] The server reads the saved report file using the PANDAS library and converts the data into a data frame, which makes the text and numeric data in the report easier to parse.

[0068] Step 4:

[0069] The server uses a natural language processing (NLP) engine to analyze the text in the report, performing operations such as grammar checks, keyword extraction, and summary generation to understand the meaning of the text.

[0070] Step 5:

[0071] The server analyzes the numerical data in the reports, performing correlation and trend analysis to detect significant patterns and outliers. This analysis ensures the reliability of the data.

[0072] Step 6:

[0073] Based on the analysis results, the server generates suggestions for improving the structure and content of the report, such as "This part's explanation is insufficient, so please add specific examples and provide more detail."

[0074] Step 7:

[0075] The server generates improvement suggestions and builds an HTML feedback report that highlights specific areas for improvement.

[0076] Step 8:

[0077] The server sends a feedback report to the user's device, allowing the user to see how the report can be improved, and the user can then revise the report based on this feedback.

[0078] Step 9:

[0079] When the user re-uploads the revised report, the server compares the new report with the previous feedback and makes further suggestions for improvement. The server repeats this process to improve the quality of the report.

[0080] Step 10:

[0081] The server collects user feedback and uses that data to improve the self-learning algorithm, which improves the accuracy of future analyses and improvement suggestions.

[0082] ---

[0083] The above is the specific processing flow of "Report Master AI".

[0084] Example 1

[0085] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0086] Conventional report analysis systems have restrictions on the format and content of report files uploaded by users, making it difficult to efficiently analyze diverse and complex data. Furthermore, the improvement suggestions generated are general and lack specific suggestions for specific issues. Furthermore, the system lacks the ability to effectively utilize user feedback and self-learn, making it difficult to improve the accuracy of the next analysis.

[0087] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0088] In this invention, the server includes means for receiving digital documents from a repository server via communication means, means for storing the received digital documents in a temporary storage device, means for analyzing the digital documents using a program and converting them into data frames, means for analyzing text data in the digital documents using natural language processing technology, means for generating improvement suggestions based on the analysis results, means for visualizing and displaying the generated improvement suggestions, and means for receiving input data from a user and updating the self-learning algorithm. This enables highly accurate analysis of digital documents in a variety of formats, provides specific and effective improvement suggestions, and self-learns using user feedback to improve the accuracy of subsequent analyses.

[0089] "Communication means" refers to an interface function including protocols and technologies for receiving digital documents from a repository server.

[0090] A "repository server" is a server system that stores and manages digital documents and allows access and transfer as needed.

[0091] "Digital documents" refers to files such as electronic reports and reports that exist in various formats (e.g., Excel files, PDFs, Word documents).

[0092] "Temporary storage device" refers to a storage device (e.g., SSD or RAM) for temporarily storing received digital documents.

[0093] A "data frame" is a two-dimensional data structure in the form of rows and columns for storing structured data.

[0094] "Natural language processing technology" is a technology for analyzing and understanding text data, and includes grammar checking, keyword extraction, summary generation, and sentiment analysis.

[0095] "Improvement Suggestion" refers to a specific suggestion for improving or correcting the content of a digital document that is generated based on the analysis of the digital document.

[0096] "Visualization" is the process of visually displaying the analysis results and improvement suggestions for digital documents.

[0097] "Input data" refers to feedback information and additional information entered by the user.

[0098] A "self-learning algorithm" is an algorithm that improves the analysis accuracy of a system based on past analysis results and feedback data.

[0099] The present invention is a system that automatically analyzes digital documents and proposes improvements. This system is particularly capable of handling a wide variety of digital document formats with high accuracy and includes a self-learning function based on user feedback. The following describes its specific operation.

[0100] First, a user selects a digital document from their device and uploads it to the system, where the file is transmitted using the HTTP protocol.

[0101] The server then receives the uploaded digital document and stores it in temporary storage (e.g. SSD), which is optimized for fast loading and processing.

[0102] The server uses the PANDAS library (a Python data analysis library) to read the document and convert the data into a data frame. In the case of an Excel file, the information on each sheet and cell data is parsed and converted into structured data for easier subsequent processing.

[0103] The server then uses a natural language processing engine (e.g., SpaCy or BERT) to analyze the text data in the digital documents, including grammar checks, keyword extraction, summary generation, and sentiment analysis, as well as trend and correlation analysis for numerical data.

[0104] Based on the analysis results, the server generates suggestions for improving the structure and content of the digital document, for example, suggesting that the background information in the introduction of the report is insufficient.

[0105] The generated improvement suggestions are generated as a feedback report in HTML format by the server and sent to the user's terminal. The user can check this feedback in a browser and visually understand the improvements to the report.

[0106] The user can modify the report based on the feedback and upload it back to the system. The server receives the new report, compares it with the previous feedback, and provides further suggestions for improvement.

[0107] Finally, the server analyzes the feedback data from users and updates the self-learning algorithm, which improves the accuracy of the analysis in the future and improves the overall performance of the system.

[0108] As a concrete example, a user uploads "Monthly Sales Report.xlsx." This file contains sales data and analytical details for each store. The server uses the PANDAS library to read this file and convert it into a data frame. It then uses a natural language processing engine to analyze the text and perform trend analysis on the sales data. As a result, the server provides feedback to the user, stating that "sales have decreased compared to the previous year, but the reasons for this have not been specifically stated," and recommends that the user provide a detailed description of the market situation and the competitive situation.

[0109] This feedback report is generated in HTML format and sent to the user's device. The user can make corrections and upload the report again, and the server will provide more accurate improvement suggestions. By repeating this process, the system will continue to learn and improve its analysis accuracy.

[0110] Example prompt sentence:

[0111] Analyze the report file "Monthly Sales Report.xlsx" to clarify the cause of the sales decline and provide suggestions for improvement.

[0112] In this way, the invention accommodates a variety of digital documents and effectively assists users in report analysis and refinement.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1: Upload the report file

[0115] The user selects a report file (e.g., "Monthly Sales Report.xlsx") from the terminal and uploads it to the system. As input, the user selects the target file in a file selection dialog. As output, the file is sent to the server using the HTTP protocol.

[0116] Step 2: Receive and temporarily save the report file

[0117] The server receives the uploaded report file. The input is the file data sent by the user. As an output, the server saves the received file to a temporary storage device (SSD). Specifically, the file is saved in the " / tmp / reports / " directory, and the completion of reception is recorded in the server log.

[0118] Step 3: Preprocessing the report file

[0119] The server uses the PANDAS library to read the report file. The input is the file stored in temporary storage. The output is the data converted to a data frame format. Specifically, in the case of an Excel file, the information on each sheet and cell data is analyzed and structured into a data frame.

[0120] Step 4: Analyzing text and numerical data

[0121] The server analyzes text data using a natural language processing engine. The input is a preprocessed data frame. The output is a text summary, keywords, grammar check results, and sentiment analysis results as the analysis results. At the same time, trend analysis and correlation analysis are performed on the numerical data. Specifically, the NLP engine analyzes the text, and the PANDAS library processes the numerical data.

[0122] Step 5: Generate improvement suggestions

[0123] The server generates improvement suggestions based on the analysis results. The input is the analysis results of text and numerical data. The output is specific improvement suggestions. As a specific operation, the server generates specific suggestions such as "The background explanation in the introduction of the report is insufficient."

[0124] Step 6: Provide feedback

[0125] The server creates a feedback report in HTML format based on the generated improvement suggestions. The input is the improvement suggestions. The output is the feedback report. Specifically, the server creates the feedback report and sends it to the user's device. The user then checks the feedback in their browser.

[0126] Step 7: Re-upload the Correction Report (Optional)

[0127] The user modifies the report based on the feedback. The input is the feedback report. The output is the modified report file. Specifically, the user uploads the modified file back to the system. The server receives the new report, compares it with the previous feedback, and provides further improvement suggestions.

[0128] Step 8: Update the self-learning algorithm

[0129] The server analyzes the feedback data from users and updates the self-learning algorithm. The input is the feedback data from users. The output is the updated learning algorithm. Specifically, the system accumulates feedback data and periodically retrains the model to improve the system's analysis accuracy.

[0130] (Application example 1)

[0131] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0132] Factories require the collection and analysis of various process and performance data, and improvement proposals are extremely important for achieving efficient production and quality control. However, the process from data collection to analysis, and the generation and implementation of improvement proposals is often done manually, which is time-consuming and prone to inaccuracies. For this reason, there is a demand for an automated, highly accurate analysis system that can improve factory production efficiency and quality control in real time.

[0133] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0134] In this invention, the server includes means for acquiring a report file, means for analyzing the contents of the report, means for generating improvement proposals based on the analysis results, means for displaying the generated improvement proposals, means for acquiring feedback from users and performing self-learning, means for collecting real-time data from equipment operating in the factory, means for analyzing the collected real-time data, means for generating improvement proposals for the factory equipment based on the analysis results, and means for displaying the generated improvement proposals for the factory equipment on a display device. This makes it possible to automate the series of processes of data collection, analysis, and improvement proposals within the factory, thereby reducing time and improving accuracy.

[0135] A "report file" is a document file that organizes data and information in an organized manner, which may include text, numerical data, graphs, etc.

[0136] "Analysis" is the process of conducting detailed analysis based on collected data and information to clarify their meaning and relationships.

[0137] "Improvement proposals" refer to specific advice and instructions based on the analysis results to improve the current situation, leading to effective problem solving and improved business efficiency.

[0138] A "display device" is a device for visually displaying information. This may include smart glasses or head-mounted displays.

[0139] "User" refers to the person who operates the system, uploads report files, and checks improvement suggestions. This applies to factory managers and engineers.

[0140] "Self-learning" is the process by which machine learning algorithms use feedback data to improve the accuracy of future analyses and suggestions.

[0141] "Factory equipment" refers to various machines and robots used in the production process, which are often equipped with sensors that monitor temperature, pressure, vibration, etc.

[0142] "Real-time data" is dynamic data that records the behavior and state of the object being collected in real time.

[0143] "Analysis results" refers to information and knowledge obtained as a result of analysis based on collected data.

[0144] "Server" refers to a central processing unit for receiving, storing, analyzing report files, and transmitting analysis results.

[0145] This invention applies "Report Master AI" to factories, creating a system that collects and analyzes data in real time, automating the entire process of generating and displaying improvement suggestions.

[0146] Factories are equipped with various sensors that collect real-time data, such as temperature, pressure, and vibration, and the data is sent to a server via Wi-Fi or 5G networks.

[0147] The server first receives the collected data and stores it in temporary storage, then uses the PANDAS library installed on the high-performance server to convert the data into a data frame, which is then prepared for subsequent analysis.

[0148] The analysis uses a generative AI model that applies natural language processing technology. Specifically, the server analyzes the data using a machine learning library (e.g., TensorFlow or PyTorch), while simultaneously generating improvement suggestions using a natural language processing engine (e.g., NLTK or SpaCy). This process detects anomalies in the data, analyzes their causes, and derives specific improvement suggestions.

[0149] Improvement suggestions are written in HTML format and sent to smart glasses or head-mounted displays via Wi-Fi or 5G networks, allowing factory managers and engineers to view the suggestions in real time and take appropriate action on the spot.

[0150] The server also collects user feedback and updates the self-learning algorithm, which improves the accuracy of future analyses and improvement suggestions.

[0151] A specific example is shown below: When an abnormal vibration value is detected based on vibration data collected by a factory robot, the server generates an analysis result and improvement proposals based on that data.

[0152] An example of a prompt is as follows:

[0153] Prompt statement:

[0154] "Analyze the vibration data below, check for any abnormal values, generate any necessary improvement suggestions, and return the improvement suggestions in HTML format."

[0155] Vibration Data:

[0156] Time: 2023-10-01 10:00, Vibration value: 1.2

[0157] Time: 2023-10-01 10:01, Vibration value: 1.4

[0158] Time: 2023-10-01 10:02, Vibration level: 5.6 (abnormal value)

[0159] Desired improvement suggestions:

[0160] "At 10:02, an abnormal vibration value of 5.6 was detected. This vibration is more than twice the normal value. Possible causes include deterioration of the device's components or misalignment. Please perform maintenance immediately and recheck the device's operation."

[0161] In this way, the present invention automates the entire process of data collection, analysis, and improvement proposals within a factory, thereby reducing time and improving accuracy.

[0162] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0163] Step 1:

[0164] Factory equipment collects real-time data such as temperature, pressure, and vibration through sensors. Each sensor captures data about the operation and status of the equipment and records it at regular intervals.

[0165] Input: Sensor data from factory equipment

[0166] Output: Real-time sensor data

[0167] Step 2:

[0168] The device transmits the collected real-time data over Wi-Fi or 5G networks to a server, where the data may be formatted, compressed, etc.

[0169] Input: Real-time sensor data

[0170] Output: Real-time data sent to the server

[0171] Step 3:

[0172] The server stores the received data in temporary storage, where it is converted into a data frame using libraries such as Pandas and processed into a format suitable for analysis.

[0173] Input: Real-time data sent to the server

[0174] Output: Data in data frame format

[0175] Step 4:

[0176] The server analyzes the data using machine learning libraries (e.g., TensorFlow or PyTorch) and uses natural language processing engines (e.g., NLTK or SpaCy) to understand the results and detect abnormal conditions and patterns in the factory equipment.

[0177] Input: Data in data frame format

[0178] Output: Analysis results (including anomaly detection)

[0179] Step 5:

[0180] The server generates improvement suggestions based on the analysis results, which are then converted into a human-readable format using a natural language processing engine.

[0181] Input: Analysis results (including anomaly detection)

[0182] Output: Improvement suggestions expressed in natural language

[0183] Step 6:

[0184] The server constructs the generated improvement suggestions in HTML format and transmits them to smart glasses or head-mounted displays via Wi-Fi or 5G networks.

[0185] Input: Improvement suggestions expressed in natural language

[0186] Output: HTML format improvement suggestions

[0187] Step 7:

[0188] Users can check the improvement suggestions displayed through smart glasses or a head-mounted display and take necessary actions, such as performing maintenance on factory equipment or adjusting settings.

[0189] Input: HTML format improvement suggestions

[0190] Output: User actions (maintenance, configuration adjustments, etc.)

[0191] Step 8:

[0192] The server receives feedback from users and updates its self-learning algorithm, improving the accuracy of future analyses and improvement suggestions.

[0193] Input: User feedback

[0194] Output: Self-learning updated analytical model

[0195] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0196] ---

[0197] This invention provides a system that automatically analyzes reports and proposes improvements by combining a "Report Master AI" with an emotion engine that recognizes user emotions, and provides feedback based on the user's emotions. This system analyzes report files uploaded by users, generates improvement suggestions, and further recognizes the user's emotions when giving feedback using the emotion engine, which can be reflected in the next improvement suggestions.

[0198] Specifically, the system operates as follows.

[0199] 1. Uploading a report: The user selects a report file from the terminal and uploads it to the system. The terminal sends the selected report file to the server via an HTTP POST request.

[0200] 2. Receiving and saving reports: The server saves the received report files in temporary storage, which is optimized for smooth subsequent analysis.

[0201] 3. Report preprocessing: The server reads the report file using a predefined library and converts the data into an appropriate format. For example, if it is an Excel file, it parses the sheet information and cell data and converts it into a data frame.

[0202] 4. Text and Data Analysis: The server uses a natural language processing (NLP) engine to analyze the text in the report, including grammar checks, keyword extraction, and summary generation, as well as correlation and trend analysis of numerical data.

[0203] 5. Generating peer review results: The server integrates the results of the text and data analysis and generates recommendations for improving the structure and content of the report, such as "The introduction to the report lacks background information."

[0204] 6. Emotion Recognition by Emotion Engine: The server uses an emotion engine to recognize the user's emotion in the feedback. This includes analyzing the user's emotional state (e.g., satisfaction, dissatisfaction, confusion, etc.) from their written or spoken words.

[0205] 7. Providing feedback: The server creates an HTML-formatted feedback report based on the generated improvement suggestions and provides feedback in a tone that reflects the user's emotional state. For example, if the user has experienced emotional stress in the past, the server may soften the tone of the feedback.

[0206] 8. Re-upload revised report (optional): The user can revise the report based on the feedback and re-upload it to the system. The server will receive the new report, compare it with the previous feedback, and make further suggestions for improvement.

[0207] 9. Self-learning function: The server collects and analyzes user feedback and emotional data, and uses that data to update the self-learning algorithm, allowing the system to improve the accuracy of its analysis and improvement suggestions in the future.

[0208] The following explains this with specific examples.

[0209] The user uploads an Excel file called "Monthly Sales Report.xlsx" from their device. This file contains sales data and analysis details for each store. The server receives this file and saves it in temporary storage. Next, the PANDAS library reads the Excel file and converts the data in each sheet into a data frame.

[0210] The server uses a natural language processing engine to analyze the text and extract keywords such as "causes of sales decline." At the same time, it performs trend and correlation analysis on the numerical data. Based on the results, the server realizes that "sales have declined compared to the previous year, but the reasons for this have not been specifically stated," and suggests adding specific market and competitive situations.

[0211] Furthermore, an emotion engine is used to analyze user emotions. For example, when a user enters a comment when providing feedback, the system reads the user's emotions from the text and determines whether the improvement proposal is appropriate for the user. If the user is expressing strong dissatisfaction, the system softens the tone of the feedback and provides information in a more understandable format.

[0212] These improvement suggestions are sent to the user's device in HTML format, where the user can review and revise the report. When the revised report is uploaded again, the server compares the differences with the previous version and makes further improvement suggestions. Furthermore, the self-learning algorithm is improved based on user feedback and emotional data, improving the accuracy of subsequent analyses.

[0213] In this way, "Report Master AI" effectively supports users in creating and improving reports, while providing feedback that takes users' emotions into consideration, thereby increasing the usefulness of the system.

[0214] The processing flow will be explained below.

[0215] ---

[0216] Step 1:

[0217] The user selects a report file (e.g., an Excel file) from the terminal and clicks the upload button. The terminal sends the selected report file to the server via an HTTP POST request.

[0218] Step 2:

[0219] The server parses the received HTTP POST request, retrieves the attached report file, saves the report file in a temporary folder, and records the file path.

[0220] Step 3:

[0221] The server reads the saved report file using the PANDAS library and converts the data into a data frame format, which makes the text and numeric data in the report easier to parse.

[0222] Step 4:

[0223] The server uses a natural language processing (NLP) engine to analyze the text in the report, performing operations such as grammar checks, keyword extraction, and summary generation to understand the meaning of the text.

[0224] Step 5:

[0225] The server analyzes the numerical data in the reports, performing correlation and trend analysis to detect significant patterns and outliers. This analysis ensures the reliability of the data.

[0226] Step 6:

[0227] Based on the results of the text and data analysis, the server generates suggestions for improving the structure and content of the report, such as "This part's explanation is insufficient, so please add specific examples and provide more detail."

[0228] Step 7:

[0229] The server uses an emotion engine to recognize the user's emotion when providing feedback. The emotion engine identifies the user's emotional state from the text and voice when the user provides feedback, and analyzes the emotional state.

[0230] Step 8:

[0231] The server adjusts the content and tone of the feedback report based on the user's emotional data obtained from the emotion engine. For example, if the user expresses dissatisfaction, the server softens the feedback and provides additional explanatory comments.

[0232] Step 9:

[0233] The server creates an HTML-formatted feedback report based on the generated improvement suggestions and sends it to the user's device, allowing the user to visually confirm the improvements made to the report.

[0234] Step 10:

[0235] The user then modifies the report based on the feedback and uploads it to the server again from their device. The server compares the new report with the previous feedback and makes suggestions for further improvement.

