system

Abstract

We provide the system. [Solution] A means of retrieving error data from a database that stores past error information, A means to generate a machine learning model based on the aforementioned data of criticisms and to learn the patterns of criticisms made by superiors, A means for receiving data, predicting areas for improvement using the machine learning model, and generating feedback, Means for providing the aforementioned feedback to the document creator, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] It is an important issue to reduce the time and mental burden caused by repeated pointing out and correction during document review. In particular, it is a problem that feedback from superiors cannot be predicted in advance and efficient document creation is difficult. As a result, inefficiency in communication occurs between members and superiors, which is a factor contributing to a prolonged review time. Therefore, means for improving the efficiency of document creation are required.

Means for Solving the Problems

[0005] This invention relates to a system that builds a machine learning model based on past feedback data and provides advance feedback to documents created by document creators. Specifically, it uses a model that has learned the patterns of feedback from supervisors to predict areas in the document that need correction and shows the document creator the areas that need correction. This system allows document creators to address issues before review, thereby reducing work time and mental burden.

[0006] A "database" is a system for systematically organizing information and efficiently utilizing and managing accumulated data.

[0007] "Feedback data" refers to information that includes the content of feedback and points for correction that a supervisor has previously given to a document.

[0008] A "machine learning model" is a computational model built using algorithms that learn patterns and rules from a given dataset to perform predictions and classifications.

[0009] "Supervisor feedback patterns" refer to a series of trends regarding the content and characteristic revision requests that supervisors frequently point out during document reviews.

[0010] "Feedback" refers to information that includes evaluations, suggestions, and areas for improvement, with the aim of promoting quality improvement in the subject matter.

[0011] A "document creator" is a person whose role is to create documents such as reports and proposals for work or other purposes.

[0012] "Visual display" refers to a method of enabling users to understand information by presenting it in a visually apparent form on a display or screen. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention relates to a system that improves the efficiency of feedback from supervisors during document creation. In this system, a server, terminals, and users work together to generate and provide effective feedback.

[0035] System Overview

[0036] First, the server maintains a database that stores past feedback data. This database contains points raised by supervisors during past reviews and the corrections made to those points. This data is regularly updated and managed by the server.

[0037] Next, the server uses a machine learning model to analyze and learn patterns of feedback from supervisors. This process allows the server to predict common points of feedback on documents in advance, based on past review information.

[0038] After the user creates a document, they upload it to their device. The device then sends the document to a server for analysis and requests the generation of preliminary feedback.

[0039] The server applies a pre-trained machine learning model to the received documents to identify areas for improvement. Specifically, it predicts points that require correction based on content consistency, data accuracy, and formatting integrity.

[0040] The server then sends the generated feedback back to the terminal, providing it to the user. The user can then modify the document while referring to this feedback. The feedback is displayed visually and designed to be easily understood and applied by the user.

[0041] Specific example

[0042] For example, consider a scenario where a user creates a sales report. This report includes numerical data and market analysis. After completing the report, the user sends it to a server via their terminal. Based on patterns of feedback from similar past reports, the server generates feedback regarding the consistency of the figures and any missing analysis, and sends it back to the terminal. The user can then use this feedback to correct the figures and enhance the analysis, ultimately submitting a high-quality report to their supervisor.

[0043] By improving quality during the document creation stage in this way, potential issues from superiors can be addressed in advance, and review time can be made more efficient.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server retrieves past feedback data from the database. This includes the feedback made by supervisors and the corrections made based on those feedback. This data is then used to create a new training dataset.

[0047] Step 2:

[0048] The server trains a machine learning model based on the created dataset. The model identifies patterns in supervisor feedback and learns what points are most likely to be criticized.

[0049] Step 3:

[0050] The user uploads the created document to their device. The device sends the document specified by the user to the server and requests feedback generation.

[0051] Step 4:

[0052] The server analyzes the received data. It applies a pre-trained machine learning model to identify potential issues in the data and generate specific feedback for improvement.

[0053] Step 5:

[0054] The server sends the generated feedback back to the terminal. The terminal interprets the feedback and presents it visually to the user.

[0055] Step 6:

[0056] Users revise the materials based on the feedback they receive. They finalize the materials by reviewing them again as needed.

[0057] Step 7:

[0058] Finally, once the document is satisfactory to the user, it is submitted directly to the supervisor. This process minimizes additional feedback from the supervisor and ensures efficient document submission.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] A challenge with document creation is the frequent criticism from superiors, which results in significant time and effort spent on revisions. Furthermore, the criticisms are sometimes inconsistent, leading to repeated mistakes and decreased work efficiency. The goal is to resolve these issues, improve document quality, and reduce the time spent on reviews.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for acquiring data from an information resource that stores past feedback information, means for generating a learning model using the data and learning the supervisor's tendency to make criticisms, and means for receiving materials, applying the learning model to predict areas of criticism, and generating a response. This makes it possible to automatically generate high-quality feedback during the material creation stage and to resolve criticisms from supervisors in advance.

[0064] "Feedback information" refers to information resources that include comments and corrections made regarding past documents.

[0065] "Information resources" refers to data sets stored in databases and other similar systems, and includes information pointing out flaws in past documents.

[0066] "Data" refers to specific comments and information about corrections obtained from information resources.

[0067] A "learning model" is an algorithm that uses machine learning to make predictions and classifications for specific tasks, and is used to learn the tendencies of a supervisor's feedback.

[0068] "Tendency to point out flaws" refers to the patterns and characteristics of the types of criticisms a supervisor tends to make about a document.

[0069] "Documents" refer to documents and data that users create and submit for review.

[0070] "Points of concern" refer to sections of the document that are expected to require correction.

[0071] "Response" refers to information that includes specific feedback on the points raised, and is provided to the document creator.

[0072] This invention provides a system that improves the efficiency of feedback from supervisors during document creation. The central components of the system are the server, the terminal, and the user who creates the document.

[0073] The server is responsible for managing information resources that store past feedback data. Specifically, it stores past feedback and correction information in a database and generates a learning model using machine learning algorithms based on that information. This learning model analyzes the supervisor's feedback tendencies and helps predict future areas of feedback. The server builds the machine learning model and processes the data using software such as Python or Tensorflow®.

[0074] Users create documents and upload them to their devices. The devices then send the documents to the server and request analysis. This allows users to easily provide documents to the server and receive feedback.

[0075] The server applies a pre-trained model to the received material to identify areas for improvement regarding content consistency, data accuracy, and formatting. Natural language processing techniques are used to generate a response for the material creator. The generated response is displayed visually, designed to allow users to easily understand the points that need correction.

[0076] For example, when a user creates a sales report, the report includes numerical data and market analysis. After the user completes the document, they send it to the server via their terminal. Based on patterns of feedback from similar past reports, the server generates feedback regarding the consistency of the figures and any missing analysis, and sends it back to the terminal. This allows the user to revise the document based on the feedback and submit a high-quality report to their supervisor.

[0077] An example of a prompt message might be, "While maintaining consistency between the numerical data in the sales report and the market analysis, use past feedback data to predict potential issues." This system is expected to improve quality during the document creation stage and proactively address potential issues from supervisors.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The server retrieves past feedback information from the database. Its input includes comments and correction history regarding past documents, and its output generates a dataset for analysis. This dataset is then processed to serve as training data for a machine learning model.

[0081] Step 2:

[0082] The server uses the acquired data to train a machine learning model. The dataset is used as input for training, and the output is a model that has learned the supervisor's tendency to give feedback. In this process, natural language processing techniques and algorithms are used to perform data calculations, improving the accuracy of the model.

[0083] Step 3:

[0084] The user uploads the completed document to the terminal. The input data is the document created by the user, and the output is the document sent to the server. The terminal provides a simple interface, creating an environment where users can easily submit documents.