[0236] Step 11:

[0237] The server collects user feedback and emotional data and uses it to update the self-learning algorithm, allowing the system to improve the accuracy of future analyses and improvement suggestions.

[0238] ---

[0239] The above is the specific processing flow of the system that combines the "Report Master AI" with an emotion engine.

[0240] Example 2

[0241] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0242] Conventional report analysis systems have the ability to analyze report content and provide improvement suggestions, but they lack the ability to provide feedback that takes user emotions into consideration or to self-learn based on user feedback. This limits the system's usefulness because it is unable to provide flexible improvement suggestions that reflect user emotions. Furthermore, limitations on report file formats make it difficult to analyze reports in a variety of formats.

[0243] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0244] In this invention, the server includes a means for acquiring a report file, a means for saving the report file, and a means for reading and converting data in the report file, thereby enabling a means for generating improvement suggestions based on the analysis results, a means for displaying the generated improvement suggestions, a means for acquiring feedback from a user and recognizing the user's emotions, and a means for self-learning based on the feedback.

[0245] "Report file" refers to an electronic document that records reports or data analysis results, and specifically includes formats such as Excel, PDF, and Word.

[0246] The "means of acquisition" refers to an interface or protocol for receiving data from a user terminal, and has functions including HTTP POST requests.

[0247] "Means for storing" refers to storage for temporarily or permanently storing received data, and includes media such as disks and cloud storage.

[0248] "Means to read and transform" refers to the process of converting data in a particular format into an analyzable format, including, for example, the ability to convert Excel data into a data frame using the pandas library.

[0249] "Means of analysis" refers to the process of analyzing the content of data using specific algorithms or technologies and obtaining the results, including natural language processing technology and statistical analysis technology.

[0250] The "means for generating improvement proposals" refers to a function for automatically extracting and proposing improvements to the report based on the analysis results, and includes a proposal generation engine that uses a specific algorithm.

[0251] The "display means" refers to an interface for presenting the generated improvement proposals to the user in an easy-to-understand manner, and includes a feedback report in HTML format.

[0252] "Means for obtaining feedback" refers to the process by which the system collects user ratings and opinions, and includes feedback forms, comment sections, etc.

[0253] "Means for recognizing emotions" refers to technologies that analyze the emotional state of a user from feedback data provided by the user, and includes text analysis and voice analysis.

[0254] "Means for self-learning" refers to the process of improving the system's algorithms using the obtained feedback and emotional data to improve the accuracy of analysis from the next time onwards, and includes machine learning techniques.

[0255] This invention relates to a system that allows users to upload report files, analyzes their contents, and generates improvement suggestions. It also has the ability to analyze the user's feedback and emotional state, adjust the feedback based on that, and perform self-learning. This system uses natural language processing and machine learning technologies to achieve efficient and flexible report improvement.

[0256] System Overview

[0257] Obtaining and saving report files

[0258] The terminal provides an interface for the user to select a report file of their choice and upload it to the system. The user uses a file selection dialog to select the file they want to upload (e.g., "Monthly Sales Report.xlsx"). Once selected, the terminal creates an HTTP POST request and sends it to the server, including the selected file.

[0259] The server receives the HTTP POST request from the terminal and extracts the report file. The extracted file is saved in temporary storage (for example, the / tmp directory). The save location is managed by a unique identifier that includes the file name and timestamp.

[0260] Preprocessing the report file

[0261] The server loads the saved report file using a specific library (for example, the pandas library). If the file is an Excel file, the server converts each sheet and cell data into a data frame. The converted data is temporarily stored in memory in preparation for analysis.

[0262] Text and Data Analysis

[0263] The server uses a natural language processing (NLP) engine and a data analysis engine to analyze the text and numerical data based on each data frame. Specifically, the text is checked for grammar, keywords are extracted, and summaries are generated, while correlation and trend analysis are performed on the numerical data. This results in analysis results from both the content and data aspects of the report.

[0264] Generate improvement suggestions

[0265] The server integrates the results of the text and data analysis and generates specific suggestions for improving the structure and content of the report, such as "the introduction lacks background information" or "add specific market conditions." These suggestions are stored in a temporary database.

[0266] Feedback acquisition and emotion recognition

[0267] The server uses an emotion engine to recognize the user's emotions when providing feedback. This is done by analyzing the text data entered by the user in the feedback form. The analyzed emotion data (e.g., satisfaction, dissatisfaction, confusion, etc.) is reflected in the next feedback and improvement suggestions.

[0268] Providing feedback

[0269] The server generates a feedback report in HTML format based on the generated improvement suggestions and emotional data. The tone of this feedback report is adjusted according to the user's emotional state. For example, if the user has expressed strong dissatisfaction in the past, the tone of the feedback will be softened. The generated feedback report is sent to the terminal and displayed to the user.

[0270] Re-upload the correction report (optional)

[0271] Users can modify their reports based on the feedback and re-upload them, in which case the server receives the new report, compares it with the previous feedback, and makes further suggestions for improvement.

[0272] Self-learning function

[0273] The server collects and analyzes user feedback and emotional data, and uses that data to update the self-learning algorithm, allowing the system to improve the accuracy of future analyses and improvement suggestions.

[0274] Specific examples are shown below.

[0275] Specific examples

[0276] The user uploads an Excel file called "Monthly Sales Report.xlsx" from their device. This file contains sales data and analysis details for each store. The server receives this file and saves it in temporary storage. Next, the pandas library reads the Excel file and converts the data in each sheet into a data frame.

[0277] The server uses a natural language processing engine to analyze the text and extract keywords such as "causes of sales decline." At the same time, it performs trend and correlation analysis on the numerical data. Based on the results, the server realizes that "sales have declined compared to the previous year, but the reasons for this have not been specifically stated," and suggests adding specific market and competitive situations.

[0278] Furthermore, an emotion engine is used to analyze user emotions. For example, when a user enters a comment when providing feedback, the system reads the user's emotions from the text and determines whether the improvement proposal is appropriate for the user. If the user is expressing strong dissatisfaction, the system softens the tone of the feedback and provides information in a more understandable format.

[0279] These improvement suggestions are sent to the user's device in HTML format, where the user can review and revise the report. When the revised report is uploaded again, the server compares the differences with the previous version and makes further improvement suggestions. Furthermore, the self-learning algorithm is improved based on user feedback and emotional data, improving the accuracy of subsequent analyses.

[0280] Prompt Sentence Examples

[0281] Analyze Monthly Sales Report.xlsx and generate improvement suggestions. Adjust the tone of the analysis results based on user feedback.

[0282] In this way, the system of the present invention effectively supports the user in creating and improving reports, while providing feedback that takes into account the user's emotions.

[0283] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0284] Step 1:

[0285] Uploading a report file

[0286] A user selects a specific report file (e.g., "Monthly Sales Report.xlsx") from the terminal and uploads it to the system. The terminal sends the selected report file to the server using an HTTP POST request. The input is the report file selected by the user, and the output is the HTTP POST request sent to the server. Specifically, the terminal opens a file selection dialog, and after the user selects a file, it sends the file to the server as an HTTP POST request.

[0287] Step 2:

[0288] Receiving and saving report files

[0289] The server receives the HTTP POST request from the terminal and extracts the report file. It saves the extracted file in temporary storage (e.g., the / tmp directory). The input is the HTTP POST request, and the output is the saved report file. Specifically, the server analyzes the HTTP request and saves the file in a temporary storage directory.

[0290] Step 3:

[0291] Preprocessing the report file

[0292] The server reads the saved report file using a specified library (e.g., the pandas library). If it is an Excel file, it converts each sheet information and cell data into a data frame. The input is the saved report file, and the output is data in data frame format. Specifically, the server reads the Excel file using the pandas library and converts it into a data frame.

[0293] Step 4:

[0294] Text and Data Analysis

[0295] The server uses a natural language processing (NLP) engine and a data analysis engine to analyze the text and numerical data of the data frame. Specifically, it performs grammar checks, keyword extraction, and summary generation on the text portion, and performs correlation analysis and trend analysis on the numerical data. The input is data in data frame format, and the output is the analysis results. Specifically, the server uses the natural language processing engine to perform text analysis, and the statistical analysis engine to analyze correlations and trends in the numerical data.

[0296] Step 5:

[0297] Generate improvement suggestions

[0298] The server integrates the results of the text and data analysis and generates specific improvement suggestions for the structure and content of the report. For example, it may make suggestions such as "the background explanation in the introduction is insufficient" or "specific market conditions should be added." The input is the analysis results and the output is improvement suggestions. Specifically, the server uses a suggestion generation algorithm based on the analysis results to extract areas for improvement and generate specific suggestions.

[0299] Step 6:

[0300] Feedback acquisition and emotion recognition

[0301] The server receives the user's feedback and recognizes the emotion using the emotion engine. This is done by analyzing the text data the user enters into the feedback form. The input is the user's feedback, and the output is the analyzed emotion data. Specifically, the server receives the feedback form data, performs text analysis, and infers the user's emotion.

[0302] Step 7:

[0303] Providing feedback

[0304] The server generates a feedback report in HTML format based on the generated improvement suggestions and emotion data, and adjusts the tone of the feedback. The generated report is sent to the terminal and displayed to the user. The input is the improvement suggestions and emotion data, and the output is a feedback report in HTML format. Specifically, the server adjusts the tone of the feedback taking into account the emotion data, generates the report in HTML format, and sends it to the terminal.

[0305] Step 8:

[0306] Re-upload the correction report (optional)

[0307] The user can modify the report based on the feedback and upload it again. The server receives the new report, compares it with the previous feedback, and makes further improvement suggestions. The input is the report file modified by the user, and the output is new improvement suggestions. Specifically, the server receives the modified report, processes it in the same way as the initial analysis, and suggests new improvements.

[0308] Step 9:

[0309] Self-learning function

[0310] The server collects and analyzes user feedback and emotional data, and uses that data to update the self-learning algorithm. The input is feedback and emotional data, and the output is the updated algorithm. Specifically, the server adjusts the parameters of the machine learning model based on the collected data, improving the accuracy of future analyses.

[0311] (Application example 2)

[0312] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0313] Conventional report analysis systems can provide objective analysis results and improvement suggestions for created reports, but they lack feedback that takes into account the user's emotional state or consideration for reducing stress caused by emotions. Furthermore, they cannot provide real-time improvement suggestions, which means they cannot be expected to improve work efficiency. In particular, in on-site work environments such as factories, support systems incorporating emotion recognition would be effective, but such systems have not existed.

[0314] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0315] In this invention, the server includes means for acquiring a report file, means for analyzing the contents of the report, means for generating improvement suggestions based on the analysis results, emotion recognition means for recognizing the user's emotion, and means for adjusting the tone of the feedback based on the emotion recognition. This enables feedback that is considerate to the user's emotional state, reducing the user's stress and improving work efficiency through improvement suggestions in real time.

[0316] A "report file" is document data in a report format that is submitted or created by a user.

[0317] "Analysis Means" refers to the technical means for automatically analyzing the contents of the Report File.

[0318] "Improvement proposals" refer to specific proposals for improving the content of the report based on the results obtained by the analysis means.

[0319] "Display means" refers to a device or software for visually displaying the generated improvement proposals.

[0320] "Emotion recognition means" refers to technical means, including voice analysis and facial expression recognition technology, for recognizing a user's emotions.

[0321] "Feedback" refers to the process within the system for collecting opinions and feedback from users.

[0322] "Self-learning means" refers to functions that improve the accuracy of system analysis and improvement suggestions based on collected feedback.

[0323] "Natural language processing technology" refers to a group of computer technologies for analyzing and processing linguistic data.

[0324] "Various formats" refers to including a wide variety of file formats without being limited to a specific file format.

[0325] "Voice analysis" refers to the technology of processing the user's voice as digital data and analyzing its content and emotions.

[0326] "Facial expression recognition" refers to image processing technology for reading emotions from a user's facial image.

[0327] "Real-time" refers to data processing and feedback occurring immediately.

[0328] The present invention is a system that combines emotion recognition means to analyze report files and provide improvement suggestions, with the aim of improving the work efficiency of factory workers.

[0329] The system program operates as follows.

[0330] The server receives the report file uploaded by the user and stores it in temporary storage. The server then uses an analysis means to analyze the contents of the report file and generates improvement suggestions based on the analysis results. This analysis uses natural language processing technology to analyze the text in the report. The server also uses an emotion recognition means to detect the user's emotions through voice analysis and facial expression recognition.

[0331] Specifically, the server uses software libraries such as OpenCV and SpeechRecognition to analyze the user's camera footage and audio data. This allows it to read emotions from the user's facial expressions and speech. The analyzed emotional data is reflected in the tone of the improvement suggestions, allowing the user to receive feedback without feeling stressed.

[0332] The improvement proposals are generated in HTML format and provided to the user through a display means, allowing the user to check the analysis results and improvement proposals in real time. Furthermore, feedback from users is collected and the system's accuracy is improved through self-learning means.

[0333] As a concrete example, consider a scenario in which an Excel file called "Monthly Sales Report.xlsx" is uploaded. The user uploads "Monthly Sales Report.xlsx" to the system. The server receives this file and stores it in temporary storage. Next, the Pandas library is used to read the Excel file and convert it into a data frame. TextBlob is used to analyze the sentiment in the text, and OpenCV and SpeechRecognition are used to analyze the voice and facial expression. Finally, improvement suggestions based on the analysis results are generated in HTML format and provided to the user.

[0334] An example prompt might be something like, "Please upload Monthly Sales Report.xlsx. We'll provide you with analysis of the report and feedback based on your sentiment."

[0335] As described above, the present invention provides a report analysis and improvement proposal system that combines emotion recognition means, and contributes to improving the efficiency of factory work and reducing worker stress.

[0336] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0337] Step 1:

[0338] The user uses a terminal to select a report file and upload it to the system. As input, the user provides a report file (e.g., "Monthly Sales Report.xlsx"), and the output is that the server receives this file.

[0339] Step 2:

[0340] The server stores the received report file in temporary storage. It receives the uploaded report file as input and generates a file stored in temporary storage as output.

[0341] Step 3:

[0342] The server uses the Pandas library to convert the saved Excel file into a data frame. The input is the report file in temporary storage, and the output is data in data frame format. Specifically, the server calls the Pandas read_excel function to read the sheet information and cell data.

[0343] Step 4:

[0344] The server uses the TextBlob library to analyze the text in the data frame. The input is the text data in the data frame, and the output is the sentiment analysis results and keyword extraction results. Specifically, the server evaluates the sentiment of the text using the sentiment function of TextBlob.

[0345] Step 5:

[0346] The server uses OpenCV and the SpeechRecognition library to acquire the user's camera video and audio data and recognize emotions. The input is the camera video and audio data, and the output is the user's emotional state. Specifically, the server captures the camera video, records the audio, and passes this data to the analysis engine.

[0347] Step 6:

[0348] The server generates improvement suggestions based on the text analysis results and emotion recognition results. It receives the text analysis results, emotional state, and existing feedback as input, and generates a feedback report with adjusted tone as output. Specifically, the server integrates the analysis results and constructs specific improvement suggestions.

[0349] Step 7:

[0350] The server converts the generated improvement suggestions into a feedback report in HTML format and sends it to the user's terminal. The improvement suggestions are received as input, and a feedback report is generated as output, which is displayed on the user's terminal. Specifically, the server uses an HTML template engine to construct the report.

[0351] Step 8:

[0352] The user checks the feedback report through the terminal, revises the report if necessary, and uploads it to the system. The input is the report revised by the user based on the feedback, and the output is the revised report that has been uploaded again.

[0353] Step 9:

[0354] The server receives the re-uploaded correction report, compares it with the initial report, and makes further improvement suggestions. The input is the corrected report file, and the output is additional improvement suggestions based on the differential analysis. Specifically, the server compares the previous analysis results with the new analysis results to identify new improvements.

[0355] These steps result in a system that allows users to efficiently create and improve reports while receiving stress-reducing feedback based on emotion recognition.

[0356] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0357] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0358] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0359] [Second embodiment]

[0360] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0361] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0362] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0363] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0364] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0365] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0366] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0367] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0368] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0369] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0370] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0371] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0372] ---

[0373] This invention provides a method for automatically analyzing reports and making improvement suggestions using a system called "Report Master AI." This system analyzes the contents of reports based on report files uploaded by users, generates improvement suggestions, and provides feedback to users.

[0374] Specifically, the system operates as follows.

[0375] 1. Uploading a report: The user selects a report file from the terminal and uploads it to the system, which then transfers the file to the server using the HTTP protocol.

[0376] 2. Receiving and saving reports: The server saves the received report files in temporary storage, which is optimized for smooth subsequent analysis.

[0377] 3. Report preprocessing: The server reads the report file using a specific library (e.g., Pandas library) and converts the data into an appropriate format. For example, if it is an Excel file, it parses the sheet information and cell data and converts it into a data frame.

[0378] 4. Text and Data Analysis: The server uses a natural language processing (NLP) engine to analyze the text in the report, including grammar checks, keyword extraction, and summary generation, as well as correlation and trend analysis of numerical data.

[0379] 5. Generating peer review results: The server integrates the results of the text and data analysis and generates recommendations for improving the structure and content of the report, such as "The introduction to the report lacks background information."

[0380] 6. Providing feedback: The server creates an HTML feedback report based on the generated improvement suggestions and sends it to the user's device. Through this feedback, the user can visually confirm the improvements made to the report.

[0381] 7. Re-upload revised report (optional): The user can revise the report based on the feedback and re-upload it to the system. The server will receive the new report, compare it with the previous feedback and make further improvement suggestions.

[0382] 8. Self-learning function: The server collects and analyzes user feedback and uses that data to update the self-learning algorithm, allowing the system to improve the accuracy of its analysis and improvement suggestions in future sessions.

[0383] The following explains this with specific examples.

[0384] The user uploads an Excel file called "Monthly Sales Report.xlsx" from their device. This file contains sales data and analysis details for each store. The server receives this file and saves it in temporary storage. Next, the PANDAS library reads the Excel file and converts the data in each sheet into a data frame.

[0385] The server uses a natural language processing engine to analyze the text and extract keywords such as "causes of sales decline." At the same time, it performs trend and correlation analysis on the numerical data. Based on the results, the server realizes that "sales have declined compared to the previous year, but the reasons for this have not been specifically stated," and suggests adding specific market and competitive situations.

[0386] These improvement suggestions are sent to the user's device in HTML format, where the user can review the improvements and modify the report. When the modified report is uploaded again, the server compares the differences with the previous version and makes further improvement suggestions. Furthermore, based on user feedback, the self-learning algorithm is improved to improve the accuracy of future analyses.

[0387] In this way, "Report Master AI" effectively supports users in creating and improving reports, helping companies make quick and accurate decisions.

[0388] The processing flow will be explained below.

[0389] ---

[0390] Step 1:

[0391] The user selects a report file (e.g., an Excel file) from the terminal and clicks the upload button. The terminal sends the selected report file to the server via an HTTP POST request.

[0392] Step 2:

[0393] The server parses the received HTTP POST request, retrieves the attached report file, saves the report file in a temporary folder, and records the file path.

[0394] Step 3:

[0395] The server reads the saved report file using the PANDAS library and converts the data into a data frame, which makes the text and numeric data in the report easier to parse.

[0396] Step 4:

[0397] The server uses a natural language processing (NLP) engine to analyze the text in the report, performing operations such as grammar checks, keyword extraction, and summary generation to understand the meaning of the text.

[0398] Step 5:

[0399] The server analyzes the numerical data in the reports, performing correlation and trend analysis to detect significant patterns and outliers. This analysis ensures the reliability of the data.

[0400] Step 6:

[0401] Based on the analysis results, the server generates suggestions for improving the structure and content of the report, such as "This part's explanation is insufficient, so please add specific examples and provide more detail."

[0402] Step 7:

[0403] The server generates improvement suggestions and builds an HTML feedback report that highlights specific areas for improvement.

[0404] Step 8:

[0405] The server sends a feedback report to the user's device, allowing the user to see how the report can be improved, and the user can then revise the report based on this feedback.

[0406] Step 9:

[0407] When the user re-uploads the revised report, the server compares the new report with the previous feedback and makes further suggestions for improvement. The server repeats this process to improve the quality of the report.

[0408] Step 10:

[0409] The server collects user feedback and uses that data to improve the self-learning algorithm, which improves the accuracy of future analyses and improvement suggestions.

[0410] ---

[0411] The above is the specific processing flow of "Report Master AI".

[0412] Example 1

[0413] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0414] Conventional report analysis systems have restrictions on the format and content of report files uploaded by users, making it difficult to efficiently analyze diverse and complex data. Furthermore, the improvement suggestions generated are general and lack specific suggestions for specific issues. Furthermore, the system lacks the ability to effectively utilize user feedback and self-learn, making it difficult to improve the accuracy of the next analysis.

[0415] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0416] In this invention, the server includes means for receiving digital documents from a repository server via communication means, means for storing the received digital documents in a temporary storage device, means for analyzing the digital documents using a program and converting them into data frames, means for analyzing text data in the digital documents using natural language processing technology, means for generating improvement suggestions based on the analysis results, means for visualizing and displaying the generated improvement suggestions, and means for receiving input data from a user and updating the self-learning algorithm. This enables highly accurate analysis of digital documents in a variety of formats, provides specific and effective improvement suggestions, and self-learns using user feedback to improve the accuracy of subsequent analyses.

[0417] "Communication means" refers to an interface function including protocols and technologies for receiving digital documents from a repository server.

[0418] A "repository server" is a server system that stores and manages digital documents and allows access and transfer as needed.

[0419] "Digital documents" refers to files such as electronic reports and reports that exist in various formats (e.g., Excel files, PDFs, Word documents).

[0420] "Temporary storage device" refers to a storage device (e.g., SSD or RAM) for temporarily storing received digital documents.

[0421] A "data frame" is a two-dimensional data structure in the form of rows and columns for storing structured data.

[0422] "Natural language processing technology" is a technology for analyzing and understanding text data, and includes grammar checking, keyword extraction, summary generation, and sentiment analysis.

[0423] "Improvement Suggestion" refers to a specific suggestion for improving or correcting the content of a digital document that is generated based on the analysis of the digital document.

[0424] "Visualization" is the process of visually displaying the analysis results and improvement suggestions for digital documents.

[0425] "Input data" refers to feedback information and additional information entered by the user.

[0426] A "self-learning algorithm" is an algorithm that improves the analysis accuracy of a system based on past analysis results and feedback data.

[0427] The present invention is a system that automatically analyzes digital documents and proposes improvements. This system is particularly capable of handling a wide variety of digital document formats with high accuracy and includes a self-learning function based on user feedback. The following describes its specific operation.

[0428] First, a user selects a digital document from their device and uploads it to the system, where the file is transmitted using the HTTP protocol.

[0429] The server then receives the uploaded digital document and stores it in temporary storage (e.g. SSD), which is optimized for fast loading and processing.

[0430] The server uses the PANDAS library (a Python data analysis library) to read the document and convert the data into a data frame. In the case of an Excel file, the information on each sheet and cell data is parsed and converted into structured data for easier subsequent processing.

[0431] The server then uses a natural language processing engine (e.g., SpaCy or BERT) to analyze the text data in the digital documents, including grammar checks, keyword extraction, summary generation, and sentiment analysis, as well as trend and correlation analysis for numerical data.

[0432] Based on the analysis results, the server generates suggestions for improving the structure and content of the digital document, for example, suggesting that the background information in the introduction of the report is insufficient.

[0433] The generated improvement suggestions are generated as a feedback report in HTML format by the server and sent to the user's terminal. The user can check this feedback in a browser and visually understand the improvements to the report.

[0434] The user can modify the report based on the feedback and upload it back to the system. The server receives the new report, compares it with the previous feedback, and provides further suggestions for improvement.

[0435] Finally, the server analyzes the feedback data from users and updates the self-learning algorithm, which improves the accuracy of the analysis in the future and improves the overall performance of the system.

[0436] As a concrete example, a user uploads "Monthly Sales Report.xlsx." This file contains sales data and analytical details for each store. The server uses the PANDAS library to read this file and convert it into a data frame. It then uses a natural language processing engine to analyze the text and perform trend analysis on the sales data. As a result, the server provides feedback to the user, stating that "sales have decreased compared to the previous year, but the reasons for this have not been specifically stated," and recommends that the user provide a detailed description of the market situation and the competitive situation.

[0437] This feedback report is generated in HTML format and sent to the user's device. The user can make corrections and upload the report again, and the server will provide more accurate improvement suggestions. By repeating this process, the system will continue to learn and improve its analysis accuracy.

[0438] Example prompt sentence:

[0439] Analyze the report file "Monthly Sales Report.xlsx" to clarify the cause of the sales decline and provide suggestions for improvement.

[0440] In this way, the invention accommodates a variety of digital documents and effectively assists users in report analysis and refinement.

[0441] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0442] Step 1: Upload the report file

[0443] The user selects a report file (e.g., "Monthly Sales Report.xlsx") from the terminal and uploads it to the system. As input, the user selects the target file in a file selection dialog. As output, the file is sent to the server using the HTTP protocol.

[0444] Step 2: Receive and temporarily save the report file

[0445] The server receives the uploaded report file. The input is the file data sent by the user. As an output, the server saves the received file to a temporary storage device (SSD). Specifically, the file is saved in the " / tmp / reports / " directory, and the completion of reception is recorded in the server log.

[0446] Step 3: Preprocessing the report file

[0447] The server uses the PANDAS library to read the report file. The input is the file stored in temporary storage. The output is the data converted to a data frame format. Specifically, in the case of an Excel file, the information on each sheet and cell data is analyzed and structured into a data frame.

[0448] Step 4: Analyzing text and numerical data

[0449] The server analyzes text data using a natural language processing engine. The input is a preprocessed data frame. The output is a text summary, keywords, grammar check results, and sentiment analysis results as the analysis results. At the same time, trend analysis and correlation analysis are performed on the numerical data. Specifically, the NLP engine analyzes the text, and the PANDAS library processes the numerical data.

[0450] Step 5: Generate improvement suggestions

[0451] The server generates improvement suggestions based on the analysis results. The input is the analysis results of text and numerical data. The output is specific improvement suggestions. As a specific operation, the server generates specific suggestions such as "The background explanation in the introduction of the report is insufficient."

[0452] Step 6: Provide feedback

[0453] The server creates a feedback report in HTML format based on the generated improvement suggestions. The input is the improvement suggestions. The output is the feedback report. Specifically, the server creates the feedback report and sends it to the user's device. The user then checks the feedback in their browser.

[0454] Step 7: Re-upload the Correction Report (Optional)

[0455] The user modifies the report based on the feedback. The input is the feedback report. The output is the modified report file. Specifically, the user uploads the modified file back to the system. The server receives the new report, compares it with the previous feedback, and provides further improvement suggestions.

[0456] Step 8: Update the self-learning algorithm

[0457] The server analyzes the feedback data from users and updates the self-learning algorithm. The input is the feedback data from users. The output is the updated learning algorithm. Specifically, the system accumulates feedback data and periodically retrains the model to improve the system's analysis accuracy.

[0458] (Application example 1)

[0459] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0460] Factories require the collection and analysis of various process and performance data, and improvement proposals are extremely important for achieving efficient production and quality control. However, the process from data collection to analysis, and the generation and implementation of improvement proposals is often done manually, which is time-consuming and prone to inaccuracies. For this reason, there is a demand for an automated, highly accurate analysis system that can improve factory production efficiency and quality control in real time.

[0461] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0462] In this invention, the server includes means for acquiring a report file, means for analyzing the contents of the report, means for generating improvement proposals based on the analysis results, means for displaying the generated improvement proposals, means for acquiring feedback from users and performing self-learning, means for collecting real-time data from equipment operating in the factory, means for analyzing the collected real-time data, means for generating improvement proposals for the factory equipment based on the analysis results, and means for displaying the generated improvement proposals for the factory equipment on a display device. This makes it possible to automate the series of processes of data collection, analysis, and improvement proposals within the factory, thereby reducing time and improving accuracy.

[0463] A "report file" is a document file that organizes data and information in an organized manner, which may include text, numerical data, graphs, etc.

[0464] "Analysis" is the process of conducting detailed analysis based on collected data and information to clarify their meaning and relationships.

[0465] "Improvement proposals" refer to specific advice and instructions based on the analysis results to improve the current situation, leading to effective problem solving and improved business efficiency.

[0466] A "display device" is a device for visually displaying information. This may include smart glasses or head-mounted displays.

[0467] "User" refers to the person who operates the system, uploads report files, and checks improvement suggestions. This applies to factory managers and engineers.

[0468] "Self-learning" is the process by which machine learning algorithms use feedback data to improve the accuracy of future analyses and suggestions.

[0469] "Factory equipment" refers to various machines and robots used in the production process, which are often equipped with sensors that monitor temperature, pressure, vibration, etc.

[0470] "Real-time data" is dynamic data that records the behavior and state of the object being collected in real time.

[0471] "Analysis results" refers to information and knowledge obtained as a result of analysis based on collected data.

[0472] "Server" refers to a central processing unit for receiving, storing, analyzing report files, and transmitting analysis results.

[0473] This invention applies "Report Master AI" to factories, creating a system that collects and analyzes data in real time, automating the entire process of generating and displaying improvement suggestions.

[0474] Factories are equipped with various sensors that collect real-time data, such as temperature, pressure, and vibration, and the data is sent to a server via Wi-Fi or 5G networks.

[0475] The server first receives the collected data and stores it in temporary storage, then uses the PANDAS library installed on the high-performance server to convert the data into a data frame, which is then prepared for subsequent analysis.

[0476] The analysis uses a generative AI model that applies natural language processing technology. Specifically, the server analyzes the data using a machine learning library (e.g., TensorFlow or PyTorch), while simultaneously generating improvement suggestions using a natural language processing engine (e.g., NLTK or SpaCy). This process detects anomalies in the data, analyzes their causes, and derives specific improvement suggestions.

[0477] Improvement suggestions are written in HTML format and sent to smart glasses or head-mounted displays via Wi-Fi or 5G networks, allowing factory managers and engineers to view the suggestions in real time and take appropriate action on the spot.

[0478] The server also collects user feedback and updates the self-learning algorithm, which improves the accuracy of future analyses and improvement suggestions.

[0479] A specific example is shown below: When an abnormal vibration value is detected based on vibration data collected by a factory robot, the server generates an analysis result and improvement proposals based on that data.

[0480] An example of a prompt is as follows:

[0481] Prompt statement:

[0482] "Analyze the vibration data below, check for any abnormal values, generate any necessary improvement suggestions, and return the improvement suggestions in HTML format."

[0483] Vibration Data:

[0484] Time: 2023-10-01 10:00, Vibration value: 1.2

[0485] Time: 2023-10-01 10:01, Vibration value: 1.4

[0486] Time: 2023-10-01 10:02, Vibration level: 5.6 (abnormal value)

[0487] Desired improvement suggestions:

[0488] "At 10:02, an abnormal vibration value of 5.6 was detected. This vibration is more than twice the normal value. Possible causes include deterioration of the device's components or misalignment. Please perform maintenance immediately and recheck the device's operation."

[0489] In this way, the present invention automates the entire process of data collection, analysis, and improvement proposals within a factory, thereby reducing time and improving accuracy.

[0490] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0491] Step 1:

[0492] Factory equipment collects real-time data such as temperature, pressure, and vibration through sensors. Each sensor captures data about the operation and status of the equipment and records it at regular intervals.

[0493] Input: Sensor data from factory equipment

[0494] Output: Real-time sensor data

[0495] Step 2:

[0496] The device transmits the collected real-time data over Wi-Fi or 5G networks to a server, where the data may be formatted, compressed, etc.

[0497] Input: Real-time sensor data

[0498] Output: Real-time data sent to the server

[0499] Step 3:

[0500] The server stores the received data in temporary storage, where it is converted into a data frame using libraries such as Pandas and processed into a format suitable for analysis.

[0501] Input: Real-time data sent to the server

[0502] Output: Data in data frame format

[0503] Step 4:

[0504] The server analyzes the data using machine learning libraries (e.g., TensorFlow or PyTorch) and uses natural language processing engines (e.g., NLTK or SpaCy) to understand the results and detect abnormal conditions and patterns in the factory equipment.

[0505] Input: Data in data frame format

[0506] Output: Analysis results (including anomaly detection)

[0507] Step 5:

[0508] The server generates improvement suggestions based on the analysis results, which are then converted into a human-readable format using a natural language processing engine.

[0509] Input: Analysis results (including anomaly detection)

[0510] Output: Improvement suggestions expressed in natural language

[0511] Step 6:

[0512] The server constructs the generated improvement suggestions in HTML format and transmits them to smart glasses or head-mounted displays via Wi-Fi or 5G networks.

[0513] Input: Improvement suggestions expressed in natural language

[0514] Output: HTML format improvement suggestions

[0515] Step 7:

[0516] Users can check the improvement suggestions displayed through smart glasses or a head-mounted display and take necessary actions, such as performing maintenance on factory equipment or adjusting settings.

[0517] Input: HTML format improvement suggestions

[0518] Output: User actions (maintenance, configuration adjustments, etc.)

[0519] Step 8:

[0520] The server receives feedback from users and updates its self-learning algorithm, improving the accuracy of future analyses and improvement suggestions.

[0521] Input: User feedback

[0522] Output: Self-learning updated analytical model

[0523] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0524] ---

[0525] This invention provides a system that automatically analyzes reports and proposes improvements by combining a "Report Master AI" with an emotion engine that recognizes user emotions, and provides feedback based on the user's emotions. This system analyzes report files uploaded by users, generates improvement suggestions, and further recognizes the user's emotions when giving feedback using the emotion engine, which can be reflected in the next improvement suggestions.

[0526] Specifically, the system operates as follows.

[0527] 1. Uploading a report: The user selects a report file from the terminal and uploads it to the system. The terminal sends the selected report file to the server via an HTTP POST request.

[0528] 2. Receiving and saving reports: The server saves the received report files in temporary storage, which is optimized for smooth subsequent analysis.

[0529] 3. Report preprocessing: The server reads the report file using a predefined library and converts the data into an appropriate format. For example, if it is an Excel file, it parses the sheet information and cell data and converts it into a data frame.

[0530] 4. Text and Data Analysis: The server uses a natural language processing (NLP) engine to analyze the text in the report, including grammar checks, keyword extraction, and summary generation, as well as correlation and trend analysis of numerical data.

[0531] 5. Generating peer review results: The server integrates the results of the text and data analysis and generates recommendations for improving the structure and content of the report, such as "The introduction to the report lacks background information."

[0532] 6. Emotion Recognition by Emotion Engine: The server uses an emotion engine to recognize the user's emotion in the feedback. This includes analyzing the user's emotional state (e.g., satisfaction, dissatisfaction, confusion, etc.) from their written or spoken words.

[0533] 7. Providing feedback: The server creates an HTML-formatted feedback report based on the generated improvement suggestions and provides feedback in a tone that reflects the user's emotional state. For example, if the user has experienced emotional stress in the past, the server may soften the tone of the feedback.

[0534] 8. Re-upload revised report (optional): The user can revise the report based on the feedback and re-upload it to the system. The server will receive the new report, compare it with the previous feedback, and make further suggestions for improvement.

[0535] 9. Self-learning function: The server collects and analyzes user feedback and emotional data, and uses that data to update the self-learning algorithm, allowing the system to improve the accuracy of its analysis and improvement suggestions in the future.

[0536] The following explains this with specific examples.

[0537] The user uploads an Excel file called "Monthly Sales Report.xlsx" from their device. This file contains sales data and analysis details for each store. The server receives this file and saves it in temporary storage. Next, the PANDAS library reads the Excel file and converts the data in each sheet into a data frame.

[0538] The server uses a natural language processing engine to analyze the text and extract keywords such as "causes of sales decline." At the same time, it performs trend and correlation analysis on the numerical data. Based on the results, the server realizes that "sales have declined compared to the previous year, but the reasons for this have not been specifically stated," and suggests adding specific market and competitive situations.

[0539] Furthermore, an emotion engine is used to analyze user emotions. For example, when a user enters a comment when providing feedback, the system reads the user's emotions from the text and determines whether the improvement proposal is appropriate for the user. If the user is expressing strong dissatisfaction, the system softens the tone of the feedback and provides information in a more understandable format.

[0540] These improvement suggestions are sent to the user's device in HTML format, where the user can review and revise the report. When the revised report is uploaded again, the server compares the differences with the previous version and makes further improvement suggestions. Furthermore, the self-learning algorithm is improved based on user feedback and emotional data, improving the accuracy of subsequent analyses.

[0541] In this way, "Report Master AI" effectively supports users in creating and improving reports, while providing feedback that takes users' emotions into consideration, thereby increasing the usefulness of the system.

[0542] The processing flow will be explained below.

[0543] ---

[0544] Step 1:

[0545] The user selects a report file (e.g., an Excel file) from the terminal and clicks the upload button. The terminal sends the selected report file to the server via an HTTP POST request.

[0546] Step 2:

[0547] The server parses the received HTTP POST request, retrieves the attached report file, saves the report file in a temporary folder, and records the file path.

[0548] Step 3:

[0549] The server reads the saved report file using the PANDAS library and converts the data into a data frame format, which makes the text and numeric data in the report easier to parse.

[0550] Step 4:

[0551] The server uses a natural language processing (NLP) engine to analyze the text in the report, performing operations such as grammar checks, keyword extraction, and summary generation to understand the meaning of the text.

[0552] Step 5:

[0553] The server analyzes the numerical data in the reports, performing correlation and trend analysis to detect significant patterns and outliers. This analysis ensures the reliability of the data.

[0554] Step 6:

[0555] Based on the results of the text and data analysis, the server generates suggestions for improving the structure and content of the report, such as "This part's explanation is insufficient, so please add specific examples and provide more detail."

[0556] Step 7:

[0557] The server uses an emotion engine to recognize the user's emotion when providing feedback. The emotion engine identifies the user's emotional state from the text and voice when the user provides feedback, and analyzes the emotional state.

[0558] Step 8:

[0559] The server adjusts the content and tone of the feedback report based on the user's emotional data obtained from the emotion engine. For example, if the user expresses dissatisfaction, the server softens the feedback and provides additional explanatory comments.

[0560] Step 9:

[0561] The server creates an HTML-formatted feedback report based on the generated improvement suggestions and sends it to the user's device, allowing the user to visually confirm the improvements made to the report.

[0562] Step 10:

[0563] The user then modifies the report based on the feedback and uploads it to the server again from their device. The server compares the new report with the previous feedback and makes suggestions for further improvement.

[0564] Step 11:

[0565] The server collects user feedback and emotional data and uses it to update the self-learning algorithm, allowing the system to improve the accuracy of future analyses and improvement suggestions.

[0566] ---

[0567] The above is the specific processing flow of the system that combines the "Report Master AI" with an emotion engine.