[0085] Step 4:

[0086] The server inputs the received data into a machine learning model for analysis. The input data is the uploaded document, and the output predicts the areas of concern within the document. The data calculation performed involves identifying areas of concern based on the model, and the consistency of the content, the accuracy of the data, and the consistency of the format are evaluated.

[0087] Step 5:

[0088] The server generates feedback based on the analysis results. The input is information about the identified issues, and the output includes visually presented feedback for the user. The server organizes the feedback clearly and outputs it in a highly practical format.

[0089] Step 6:

[0090] Users revise the document based on feedback received on their device. The input is feedback provided by the server, and the output is the improved document. By following the feedback and correcting the indicated areas, users can improve the quality of the document.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] In quality control of industrial products, conventional methods have challenges in terms of the accuracy and time efficiency of defect detection. These methods primarily rely on manual verification, often resulting in reactive measures and wasted time and money. There is a need for efficient methods to detect and correct defects before shipment.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes means for acquiring defect data from a database storing past defect information, means for generating a machine learning model based on the defect data and learning defect patterns, means for receiving quality control activities, predicting defect locations using the machine learning model, and generating feedback, and means for displaying the feedback information on a manufacturing machine. This enables highly accurate and time-efficient detection and improvement of defective products in product quality control.

[0096] 1. "Identification information" refers to records of information and identifications that indicated past improvements needed in the quality control process.

[0097] 2. A "database" is a system for storing and managing information and related data.

[0098] 3. A "machine learning model" refers to an algorithm that learns data patterns and makes predictions and classifications based on new data.

[0099] 4. "Patient feedback patterns" are data extracted from past feedback information that represent specific trends or common signs of defects.

[0100] 5. "Quality control activities" refer to a series of processes carried out to maintain and improve the quality of a product.

[0101] 6. "Feedback" refers to information such as improvement suggestions and points to note that are generated based on the results of analysis and checks.

[0102] 7. A "manufacturing machine" is an automated machine or device used to manufacture products, and it can also display quality control information.

[0103] This invention relates to a system aimed at improving the efficiency and accuracy of quality control. It links a server with manufacturing machinery (robots), analyzes past feedback data, and generates automated feedback.

[0104] The server first retrieves issue data from a database containing past issue information. This data includes records of past product defects and improvement suggestions in quality control. The server then generates a machine learning model based on the issue data and learns specific issue patterns. Machine learning frameworks such as TensorFlow and PyTorch can be used during this process.

[0105] As part of quality control activities, when a product is checked by a manufacturing machine, the data is received by a server. The server applies a trained machine learning model to predict quality issues and generates feedback indicating areas for improvement. This feedback is visually displayed on the manufacturing machine's screen, allowing on-site workers to immediately correct the product.

[0106] For example, when an automotive part is produced on an assembly line, the server uses previous defect data to identify insufficiently tightened bolts and provides immediate feedback. This process enables highly accurate defect detection, contributing to improved product quality.

[0107] An example of a prompt in a generative AI model is, "Please advise on building a feedback system for factory quality control that automatically predicts defective areas based on past data and generates improvement suggestions."

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The server retrieves existing issue data from a database that stores past issue information. The input is a database query, and the output is the issue information itself. Specifically, it executes SQL queries in the database management system and aggregates the relevant data.

[0111] Step 2:

[0112] The server generates a machine learning model based on the feedback data obtained in Step 1 and learns the feedback patterns. The input is the feedback data, and the output is a trained machine learning model. Specifically, TensorFlow is used to process the dataset and train the pattern recognition model.

[0113] Step 3:

[0114] The manufacturing machine acquires product quality control information and transmits this data to a server. The input is real-time quality data, and the output, which is the data of the product being inspected, is stored on the server. Specifically, the data is securely transmitted via a communication protocol.

[0115] Step 4:

[0116] The server applies a pre-trained machine learning model to quality control data transmitted from manufacturing machines to predict areas of concern. The input is quality control data, and the output is the predicted areas of concern. Specifically, the model is executed to analyze the data.

[0117] Step 5:

[0118] The server generates feedback based on the prediction in step 4. The input is the prediction result, and the output is feedback information with improvement suggestions. The specific action is to convert the feedback content into a format that is easy to visually interpret.

[0119] Step 6:

[0120] The server sends the generated feedback back to the manufacturing machine for display. The input is feedback information, and the output is the feedback displayed on the manufacturing machine's screen. Specifically, it is visualized based on UI / UX design and provided in a way that is easy for the user to understand.

[0121] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0122] This invention relates to a system that, in addition to improving the efficiency of feedback in document creation, recognizes the user's emotional state and provides appropriate support accordingly. The central elements are a server, a terminal, and an emotion engine that analyzes the user's emotions.

[0123] System Overview

[0124] First, the server maintains a database of past feedback data and uses it to train a machine learning model. The model adapts to the patterns of feedback from supervisors and provides a foundation for making predictions based on documents submitted by users.

[0125] When a user creates a document and uploads it to the system via their device, the server receives the document, uses a machine learning model to predict areas for improvement, and generates specific feedback. In this process, the server also uses an emotion engine to analyze the user's current emotional state. The emotion engine analyzes data obtained from the user (e.g., facial recognition and voice data) to determine whether the user is stressed or relaxed.

[0126] In generating feedback, the server considers the results of the emotion engine and makes adjustments according to the user's emotional state. For example, if the user is experiencing high levels of stress, the feedback is rephrased in gentler language; conversely, if the user is relaxed, more detailed suggestions for improvement are provided.

[0127] The generated feedback is sent back to the device, which visually displays it to the user. The user then revises the material based on the feedback. If necessary, the sentiment engine monitors the user's emotional changes after receiving the feedback to determine if further support is needed.

[0128] Specific example

[0129] For example, suppose a user is writing a technical report and wants it reviewed by the system before submitting it. The server detects that this report is the type that has been flagged for many errors in the past and generates feedback. In this process, if the sentiment engine determines that the user is feeling stressed before submission, the user will be provided with feedback in a softer tone, along with an encouraging message.

[0130] In this way, document creators can efficiently revise their documents while receiving support that takes their emotional state into consideration. This system improves the quality of feedback and reduces the mental burden on users.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The user creates a document and saves the document file to their device. Once the document is complete, they upload it to the system using their device.

[0134] Step 2:

[0135] The device sends the uploaded data to the server and requests the generation of feedback. This request includes a signal to initiate the feedback process.

[0136] Step 3:

[0137] The server receives the document file and first analyzes its contents based on a machine learning model. The model identifies areas where issues are predicted to occur, based on patterns learned from past feedback data.

[0138] Step 4:

[0139] The server generates specific feedback based on the analysis results. This feedback includes areas for improvement and recommended revisions within the document.

[0140] Step 5:

[0141] The server simultaneously monitors the user's current emotional state using an emotion engine. This is done by analyzing the user's voice and video data transmitted from the device, and based on the results, it determines whether the user is tense or relaxed.

[0142] Step 6:

[0143] The server adjusts the generated feedback according to the user's emotional state. If the user is feeling stressed, the feedback is changed to gentler language, and messages are added to alleviate the user's anxiety.

[0144] Step 7:

[0145] The server sends the adjusted feedback to the device. The device displays the feedback visually, presenting it in a way that is easy for the user to understand.

[0146] Step 8:

[0147] Users revise their materials while referring to feedback. After completing the revisions, they can re-upload the materials and request new feedback if necessary.

[0148] Step 9:

[0149] Once the user has completed the final document, they formally submit it to their supervisor or relevant department. This process improves the quality of the document and ensures the user's emotional support.

[0150] (Example 2)

[0151] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0152] In the current document creation process, feedback is often mechanical and fails to consider the creator's emotional state, which can cause significant stress. Furthermore, inaccurate feedback makes it difficult to efficiently improve the document.