[0568] Example 2

[0569] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0570] Conventional report analysis systems have the ability to analyze report content and provide improvement suggestions, but they lack the ability to provide feedback that takes user emotions into consideration or to self-learn based on user feedback. This limits the system's usefulness because it is unable to provide flexible improvement suggestions that reflect user emotions. Furthermore, limitations on report file formats make it difficult to analyze reports in a variety of formats.

[0571] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0572] In this invention, the server includes a means for acquiring a report file, a means for saving the report file, and a means for reading and converting data in the report file, thereby enabling a means for generating improvement suggestions based on the analysis results, a means for displaying the generated improvement suggestions, a means for acquiring feedback from a user and recognizing the user's emotions, and a means for self-learning based on the feedback.

[0573] "Report file" refers to an electronic document that records reports or data analysis results, and specifically includes formats such as Excel, PDF, and Word.

[0574] The "means of acquisition" refers to an interface or protocol for receiving data from a user terminal, and has functions including HTTP POST requests.

[0575] "Means for storing" refers to storage for temporarily or permanently storing received data, and includes media such as disks and cloud storage.

[0576] "Means to read and transform" refers to the process of converting data in a particular format into an analyzable format, including, for example, the ability to convert Excel data into a data frame using the pandas library.

[0577] "Means of analysis" refers to the process of analyzing the content of data using specific algorithms or technologies and obtaining the results, including natural language processing technology and statistical analysis technology.

[0578] The "means for generating improvement proposals" refers to a function for automatically extracting and proposing improvements to the report based on the analysis results, and includes a proposal generation engine that uses a specific algorithm.

[0579] The "display means" refers to an interface for presenting the generated improvement proposals to the user in an easy-to-understand manner, and includes a feedback report in HTML format.

[0580] "Means for obtaining feedback" refers to the process by which the system collects user ratings and opinions, and includes feedback forms, comment sections, etc.

[0581] "Means for recognizing emotions" refers to technologies that analyze the emotional state of a user from feedback data provided by the user, and includes text analysis and voice analysis.

[0582] "Means for self-learning" refers to the process of improving the system's algorithms using the obtained feedback and emotional data to improve the accuracy of analysis from the next time onwards, and includes machine learning techniques.

[0583] This invention relates to a system that allows users to upload report files, analyzes their contents, and generates improvement suggestions. It also has the ability to analyze the user's feedback and emotional state, adjust the feedback based on that, and perform self-learning. This system uses natural language processing and machine learning technologies to achieve efficient and flexible report improvement.

[0584] System Overview

[0585] Obtaining and saving report files

[0586] The terminal provides an interface for the user to select a report file of their choice and upload it to the system. The user uses a file selection dialog to select the file they want to upload (e.g., "Monthly Sales Report.xlsx"). Once selected, the terminal creates an HTTP POST request and sends it to the server, including the selected file.

[0587] The server receives the HTTP POST request from the terminal and extracts the report file. The extracted file is saved in temporary storage (for example, the / tmp directory). The save location is managed by a unique identifier that includes the file name and timestamp.

[0588] Preprocessing the report file

[0589] The server loads the saved report file using a specific library (for example, the pandas library). If the file is an Excel file, the server converts each sheet and cell data into a data frame. The converted data is temporarily stored in memory in preparation for analysis.

[0590] Text and Data Analysis

[0591] The server uses a natural language processing (NLP) engine and a data analysis engine to analyze the text and numerical data based on each data frame. Specifically, the text is checked for grammar, keywords are extracted, and summaries are generated, while correlation and trend analysis are performed on the numerical data. This results in analysis results from both the content and data aspects of the report.

[0592] Generate improvement suggestions

[0593] The server integrates the results of the text and data analysis and generates specific suggestions for improving the structure and content of the report, such as "the introduction lacks background information" or "add specific market conditions." These suggestions are stored in a temporary database.

[0594] Feedback acquisition and emotion recognition

[0595] The server uses an emotion engine to recognize the user's emotions when providing feedback. This is done by analyzing the text data entered by the user in the feedback form. The analyzed emotion data (e.g., satisfaction, dissatisfaction, confusion, etc.) is reflected in the next feedback and improvement suggestions.

[0596] Providing feedback

[0597] The server generates a feedback report in HTML format based on the generated improvement suggestions and emotional data. The tone of this feedback report is adjusted according to the user's emotional state. For example, if the user has expressed strong dissatisfaction in the past, the tone of the feedback will be softened. The generated feedback report is sent to the terminal and displayed to the user.

[0598] Re-upload the correction report (optional)

[0599] Users can modify their reports based on the feedback and re-upload them, in which case the server receives the new report, compares it with the previous feedback, and makes further suggestions for improvement.

[0600] Self-learning function

[0601] The server collects and analyzes user feedback and emotional data, and uses that data to update the self-learning algorithm, allowing the system to improve the accuracy of future analyses and improvement suggestions.

[0602] Specific examples are shown below.

[0603] Specific examples

[0604] The user uploads an Excel file called "Monthly Sales Report.xlsx" from their device. This file contains sales data and analysis details for each store. The server receives this file and saves it in temporary storage. Next, the pandas library reads the Excel file and converts the data in each sheet into a data frame.

[0605] The server uses a natural language processing engine to analyze the text and extract keywords such as "causes of sales decline." At the same time, it performs trend and correlation analysis on the numerical data. Based on the results, the server realizes that "sales have declined compared to the previous year, but the reasons for this have not been specifically stated," and suggests adding specific market and competitive situations.

[0606] Furthermore, an emotion engine is used to analyze user emotions. For example, when a user enters a comment when providing feedback, the system reads the user's emotions from the text and determines whether the improvement proposal is appropriate for the user. If the user is expressing strong dissatisfaction, the system softens the tone of the feedback and provides information in a more understandable format.

[0607] These improvement suggestions are sent to the user's device in HTML format, where the user can review and revise the report. When the revised report is uploaded again, the server compares the differences with the previous version and makes further improvement suggestions. Furthermore, the self-learning algorithm is improved based on user feedback and emotional data, improving the accuracy of subsequent analyses.

[0608] Prompt Sentence Examples

[0609] Analyze Monthly Sales Report.xlsx and generate improvement suggestions. Adjust the tone of the analysis results based on user feedback.

[0610] In this way, the system of the present invention effectively supports the user in creating and improving reports, while providing feedback that takes into account the user's emotions.

[0611] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0612] Step 1:

[0613] Uploading a report file

[0614] A user selects a specific report file (e.g., "Monthly Sales Report.xlsx") from the terminal and uploads it to the system. The terminal sends the selected report file to the server using an HTTP POST request. The input is the report file selected by the user, and the output is the HTTP POST request sent to the server. Specifically, the terminal opens a file selection dialog, and after the user selects a file, it sends the file to the server as an HTTP POST request.

[0615] Step 2:

[0616] Receiving and saving report files

[0617] The server receives the HTTP POST request from the terminal and extracts the report file. It saves the extracted file in temporary storage (e.g., the / tmp directory). The input is the HTTP POST request, and the output is the saved report file. Specifically, the server analyzes the HTTP request and saves the file in a temporary storage directory.

[0618] Step 3:

[0619] Preprocessing the report file

[0620] The server reads the saved report file using a specified library (e.g., the pandas library). If it is an Excel file, it converts each sheet information and cell data into a data frame. The input is the saved report file, and the output is data in data frame format. Specifically, the server reads the Excel file using the pandas library and converts it into a data frame.

[0621] Step 4:

[0622] Text and Data Analysis

[0623] The server uses a natural language processing (NLP) engine and a data analysis engine to analyze the text and numerical data of the data frame. Specifically, it performs grammar checks, keyword extraction, and summary generation on the text portion, and performs correlation analysis and trend analysis on the numerical data. The input is data in data frame format, and the output is the analysis results. Specifically, the server uses the natural language processing engine to perform text analysis, and the statistical analysis engine to analyze correlations and trends in the numerical data.

[0624] Step 5:

[0625] Generate improvement suggestions

[0626] The server integrates the results of the text and data analysis and generates specific improvement suggestions for the structure and content of the report. For example, it may make suggestions such as "the background explanation in the introduction is insufficient" or "specific market conditions should be added." The input is the analysis results and the output is improvement suggestions. Specifically, the server uses a suggestion generation algorithm based on the analysis results to extract areas for improvement and generate specific suggestions.

[0627] Step 6:

[0628] Feedback acquisition and emotion recognition

[0629] The server receives the user's feedback and recognizes the emotion using the emotion engine. This is done by analyzing the text data the user enters into the feedback form. The input is the user's feedback, and the output is the analyzed emotion data. Specifically, the server receives the feedback form data, performs text analysis, and infers the user's emotion.

[0630] Step 7:

[0631] Providing feedback

[0632] The server generates a feedback report in HTML format based on the generated improvement suggestions and emotion data, and adjusts the tone of the feedback. The generated report is sent to the terminal and displayed to the user. The input is the improvement suggestions and emotion data, and the output is a feedback report in HTML format. Specifically, the server adjusts the tone of the feedback taking into account the emotion data, generates the report in HTML format, and sends it to the terminal.

[0633] Step 8:

[0634] Re-upload the correction report (optional)

[0635] The user can modify the report based on the feedback and upload it again. The server receives the new report, compares it with the previous feedback, and makes further improvement suggestions. The input is the report file modified by the user, and the output is new improvement suggestions. Specifically, the server receives the modified report, processes it in the same way as the initial analysis, and suggests new improvements.

[0636] Step 9:

[0637] Self-learning function

[0638] The server collects and analyzes user feedback and emotional data, and uses that data to update the self-learning algorithm. The input is feedback and emotional data, and the output is the updated algorithm. Specifically, the server adjusts the parameters of the machine learning model based on the collected data, improving the accuracy of future analyses.

[0639] (Application example 2)

[0640] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0641] Conventional report analysis systems can provide objective analysis results and improvement suggestions for created reports, but they lack feedback that takes into account the user's emotional state or consideration for reducing stress caused by emotions. Furthermore, they cannot provide real-time improvement suggestions, which means they cannot be expected to improve work efficiency. In particular, in on-site work environments such as factories, support systems incorporating emotion recognition would be effective, but such systems have not existed.

[0642] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0643] In this invention, the server includes means for acquiring a report file, means for analyzing the contents of the report, means for generating improvement suggestions based on the analysis results, emotion recognition means for recognizing the user's emotion, and means for adjusting the tone of the feedback based on the emotion recognition. This enables feedback that is considerate to the user's emotional state, reducing the user's stress and improving work efficiency through improvement suggestions in real time.

[0644] A "report file" is document data in a report format that is submitted or created by a user.

[0645] "Analysis Means" refers to the technical means for automatically analyzing the contents of the Report File.

[0646] "Improvement proposals" refer to specific proposals for improving the content of the report based on the results obtained by the analysis means.

[0647] "Display means" refers to a device or software for visually displaying the generated improvement proposals.

[0648] "Emotion recognition means" refers to technical means, including voice analysis and facial expression recognition technology, for recognizing a user's emotions.

[0649] "Feedback" refers to the process within the system for collecting opinions and feedback from users.

[0650] "Self-learning means" refers to functions that improve the accuracy of system analysis and improvement suggestions based on collected feedback.

[0651] "Natural language processing technology" refers to a group of computer technologies for analyzing and processing linguistic data.

[0652] "Various formats" refers to including a wide variety of file formats without being limited to a specific file format.

[0653] "Voice analysis" refers to the technology of processing the user's voice as digital data and analyzing its content and emotions.

[0654] "Facial expression recognition" refers to image processing technology for reading emotions from a user's facial image.

[0655] "Real-time" refers to data processing and feedback occurring immediately.

[0656] The present invention is a system that combines emotion recognition means to analyze report files and provide improvement suggestions, with the aim of improving the work efficiency of factory workers.

[0657] The system program operates as follows.

[0658] The server receives the report file uploaded by the user and stores it in temporary storage. The server then uses an analysis means to analyze the contents of the report file and generates improvement suggestions based on the analysis results. This analysis uses natural language processing technology to analyze the text in the report. The server also uses an emotion recognition means to detect the user's emotions through voice analysis and facial expression recognition.

[0659] Specifically, the server uses software libraries such as OpenCV and SpeechRecognition to analyze the user's camera footage and audio data. This allows it to read emotions from the user's facial expressions and speech. The analyzed emotional data is reflected in the tone of the improvement suggestions, allowing the user to receive feedback without feeling stressed.

[0660] The improvement proposals are generated in HTML format and provided to the user through a display means, allowing the user to check the analysis results and improvement proposals in real time. Furthermore, feedback from users is collected and the system's accuracy is improved through self-learning means.

[0661] As a concrete example, consider a scenario in which an Excel file called "Monthly Sales Report.xlsx" is uploaded. The user uploads "Monthly Sales Report.xlsx" to the system. The server receives this file and stores it in temporary storage. Next, the Pandas library is used to read the Excel file and convert it into a data frame. TextBlob is used to analyze the sentiment in the text, and OpenCV and SpeechRecognition are used to analyze the voice and facial expression. Finally, improvement suggestions based on the analysis results are generated in HTML format and provided to the user.

[0662] An example prompt might be something like, "Please upload Monthly Sales Report.xlsx. We'll provide you with analysis of the report and feedback based on your sentiment."

[0663] As described above, the present invention provides a report analysis and improvement proposal system that combines emotion recognition means, and contributes to improving the efficiency of factory work and reducing worker stress.

[0664] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0665] Step 1:

[0666] The user uses a terminal to select a report file and upload it to the system. As input, the user provides a report file (e.g., "Monthly Sales Report.xlsx"), and the output is that the server receives this file.

[0667] Step 2:

[0668] The server stores the received report file in temporary storage. It receives the uploaded report file as input and generates a file stored in temporary storage as output.

[0669] Step 3:

[0670] The server uses the Pandas library to convert the saved Excel file into a data frame. The input is the report file in temporary storage, and the output is data in data frame format. Specifically, the server calls the Pandas read_excel function to read the sheet information and cell data.

[0671] Step 4:

[0672] The server uses the TextBlob library to analyze the text in the data frame. The input is the text data in the data frame, and the output is the sentiment analysis results and keyword extraction results. Specifically, the server evaluates the sentiment of the text using the sentiment function of TextBlob.

[0673] Step 5:

[0674] The server uses OpenCV and the SpeechRecognition library to acquire the user's camera video and audio data and recognize emotions. The input is the camera video and audio data, and the output is the user's emotional state. Specifically, the server captures the camera video, records the audio, and passes this data to the analysis engine.

[0675] Step 6:

[0676] The server generates improvement suggestions based on the text analysis results and emotion recognition results. It receives the text analysis results, emotional state, and existing feedback as input, and generates a feedback report with adjusted tone as output. Specifically, the server integrates the analysis results and constructs specific improvement suggestions.

[0677] Step 7:

[0678] The server converts the generated improvement suggestions into a feedback report in HTML format and sends it to the user's terminal. The improvement suggestions are received as input, and a feedback report is generated as output, which is displayed on the user's terminal. Specifically, the server uses an HTML template engine to construct the report.

[0679] Step 8:

[0680] The user checks the feedback report through the terminal, revises the report if necessary, and uploads it to the system. The input is the report revised by the user based on the feedback, and the output is the revised report that has been uploaded again.

[0681] Step 9:

[0682] The server receives the re-uploaded correction report, compares it with the initial report, and makes further improvement suggestions. The input is the corrected report file, and the output is additional improvement suggestions based on the differential analysis. Specifically, the server compares the previous analysis results with the new analysis results to identify new improvements.

[0683] These steps result in a system that allows users to efficiently create and improve reports while receiving stress-reducing feedback based on emotion recognition.

[0684] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0685] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0686] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0687] [Third embodiment]

[0688] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0689] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0690] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0691] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0692] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0693] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0694] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0695] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0696] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0697] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0698] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0699] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0700] ---

[0701] This invention provides a method for automatically analyzing reports and making improvement suggestions using a system called "Report Master AI." This system analyzes the contents of reports based on report files uploaded by users, generates improvement suggestions, and provides feedback to users.

[0702] Specifically, the system operates as follows.

[0703] 1. Uploading a report: The user selects a report file from the terminal and uploads it to the system, which then transfers the file to the server using the HTTP protocol.

[0704] 2. Receiving and saving reports: The server saves the received report files in temporary storage, which is optimized for smooth subsequent analysis.

[0705] 3. Report preprocessing: The server reads the report file using a specific library (e.g., Pandas library) and converts the data into an appropriate format. For example, if it is an Excel file, it parses the sheet information and cell data and converts it into a data frame.

[0706] 4. Text and Data Analysis: The server uses a natural language processing (NLP) engine to analyze the text in the report, including grammar checks, keyword extraction, and summary generation, as well as correlation and trend analysis of numerical data.

[0707] 5. Generating peer review results: The server integrates the results of the text and data analysis and generates recommendations for improving the structure and content of the report, such as "The introduction to the report lacks background information."

[0708] 6. Providing feedback: The server creates an HTML feedback report based on the generated improvement suggestions and sends it to the user's device. Through this feedback, the user can visually confirm the improvements made to the report.

[0709] 7. Re-upload revised report (optional): The user can revise the report based on the feedback and re-upload it to the system. The server will receive the new report, compare it with the previous feedback and make further improvement suggestions.

[0710] 8. Self-learning function: The server collects and analyzes user feedback and uses that data to update the self-learning algorithm, allowing the system to improve the accuracy of its analysis and improvement suggestions in future sessions.

[0711] The following explains this with specific examples.

[0712] The user uploads an Excel file called "Monthly Sales Report.xlsx" from their device. This file contains sales data and analysis details for each store. The server receives this file and saves it in temporary storage. Next, the PANDAS library reads the Excel file and converts the data in each sheet into a data frame.

[0713] The server uses a natural language processing engine to analyze the text and extract keywords such as "causes of sales decline." At the same time, it performs trend and correlation analysis on the numerical data. Based on the results, the server realizes that "sales have declined compared to the previous year, but the reasons for this have not been specifically stated," and suggests adding specific market and competitive situations.

[0714] These improvement suggestions are sent to the user's device in HTML format, where the user can review the improvements and modify the report. When the modified report is uploaded again, the server compares the differences with the previous version and makes further improvement suggestions. Furthermore, based on user feedback, the self-learning algorithm is improved to improve the accuracy of future analyses.

[0715] In this way, "Report Master AI" effectively supports users in creating and improving reports, helping companies make quick and accurate decisions.

[0716] The processing flow will be explained below.

[0717] ---

[0718] Step 1:

[0719] The user selects a report file (e.g., an Excel file) from the terminal and clicks the upload button. The terminal sends the selected report file to the server via an HTTP POST request.

[0720] Step 2:

[0721] The server parses the received HTTP POST request, retrieves the attached report file, saves the report file in a temporary folder, and records the file path.

[0722] Step 3:

[0723] The server reads the saved report file using the PANDAS library and converts the data into a data frame, which makes the text and numeric data in the report easier to parse.

[0724] Step 4:

[0725] The server uses a natural language processing (NLP) engine to analyze the text in the report, performing operations such as grammar checks, keyword extraction, and summary generation to understand the meaning of the text.

[0726] Step 5:

[0727] The server analyzes the numerical data in the reports, performing correlation and trend analysis to detect significant patterns and outliers. This analysis ensures the reliability of the data.

[0728] Step 6:

[0729] Based on the analysis results, the server generates suggestions for improving the structure and content of the report, such as "This part's explanation is insufficient, so please add specific examples and provide more detail."

[0730] Step 7:

[0731] The server generates improvement suggestions and builds an HTML feedback report that highlights specific areas for improvement.

[0732] Step 8:

[0733] The server sends a feedback report to the user's device, allowing the user to see how the report can be improved, and the user can then revise the report based on this feedback.

[0734] Step 9:

[0735] When the user re-uploads the revised report, the server compares the new report with the previous feedback and makes further suggestions for improvement. The server repeats this process to improve the quality of the report.

[0736] Step 10:

[0737] The server collects user feedback and uses that data to improve the self-learning algorithm, which improves the accuracy of future analyses and improvement suggestions.

[0738] ---

[0739] The above is the specific processing flow of "Report Master AI".

[0740] Example 1

[0741] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0742] Conventional report analysis systems have restrictions on the format and content of report files uploaded by users, making it difficult to efficiently analyze diverse and complex data. Furthermore, the improvement suggestions generated are general and lack specific suggestions for specific issues. Furthermore, the system lacks the ability to effectively utilize user feedback and self-learn, making it difficult to improve the accuracy of the next analysis.

[0743] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0744] In this invention, the server includes means for receiving digital documents from a repository server via communication means, means for storing the received digital documents in a temporary storage device, means for analyzing the digital documents using a program and converting them into data frames, means for analyzing text data in the digital documents using natural language processing technology, means for generating improvement suggestions based on the analysis results, means for visualizing and displaying the generated improvement suggestions, and means for receiving input data from a user and updating the self-learning algorithm. This enables highly accurate analysis of digital documents in a variety of formats, provides specific and effective improvement suggestions, and self-learns using user feedback to improve the accuracy of subsequent analyses.

[0745] "Communication means" refers to an interface function including protocols and technologies for receiving digital documents from a repository server.

[0746] A "repository server" is a server system that stores and manages digital documents and allows access and transfer as needed.

[0747] "Digital documents" refers to files such as electronic reports and reports that exist in various formats (e.g., Excel files, PDFs, Word documents).

[0748] "Temporary storage device" refers to a storage device (e.g., SSD or RAM) for temporarily storing received digital documents.

[0749] A "data frame" is a two-dimensional data structure in the form of rows and columns for storing structured data.

[0750] "Natural language processing technology" is a technology for analyzing and understanding text data, and includes grammar checking, keyword extraction, summary generation, and sentiment analysis.

[0751] "Improvement Suggestion" refers to a specific suggestion for improving or correcting the content of a digital document that is generated based on the analysis of the digital document.

[0752] "Visualization" is the process of visually displaying the analysis results and improvement suggestions for digital documents.

[0753] "Input data" refers to feedback information and additional information entered by the user.

[0754] A "self-learning algorithm" is an algorithm that improves the analysis accuracy of a system based on past analysis results and feedback data.

[0755] The present invention is a system that automatically analyzes digital documents and proposes improvements. This system is particularly capable of handling a wide variety of digital document formats with high accuracy and includes a self-learning function based on user feedback. The following describes its specific operation.

[0756] First, a user selects a digital document from their device and uploads it to the system, where the file is transmitted using the HTTP protocol.

[0757] The server then receives the uploaded digital document and stores it in temporary storage (e.g. SSD), which is optimized for fast loading and processing.

[0758] The server uses the PANDAS library (a Python data analysis library) to read the document and convert the data into a data frame. In the case of an Excel file, the information on each sheet and cell data is parsed and converted into structured data for easier subsequent processing.

[0759] The server then uses a natural language processing engine (e.g., SpaCy or BERT) to analyze the text data in the digital documents, including grammar checks, keyword extraction, summary generation, and sentiment analysis, as well as trend and correlation analysis for numerical data.

[0760] Based on the analysis results, the server generates suggestions for improving the structure and content of the digital document, for example, suggesting that the background information in the introduction of the report is insufficient.

[0761] The generated improvement suggestions are generated as a feedback report in HTML format by the server and sent to the user's terminal. The user can check this feedback in a browser and visually understand the improvements to the report.

[0762] The user can modify the report based on the feedback and upload it back to the system. The server receives the new report, compares it with the previous feedback, and provides further suggestions for improvement.

[0763] Finally, the server analyzes the feedback data from users and updates the self-learning algorithm, which improves the accuracy of the analysis in the future and improves the overall performance of the system.

[0764] As a concrete example, a user uploads "Monthly Sales Report.xlsx." This file contains sales data and analytical details for each store. The server uses the PANDAS library to read this file and convert it into a data frame. It then uses a natural language processing engine to analyze the text and perform trend analysis on the sales data. As a result, the server provides feedback to the user, stating that "sales have decreased compared to the previous year, but the reasons for this have not been specifically stated," and recommends that the user provide a detailed description of the market situation and the competitive situation.

[0765] This feedback report is generated in HTML format and sent to the user's device. The user can make corrections and upload the report again, and the server will provide more accurate improvement suggestions. By repeating this process, the system will continue to learn and improve its analysis accuracy.

[0766] Example prompt sentence:

[0767] Analyze the report file "Monthly Sales Report.xlsx" to clarify the cause of the sales decline and provide suggestions for improvement.

[0768] In this way, the invention accommodates a variety of digital documents and effectively assists users in report analysis and refinement.

[0769] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0770] Step 1: Upload the report file

[0771] The user selects a report file (e.g., "Monthly Sales Report.xlsx") from the terminal and uploads it to the system. As input, the user selects the target file in a file selection dialog. As output, the file is sent to the server using the HTTP protocol.

[0772] Step 2: Receive and temporarily save the report file

[0773] The server receives the uploaded report file. The input is the file data sent by the user. As an output, the server saves the received file to a temporary storage device (SSD). Specifically, the file is saved in the " / tmp / reports / " directory, and the completion of reception is recorded in the server log.

[0774] Step 3: Preprocessing the report file

[0775] The server uses the PANDAS library to read the report file. The input is the file stored in temporary storage. The output is the data converted to a data frame format. Specifically, in the case of an Excel file, the information on each sheet and cell data is analyzed and structured into a data frame.

[0776] Step 4: Analyzing text and numerical data

[0777] The server analyzes text data using a natural language processing engine. The input is a preprocessed data frame. The output is a text summary, keywords, grammar check results, and sentiment analysis results as the analysis results. At the same time, trend analysis and correlation analysis are performed on the numerical data. Specifically, the NLP engine analyzes the text, and the PANDAS library processes the numerical data.

[0778] Step 5: Generate improvement suggestions

[0779] The server generates improvement suggestions based on the analysis results. The input is the analysis results of text and numerical data. The output is specific improvement suggestions. As a specific operation, the server generates specific suggestions such as "The background explanation in the introduction of the report is insufficient."

[0780] Step 6: Provide feedback

[0781] The server creates a feedback report in HTML format based on the generated improvement suggestions. The input is the improvement suggestions. The output is the feedback report. Specifically, the server creates the feedback report and sends it to the user's device. The user then checks the feedback in their browser.

[0782] Step 7: Re-upload the Correction Report (Optional)

[0783] The user modifies the report based on the feedback. The input is the feedback report. The output is the modified report file. Specifically, the user uploads the modified file back to the system. The server receives the new report, compares it with the previous feedback, and provides further improvement suggestions.

[0784] Step 8: Update the self-learning algorithm

[0785] The server analyzes the feedback data from users and updates the self-learning algorithm. The input is the feedback data from users. The output is the updated learning algorithm. Specifically, the system accumulates feedback data and periodically retrains the model to improve the system's analysis accuracy.

[0786] (Application example 1)

[0787] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0788] Factories require the collection and analysis of various process and performance data, and improvement proposals are extremely important for achieving efficient production and quality control. However, the process from data collection to analysis, and the generation and implementation of improvement proposals is often done manually, which is time-consuming and prone to inaccuracies. For this reason, there is a demand for an automated, highly accurate analysis system that can improve factory production efficiency and quality control in real time.

[0789] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0790] In this invention, the server includes means for acquiring a report file, means for analyzing the contents of the report, means for generating improvement proposals based on the analysis results, means for displaying the generated improvement proposals, means for acquiring feedback from users and performing self-learning, means for collecting real-time data from equipment operating in the factory, means for analyzing the collected real-time data, means for generating improvement proposals for the factory equipment based on the analysis results, and means for displaying the generated improvement proposals for the factory equipment on a display device. This makes it possible to automate the series of processes of data collection, analysis, and improvement proposals within the factory, thereby reducing time and improving accuracy.

[0791] A "report file" is a document file that organizes data and information in an organized manner, which may include text, numerical data, graphs, etc.

[0792] "Analysis" is the process of conducting detailed analysis based on collected data and information to clarify their meaning and relationships.

[0793] "Improvement proposals" refer to specific advice and instructions based on the analysis results to improve the current situation, leading to effective problem solving and improved business efficiency.

[0794] A "display device" is a device for visually displaying information. This may include smart glasses or head-mounted displays.

[0795] "User" refers to the person who operates the system, uploads report files, and checks improvement suggestions. This applies to factory managers and engineers.

[0796] "Self-learning" is the process by which machine learning algorithms use feedback data to improve the accuracy of future analyses and suggestions.

[0797] "Factory equipment" refers to various machines and robots used in the production process, which are often equipped with sensors that monitor temperature, pressure, vibration, etc.

[0798] "Real-time data" is dynamic data that records the behavior and state of the object being collected in real time.

[0799] "Analysis results" refers to information and knowledge obtained as a result of analysis based on collected data.

[0800] "Server" refers to a central processing unit for receiving, storing, analyzing report files, and transmitting analysis results.

[0801] This invention applies "Report Master AI" to factories, creating a system that collects and analyzes data in real time, automating the entire process of generating and displaying improvement suggestions.

[0802] Factories are equipped with various sensors that collect real-time data, such as temperature, pressure, and vibration, and the data is sent to a server via Wi-Fi or 5G networks.

[0803] The server first receives the collected data and stores it in temporary storage, then uses the PANDAS library installed on the high-performance server to convert the data into a data frame, which is then prepared for subsequent analysis.

[0804] The analysis uses a generative AI model that applies natural language processing technology. Specifically, the server analyzes the data using a machine learning library (e.g., TensorFlow or PyTorch), while simultaneously generating improvement suggestions using a natural language processing engine (e.g., NLTK or SpaCy). This process detects anomalies in the data, analyzes their causes, and derives specific improvement suggestions.

[0805] Improvement suggestions are written in HTML format and sent to smart glasses or head-mounted displays via Wi-Fi or 5G networks, allowing factory managers and engineers to view the suggestions in real time and take appropriate action on the spot.

[0806] The server also collects user feedback and updates the self-learning algorithm, which improves the accuracy of future analyses and improvement suggestions.

[0807] A specific example is shown below: When an abnormal vibration value is detected based on vibration data collected by a factory robot, the server generates an analysis result and improvement proposals based on that data.

[0808] An example of a prompt is as follows:

[0809] Prompt statement:

[0810] "Analyze the vibration data below, check for any abnormal values, generate any necessary improvement suggestions, and return the improvement suggestions in HTML format."

[0811] Vibration Data:

[0812] Time: 2023-10-01 10:00, Vibration value: 1.2

[0813] Time: 2023-10-01 10:01, Vibration value: 1.4

[0814] Time: 2023-10-01 10:02, Vibration level: 5.6 (abnormal value)

[0815] Desired improvement suggestions:

[0816] "At 10:02, an abnormal vibration value of 5.6 was detected. This vibration is more than twice the normal value. Possible causes include deterioration of the device's components or misalignment. Please perform maintenance immediately and recheck the device's operation."

[0817] In this way, the present invention automates the entire process of data collection, analysis, and improvement proposals within a factory, thereby reducing time and improving accuracy.

[0818] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0819] Step 1:

[0820] Factory equipment collects real-time data such as temperature, pressure, and vibration through sensors. Each sensor captures data about the operation and status of the equipment and records it at regular intervals.

[0821] Input: Sensor data from factory equipment

[0822] Output: Real-time sensor data

[0823] Step 2:

[0824] The device transmits the collected real-time data over Wi-Fi or 5G networks to a server, where the data may be formatted, compressed, etc.

[0825] Input: Real-time sensor data

[0826] Output: Real-time data sent to the server

[0827] Step 3:

[0828] The server stores the received data in temporary storage, where it is converted into a data frame using libraries such as Pandas and processed into a format suitable for analysis.

[0829] Input: Real-time data sent to the server

[0830] Output: Data in data frame format

[0831] Step 4:

[0832] The server analyzes the data using machine learning libraries (e.g., TensorFlow or PyTorch) and uses natural language processing engines (e.g., NLTK or SpaCy) to understand the results and detect abnormal conditions and patterns in the factory equipment.

[0833] Input: Data in data frame format

[0834] Output: Analysis results (including anomaly detection)

[0835] Step 5:

[0836] The server generates improvement suggestions based on the analysis results, which are then converted into a human-readable format using a natural language processing engine.

[0837] Input: Analysis results (including anomaly detection)

[0838] Output: Improvement suggestions expressed in natural language

[0839] Step 6:

[0840] The server constructs the generated improvement suggestions in HTML format and transmits them to smart glasses or head-mounted displays via Wi-Fi or 5G networks.

[0841] Input: Improvement suggestions expressed in natural language

[0842] Output: HTML format improvement suggestions

[0843] Step 7:

[0844] Users can check the improvement suggestions displayed through smart glasses or a head-mounted display and take necessary actions, such as performing maintenance on factory equipment or adjusting settings.

[0845] Input: HTML format improvement suggestions

[0846] Output: User actions (maintenance, configuration adjustments, etc.)

[0847] Step 8:

[0848] The server receives feedback from users and updates its self-learning algorithm, improving the accuracy of future analyses and improvement suggestions.

[0849] Input: User feedback

[0850] Output: Self-learning updated analytical model

[0851] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0852] ---

[0853] This invention provides a system that automatically analyzes reports and proposes improvements by combining a "Report Master AI" with an emotion engine that recognizes user emotions, and provides feedback based on the user's emotions. This system analyzes report files uploaded by users, generates improvement suggestions, and further recognizes the user's emotions when giving feedback using the emotion engine, which can be reflected in the next improvement suggestions.

[0854] Specifically, the system operates as follows.

[0855] 1. Uploading a report: The user selects a report file from the terminal and uploads it to the system. The terminal sends the selected report file to the server via an HTTP POST request.

[0856] 2. Receiving and saving reports: The server saves the received report files in temporary storage, which is optimized for smooth subsequent analysis.

[0857] 3. Report preprocessing: The server reads the report file using a predefined library and converts the data into an appropriate format. For example, if it is an Excel file, it parses the sheet information and cell data and converts it into a data frame.

[0858] 4. Text and Data Analysis: The server uses a natural language processing (NLP) engine to analyze the text in the report, including grammar checks, keyword extraction, and summary generation, as well as correlation and trend analysis of numerical data.

[0859] 5. Generating peer review results: The server integrates the results of the text and data analysis and generates recommendations for improving the structure and content of the report, such as "The introduction to the report lacks background information."

[0860] 6. Emotion Recognition by Emotion Engine: The server uses an emotion engine to recognize the user's emotion in the feedback. This includes analyzing the user's emotional state (e.g., satisfaction, dissatisfaction, confusion, etc.) from their written or spoken words.

[0861] 7. Providing feedback: The server creates an HTML-formatted feedback report based on the generated improvement suggestions and provides feedback in a tone that reflects the user's emotional state. For example, if the user has experienced emotional stress in the past, the server may soften the tone of the feedback.

[0862] 8. Re-upload revised report (optional): The user can revise the report based on the feedback and re-upload it to the system. The server will receive the new report, compare it with the previous feedback, and make further suggestions for improvement.

[0863] 9. Self-learning function: The server collects and analyzes user feedback and emotional data, and uses that data to update the self-learning algorithm, allowing the system to improve the accuracy of its analysis and improvement suggestions in the future.

[0864] The following explains this with specific examples.

[0865] The user uploads an Excel file called "Monthly Sales Report.xlsx" from their device. This file contains sales data and analysis details for each store. The server receives this file and saves it in temporary storage. Next, the PANDAS library reads the Excel file and converts the data in each sheet into a data frame.

[0866] The server uses a natural language processing engine to analyze the text and extract keywords such as "causes of sales decline." At the same time, it performs trend and correlation analysis on the numerical data. Based on the results, the server realizes that "sales have declined compared to the previous year, but the reasons for this have not been specifically stated," and suggests adding specific market and competitive situations.

[0867] Furthermore, an emotion engine is used to analyze user emotions. For example, when a user enters a comment when providing feedback, the system reads the user's emotions from the text and determines whether the improvement proposal is appropriate for the user. If the user is expressing strong dissatisfaction, the system softens the tone of the feedback and provides information in a more understandable format.

[0868] These improvement suggestions are sent to the user's device in HTML format, where the user can review and revise the report. When the revised report is uploaded again, the server compares the differences with the previous version and makes further improvement suggestions. Furthermore, the self-learning algorithm is improved based on user feedback and emotional data, improving the accuracy of subsequent analyses.

[0869] In this way, "Report Master AI" effectively supports users in creating and improving reports, while providing feedback that takes users' emotions into consideration, thereby increasing the usefulness of the system.

[0870] The processing flow will be explained below.

[0871] ---

[0872] Step 1:

[0873] The user selects a report file (e.g., an Excel file) from the terminal and clicks the upload button. The terminal sends the selected report file to the server via an HTTP POST request.

[0874] Step 2:

[0875] The server parses the received HTTP POST request, retrieves the attached report file, saves the report file in a temporary folder, and records the file path.

[0876] Step 3:

[0877] The server reads the saved report file using the PANDAS library and converts the data into a data frame format, which makes the text and numeric data in the report easier to parse.

[0878] Step 4:

[0879] The server uses a natural language processing (NLP) engine to analyze the text in the report, performing operations such as grammar checks, keyword extraction, and summary generation to understand the meaning of the text.

[0880] Step 5:

[0881] The server analyzes the numerical data in the reports, performing correlation and trend analysis to detect significant patterns and outliers. This analysis ensures the reliability of the data.

[0882] Step 6:

[0883] Based on the results of the text and data analysis, the server generates suggestions for improving the structure and content of the report, such as "This part's explanation is insufficient, so please add specific examples and provide more detail."

[0884] Step 7:

[0885] The server uses an emotion engine to recognize the user's emotion when providing feedback. The emotion engine identifies the user's emotional state from the text and voice when the user provides feedback, and analyzes the emotional state.

[0886] Step 8:

[0887] The server adjusts the content and tone of the feedback report based on the user's emotional data obtained from the emotion engine. For example, if the user expresses dissatisfaction, the server softens the feedback and provides additional explanatory comments.

[0888] Step 9:

[0889] The server creates an HTML-formatted feedback report based on the generated improvement suggestions and sends it to the user's device, allowing the user to visually confirm the improvements made to the report.

[0890] Step 10:

[0891] The user then modifies the report based on the feedback and uploads it to the server again from their device. The server compares the new report with the previous feedback and makes suggestions for further improvement.

[0892] Step 11:

[0893] The server collects user feedback and emotional data and uses it to update the self-learning algorithm, allowing the system to improve the accuracy of future analyses and improvement suggestions.

[0894] ---

[0895] The above is the specific processing flow of the system that combines the "Report Master AI" with an emotion engine.

[0896] Example 2

[0897] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0898] Conventional report analysis systems have the ability to analyze report content and provide improvement suggestions, but they lack the ability to provide feedback that takes user emotions into consideration or to self-learn based on user feedback. This limits the system's usefulness because it is unable to provide flexible improvement suggestions that reflect user emotions. Furthermore, limitations on report file formats make it difficult to analyze reports in a variety of formats.