[0153] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0154] In this invention, the server includes means for acquiring feedback data from a storage device that stores past feedback information, means for generating a machine learning model based on the feedback data and learning the feedback patterns of higher-ranking users, means for receiving materials, predicting areas for feedback using the machine learning model, and generating feedback, means for analyzing the emotional state of the material creator and adjusting the feedback according to that emotional state, and means for providing the feedback to the material creator. This makes it possible to provide feedback that takes the emotions of the material creator into consideration, reducing stress and enabling efficient material improvement.

[0155] "Information gathering data" refers to a collection of data that shows past feedback and revision history regarding a document.

[0156] A "memory device" is a general term for a device that has the function of storing and retaining data such as pointed-out information.

[0157] A "machine learning model" is an algorithm or mechanism that learns from feedback data and understands the feedback patterns of top performers.

[0158] A "senior" is someone responsible for evaluating the materials and providing feedback on their content.

[0159] "Emotional state" refers to the psychological state of the document creator and is a concept that encompasses multiple emotions, including stress and relaxation.

[0160] "Feedback" refers to information, including suggestions for improvement and evaluations, that is provided regarding a document, and is primarily received by the document creator.

[0161] "Means of adjustment" refers to procedures and mechanisms for modifying the content and expression of feedback, taking into account the emotional state of the document creator.

[0162] A "document creator" is a user who creates documents and receives feedback through the system.

[0163] This system is designed to streamline feedback during document creation and provide support that takes into account the user's emotional state. A specific implementation is described below.

[0164] The server retrieves data from a storage device that has accumulated past feedback information and learns feedback patterns using a machine learning model. The server uses this model to generate predictions and feedback for documents, often employing Python as the programming language and TensorFlow as the machine learning library. It also uses OpenCV or Librosa for sentiment analysis. Leveraging these tools, the server has the ability to analyze the emotions of the document creator and adjust the feedback accordingly.

[0165] Users create documents and upload them to the system using a terminal. The terminal is typically an internet-connected computer that accesses the server via a browser or dedicated application. The uploaded documents are transferred to the server using the HTTP protocol.

[0166] The device also acquires user emotion data via its camera and microphone and sends it to the server. The device processes this data in real time, supporting the server in accurately analyzing the user's emotional state. Receiving feedback tailored to the user's emotional state allows for more appropriate revisions to the materials.

[0167] As a concrete example, consider a scenario where a user creates a technical report and requests a review. The server matches the report type to past feedback data and generates appropriate feedback. If the emotion engine determines during this process that the user is stressed, it provides feedback in softer language and encouraging messages.

[0168] As an example of a prompt message, a user could send text to the server such as, "Please review the technical report. I would appreciate feedback in a gentle tone, taking into account past error patterns," to receive better feedback.

[0169] These steps not only streamline the process of improving materials, but also enable the system to provide flexible support tailored to the user's emotions.

[0170] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0171] Step 1:

[0172] The server retrieves data from a storage device that holds past complaint information. Using this data as input, the server trains a machine learning model to learn complaint patterns. A Python dataframe processing library is used for data processing to extract necessary features. The output is the trained machine learning model.

[0173] Step 2:

[0174] The user creates a document and uploads it to the system using a terminal. The terminal sends the document to the server using the HTTP protocol. The input is the document created by the user, and the server receives it and proceeds to the next processing step. The output is the document data received by the server.

[0175] Step 3:

[0176] The server passes the received data to a machine learning model to predict areas for improvement. The server then performs textual analysis of the data to identify errors and areas for improvement. The input consists of the received data and the trained model, while the output includes the areas of concern and specific feedback.

[0177] Step 4:

[0178] The device uses the user's camera and microphone to acquire emotional data in real time. The device sends this data to a server, which is used as input for emotional analysis. The input is the user's emotional data, and the output is the process of sending this data to the server.

[0179] Step 5:

[0180] The server uses an emotion engine to analyze the user's emotional state. A Python emotion analysis library is used to determine whether the user is stressed or relaxed. The input is emotion data sent from the terminal, and the output is information about the analyzed emotional state.

[0181] Step 6:

[0182] The server adjusts the feedback based on the analyzed emotional state. If the user is stressed, the feedback tone becomes gentler; if relaxed, it provides detailed suggestions for improvement. The input is the analyzed emotional state, and the output is the adjusted feedback.

[0183] Step 7:

[0184] The server sends the adjusted feedback to the terminal. The terminal displays the feedback visually, making it easy for the user to understand. The input is the adjusted feedback, and the output is the feedback information displayed to the user.

[0185] (Application Example 2)

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

[0187] It is crucial to appropriately analyze the emotional state of factory workers and improve the work environment accordingly. However, conventional systems have not adequately recognized workers' stress and relaxation levels in real time, provided appropriate feedback based on these levels, and reduced work efficiency and psychological burden. Therefore, there is a need to provide a system that customizes feedback based on workers' emotional states and improves the factory work environment.

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

[0189] In this invention, the server includes means for acquiring feedback data from an information recording device that stores past feedback information, means for analyzing the emotional state of the creator and adjusting the feedback according to that state, and means for collecting data for analyzing the emotional state of the worker and generating actions and feedback according to that state. This enables automatic adjustment of feedback and actions according to the emotional state of the worker.

[0190] An "information recording device" is a device that stores past information and data regarding incidents and retrieves it as needed.

[0191] A "machine learning model" is an algorithm that learns from collected data and makes predictions and judgments about new information.

[0192] "Instructor" refers to a person or system whose role is to provide feedback and guidance on document creation and work.

[0193] "Feedback" refers to information that provides comments or suggestions for improvement regarding documents or work.

[0194] "Emotional state" refers to the psychological state or mood of the worker or document creator.

[0195] "Automatic adjustment of operation and feedback" is a process that automatically adjusts the operation of a device or system and the feedback it provides in accordance with the emotional state of the operator.

[0196] The system that implements this application primarily consists of a server, a terminal, and an emotion analysis system. The server retrieves previously accumulated feedback information from an information recording device and generates a machine learning model based on it. This model learns the patterns of feedback given by supervisors to workers and document creators and is used to provide appropriate feedback for new documents and tasks.

[0197] The server also collects data from the worker's terminals and equipment and performs sentiment analysis. Specifically, it uses the camera and microphone installed in the terminal to capture the worker's facial expressions and voice, and analyzes them. This uses technologies such as the OpenCV image processing library and Google® Cloud Speech-to-Text for speech recognition. The analyzed data is used by an emotion AI engine to determine the worker's emotional state, and the content of the feedback and the operation of the system are adjusted based on that information.

[0198] For example, while a factory worker is assembling precision parts, the system might detect that the worker looks tired and determine that their stress levels are rising. In this case, the server would generate encouraging feedback for the worker, providing a message such as, "You've worked hard. Maybe you should take a break."

[0199] The generative AI model serves as the foundation for generating feedback and suggestions based on collected data, customizing prompts according to the user's emotional changes. A specific example of a prompt might be, "Analyze the emotional state of workers in the factory and tell me how a robot can assist them if they are feeling stressed."

[0200] This allows terminals and servers to provide personalized feedback based on the worker's emotional state, thereby improving work efficiency and safety.

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] Users upload work data and documents to the server using a terminal. This input includes the worker's facial expressions and voice data. The terminal uses a camera and microphone to capture real-time data of the worker. This data is used later for sentiment analysis.

[0204] Step 2:

[0205] The server receives uploaded documents and related data, and retrieves past issue information from the information recording device. Using this issue data as input, the server uses a machine learning model to predict the areas of concern in the documents and generates feedback data. In this process, the generated AI model outputs optimal feedback based on the characteristics of the documents and data.

[0206] Step 3:

[0207] The server inputs the collected audio and image data into an emotion analysis engine. The server then uses TensorFlow for facial recognition and Google Cloud Speech-to-Text to convert the audio to text. The data is then analyzed by an emotion AI library, and the user's emotional state (e.g., stressed or relaxed) is output.