[0899] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0900] In this invention, the server includes a means for acquiring a report file, a means for saving the report file, and a means for reading and converting data in the report file, thereby enabling a means for generating improvement suggestions based on the analysis results, a means for displaying the generated improvement suggestions, a means for acquiring feedback from a user and recognizing the user's emotions, and a means for self-learning based on the feedback.

[0901] "Report file" refers to an electronic document that records reports or data analysis results, and specifically includes formats such as Excel, PDF, and Word.

[0902] The "means of acquisition" refers to an interface or protocol for receiving data from a user terminal, and has functions including HTTP POST requests.

[0903] "Means for storing" refers to storage for temporarily or permanently storing received data, and includes media such as disks and cloud storage.

[0904] "Means to read and transform" refers to the process of converting data in a particular format into an analyzable format, including, for example, the ability to convert Excel data into a data frame using the pandas library.

[0905] "Means of analysis" refers to the process of analyzing the content of data using specific algorithms or technologies and obtaining the results, including natural language processing technology and statistical analysis technology.

[0906] The "means for generating improvement proposals" refers to a function for automatically extracting and proposing improvements to the report based on the analysis results, and includes a proposal generation engine that uses a specific algorithm.

[0907] The "display means" refers to an interface for presenting the generated improvement proposals to the user in an easy-to-understand manner, and includes a feedback report in HTML format.

[0908] "Means for obtaining feedback" refers to the process by which the system collects user ratings and opinions, and includes feedback forms, comment sections, etc.

[0909] "Means for recognizing emotions" refers to technologies that analyze the emotional state of a user from feedback data provided by the user, and includes text analysis and voice analysis.

[0910] "Means for self-learning" refers to the process of improving the system's algorithms using the obtained feedback and emotional data to improve the accuracy of analysis from the next time onwards, and includes machine learning techniques.

[0911] This invention relates to a system that allows users to upload report files, analyzes their contents, and generates improvement suggestions. It also has the ability to analyze the user's feedback and emotional state, adjust the feedback based on that, and perform self-learning. This system uses natural language processing and machine learning technologies to achieve efficient and flexible report improvement.

[0912] System Overview

[0913] Obtaining and saving report files

[0914] The terminal provides an interface for the user to select a report file of their choice and upload it to the system. The user uses a file selection dialog to select the file they want to upload (e.g., "Monthly Sales Report.xlsx"). Once selected, the terminal creates an HTTP POST request and sends it to the server, including the selected file.

[0915] The server receives the HTTP POST request from the terminal and extracts the report file. The extracted file is saved in temporary storage (for example, the / tmp directory). The save location is managed by a unique identifier that includes the file name and timestamp.

[0916] Preprocessing the report file

[0917] The server loads the saved report file using a specific library (for example, the pandas library). If the file is an Excel file, the server converts each sheet and cell data into a data frame. The converted data is temporarily stored in memory in preparation for analysis.

[0918] Text and Data Analysis

[0919] The server uses a natural language processing (NLP) engine and a data analysis engine to analyze the text and numerical data based on each data frame. Specifically, the text is checked for grammar, keywords are extracted, and summaries are generated, while correlation and trend analysis are performed on the numerical data. This results in analysis results from both the content and data aspects of the report.

[0920] Generate improvement suggestions

[0921] The server integrates the results of the text and data analysis and generates specific suggestions for improving the structure and content of the report, such as "the introduction lacks background information" or "add specific market conditions." These suggestions are stored in a temporary database.

[0922] Feedback acquisition and emotion recognition

[0923] The server uses an emotion engine to recognize the user's emotions when providing feedback. This is done by analyzing the text data entered by the user in the feedback form. The analyzed emotion data (e.g., satisfaction, dissatisfaction, confusion, etc.) is reflected in the next feedback and improvement suggestions.

[0924] Providing feedback

[0925] The server generates a feedback report in HTML format based on the generated improvement suggestions and emotional data. The tone of this feedback report is adjusted according to the user's emotional state. For example, if the user has expressed strong dissatisfaction in the past, the tone of the feedback will be softened. The generated feedback report is sent to the terminal and displayed to the user.

[0926] Re-upload the correction report (optional)

[0927] Users can modify their reports based on the feedback and re-upload them, in which case the server receives the new report, compares it with the previous feedback, and makes further suggestions for improvement.

[0928] Self-learning function

[0929] The server collects and analyzes user feedback and emotional data, and uses that data to update the self-learning algorithm, allowing the system to improve the accuracy of future analyses and improvement suggestions.

[0930] Specific examples are shown below.

[0931] Specific examples

[0932] The user uploads an Excel file called "Monthly Sales Report.xlsx" from their device. This file contains sales data and analysis details for each store. The server receives this file and saves it in temporary storage. Next, the pandas library reads the Excel file and converts the data in each sheet into a data frame.

[0933] The server uses a natural language processing engine to analyze the text and extract keywords such as "causes of sales decline." At the same time, it performs trend and correlation analysis on the numerical data. Based on the results, the server realizes that "sales have declined compared to the previous year, but the reasons for this have not been specifically stated," and suggests adding specific market and competitive situations.

[0934] Furthermore, an emotion engine is used to analyze user emotions. For example, when a user enters a comment when providing feedback, the system reads the user's emotions from the text and determines whether the improvement proposal is appropriate for the user. If the user is expressing strong dissatisfaction, the system softens the tone of the feedback and provides information in a more understandable format.

[0935] These improvement suggestions are sent to the user's device in HTML format, where the user can review and revise the report. When the revised report is uploaded again, the server compares the differences with the previous version and makes further improvement suggestions. Furthermore, the self-learning algorithm is improved based on user feedback and emotional data, improving the accuracy of subsequent analyses.

[0936] Prompt Sentence Examples

[0937] Analyze Monthly Sales Report.xlsx and generate improvement suggestions. Adjust the tone of the analysis results based on user feedback.

[0938] In this way, the system of the present invention effectively supports the user in creating and improving reports, while providing feedback that takes into account the user's emotions.

[0939] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0940] Step 1:

[0941] Uploading a report file

[0942] A user selects a specific report file (e.g., "Monthly Sales Report.xlsx") from the terminal and uploads it to the system. The terminal sends the selected report file to the server using an HTTP POST request. The input is the report file selected by the user, and the output is the HTTP POST request sent to the server. Specifically, the terminal opens a file selection dialog, and after the user selects a file, it sends the file to the server as an HTTP POST request.

[0943] Step 2:

[0944] Receiving and saving report files

[0945] The server receives the HTTP POST request from the terminal and extracts the report file. It saves the extracted file in temporary storage (e.g., the / tmp directory). The input is the HTTP POST request, and the output is the saved report file. Specifically, the server analyzes the HTTP request and saves the file in a temporary storage directory.

[0946] Step 3:

[0947] Preprocessing the report file

[0948] The server reads the saved report file using a specified library (e.g., the pandas library). If it is an Excel file, it converts each sheet information and cell data into a data frame. The input is the saved report file, and the output is data in data frame format. Specifically, the server reads the Excel file using the pandas library and converts it into a data frame.

[0949] Step 4:

[0950] Text and Data Analysis

[0951] The server uses a natural language processing (NLP) engine and a data analysis engine to analyze the text and numerical data of the data frame. Specifically, it performs grammar checks, keyword extraction, and summary generation on the text portion, and performs correlation analysis and trend analysis on the numerical data. The input is data in data frame format, and the output is the analysis results. Specifically, the server uses the natural language processing engine to perform text analysis, and the statistical analysis engine to analyze correlations and trends in the numerical data.

[0952] Step 5:

[0953] Generate improvement suggestions

[0954] The server integrates the results of the text and data analysis and generates specific improvement suggestions for the structure and content of the report. For example, it may make suggestions such as "the background explanation in the introduction is insufficient" or "specific market conditions should be added." The input is the analysis results and the output is improvement suggestions. Specifically, the server uses a suggestion generation algorithm based on the analysis results to extract areas for improvement and generate specific suggestions.

[0955] Step 6:

[0956] Feedback acquisition and emotion recognition

[0957] The server receives the user's feedback and recognizes the emotion using the emotion engine. This is done by analyzing the text data the user enters into the feedback form. The input is the user's feedback, and the output is the analyzed emotion data. Specifically, the server receives the feedback form data, performs text analysis, and infers the user's emotion.

[0958] Step 7:

[0959] Providing feedback

[0960] The server generates a feedback report in HTML format based on the generated improvement suggestions and emotion data, and adjusts the tone of the feedback. The generated report is sent to the terminal and displayed to the user. The input is the improvement suggestions and emotion data, and the output is a feedback report in HTML format. Specifically, the server adjusts the tone of the feedback taking into account the emotion data, generates the report in HTML format, and sends it to the terminal.

[0961] Step 8:

[0962] Re-upload the correction report (optional)

[0963] The user can modify the report based on the feedback and upload it again. The server receives the new report, compares it with the previous feedback, and makes further improvement suggestions. The input is the report file modified by the user, and the output is new improvement suggestions. Specifically, the server receives the modified report, processes it in the same way as the initial analysis, and suggests new improvements.

[0964] Step 9:

[0965] Self-learning function

[0966] The server collects and analyzes user feedback and emotional data, and uses that data to update the self-learning algorithm. The input is feedback and emotional data, and the output is the updated algorithm. Specifically, the server adjusts the parameters of the machine learning model based on the collected data, improving the accuracy of future analyses.

[0967] (Application example 2)

[0968] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0969] Conventional report analysis systems can provide objective analysis results and improvement suggestions for created reports, but they lack feedback that takes into account the user's emotional state or consideration for reducing stress caused by emotions. Furthermore, they cannot provide real-time improvement suggestions, which means they cannot be expected to improve work efficiency. In particular, in on-site work environments such as factories, support systems incorporating emotion recognition would be effective, but such systems have not existed.

[0970] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0971] In this invention, the server includes means for acquiring a report file, means for analyzing the contents of the report, means for generating improvement suggestions based on the analysis results, emotion recognition means for recognizing the user's emotion, and means for adjusting the tone of the feedback based on the emotion recognition. This enables feedback that is considerate to the user's emotional state, reducing the user's stress and improving work efficiency through improvement suggestions in real time.

[0972] A "report file" is document data in a report format that is submitted or created by a user.

[0973] "Analysis Means" refers to the technical means for automatically analyzing the contents of the Report File.

[0974] "Improvement proposals" refer to specific proposals for improving the content of the report based on the results obtained by the analysis means.

[0975] "Display means" refers to a device or software for visually displaying the generated improvement proposals.

[0976] "Emotion recognition means" refers to technical means, including voice analysis and facial expression recognition technology, for recognizing a user's emotions.

[0977] "Feedback" refers to the process within the system for collecting opinions and feedback from users.

[0978] "Self-learning means" refers to functions that improve the accuracy of system analysis and improvement suggestions based on collected feedback.

[0979] "Natural language processing technology" refers to a group of computer technologies for analyzing and processing linguistic data.

[0980] "Various formats" refers to including a wide variety of file formats without being limited to a specific file format.

[0981] "Voice analysis" refers to the technology of processing the user's voice as digital data and analyzing its content and emotions.

[0982] "Facial expression recognition" refers to image processing technology for reading emotions from a user's facial image.

[0983] "Real-time" refers to data processing and feedback occurring immediately.

[0984] The present invention is a system that combines emotion recognition means to analyze report files and provide improvement suggestions, with the aim of improving the work efficiency of factory workers.

[0985] The system program operates as follows.

[0986] The server receives the report file uploaded by the user and stores it in temporary storage. The server then uses an analysis means to analyze the contents of the report file and generates improvement suggestions based on the analysis results. This analysis uses natural language processing technology to analyze the text in the report. The server also uses an emotion recognition means to detect the user's emotions through voice analysis and facial expression recognition.

[0987] Specifically, the server uses software libraries such as OpenCV and SpeechRecognition to analyze the user's camera footage and audio data. This allows it to read emotions from the user's facial expressions and speech. The analyzed emotional data is reflected in the tone of the improvement suggestions, allowing the user to receive feedback without feeling stressed.

[0988] The improvement proposals are generated in HTML format and provided to the user through a display means, allowing the user to check the analysis results and improvement proposals in real time. Furthermore, feedback from users is collected and the system's accuracy is improved through self-learning means.

[0989] As a concrete example, consider a scenario in which an Excel file called "Monthly Sales Report.xlsx" is uploaded. The user uploads "Monthly Sales Report.xlsx" to the system. The server receives this file and stores it in temporary storage. Next, the Pandas library is used to read the Excel file and convert it into a data frame. TextBlob is used to analyze the sentiment in the text, and OpenCV and SpeechRecognition are used to analyze the voice and facial expression. Finally, improvement suggestions based on the analysis results are generated in HTML format and provided to the user.

[0990] An example prompt might be something like, "Please upload Monthly Sales Report.xlsx. We'll provide you with analysis of the report and feedback based on your sentiment."

[0991] As described above, the present invention provides a report analysis and improvement proposal system that combines emotion recognition means, and contributes to improving the efficiency of factory work and reducing worker stress.

[0992] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0993] Step 1:

[0994] The user uses a terminal to select a report file and upload it to the system. As input, the user provides a report file (e.g., "Monthly Sales Report.xlsx"), and the output is that the server receives this file.

[0995] Step 2:

[0996] The server stores the received report file in temporary storage. It receives the uploaded report file as input and generates a file stored in temporary storage as output.

[0997] Step 3:

[0998] The server uses the Pandas library to convert the saved Excel file into a data frame. The input is the report file in temporary storage, and the output is data in data frame format. Specifically, the server calls the Pandas read_excel function to read the sheet information and cell data.

[0999] Step 4:

[1000] The server uses the TextBlob library to analyze the text in the data frame. The input is the text data in the data frame, and the output is the sentiment analysis results and keyword extraction results. Specifically, the server evaluates the sentiment of the text using the sentiment function of TextBlob.

[1001] Step 5:

[1002] The server uses OpenCV and the SpeechRecognition library to acquire the user's camera video and audio data and recognize emotions. The input is the camera video and audio data, and the output is the user's emotional state. Specifically, the server captures the camera video, records the audio, and passes this data to the analysis engine.

[1003] Step 6:

[1004] The server generates improvement suggestions based on the text analysis results and emotion recognition results. It receives the text analysis results, emotional state, and existing feedback as input, and generates a feedback report with adjusted tone as output. Specifically, the server integrates the analysis results and constructs specific improvement suggestions.

[1005] Step 7:

[1006] The server converts the generated improvement suggestions into a feedback report in HTML format and sends it to the user's terminal. The improvement suggestions are received as input, and a feedback report is generated as output, which is displayed on the user's terminal. Specifically, the server uses an HTML template engine to construct the report.

[1007] Step 8:

[1008] The user checks the feedback report through the terminal, revises the report if necessary, and uploads it to the system. The input is the report revised by the user based on the feedback, and the output is the revised report that has been uploaded again.

[1009] Step 9:

[1010] The server receives the re-uploaded correction report, compares it with the initial report, and makes further improvement suggestions. The input is the corrected report file, and the output is additional improvement suggestions based on the differential analysis. Specifically, the server compares the previous analysis results with the new analysis results to identify new improvements.

[1011] These steps result in a system that allows users to efficiently create and improve reports while receiving stress-reducing feedback based on emotion recognition.

[1012] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1013] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1014] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1015] [Fourth embodiment]

[1016] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1017] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1019] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1020] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1021] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1023] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1024] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1025] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1026] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1027] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1028] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1029] ---

[1030] This invention provides a method for automatically analyzing reports and making improvement suggestions using a system called "Report Master AI." This system analyzes the contents of reports based on report files uploaded by users, generates improvement suggestions, and provides feedback to users.

[1031] Specifically, the system operates as follows.

[1032] 1. Uploading a report: The user selects a report file from the terminal and uploads it to the system, which then transfers the file to the server using the HTTP protocol.

[1033] 2. Receiving and saving reports: The server saves the received report files in temporary storage, which is optimized for smooth subsequent analysis.

[1034] 3. Report preprocessing: The server reads the report file using a specific library (e.g., Pandas library) and converts the data into an appropriate format. For example, if it is an Excel file, it parses the sheet information and cell data and converts it into a data frame.

[1035] 4. Text and Data Analysis: The server uses a natural language processing (NLP) engine to analyze the text in the report, including grammar checks, keyword extraction, and summary generation, as well as correlation and trend analysis of numerical data.

[1036] 5. Generating peer review results: The server integrates the results of the text and data analysis and generates recommendations for improving the structure and content of the report, such as "The introduction to the report lacks background information."

[1037] 6. Providing feedback: The server creates an HTML feedback report based on the generated improvement suggestions and sends it to the user's device. Through this feedback, the user can visually confirm the improvements made to the report.

[1038] 7. Re-upload revised report (optional): The user can revise the report based on the feedback and re-upload it to the system. The server will receive the new report, compare it with the previous feedback and make further improvement suggestions.

[1039] 8. Self-learning function: The server collects and analyzes user feedback and uses that data to update the self-learning algorithm, allowing the system to improve the accuracy of its analysis and improvement suggestions in future sessions.

[1040] The following explains this with specific examples.

[1041] The user uploads an Excel file called "Monthly Sales Report.xlsx" from their device. This file contains sales data and analysis details for each store. The server receives this file and saves it in temporary storage. Next, the PANDAS library reads the Excel file and converts the data in each sheet into a data frame.

[1042] The server uses a natural language processing engine to analyze the text and extract keywords such as "causes of sales decline." At the same time, it performs trend and correlation analysis on the numerical data. Based on the results, the server realizes that "sales have declined compared to the previous year, but the reasons for this have not been specifically stated," and suggests adding specific market and competitive situations.

[1043] These improvement suggestions are sent to the user's device in HTML format, where the user can review the improvements and modify the report. When the modified report is uploaded again, the server compares the differences with the previous version and makes further improvement suggestions. Furthermore, based on user feedback, the self-learning algorithm is improved to improve the accuracy of future analyses.

[1044] In this way, "Report Master AI" effectively supports users in creating and improving reports, helping companies make quick and accurate decisions.

[1045] The processing flow will be explained below.

[1046] ---

[1047] Step 1:

[1048] The user selects a report file (e.g., an Excel file) from the terminal and clicks the upload button. The terminal sends the selected report file to the server via an HTTP POST request.

[1049] Step 2:

[1050] The server parses the received HTTP POST request, retrieves the attached report file, saves the report file in a temporary folder, and records the file path.

[1051] Step 3:

[1052] The server reads the saved report file using the PANDAS library and converts the data into a data frame, which makes the text and numeric data in the report easier to parse.

[1053] Step 4:

[1054] The server uses a natural language processing (NLP) engine to analyze the text in the report, performing operations such as grammar checks, keyword extraction, and summary generation to understand the meaning of the text.

[1055] Step 5:

[1056] The server analyzes the numerical data in the reports, performing correlation and trend analysis to detect significant patterns and outliers. This analysis ensures the reliability of the data.

[1057] Step 6:

[1058] Based on the analysis results, the server generates suggestions for improving the structure and content of the report, such as "This part's explanation is insufficient, so please add specific examples and provide more detail."

[1059] Step 7:

[1060] The server generates improvement suggestions and builds an HTML feedback report that highlights specific areas for improvement.

[1061] Step 8:

[1062] The server sends a feedback report to the user's device, allowing the user to see how the report can be improved, and the user can then revise the report based on this feedback.

[1063] Step 9:

[1064] When the user re-uploads the revised report, the server compares the new report with the previous feedback and makes further suggestions for improvement. The server repeats this process to improve the quality of the report.

[1065] Step 10:

[1066] The server collects user feedback and uses that data to improve the self-learning algorithm, which improves the accuracy of future analyses and improvement suggestions.