[0208] Step 4:

[0209] The server combines the generated feedback with the user's emotional state to adjust the final feedback. For example, if the server determines that the user is stressed, it will output feedback that includes gentle language and encouragement. This feedback becomes the final output.

[0210] Step 5:

[0211] The terminal receives feedback from the server and displays it visually to the user. The user then uses this feedback to revise their work or documents. The user's reaction after receiving feedback is also monitored and, if necessary, fed back as data to generate new feedback.

[0212] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0213] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0214] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0218] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0219] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0220] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0221] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0222] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0223] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0224] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0225] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0226] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0227] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0228] This invention relates to a system that improves the efficiency of feedback from supervisors during document creation. In this system, a server, terminals, and users work together to generate and provide effective feedback.

[0229] System Overview

[0230] First, the server maintains a database that stores past feedback data. This database contains points raised by supervisors during past reviews and the corrections made to those points. This data is regularly updated and managed by the server.

[0231] Next, the server uses a machine learning model to analyze and learn patterns of feedback from supervisors. This process allows the server to predict common points of feedback on documents in advance, based on past review information.

[0232] After the user creates a document, they upload it to their device. The device then sends the document to a server for analysis and requests the generation of preliminary feedback.

[0233] The server applies a pre-trained machine learning model to the received documents to identify areas for improvement. Specifically, it predicts points that require correction based on content consistency, data accuracy, and formatting integrity.

[0234] The server then sends the generated feedback back to the terminal, providing it to the user. The user can then modify the document while referring to this feedback. The feedback is displayed visually and designed to be easily understood and applied by the user.

[0235] Specific example

[0236] For example, consider a scenario where a user creates a sales report. This report includes numerical data and market analysis. After completing the report, the user sends it to a server via their terminal. Based on patterns of feedback from similar past reports, the server generates feedback regarding the consistency of the figures and any missing analysis, and sends it back to the terminal. The user can then use this feedback to correct the figures and enhance the analysis, ultimately submitting a high-quality report to their supervisor.

[0237] By improving quality during the document creation stage in this way, potential issues from superiors can be addressed in advance, and review time can be made more efficient.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The server retrieves past feedback data from the database. This includes the feedback made by supervisors and the corrections made based on those feedback. This data is then used to create a new training dataset.

[0241] Step 2:

[0242] The server trains a machine learning model based on the created dataset. The model identifies patterns in supervisor feedback and learns what points are most likely to be criticized.

[0243] Step 3:

[0244] The user uploads the created document to their device. The device sends the document specified by the user to the server and requests feedback generation.

[0245] Step 4:

[0246] The server analyzes the received data. It applies a pre-trained machine learning model to identify potential issues in the data and generate specific feedback for improvement.

[0247] Step 5:

[0248] The server sends the generated feedback back to the terminal. The terminal interprets the feedback and presents it visually to the user.

[0249] Step 6:

[0250] Users revise the materials based on the feedback they receive. They finalize the materials by reviewing them again as needed.

[0251] Step 7:

[0252] Finally, once the document is satisfactory to the user, it is submitted directly to the supervisor. This process minimizes additional feedback from the supervisor and ensures efficient document submission.

[0253] (Example 1)

[0254] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0255] A challenge with document creation is the frequent criticism from superiors, which results in significant time and effort spent on revisions. Furthermore, the criticisms are sometimes inconsistent, leading to repeated mistakes and decreased work efficiency. The goal is to resolve these issues, improve document quality, and reduce the time spent on reviews.

[0256] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0257] In this invention, the server includes means for acquiring data from an information resource that stores past feedback information, means for generating a learning model using the data and learning the supervisor's tendency to make criticisms, and means for receiving materials, applying the learning model to predict areas of criticism, and generating a response. This makes it possible to automatically generate high-quality feedback during the material creation stage and to resolve criticisms from supervisors in advance.

[0258] "Feedback information" refers to information resources that include comments and corrections made regarding past documents.

[0259] "Information resources" refers to data sets stored in databases and other similar systems, and includes information pointing out flaws in past documents.

[0260] "Data" refers to specific comments and information about corrections obtained from information resources.

[0261] A "learning model" is an algorithm that uses machine learning to make predictions and classifications for specific tasks, and is used to learn the tendencies of a supervisor's feedback.

[0262] "Tendency to point out flaws" refers to the patterns and characteristics of the types of criticisms a supervisor tends to make about a document.

[0263] "Documents" refer to documents and data that users create and submit for review.

[0264] "Points of concern" refer to sections of the document that are expected to require correction.

[0265] "Response" refers to information that includes specific feedback on the points raised, and is provided to the document creator.

[0266] This invention provides a system that improves the efficiency of feedback from supervisors during document creation. The central components of the system are the server, the terminal, and the user who creates the document.

[0267] The server is responsible for managing information resources that store past feedback data. Specifically, it stores past feedback and correction information in a database and generates a learning model using machine learning algorithms based on that information. This learning model analyzes the supervisor's feedback tendencies and helps predict future areas of concern. The server builds the machine learning model and processes the data using software such as Python or TensorFlow.

[0268] Users create documents and upload them to their devices. The devices then send the documents to the server and request analysis. This allows users to easily provide documents to the server and receive feedback.

[0269] The server applies a pre-trained model to the received material to identify areas for improvement regarding content consistency, data accuracy, and formatting. Natural language processing techniques are used to generate a response for the material creator. The generated response is displayed visually, designed to allow users to easily understand the points that need correction.

[0270] For example, when a user creates a sales report, the report includes numerical data and market analysis. After the user completes the document, they send it to the server via their terminal. Based on patterns of feedback from similar past reports, the server generates feedback regarding the consistency of the figures and any missing analysis, and sends it back to the terminal. This allows the user to revise the document based on the feedback and submit a high-quality report to their supervisor.

[0271] An example of a prompt message might be, "While maintaining consistency between the numerical data in the sales report and the market analysis, use past feedback data to predict potential issues." This system is expected to improve quality during the document creation stage and proactively address potential issues from supervisors.

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The server retrieves past feedback information from the database. Its input includes comments and correction history regarding past documents, and its output generates a dataset for analysis. This dataset is then processed to serve as training data for a machine learning model.

[0275] Step 2:

[0276] The server uses the acquired data to train a machine learning model. As the input for training, a dataset is used, and as the output, a model that has learned the supervisor's pointing tendencies is generated. In this process, data operations are performed by leveraging natural language processing techniques and algorithms, improving the accuracy of the model.

[0277] Step 3:

[0278] The user uploads the completed document to the terminal. As the input data, there is the document created by the user, and as the output, the document is sent to the server. The terminal provides a simple interface, creating an environment where the user can easily send the document.

[0279] Step 4:

[0280] The server inputs the received document into the machine learning model for analysis. The input data is the uploaded document, and as the output, the pointed-out locations within the document are predicted. The data operation performed is the identification of the pointed-out locations based on the model, and the content consistency, data accuracy, and format consistency are evaluated.

[0281] Step 5:

[0282] The server generates feedback based on the analysis results. This input is the information on the pointed-out locations, and as the output, the feedback visually provided to the user is included. At this time, the server organizes the feedback in an understandable manner and outputs it in a highly practical form.

[0283] Step 6:

[0284] The user modifies the document based on the feedback received on the terminal. The input is the feedback provided by the server, and the output is the improved document. The user can enhance the completeness of the document by following the feedback and correcting the pointed-out locations.

[0285] (Application Example 1)

[0286] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0287] In the quality control of industrial products, the conventional method has problems in the detection accuracy and time efficiency of defective products. The main method is manual confirmation work, and there are many post-event responses, which may waste costs and time. There is a need for means to efficiently detect and improve defects before shipment.

[0288] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0289] In this invention, the server includes means for acquiring pointing data from a database storing past pointing information, means for generating a machine learning model based on the pointing data and learning a pointing pattern, means for receiving a quality control activity, predicting a pointing location using the machine learning model, and generating feedback, and means for displaying feedback information on a manufacturing machine. Thereby, it becomes possible to detect and improve defective products with high accuracy and good time efficiency in the quality control of products.