[1067] ---

[1068] The above is the specific processing flow of "Report Master AI".

[1069] Example 1

[1070] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1071] Conventional report analysis systems have restrictions on the format and content of report files uploaded by users, making it difficult to efficiently analyze diverse and complex data. Furthermore, the improvement suggestions generated are general and lack specific suggestions for specific issues. Furthermore, the system lacks the ability to effectively utilize user feedback and self-learn, making it difficult to improve the accuracy of the next analysis.

[1072] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1073] In this invention, the server includes means for receiving digital documents from a repository server via communication means, means for storing the received digital documents in a temporary storage device, means for analyzing the digital documents using a program and converting them into data frames, means for analyzing text data in the digital documents using natural language processing technology, means for generating improvement suggestions based on the analysis results, means for visualizing and displaying the generated improvement suggestions, and means for receiving input data from a user and updating the self-learning algorithm. This enables highly accurate analysis of digital documents in a variety of formats, provides specific and effective improvement suggestions, and self-learns using user feedback to improve the accuracy of subsequent analyses.

[1074] "Communication means" refers to an interface function including protocols and technologies for receiving digital documents from a repository server.

[1075] A "repository server" is a server system that stores and manages digital documents and allows access and transfer as needed.

[1076] "Digital documents" refers to files such as electronic reports and reports that exist in various formats (e.g., Excel files, PDFs, Word documents).

[1077] "Temporary storage device" refers to a storage device (e.g., SSD or RAM) for temporarily storing received digital documents.

[1078] A "data frame" is a two-dimensional data structure in the form of rows and columns for storing structured data.

[1079] "Natural language processing technology" is a technology for analyzing and understanding text data, and includes grammar checking, keyword extraction, summary generation, and sentiment analysis.

[1080] "Improvement Suggestion" refers to a specific suggestion for improving or correcting the content of a digital document that is generated based on the analysis of the digital document.

[1081] "Visualization" is the process of visually displaying the analysis results and improvement suggestions for digital documents.

[1082] "Input data" refers to feedback information and additional information entered by the user.

[1083] A "self-learning algorithm" is an algorithm that improves the analysis accuracy of a system based on past analysis results and feedback data.

[1084] The present invention is a system that automatically analyzes digital documents and proposes improvements. This system is particularly capable of handling a wide variety of digital document formats with high accuracy and includes a self-learning function based on user feedback. The following describes its specific operation.

[1085] First, a user selects a digital document from their device and uploads it to the system, where the file is transmitted using the HTTP protocol.

[1086] The server then receives the uploaded digital document and stores it in temporary storage (e.g. SSD), which is optimized for fast loading and processing.

[1087] The server uses the PANDAS library (a Python data analysis library) to read the document and convert the data into a data frame. In the case of an Excel file, the information on each sheet and cell data is parsed and converted into structured data for easier subsequent processing.

[1088] The server then uses a natural language processing engine (e.g., SpaCy or BERT) to analyze the text data in the digital documents, including grammar checks, keyword extraction, summary generation, and sentiment analysis, as well as trend and correlation analysis for numerical data.

[1089] Based on the analysis results, the server generates suggestions for improving the structure and content of the digital document, for example, suggesting that the background information in the introduction of the report is insufficient.

[1090] The generated improvement suggestions are generated as a feedback report in HTML format by the server and sent to the user's terminal. The user can check this feedback in a browser and visually understand the improvements to the report.

[1091] The user can modify the report based on the feedback and upload it back to the system. The server receives the new report, compares it with the previous feedback, and provides further suggestions for improvement.

[1092] Finally, the server analyzes the feedback data from users and updates the self-learning algorithm, which improves the accuracy of the analysis in the future and improves the overall performance of the system.

[1093] As a concrete example, a user uploads "Monthly Sales Report.xlsx." This file contains sales data and analytical details for each store. The server uses the PANDAS library to read this file and convert it into a data frame. It then uses a natural language processing engine to analyze the text and perform trend analysis on the sales data. As a result, the server provides feedback to the user, stating that "sales have decreased compared to the previous year, but the reasons for this have not been specifically stated," and recommends that the user provide a detailed description of the market situation and the competitive situation.

[1094] This feedback report is generated in HTML format and sent to the user's device. The user can make corrections and upload the report again, and the server will provide more accurate improvement suggestions. By repeating this process, the system will continue to learn and improve its analysis accuracy.

[1095] Example prompt sentence:

[1096] Analyze the report file "Monthly Sales Report.xlsx" to clarify the cause of the sales decline and provide suggestions for improvement.

[1097] In this way, the invention accommodates a variety of digital documents and effectively assists users in report analysis and refinement.

[1098] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1099] Step 1: Upload the report file

[1100] The user selects a report file (e.g., "Monthly Sales Report.xlsx") from the terminal and uploads it to the system. As input, the user selects the target file in a file selection dialog. As output, the file is sent to the server using the HTTP protocol.

[1101] Step 2: Receive and temporarily save the report file

[1102] The server receives the uploaded report file. The input is the file data sent by the user. As an output, the server saves the received file to a temporary storage device (SSD). Specifically, the file is saved in the " / tmp / reports / " directory, and the completion of reception is recorded in the server log.

[1103] Step 3: Preprocessing the report file

[1104] The server uses the PANDAS library to read the report file. The input is the file stored in temporary storage. The output is the data converted to a data frame format. Specifically, in the case of an Excel file, the information on each sheet and cell data is analyzed and structured into a data frame.

[1105] Step 4: Analyzing text and numerical data

[1106] The server analyzes text data using a natural language processing engine. The input is a preprocessed data frame. The output is a text summary, keywords, grammar check results, and sentiment analysis results as the analysis results. At the same time, trend analysis and correlation analysis are performed on the numerical data. Specifically, the NLP engine analyzes the text, and the PANDAS library processes the numerical data.

[1107] Step 5: Generate improvement suggestions

[1108] The server generates improvement suggestions based on the analysis results. The input is the analysis results of text and numerical data. The output is specific improvement suggestions. As a specific operation, the server generates specific suggestions such as "The background explanation in the introduction of the report is insufficient."

[1109] Step 6: Provide feedback

[1110] The server creates a feedback report in HTML format based on the generated improvement suggestions. The input is the improvement suggestions. The output is the feedback report. Specifically, the server creates the feedback report and sends it to the user's device. The user then checks the feedback in their browser.

[1111] Step 7: Re-upload the Correction Report (Optional)

[1112] The user modifies the report based on the feedback. The input is the feedback report. The output is the modified report file. Specifically, the user uploads the modified file back to the system. The server receives the new report, compares it with the previous feedback, and provides further improvement suggestions.

[1113] Step 8: Update the self-learning algorithm

[1114] The server analyzes the feedback data from users and updates the self-learning algorithm. The input is the feedback data from users. The output is the updated learning algorithm. Specifically, the system accumulates feedback data and periodically retrains the model to improve the system's analysis accuracy.

[1115] (Application example 1)

[1116] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1117] Factories require the collection and analysis of various process and performance data, and improvement proposals are extremely important for achieving efficient production and quality control. However, the process from data collection to analysis, and the generation and implementation of improvement proposals is often done manually, which is time-consuming and prone to inaccuracies. For this reason, there is a demand for an automated, highly accurate analysis system that can improve factory production efficiency and quality control in real time.

[1118] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1119] In this invention, the server includes means for acquiring a report file, means for analyzing the contents of the report, means for generating improvement proposals based on the analysis results, means for displaying the generated improvement proposals, means for acquiring feedback from users and performing self-learning, means for collecting real-time data from equipment operating in the factory, means for analyzing the collected real-time data, means for generating improvement proposals for the factory equipment based on the analysis results, and means for displaying the generated improvement proposals for the factory equipment on a display device. This makes it possible to automate the series of processes of data collection, analysis, and improvement proposals within the factory, thereby reducing time and improving accuracy.

[1120] A "report file" is a document file that organizes data and information in an organized manner, which may include text, numerical data, graphs, etc.

[1121] "Analysis" is the process of conducting detailed analysis based on collected data and information to clarify their meaning and relationships.

[1122] "Improvement proposals" refer to specific advice and instructions based on the analysis results to improve the current situation, leading to effective problem solving and improved business efficiency.

[1123] A "display device" is a device for visually displaying information. This may include smart glasses or head-mounted displays.

[1124] "User" refers to the person who operates the system, uploads report files, and checks improvement suggestions. This applies to factory managers and engineers.

[1125] "Self-learning" is the process by which machine learning algorithms use feedback data to improve the accuracy of future analyses and suggestions.

[1126] "Factory equipment" refers to various machines and robots used in the production process, which are often equipped with sensors that monitor temperature, pressure, vibration, etc.

[1127] "Real-time data" is dynamic data that records the behavior and state of the object being collected in real time.

[1128] "Analysis results" refers to information and knowledge obtained as a result of analysis based on collected data.

[1129] "Server" refers to a central processing unit for receiving, storing, analyzing report files, and transmitting analysis results.

[1130] This invention applies "Report Master AI" to factories, creating a system that collects and analyzes data in real time, automating the entire process of generating and displaying improvement suggestions.

[1131] Factories are equipped with various sensors that collect real-time data, such as temperature, pressure, and vibration, and the data is sent to a server via Wi-Fi or 5G networks.

[1132] The server first receives the collected data and stores it in temporary storage, then uses the PANDAS library installed on the high-performance server to convert the data into a data frame, which is then prepared for subsequent analysis.

[1133] The analysis uses a generative AI model that applies natural language processing technology. Specifically, the server analyzes the data using a machine learning library (e.g., TensorFlow or PyTorch), while simultaneously generating improvement suggestions using a natural language processing engine (e.g., NLTK or SpaCy). This process detects anomalies in the data, analyzes their causes, and derives specific improvement suggestions.

[1134] Improvement suggestions are written in HTML format and sent to smart glasses or head-mounted displays via Wi-Fi or 5G networks, allowing factory managers and engineers to view the suggestions in real time and take appropriate action on the spot.

[1135] The server also collects user feedback and updates the self-learning algorithm, which improves the accuracy of future analyses and improvement suggestions.

[1136] A specific example is shown below: When an abnormal vibration value is detected based on vibration data collected by a factory robot, the server generates an analysis result and improvement proposals based on that data.

[1137] An example of a prompt is as follows:

[1138] Prompt statement:

[1139] "Analyze the vibration data below, check for any abnormal values, generate any necessary improvement suggestions, and return the improvement suggestions in HTML format."

[1140] Vibration Data:

[1141] Time: 2023-10-01 10:00, Vibration value: 1.2

[1142] Time: 2023-10-01 10:01, Vibration value: 1.4

[1143] Time: 2023-10-01 10:02, Vibration level: 5.6 (abnormal value)

[1144] Desired improvement suggestions:

[1145] "At 10:02, an abnormal vibration value of 5.6 was detected. This vibration is more than twice the normal value. Possible causes include deterioration of the device's components or misalignment. Please perform maintenance immediately and recheck the device's operation."

[1146] In this way, the present invention automates the entire process of data collection, analysis, and improvement proposals within a factory, thereby reducing time and improving accuracy.

[1147] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1148] Step 1:

[1149] Factory equipment collects real-time data such as temperature, pressure, and vibration through sensors. Each sensor captures data about the operation and status of the equipment and records it at regular intervals.

[1150] Input: Sensor data from factory equipment

[1151] Output: Real-time sensor data

[1152] Step 2:

[1153] The device transmits the collected real-time data over Wi-Fi or 5G networks to a server, where the data may be formatted, compressed, etc.

[1154] Input: Real-time sensor data

[1155] Output: Real-time data sent to the server

[1156] Step 3:

[1157] The server stores the received data in temporary storage, where it is converted into a data frame using libraries such as Pandas and processed into a format suitable for analysis.

[1158] Input: Real-time data sent to the server

[1159] Output: Data in data frame format

[1160] Step 4:

[1161] The server analyzes the data using machine learning libraries (e.g., TensorFlow or PyTorch) and uses natural language processing engines (e.g., NLTK or SpaCy) to understand the results and detect abnormal conditions and patterns in the factory equipment.

[1162] Input: Data in data frame format

[1163] Output: Analysis results (including anomaly detection)

[1164] Step 5:

[1165] The server generates improvement suggestions based on the analysis results, which are then converted into a human-readable format using a natural language processing engine.

[1166] Input: Analysis results (including anomaly detection)

[1167] Output: Improvement suggestions expressed in natural language

[1168] Step 6:

[1169] The server constructs the generated improvement suggestions in HTML format and transmits them to smart glasses or head-mounted displays via Wi-Fi or 5G networks.

[1170] Input: Improvement suggestions expressed in natural language

[1171] Output: HTML format improvement suggestions

[1172] Step 7:

[1173] Users can check the improvement suggestions displayed through smart glasses or a head-mounted display and take necessary actions, such as performing maintenance on factory equipment or adjusting settings.

[1174] Input: HTML format improvement suggestions

[1175] Output: User actions (maintenance, configuration adjustments, etc.)

[1176] Step 8:

[1177] The server receives feedback from users and updates its self-learning algorithm, improving the accuracy of future analyses and improvement suggestions.

[1178] Input: User feedback

[1179] Output: Self-learning updated analytical model

[1180] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1181] ---

[1182] This invention provides a system that automatically analyzes reports and proposes improvements by combining a "Report Master AI" with an emotion engine that recognizes user emotions, and provides feedback based on the user's emotions. This system analyzes report files uploaded by users, generates improvement suggestions, and further recognizes the user's emotions when giving feedback using the emotion engine, which can be reflected in the next improvement suggestions.

[1183] Specifically, the system operates as follows.

[1184] 1. Uploading a report: The user selects a report file from the terminal and uploads it to the system. The terminal sends the selected report file to the server via an HTTP POST request.

[1185] 2. Receiving and saving reports: The server saves the received report files in temporary storage, which is optimized for smooth subsequent analysis.

[1186] 3. Report preprocessing: The server reads the report file using a predefined library and converts the data into an appropriate format. For example, if it is an Excel file, it parses the sheet information and cell data and converts it into a data frame.

[1187] 4. Text and Data Analysis: The server uses a natural language processing (NLP) engine to analyze the text in the report, including grammar checks, keyword extraction, and summary generation, as well as correlation and trend analysis of numerical data.

[1188] 5. Generating peer review results: The server integrates the results of the text and data analysis and generates recommendations for improving the structure and content of the report, such as "The introduction to the report lacks background information."

[1189] 6. Emotion Recognition by Emotion Engine: The server uses an emotion engine to recognize the user's emotion in the feedback. This includes analyzing the user's emotional state (e.g., satisfaction, dissatisfaction, confusion, etc.) from their written or spoken words.

[1190] 7. Providing feedback: The server creates an HTML-formatted feedback report based on the generated improvement suggestions and provides feedback in a tone that reflects the user's emotional state. For example, if the user has experienced emotional stress in the past, the server may soften the tone of the feedback.

[1191] 8. Re-upload revised report (optional): The user can revise the report based on the feedback and re-upload it to the system. The server will receive the new report, compare it with the previous feedback, and make further suggestions for improvement.

[1192] 9. Self-learning function: The server collects and analyzes user feedback and emotional data, and uses that data to update the self-learning algorithm, allowing the system to improve the accuracy of its analysis and improvement suggestions in the future.

[1193] The following explains this with specific examples.

[1194] The user uploads an Excel file called "Monthly Sales Report.xlsx" from their device. This file contains sales data and analysis details for each store. The server receives this file and saves it in temporary storage. Next, the PANDAS library reads the Excel file and converts the data in each sheet into a data frame.

[1195] The server uses a natural language processing engine to analyze the text and extract keywords such as "causes of sales decline." At the same time, it performs trend and correlation analysis on the numerical data. Based on the results, the server realizes that "sales have declined compared to the previous year, but the reasons for this have not been specifically stated," and suggests adding specific market and competitive situations.

[1196] Furthermore, an emotion engine is used to analyze user emotions. For example, when a user enters a comment when providing feedback, the system reads the user's emotions from the text and determines whether the improvement proposal is appropriate for the user. If the user is expressing strong dissatisfaction, the system softens the tone of the feedback and provides information in a more understandable format.

[1197] These improvement suggestions are sent to the user's device in HTML format, where the user can review and revise the report. When the revised report is uploaded again, the server compares the differences with the previous version and makes further improvement suggestions. Furthermore, the self-learning algorithm is improved based on user feedback and emotional data, improving the accuracy of subsequent analyses.

[1198] In this way, "Report Master AI" effectively supports users in creating and improving reports, while providing feedback that takes users' emotions into consideration, thereby increasing the usefulness of the system.

[1199] The processing flow will be explained below.

[1200] ---

[1201] Step 1:

[1202] The user selects a report file (e.g., an Excel file) from the terminal and clicks the upload button. The terminal sends the selected report file to the server via an HTTP POST request.

[1203] Step 2:

[1204] The server parses the received HTTP POST request, retrieves the attached report file, saves the report file in a temporary folder, and records the file path.

[1205] Step 3:

[1206] The server reads the saved report file using the PANDAS library and converts the data into a data frame format, which makes the text and numeric data in the report easier to parse.

[1207] Step 4:

[1208] The server uses a natural language processing (NLP) engine to analyze the text in the report, performing operations such as grammar checks, keyword extraction, and summary generation to understand the meaning of the text.

[1209] Step 5:

[1210] The server analyzes the numerical data in the reports, performing correlation and trend analysis to detect significant patterns and outliers. This analysis ensures the reliability of the data.

[1211] Step 6:

[1212] Based on the results of the text and data analysis, the server generates suggestions for improving the structure and content of the report, such as "This part's explanation is insufficient, so please add specific examples and provide more detail."

[1213] Step 7:

[1214] The server uses an emotion engine to recognize the user's emotion when providing feedback. The emotion engine identifies the user's emotional state from the text and voice when the user provides feedback, and analyzes the emotional state.

[1215] Step 8:

[1216] The server adjusts the content and tone of the feedback report based on the user's emotional data obtained from the emotion engine. For example, if the user expresses dissatisfaction, the server softens the feedback and provides additional explanatory comments.

[1217] Step 9:

[1218] The server creates an HTML-formatted feedback report based on the generated improvement suggestions and sends it to the user's device, allowing the user to visually confirm the improvements made to the report.

[1219] Step 10:

[1220] The user then modifies the report based on the feedback and uploads it to the server again from their device. The server compares the new report with the previous feedback and makes suggestions for further improvement.

[1221] Step 11:

[1222] The server collects user feedback and emotional data and uses it to update the self-learning algorithm, allowing the system to improve the accuracy of future analyses and improvement suggestions.

[1223] ---

[1224] The above is the specific processing flow of the system that combines the "Report Master AI" with an emotion engine.

[1225] Example 2

[1226] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1227] Conventional report analysis systems have the ability to analyze report content and provide improvement suggestions, but they lack the ability to provide feedback that takes user emotions into consideration or to self-learn based on user feedback. This limits the system's usefulness because it is unable to provide flexible improvement suggestions that reflect user emotions. Furthermore, limitations on report file formats make it difficult to analyze reports in a variety of formats.

[1228] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1229] In this invention, the server includes a means for acquiring a report file, a means for saving the report file, and a means for reading and converting data in the report file, thereby enabling a means for generating improvement suggestions based on the analysis results, a means for displaying the generated improvement suggestions, a means for acquiring feedback from a user and recognizing the user's emotions, and a means for self-learning based on the feedback.

[1230] "Report file" refers to an electronic document that records reports or data analysis results, and specifically includes formats such as Excel, PDF, and Word.