[0290] 1. "Pointing information" refers to information and records of past improvements and points required in the quality control process.

[0291] 2. "Database" is a system for storing and managing pointing information and related data.

[0292] 3. "Machine learning model" refers to an algorithm that learns data patterns and makes predictions and classifications based on new data.

[0293] 4. "Pointing pattern" is data representing specific trends and general defect signs extracted from past pointing information.

[0294] 5. "Quality control activities" refer to a series of processes carried out to maintain and improve the quality of a product.

[0295] 6. "Feedback" refers to information such as improvement suggestions and points to note that are generated based on the results of analysis and checks.

[0296] 7. A "manufacturing machine" is an automated machine or device used to manufacture products, and it can also display quality control information.

[0297] This invention relates to a system aimed at improving the efficiency and accuracy of quality control. It links a server with manufacturing machinery (robots), analyzes past feedback data, and generates automated feedback.

[0298] The server first retrieves issue data from a database containing past issue information. This data includes records of past product defects and improvement suggestions in quality control. The server then generates a machine learning model based on the issue data and learns specific issue patterns. Machine learning frameworks such as TensorFlow and PyTorch can be used during this process.

[0299] As part of quality control activities, when a product is checked by a manufacturing machine, the data is received by a server. The server applies a trained machine learning model to predict quality issues and generates feedback indicating areas for improvement. This feedback is visually displayed on the manufacturing machine's screen, allowing on-site workers to immediately correct the product.

[0300] For example, when an automotive part is produced on an assembly line, the server uses previous defect data to identify insufficiently tightened bolts and provides immediate feedback. This process enables highly accurate defect detection, contributing to improved product quality.

[0301] As an example of a prompt sentence in a generative AI model, utilization in the form of "Please advise on the construction of a feedback system that automatically predicts defective parts based on past data and generates improvement proposals in factory quality control." can be considered.

[0302] The flow of a specific process in Application Example 1 will be described using FIG. 12.

[0303] Step 1:

[0304] The server obtains existing pointing data from a database storing past pointing information. The input is a query to the database, and pointing information is obtained as the output. Specifically, an SQL query is executed in a database management system to aggregate relevant data.

[0305] Step 2:

[0306] Based on the pointing data obtained in Step 1, the server generates a machine learning model and learns the pointing pattern. The input is the pointing data, and a trained machine learning model is obtained as the output. Specifically, a dataset is processed using TensorFlow, and a pattern recognition model is trained.

[0307] Step 3:

[0308] The manufacturing machine obtains the quality control information of the product and transmits the data to the server. The input is real-time quality data, and the inspection target data is stored in the server as the output. As a specific operation, the data is securely transmitted via a communication protocol.

[0309] Step 4:

[0310] The server applies the trained machine learning model to the quality control data transmitted from the manufacturing machine and predicts the pointed-out locations. The input is the quality control data, and the predicted pointed-out locations are obtained as the output. Specifically, the model is executed to analyze the data.

[0311] Step 5:

[0312] The server generates feedback based on the prediction in step 4. The input is the prediction result, and the output is feedback information with improvement suggestions. The specific action is to convert the feedback content into a format that is easy to visually interpret.

[0313] Step 6:

[0314] The server sends the generated feedback back to the manufacturing machine for display. The input is feedback information, and the output is the feedback displayed on the manufacturing machine's screen. Specifically, it is visualized based on UI / UX design and provided in a way that is easy for the user to understand.

[0315] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0316] This invention relates to a system that, in addition to improving the efficiency of feedback in document creation, recognizes the user's emotional state and provides appropriate support accordingly. The central elements are a server, a terminal, and an emotion engine that analyzes the user's emotions.

[0317] System Overview

[0318] First, the server maintains a database of past feedback data and uses it to train a machine learning model. The model adapts to the patterns of feedback from supervisors and provides a foundation for making predictions based on documents submitted by users.

[0319] When a user creates a document and uploads it to the system via their device, the server receives the document, uses a machine learning model to predict areas for improvement, and generates specific feedback. In this process, the server also uses an emotion engine to analyze the user's current emotional state. The emotion engine analyzes data obtained from the user (e.g., facial recognition and voice data) to determine whether the user is stressed or relaxed.

[0320] In generating feedback, the server considers the results of the emotion engine and makes adjustments according to the user's emotional state. For example, if the user is experiencing high levels of stress, the feedback is rephrased in gentler language; conversely, if the user is relaxed, more detailed suggestions for improvement are provided.

[0321] The generated feedback is sent back to the device, which visually displays it to the user. The user then revises the material based on the feedback. If necessary, the sentiment engine monitors the user's emotional changes after receiving the feedback to determine if further support is needed.

[0322] Specific example

[0323] For example, suppose a user is writing a technical report and wants it reviewed by the system before submitting it. The server detects that this report is the type that has been flagged for many errors in the past and generates feedback. In this process, if the sentiment engine determines that the user is feeling stressed before submission, the user will be provided with feedback in a softer tone, along with an encouraging message.

[0324] In this way, document creators can efficiently revise their documents while receiving support that takes their emotional state into consideration. This system improves the quality of feedback and reduces the mental burden on users.

[0325] The following describes the processing flow.

[0326] Step 1:

[0327] The user creates a document and saves the document file to their device. Once the document is complete, they upload it to the system using their device.

[0328] Step 2:

[0329] The device sends the uploaded data to the server and requests the generation of feedback. This request includes a signal to initiate the feedback process.

[0330] Step 3:

[0331] The server receives the document file and first analyzes its contents based on a machine learning model. The model identifies areas where issues are predicted to occur, based on patterns learned from past feedback data.

[0332] Step 4:

[0333] The server generates specific feedback based on the analysis results. This feedback includes areas for improvement and recommended revisions within the document.

[0334] Step 5:

[0335] The server simultaneously monitors the user's current emotional state using an emotion engine. This is done by analyzing the user's voice and video data transmitted from the device, and based on the results, it determines whether the user is tense or relaxed.

[0336] Step 6:

[0337] The server adjusts the generated feedback according to the user's emotional state. If the user is feeling stressed, the feedback is changed to gentler language, and messages are added to alleviate the user's anxiety.

[0338] Step 7:

[0339] The server sends the adjusted feedback to the device. The device displays the feedback visually, presenting it in a way that is easy for the user to understand.

[0340] Step 8:

[0341] Users revise their materials while referring to feedback. After completing the revisions, they can re-upload the materials and request new feedback if necessary.

[0342] Step 9:

[0343] Once the user has completed the final document, they formally submit it to their supervisor or relevant department. This process improves the quality of the document and ensures the user's emotional support.

[0344] (Example 2)

[0345] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0346] In the current document creation process, feedback is often mechanical and fails to consider the creator's emotional state, which can cause significant stress. Furthermore, inaccurate feedback makes it difficult to efficiently improve the document.

[0347] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0348] In this invention, the server includes means for acquiring feedback data from a storage device that stores past feedback information, means for generating a machine learning model based on the feedback data and learning the feedback patterns of higher-ranking users, means for receiving materials, predicting areas for feedback using the machine learning model, and generating feedback, means for analyzing the emotional state of the material creator and adjusting the feedback according to that emotional state, and means for providing the feedback to the material creator. This makes it possible to provide feedback that takes the emotions of the material creator into consideration, reducing stress and enabling efficient material improvement.

[0349] "Information gathering data" refers to a collection of data that shows past feedback and revision history regarding a document.

[0350] A "memory device" is a general term for a device that has the function of storing and retaining data such as pointed-out information.

[0351] A "machine learning model" is an algorithm or mechanism that learns from feedback data and understands the feedback patterns of top performers.

[0352] A "senior" is someone responsible for evaluating the materials and providing feedback on their content.

[0353] "Emotional state" refers to the psychological state of the document creator and is a concept that encompasses multiple emotions, including stress and relaxation.

[0354] "Feedback" refers to information, including suggestions for improvement and evaluations, that is provided regarding a document, and is primarily received by the document creator.

[0355] "Means of adjustment" refers to procedures and mechanisms for modifying the content and expression of feedback, taking into account the emotional state of the document creator.

[0356] A "document creator" is a user who creates documents and receives feedback through the system.

[0357] This system is designed to streamline feedback during document creation and provide support that takes into account the user's emotional state. A specific implementation is described below.

[0358] The server retrieves data from a storage device that has accumulated past feedback information and learns feedback patterns using a machine learning model. The server uses this model to generate predictions and feedback for documents, often employing Python as the programming language and TensorFlow as the machine learning library. It also uses OpenCV or Librosa for sentiment analysis. Leveraging these tools, the server has the ability to analyze the emotions of the document creator and adjust the feedback accordingly.

[0359] Users create documents and upload them to the system using a terminal. The terminal is typically an internet-connected computer that accesses the server via a browser or dedicated application. The uploaded documents are transferred to the server using the HTTP protocol.

[0360] The device also acquires user emotion data via its camera and microphone and sends it to the server. The device processes this data in real time, supporting the server in accurately analyzing the user's emotional state. Receiving feedback tailored to the user's emotional state allows for more appropriate revisions to the materials.

[0361] As a concrete example, consider a scenario where a user creates a technical report and requests a review. The server matches the report type to past feedback data and generates appropriate feedback. If the emotion engine determines during this process that the user is stressed, it provides feedback in softer language and encouraging messages.

[0362] As an example of a prompt message, a user could send text to the server such as, "Please review the technical report. I would appreciate feedback in a gentle tone, taking into account past error patterns," to receive better feedback.

[0363] These steps not only streamline the process of improving materials, but also enable the system to provide flexible support tailored to the user's emotions.

[0364] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0365] Step 1:

[0366] The server retrieves data from a storage device that holds past complaint information. Using this data as input, the server trains a machine learning model to learn complaint patterns. A Python dataframe processing library is used for data processing to extract necessary features. The output is the trained machine learning model.

[0367] Step 2:

[0368] The user creates a document and uploads it to the system using a terminal. The terminal sends the document to the server using the HTTP protocol. The input is the document created by the user, and the server receives it and proceeds to the next processing step. The output is the document data received by the server.

[0369] Step 3:

[0370] The server passes the received data to a machine learning model to predict areas for improvement. The server then performs textual analysis of the data to identify errors and areas for improvement. The input consists of the received data and the trained model, while the output includes the areas of concern and specific feedback.

[0371] Step 4:

[0372] The device uses the user's camera and microphone to acquire emotional data in real time. The device sends this data to a server, which is used as input for emotional analysis. The input is the user's emotional data, and the output is the process of sending this data to the server.

[0373] Step 5:

[0374] The server uses an emotion engine to analyze the user's emotional state. A Python emotion analysis library is used to determine whether the user is stressed or relaxed. The input is emotion data sent from the terminal, and the output is information about the analyzed emotional state.

[0375] Step 6:

[0376] The server adjusts the feedback based on the analyzed emotional state. If the user is stressed, the feedback tone becomes gentler; if relaxed, it provides detailed suggestions for improvement. The input is the analyzed emotional state, and the output is the adjusted feedback.

[0377] Step 7:

[0378] The server sends the adjusted feedback to the terminal. The terminal displays the feedback visually, making it easy for the user to understand. The input is the adjusted feedback, and the output is the feedback information displayed to the user.

[0379] (Application Example 2)

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

[0381] It is crucial to appropriately analyze the emotional state of factory workers and improve the work environment accordingly. However, conventional systems have not adequately recognized workers' stress and relaxation levels in real time, provided appropriate feedback based on these levels, and reduced work efficiency and psychological burden. Therefore, there is a need to provide a system that customizes feedback based on workers' emotional states and improves the factory work environment.

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

[0383] In this invention, the server includes means for acquiring feedback data from an information recording device that stores past feedback information, means for analyzing the emotional state of the creator and adjusting the feedback according to that state, and means for collecting data for analyzing the emotional state of the worker and generating actions and feedback according to that state. This enables automatic adjustment of feedback and actions according to the emotional state of the worker.

[0384] An "information recording device" is a device that stores past information and data regarding incidents and retrieves it as needed.

[0385] A "machine learning model" is an algorithm that learns from collected data and makes predictions and judgments about new information.

[0386] "Instructor" refers to a person or system whose role is to provide feedback and guidance on document creation and work.

[0387] "Feedback" refers to information that provides comments or suggestions for improvement regarding documents or work.

[0388] "Emotional state" refers to the psychological state or mood of the worker or document creator.

[0389] "Automatic adjustment of operation and feedback" is a process that automatically adjusts the operation of a device or system and the feedback it provides in accordance with the emotional state of the operator.

[0390] The system that implements this application primarily consists of a server, a terminal, and an emotion analysis system. The server retrieves previously accumulated feedback information from an information recording device and generates a machine learning model based on it. This model learns the patterns of feedback given by supervisors to workers and document creators and is used to provide appropriate feedback for new documents and tasks.

[0391] The server also collects data from the worker's terminals and equipment and performs sentiment analysis. Specifically, it uses the camera and microphone installed in the terminal to capture the worker's facial expressions and voice, and analyzes them. This uses technologies such as the OpenCV image processing library and Google Cloud Speech-to-Text for speech recognition. The analyzed data is used through an emotion AI engine to determine the worker's emotional state, and the content of the feedback and the operation of the system are adjusted based on that information.

[0392] For example, while a factory worker is assembling precision parts, the system might detect that the worker looks tired and determine that their stress levels are rising. In this case, the server would generate encouraging feedback for the worker, providing a message such as, "You've worked hard. Maybe you should take a break."

[0393] The generative AI model serves as the foundation for generating feedback and suggestions based on collected data, customizing prompts according to the user's emotional changes. A specific example of a prompt might be, "Analyze the emotional state of workers in the factory and tell me how a robot can assist them if they are feeling stressed."

[0394] This allows terminals and servers to provide personalized feedback based on the worker's emotional state, thereby improving work efficiency and safety.

[0395] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0396] Step 1:

[0397] Users upload work data and documents to the server using a terminal. This input includes the worker's facial expressions and voice data. The terminal uses a camera and microphone to capture real-time data of the worker. This data is used later for sentiment analysis.

[0398] Step 2:

[0399] The server receives uploaded documents and related data, and retrieves past issue information from the information recording device. Using this issue data as input, the server uses a machine learning model to predict the areas of concern in the documents and generates feedback data. In this process, the generated AI model outputs optimal feedback based on the characteristics of the documents and data.

[0400] Step 3:

[0401] The server inputs the collected audio and image data into an emotion analysis engine. The server then uses TensorFlow for facial recognition and Google Cloud Speech-to-Text to convert the audio to text. The data is then analyzed by an emotion AI library, and the user's emotional state (e.g., stressed or relaxed) is output.

[0402] Step 4:

[0403] The server combines the generated feedback with the user's emotional state to adjust the final feedback. For example, if the server determines that the user is stressed, it will output feedback that includes gentle language and encouragement. This feedback becomes the final output.

[0404] Step 5:

[0405] The terminal receives feedback from the server and displays it visually to the user. The user then uses this feedback to revise their work or documents. The user's reaction after receiving feedback is also monitored and, if necessary, fed back as data to generate new feedback.

[0406] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0407] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0408] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0409] [Third Embodiment]

[0410] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0411] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0412] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0413] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0414] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0415] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0416] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0417] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0418] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0419] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0420] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0421] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0422] This invention relates to a system that improves the efficiency of feedback from supervisors during document creation. In this system, a server, terminals, and users work together to generate and provide effective feedback.