[1231] The "means of acquisition" refers to an interface or protocol for receiving data from a user terminal, and has functions including HTTP POST requests.

[1232] "Means for storing" refers to storage for temporarily or permanently storing received data, and includes media such as disks and cloud storage.

[1233] "Means to read and transform" refers to the process of converting data in a particular format into an analyzable format, including, for example, the ability to convert Excel data into a data frame using the pandas library.

[1234] "Means of analysis" refers to the process of analyzing the content of data using specific algorithms or technologies and obtaining the results, including natural language processing technology and statistical analysis technology.

[1235] The "means for generating improvement proposals" refers to a function for automatically extracting and proposing improvements to the report based on the analysis results, and includes a proposal generation engine that uses a specific algorithm.

[1236] The "display means" refers to an interface for presenting the generated improvement proposals to the user in an easy-to-understand manner, and includes a feedback report in HTML format.

[1237] "Means for obtaining feedback" refers to the process by which the system collects user ratings and opinions, and includes feedback forms, comment sections, etc.

[1238] "Means for recognizing emotions" refers to technologies that analyze the emotional state of a user from feedback data provided by the user, and includes text analysis and voice analysis.

[1239] "Means for self-learning" refers to the process of improving the system's algorithms using the obtained feedback and emotional data to improve the accuracy of analysis from the next time onwards, and includes machine learning techniques.

[1240] This invention relates to a system that allows users to upload report files, analyzes their contents, and generates improvement suggestions. It also has the ability to analyze the user's feedback and emotional state, adjust the feedback based on that, and perform self-learning. This system uses natural language processing and machine learning technologies to achieve efficient and flexible report improvement.

[1241] System Overview

[1242] Obtaining and saving report files

[1243] The terminal provides an interface for the user to select a report file of their choice and upload it to the system. The user uses a file selection dialog to select the file they want to upload (e.g., "Monthly Sales Report.xlsx"). Once selected, the terminal creates an HTTP POST request and sends it to the server, including the selected file.

[1244] The server receives the HTTP POST request from the terminal and extracts the report file. The extracted file is saved in temporary storage (for example, the / tmp directory). The save location is managed by a unique identifier that includes the file name and timestamp.

[1245] Preprocessing the report file

[1246] The server loads the saved report file using a specific library (for example, the pandas library). If the file is an Excel file, the server converts each sheet and cell data into a data frame. The converted data is temporarily stored in memory in preparation for analysis.

[1247] Text and Data Analysis

[1248] The server uses a natural language processing (NLP) engine and a data analysis engine to analyze the text and numerical data based on each data frame. Specifically, the text is checked for grammar, keywords are extracted, and summaries are generated, while correlation and trend analysis are performed on the numerical data. This results in analysis results from both the content and data aspects of the report.

[1249] Generate improvement suggestions

[1250] The server integrates the results of the text and data analysis and generates specific suggestions for improving the structure and content of the report, such as "the introduction lacks background information" or "add specific market conditions." These suggestions are stored in a temporary database.

[1251] Feedback acquisition and emotion recognition

[1252] The server uses an emotion engine to recognize the user's emotions when providing feedback. This is done by analyzing the text data entered by the user in the feedback form. The analyzed emotion data (e.g., satisfaction, dissatisfaction, confusion, etc.) is reflected in the next feedback and improvement suggestions.

[1253] Providing feedback

[1254] The server generates a feedback report in HTML format based on the generated improvement suggestions and emotional data. The tone of this feedback report is adjusted according to the user's emotional state. For example, if the user has expressed strong dissatisfaction in the past, the tone of the feedback will be softened. The generated feedback report is sent to the terminal and displayed to the user.

[1255] Re-upload the correction report (optional)

[1256] Users can modify their reports based on the feedback and re-upload them, in which case the server receives the new report, compares it with the previous feedback, and makes further suggestions for improvement.

[1257] Self-learning function

[1258] The server collects and analyzes user feedback and emotional data, and uses that data to update the self-learning algorithm, allowing the system to improve the accuracy of future analyses and improvement suggestions.

[1259] Specific examples are shown below.

[1260] Specific examples

[1261] The user uploads an Excel file called "Monthly Sales Report.xlsx" from their device. This file contains sales data and analysis details for each store. The server receives this file and saves it in temporary storage. Next, the pandas library reads the Excel file and converts the data in each sheet into a data frame.

[1262] The server uses a natural language processing engine to analyze the text and extract keywords such as "causes of sales decline." At the same time, it performs trend and correlation analysis on the numerical data. Based on the results, the server realizes that "sales have declined compared to the previous year, but the reasons for this have not been specifically stated," and suggests adding specific market and competitive situations.

[1263] Furthermore, an emotion engine is used to analyze user emotions. For example, when a user enters a comment when providing feedback, the system reads the user's emotions from the text and determines whether the improvement proposal is appropriate for the user. If the user is expressing strong dissatisfaction, the system softens the tone of the feedback and provides information in a more understandable format.

[1264] These improvement suggestions are sent to the user's device in HTML format, where the user can review and revise the report. When the revised report is uploaded again, the server compares the differences with the previous version and makes further improvement suggestions. Furthermore, the self-learning algorithm is improved based on user feedback and emotional data, improving the accuracy of subsequent analyses.

[1265] Prompt Sentence Examples

[1266] Analyze Monthly Sales Report.xlsx and generate improvement suggestions. Adjust the tone of the analysis results based on user feedback.

[1267] In this way, the system of the present invention effectively supports the user in creating and improving reports, while providing feedback that takes into account the user's emotions.

[1268] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1269] Step 1:

[1270] Uploading a report file

[1271] A user selects a specific report file (e.g., "Monthly Sales Report.xlsx") from the terminal and uploads it to the system. The terminal sends the selected report file to the server using an HTTP POST request. The input is the report file selected by the user, and the output is the HTTP POST request sent to the server. Specifically, the terminal opens a file selection dialog, and after the user selects a file, it sends the file to the server as an HTTP POST request.

[1272] Step 2:

[1273] Receiving and saving report files

[1274] The server receives the HTTP POST request from the terminal and extracts the report file. It saves the extracted file in temporary storage (e.g., the / tmp directory). The input is the HTTP POST request, and the output is the saved report file. Specifically, the server analyzes the HTTP request and saves the file in a temporary storage directory.

[1275] Step 3:

[1276] Preprocessing the report file

[1277] The server reads the saved report file using a specified library (e.g., the pandas library). If it is an Excel file, it converts each sheet information and cell data into a data frame. The input is the saved report file, and the output is data in data frame format. Specifically, the server reads the Excel file using the pandas library and converts it into a data frame.

[1278] Step 4:

[1279] Text and Data Analysis

[1280] The server uses a natural language processing (NLP) engine and a data analysis engine to analyze the text and numerical data of the data frame. Specifically, it performs grammar checks, keyword extraction, and summary generation on the text portion, and performs correlation analysis and trend analysis on the numerical data. The input is data in data frame format, and the output is the analysis results. Specifically, the server uses the natural language processing engine to perform text analysis, and the statistical analysis engine to analyze correlations and trends in the numerical data.

[1281] Step 5:

[1282] Generate improvement suggestions

[1283] The server integrates the results of the text and data analysis and generates specific improvement suggestions for the structure and content of the report. For example, it may make suggestions such as "the background explanation in the introduction is insufficient" or "specific market conditions should be added." The input is the analysis results and the output is improvement suggestions. Specifically, the server uses a suggestion generation algorithm based on the analysis results to extract areas for improvement and generate specific suggestions.

[1284] Step 6:

[1285] Feedback acquisition and emotion recognition

[1286] The server receives the user's feedback and recognizes the emotion using the emotion engine. This is done by analyzing the text data the user enters into the feedback form. The input is the user's feedback, and the output is the analyzed emotion data. Specifically, the server receives the feedback form data, performs text analysis, and infers the user's emotion.

[1287] Step 7:

[1288] Providing feedback

[1289] The server generates a feedback report in HTML format based on the generated improvement suggestions and emotion data, and adjusts the tone of the feedback. The generated report is sent to the terminal and displayed to the user. The input is the improvement suggestions and emotion data, and the output is a feedback report in HTML format. Specifically, the server adjusts the tone of the feedback taking into account the emotion data, generates the report in HTML format, and sends it to the terminal.

[1290] Step 8:

[1291] Re-upload the correction report (optional)

[1292] The user can modify the report based on the feedback and upload it again. The server receives the new report, compares it with the previous feedback, and makes further improvement suggestions. The input is the report file modified by the user, and the output is new improvement suggestions. Specifically, the server receives the modified report, processes it in the same way as the initial analysis, and suggests new improvements.

[1293] Step 9:

[1294] Self-learning function

[1295] The server collects and analyzes user feedback and emotional data, and uses that data to update the self-learning algorithm. The input is feedback and emotional data, and the output is the updated algorithm. Specifically, the server adjusts the parameters of the machine learning model based on the collected data, improving the accuracy of future analyses.

[1296] (Application example 2)

[1297] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1298] Conventional report analysis systems can provide objective analysis results and improvement suggestions for created reports, but they lack feedback that takes into account the user's emotional state or consideration for reducing stress caused by emotions. Furthermore, they cannot provide real-time improvement suggestions, which means they cannot be expected to improve work efficiency. In particular, in on-site work environments such as factories, support systems incorporating emotion recognition would be effective, but such systems have not existed.

[1299] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1300] In this invention, the server includes means for acquiring a report file, means for analyzing the contents of the report, means for generating improvement suggestions based on the analysis results, emotion recognition means for recognizing the user's emotion, and means for adjusting the tone of the feedback based on the emotion recognition. This enables feedback that is considerate to the user's emotional state, reducing the user's stress and improving work efficiency through improvement suggestions in real time.

[1301] A "report file" is document data in a report format that is submitted or created by a user.

[1302] "Analysis Means" refers to the technical means for automatically analyzing the contents of the Report File.

[1303] "Improvement proposals" refer to specific proposals for improving the content of the report based on the results obtained by the analysis means.

[1304] "Display means" refers to a device or software for visually displaying the generated improvement proposals.

[1305] "Emotion recognition means" refers to technical means, including voice analysis and facial expression recognition technology, for recognizing a user's emotions.

[1306] "Feedback" refers to the process within the system for collecting opinions and feedback from users.

[1307] "Self-learning means" refers to functions that improve the accuracy of system analysis and improvement suggestions based on collected feedback.

[1308] "Natural language processing technology" refers to a group of computer technologies for analyzing and processing linguistic data.

[1309] "Various formats" refers to including a wide variety of file formats without being limited to a specific file format.

[1310] "Voice analysis" refers to the technology of processing the user's voice as digital data and analyzing its content and emotions.

[1311] "Facial expression recognition" refers to image processing technology for reading emotions from a user's facial image.

[1312] "Real-time" refers to data processing and feedback occurring immediately.

[1313] The present invention is a system that combines emotion recognition means to analyze report files and provide improvement suggestions, with the aim of improving the work efficiency of factory workers.

[1314] The system program operates as follows.

[1315] The server receives the report file uploaded by the user and stores it in temporary storage. The server then uses an analysis means to analyze the contents of the report file and generates improvement suggestions based on the analysis results. This analysis uses natural language processing technology to analyze the text in the report. The server also uses an emotion recognition means to detect the user's emotions through voice analysis and facial expression recognition.

[1316] Specifically, the server uses software libraries such as OpenCV and SpeechRecognition to analyze the user's camera footage and audio data. This allows it to read emotions from the user's facial expressions and speech. The analyzed emotional data is reflected in the tone of the improvement suggestions, allowing the user to receive feedback without feeling stressed.

[1317] The improvement proposals are generated in HTML format and provided to the user through a display means, allowing the user to check the analysis results and improvement proposals in real time. Furthermore, feedback from users is collected and the system's accuracy is improved through self-learning means.

[1318] As a concrete example, consider a scenario in which an Excel file called "Monthly Sales Report.xlsx" is uploaded. The user uploads "Monthly Sales Report.xlsx" to the system. The server receives this file and stores it in temporary storage. Next, the Pandas library is used to read the Excel file and convert it into a data frame. TextBlob is used to analyze the sentiment in the text, and OpenCV and SpeechRecognition are used to analyze the voice and facial expression. Finally, improvement suggestions based on the analysis results are generated in HTML format and provided to the user.

[1319] An example prompt might be something like, "Please upload Monthly Sales Report.xlsx. We'll provide you with analysis of the report and feedback based on your sentiment."

[1320] As described above, the present invention provides a report analysis and improvement proposal system that combines emotion recognition means, and contributes to improving the efficiency of factory work and reducing worker stress.

[1321] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1322] Step 1:

[1323] The user uses a terminal to select a report file and upload it to the system. As input, the user provides a report file (e.g., "Monthly Sales Report.xlsx"), and the output is that the server receives this file.

[1324] Step 2:

[1325] The server stores the received report file in temporary storage. It receives the uploaded report file as input and generates a file stored in temporary storage as output.

[1326] Step 3:

[1327] The server uses the Pandas library to convert the saved Excel file into a data frame. The input is the report file in temporary storage, and the output is data in data frame format. Specifically, the server calls the Pandas read_excel function to read the sheet information and cell data.

[1328] Step 4:

[1329] The server uses the TextBlob library to analyze the text in the data frame. The input is the text data in the data frame, and the output is the sentiment analysis results and keyword extraction results. Specifically, the server evaluates the sentiment of the text using the sentiment function of TextBlob.

[1330] Step 5:

[1331] The server uses OpenCV and the SpeechRecognition library to acquire the user's camera video and audio data and recognize emotions. The input is the camera video and audio data, and the output is the user's emotional state. Specifically, the server captures the camera video, records the audio, and passes this data to the analysis engine.

[1332] Step 6:

[1333] The server generates improvement suggestions based on the text analysis results and emotion recognition results. It receives the text analysis results, emotional state, and existing feedback as input, and generates a feedback report with adjusted tone as output. Specifically, the server integrates the analysis results and constructs specific improvement suggestions.

[1334] Step 7:

[1335] The server converts the generated improvement suggestions into a feedback report in HTML format and sends it to the user's terminal. The improvement suggestions are received as input, and a feedback report is generated as output, which is displayed on the user's terminal. Specifically, the server uses an HTML template engine to construct the report.

[1336] Step 8:

[1337] The user checks the feedback report through the terminal, revises the report if necessary, and uploads it to the system. The input is the report revised by the user based on the feedback, and the output is the revised report that has been uploaded again.

[1338] Step 9:

[1339] The server receives the re-uploaded correction report, compares it with the initial report, and makes further improvement suggestions. The input is the corrected report file, and the output is additional improvement suggestions based on the differential analysis. Specifically, the server compares the previous analysis results with the new analysis results to identify new improvements.

[1340] These steps result in a system that allows users to efficiently create and improve reports while receiving stress-reducing feedback based on emotion recognition.

[1341] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1342] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1343] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1344] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1345] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1346] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1347] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1348] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1349] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1350] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1351] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1352] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1353] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1354] 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.

[1355] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1356] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1357] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1358] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1359] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1360] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1361] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1362] The following is further disclosed regarding the above embodiment.

[1363] Understood. Below is the draft of the patent claims for the distinctive features of "Report Master AI."

[1364] ---

[1365] (Claim 1)

[1366] a means for obtaining the report file;

[1367] a means for analyzing the contents of the report;

[1368] means for generating improvement suggestions based on the analysis results;

[1369] a means for displaying the generated improvement suggestions;

[1370] a means of obtaining user feedback and self-learning;

[1371] A system including:

[1372] (Claim 2)

[1373] 10. The system of claim 1, wherein natural language processing techniques are used in analyzing the content of the report.

[1374] (Claim 3)

[1375] The system according to claim 1, which supports a variety of formats without any restrictions on the format of the report file.

[1376] ---

[1377] That's all.

[1378] "Example 1"

[1379] (Claim 1)

[1380] means for receiving a digital document from a repository server via a communication means;

[1381] means for storing the received digital document in a temporary storage device;

[1382] means for programmatically analyzing and converting the digital document into a data frame;

[1383] means for analyzing text data of digital documents using natural language processing techniques;

[1384] means for generating improvement suggestions based on the analysis results;

[1385] a means for visualizing and displaying the generated improvement proposals;

[1386] means for receiving input data from a user and updating the self-learning algorithm;

[1387] A system including:

[1388] (Claim 2)

[1389] 10. The system of claim 1, wherein natural language processing techniques are used to perform grammar checking, keyword extraction, summary generation, and sentiment analysis.

[1390] (Claim 3)

[1391] The system according to claim 1, which is compatible with a variety of formats of digital documents without any restrictions on the format.

[1392] "Application Example 1"

[1393] (Claim 1)

[1394] a means for obtaining the report file;

[1395] a means for analyzing the contents of the report;

[1396] means for generating improvement suggestions based on the analysis results;

[1397] a means for displaying the generated improvement suggestions;

[1398] a means of obtaining user feedback and self-learning;

[1399] a means for collecting real-time data from equipment operating in a factory;

[1400] means for analyzing the collected real-time data;

[1401] means for generating improvement proposals for the factory equipment based on the analysis results;

[1402] means for displaying the generated improvement proposals for the factory equipment on a display device;

[1403] A system including:

[1404] (Claim 2)

[1405] 10. The system of claim 1, wherein natural language processing techniques are used in analyzing the content of the report.

[1406] (Claim 3)

[1407] The system according to claim 1, which supports a variety of formats without any restrictions on the format of the report file.

[1408] "Example 2: Combining Emotion Engines"

[1409] (Claim 1)

[1410] a means for obtaining the report file;

[1411] a means for saving the report file;

[1412] A means to read and convert data from report files;

[1413] a means for analyzing the contents of the report;

[1414] means for generating improvement suggestions based on the analysis results;

[1415] a means for displaying the generated improvement suggestions;

[1416] a means for obtaining feedback from a user and recognizing the user's emotions;

[1417] a means of self-learning based on feedback;

[1418] A system including:

[1419] (Claim 2)

[1420] 10. The system of claim 1, wherein natural language processing techniques are used in analyzing the content of the report.

[1421] (Claim 3)

[1422] The system according to claim 1, which supports a variety of formats without any restrictions on the format of the report file.

[1423] "Application example 2 when combining emotion engines"

[1424] (Claim 1)

[1425] a means for obtaining the report file;

[1426] a means for analyzing the contents of the report;

[1427] means for generating improvement suggestions based on the analysis results;

[1428] a means for displaying the generated improvement suggestions;

[1429] emotion recognition means for recognizing the emotion of a user;

[1430] a means of adjusting the tone of the feedback based on emotion recognition;

[1431] a means of obtaining user feedback and self-learning;

[1432] A system including:

[1433] (Claim 2)

[1434] 10. The system of claim 1, wherein natural language processing techniques are used in analyzing the content of the report.

[1435] (Claim 3)

[1436] The system according to claim 1, which supports a variety of formats without any restrictions on the format of the report file.

[1437] (Claim 4)

[1438] 2. The system of claim 1, wherein the emotion recognition means uses techniques for voice analysis and facial expression recognition.

[1439] (Claim 5)

[1440] 2. The system according to claim 1, wherein improvement suggestions are provided in real time according to implementation status. [Explanation of symbols]

[1441] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for obtaining the report file; a means for analyzing the contents of the report; means for generating improvement suggestions based on the analysis results; a means for displaying the generated improvement suggestions; a means of obtaining user feedback and self-learning; A system including:

2. 10. The system of claim 1, wherein natural language processing techniques are used in analyzing the content of the report.

3. The system according to claim 1, wherein the system is not limited to a particular format of the report file and supports a variety of formats.

Images