[0423] System Overview

[0424] First, the server maintains a database that stores past feedback data. This database contains points raised by supervisors during past reviews and the corrections made to those points. This data is regularly updated and managed by the server.

[0425] Next, the server uses a machine learning model to analyze and learn patterns of feedback from supervisors. This process allows the server to predict common points of feedback on documents in advance, based on past review information.

[0426] After the user creates a document, they upload it to their device. The device then sends the document to a server for analysis and requests the generation of preliminary feedback.

[0427] The server applies a pre-trained machine learning model to the received documents to identify areas for improvement. Specifically, it predicts points that require correction based on content consistency, data accuracy, and formatting integrity.

[0428] The server then sends the generated feedback back to the terminal, providing it to the user. The user can then modify the document while referring to this feedback. The feedback is displayed visually and designed to be easily understood and applied by the user.

[0429] Specific example

[0430] For example, consider a scenario where a user creates a sales report. This report includes numerical data and market analysis. After completing the report, the user sends it to a server via their terminal. Based on patterns of feedback from similar past reports, the server generates feedback regarding the consistency of the figures and any missing analysis, and sends it back to the terminal. The user can then use this feedback to correct the figures and enhance the analysis, ultimately submitting a high-quality report to their supervisor.

[0431] By improving quality during the document creation stage in this way, potential issues from superiors can be addressed in advance, and review time can be made more efficient.

[0432] The following describes the processing flow.

[0433] Step 1:

[0434] The server retrieves past feedback data from the database. This includes the feedback made by supervisors and the corrections made based on those feedback. This data is then used to create a new training dataset.

[0435] Step 2:

[0436] The server trains a machine learning model based on the created dataset. The model identifies patterns in supervisor feedback and learns what points are most likely to be criticized.

[0437] Step 3:

[0438] The user uploads the created document to their device. The device sends the document specified by the user to the server and requests feedback generation.

[0439] Step 4:

[0440] The server analyzes the received data. It applies a pre-trained machine learning model to identify potential issues in the data and generate specific feedback for improvement.

[0441] Step 5:

[0442] The server sends the generated feedback back to the terminal. The terminal interprets the feedback and presents it visually to the user.

[0443] Step 6:

[0444] Users revise the materials based on the feedback they receive. They finalize the materials by reviewing them again as needed.

[0445] Step 7:

[0446] Finally, once the document is satisfactory to the user, it is submitted directly to the supervisor. This process minimizes additional feedback from the supervisor and ensures efficient document submission.

[0447] (Example 1)

[0448] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0449] A challenge with document creation is the frequent criticism from superiors, which results in significant time and effort spent on revisions. Furthermore, the criticisms are sometimes inconsistent, leading to repeated mistakes and decreased work efficiency. The goal is to resolve these issues, improve document quality, and reduce the time spent on reviews.

[0450] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0451] In this invention, the server includes means for acquiring data from an information resource that stores past feedback information, means for generating a learning model using the data and learning the supervisor's tendency to make criticisms, and means for receiving materials, applying the learning model to predict areas of criticism, and generating a response. This makes it possible to automatically generate high-quality feedback during the material creation stage and to resolve criticisms from supervisors in advance.

[0452] "Feedback information" refers to information resources that include comments and corrections made regarding past documents.

[0453] "Information resources" refers to data sets stored in databases and other similar systems, and includes information pointing out flaws in past documents.

[0454] "Data" refers to specific comments and information about corrections obtained from information resources.

[0455] A "learning model" is an algorithm that uses machine learning to make predictions and classifications for specific tasks, and is used to learn the tendencies of a supervisor's feedback.

[0456] "Tendency to point out flaws" refers to the patterns and characteristics of the types of criticisms a supervisor tends to make about a document.

[0457] "Documents" refer to documents and data that users create and submit for review.

[0458] "Points of concern" refer to sections of the document that are expected to require correction.

[0459] "Response" refers to information that includes specific feedback on the points raised, and is provided to the document creator.

[0460] This invention provides a system that improves the efficiency of feedback from supervisors during document creation. The central components of the system are the server, the terminal, and the user who creates the document.

[0461] The server is responsible for managing information resources that store past feedback data. Specifically, it stores past feedback and correction information in a database and generates a learning model using machine learning algorithms based on that information. This learning model analyzes the supervisor's feedback tendencies and helps predict future areas of concern. The server builds the machine learning model and processes the data using software such as Python or TensorFlow.

[0462] Users create documents and upload them to their devices. The devices then send the documents to the server and request analysis. This allows users to easily provide documents to the server and receive feedback.

[0463] The server applies a pre-trained model to the received material to identify areas for improvement regarding content consistency, data accuracy, and formatting. Natural language processing techniques are used to generate a response for the material creator. The generated response is displayed visually, designed to allow users to easily understand the points that need correction.

[0464] For example, when a user creates a sales report, the report includes numerical data and market analysis. After the user completes the document, they send it to the server via their terminal. Based on patterns of feedback from similar past reports, the server generates feedback regarding the consistency of the figures and any missing analysis, and sends it back to the terminal. This allows the user to revise the document based on the feedback and submit a high-quality report to their supervisor.

[0465] An example of a prompt message might be, "While maintaining consistency between the numerical data in the sales report and the market analysis, use past feedback data to predict potential issues." This system is expected to improve quality during the document creation stage and proactively address potential issues from supervisors.

[0466] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0467] Step 1:

[0468] The server retrieves past feedback information from the database. Its input includes comments and correction history regarding past documents, and its output generates a dataset for analysis. This dataset is then processed to serve as training data for a machine learning model.

[0469] Step 2:

[0470] The server uses the acquired data to train a machine learning model. The dataset is used as input for training, and the output is a model that has learned the supervisor's tendency to give feedback. In this process, natural language processing techniques and algorithms are used to perform data calculations, improving the accuracy of the model.

[0471] Step 3:

[0472] The user uploads the completed document to the terminal. The input data is the document created by the user, and the output is the document sent to the server. The terminal provides a simple interface, creating an environment where users can easily submit documents.

[0473] Step 4:

[0474] The server inputs the received data into a machine learning model for analysis. The input data is the uploaded document, and the output predicts the areas of concern within the document. The data calculation performed involves identifying areas of concern based on the model, and the consistency of the content, the accuracy of the data, and the consistency of the format are evaluated.

[0475] Step 5:

[0476] The server generates feedback based on the analysis results. The input is information about the identified issues, and the output includes visually presented feedback for the user. The server organizes the feedback clearly and outputs it in a highly practical format.

[0477] Step 6:

[0478] Users revise the document based on feedback received on their device. The input is feedback provided by the server, and the output is the improved document. By following the feedback and correcting the indicated areas, users can improve the quality of the document.

[0479] (Application Example 1)

[0480] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0481] In quality control of industrial products, conventional methods have challenges in terms of the accuracy and time efficiency of defect detection. These methods primarily rely on manual verification, often resulting in reactive measures and wasted time and money. There is a need for efficient methods to detect and correct defects before shipment.

[0482] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0483] In this invention, the server includes means for acquiring defect data from a database storing past defect information, means for generating a machine learning model based on the defect data and learning defect patterns, means for receiving quality control activities, predicting defect locations using the machine learning model, and generating feedback, and means for displaying the feedback information on a manufacturing machine. This enables highly accurate and time-efficient detection and improvement of defective products in product quality control.

[0484] 1. "Identification information" refers to records of information and identifications that indicated past improvements needed in the quality control process.

[0485] 2. A "database" is a system for storing and managing information and related data.

[0486] 3. A "machine learning model" refers to an algorithm that learns data patterns and makes predictions and classifications based on new data.

[0487] 4. "Patient feedback patterns" are data extracted from past feedback information that represent specific trends or common signs of defects.

[0488] 5. "Quality control activities" refer to a series of processes carried out to maintain and improve the quality of a product.

[0489] 6. "Feedback" refers to information such as improvement suggestions and points to note that are generated based on the results of analysis and checks.

[0490] 7. A "manufacturing machine" is an automated machine or device used to manufacture products, and it can also display quality control information.

[0491] This invention relates to a system aimed at improving the efficiency and accuracy of quality control. It links a server with manufacturing machinery (robots), analyzes past feedback data, and generates automated feedback.

[0492] The server first retrieves issue data from a database containing past issue information. This data includes records of past product defects and improvement suggestions in quality control. The server then generates a machine learning model based on the issue data and learns specific issue patterns. Machine learning frameworks such as TensorFlow and PyTorch can be used during this process.

[0493] As part of quality control activities, when a product is checked by a manufacturing machine, the data is received by a server. The server applies a trained machine learning model to predict quality issues and generates feedback indicating areas for improvement. This feedback is visually displayed on the manufacturing machine's screen, allowing on-site workers to immediately correct the product.

[0494] For example, when an automotive part is produced on an assembly line, the server uses previous defect data to identify insufficiently tightened bolts and provides immediate feedback. This process enables highly accurate defect detection, contributing to improved product quality.

[0495] An example of a prompt in a generative AI model is, "Please advise on building a feedback system for factory quality control that automatically predicts defective areas based on past data and generates improvement suggestions."

[0496] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0497] Step 1:

[0498] The server retrieves existing issue data from a database that stores past issue information. The input is a database query, and the output is the issue information itself. Specifically, it executes SQL queries in the database management system and aggregates the relevant data.

[0499] Step 2:

[0500] The server generates a machine learning model based on the feedback data obtained in Step 1 and learns the feedback patterns. The input is the feedback data, and the output is a trained machine learning model. Specifically, TensorFlow is used to process the dataset and train the pattern recognition model.

[0501] Step 3:

[0502] The manufacturing machine acquires product quality control information and transmits this data to a server. The input is real-time quality data, and the output, which is the data of the product being inspected, is stored on the server. Specifically, the data is securely transmitted via a communication protocol.

[0503] Step 4:

[0504] The server applies a pre-trained machine learning model to quality control data transmitted from manufacturing machines to predict areas of concern. The input is quality control data, and the output is the predicted areas of concern. Specifically, the model is executed to analyze the data.

[0505] Step 5:

[0506] The server generates feedback based on the prediction in step 4. The input is the prediction result, and the output is feedback information with improvement suggestions. The specific action is to convert the feedback content into a format that is easy to visually interpret.

[0507] Step 6:

[0508] The server sends the generated feedback back to the manufacturing machine for display. The input is feedback information, and the output is the feedback displayed on the manufacturing machine's screen. Specifically, it is visualized based on UI / UX design and provided in a way that is easy for the user to understand.

[0509] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0510] This invention relates to a system that, in addition to improving the efficiency of feedback in document creation, recognizes the user's emotional state and provides appropriate support accordingly. The central elements are a server, a terminal, and an emotion engine that analyzes the user's emotions.

[0511] System Overview

[0512] First, the server maintains a database of past feedback data and uses it to train a machine learning model. The model adapts to the patterns of feedback from supervisors and provides a foundation for making predictions based on documents submitted by users.

[0513] When a user creates a document and uploads it to the system via their device, the server receives the document, uses a machine learning model to predict areas for improvement, and generates specific feedback. In this process, the server also uses an emotion engine to analyze the user's current emotional state. The emotion engine analyzes data obtained from the user (e.g., facial recognition and voice data) to determine whether the user is stressed or relaxed.

[0514] In generating feedback, the server considers the results of the emotion engine and makes adjustments according to the user's emotional state. For example, if the user is experiencing high levels of stress, the feedback is rephrased in gentler language; conversely, if the user is relaxed, more detailed suggestions for improvement are provided.

[0515] The generated feedback is sent back to the device, which visually displays it to the user. The user then revises the material based on the feedback. If necessary, the sentiment engine monitors the user's emotional changes after receiving the feedback to determine if further support is needed.

[0516] Specific example

[0517] For example, suppose a user is writing a technical report and wants it reviewed by the system before submitting it. The server detects that this report is the type that has been flagged for many errors in the past and generates feedback. In this process, if the sentiment engine determines that the user is feeling stressed before submission, the user will be provided with feedback in a softer tone, along with an encouraging message.

[0518] In this way, document creators can efficiently revise their documents while receiving support that takes their emotional state into consideration. This system improves the quality of feedback and reduces the mental burden on users.

[0519] The following describes the processing flow.

[0520] Step 1:

[0521] The user creates a document and saves the document file to their device. Once the document is complete, they upload it to the system using their device.

[0522] Step 2:

[0523] The device sends the uploaded data to the server and requests the generation of feedback. This request includes a signal to initiate the feedback process.

[0524] Step 3:

[0525] The server receives the document file and first analyzes its contents based on a machine learning model. The model identifies areas where issues are predicted to occur, based on patterns learned from past feedback data.

[0526] Step 4:

[0527] The server generates specific feedback based on the analysis results. This feedback includes areas for improvement and recommended revisions within the document.

[0528] Step 5:

[0529] The server simultaneously monitors the user's current emotional state using an emotion engine. This is done by analyzing the user's voice and video data transmitted from the device, and based on the results, it determines whether the user is tense or relaxed.

[0530] Step 6:

[0531] The server adjusts the generated feedback according to the user's emotional state. If the user is feeling stressed, the feedback is changed to gentler language, and messages are added to alleviate the user's anxiety.

[0532] Step 7:

[0533] The server sends the adjusted feedback to the device. The device displays the feedback visually, presenting it in a way that is easy for the user to understand.

[0534] Step 8:

[0535] Users revise their materials while referring to feedback. After completing the revisions, they can re-upload the materials and request new feedback if necessary.

[0536] Step 9:

[0537] Once the user has completed the final document, they formally submit it to their supervisor or relevant department. This process improves the quality of the document and ensures the user's emotional support.

[0538] (Example 2)

[0539] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0540] In the current document creation process, feedback is often mechanical and fails to consider the creator's emotional state, which can cause significant stress. Furthermore, inaccurate feedback makes it difficult to efficiently improve the document.

[0541] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0542] In this invention, the server includes means for acquiring feedback data from a storage device that stores past feedback information, means for generating a machine learning model based on the feedback data and learning the feedback patterns of higher-ranking users, means for receiving materials, predicting areas for feedback using the machine learning model, and generating feedback, means for analyzing the emotional state of the material creator and adjusting the feedback according to that emotional state, and means for providing the feedback to the material creator. This makes it possible to provide feedback that takes the emotions of the material creator into consideration, reducing stress and enabling efficient material improvement.

[0543] "Information gathering data" refers to a collection of data that shows past feedback and revision history regarding a document.

[0544] A "memory device" is a general term for a device that has the function of storing and retaining data such as pointed-out information.

[0545] A "machine learning model" is an algorithm or mechanism that learns from feedback data and understands the feedback patterns of top performers.

[0546] A "senior" is someone responsible for evaluating the materials and providing feedback on their content.

[0547] "Emotional state" refers to the psychological state of the document creator and is a concept that encompasses multiple emotions, including stress and relaxation.

[0548] "Feedback" refers to information, including suggestions for improvement and evaluations, that is provided regarding a document, and is primarily received by the document creator.

[0549] "Means of adjustment" refers to procedures and mechanisms for modifying the content and expression of feedback, taking into account the emotional state of the document creator.

[0550] A "document creator" is a user who creates documents and receives feedback through the system.

[0551] This system is designed to streamline feedback during document creation and provide support that takes into account the user's emotional state. A specific implementation is described below.

[0552] The server retrieves data from a storage device that has accumulated past feedback information and learns feedback patterns using a machine learning model. The server uses this model to generate predictions and feedback for documents, often employing Python as the programming language and TensorFlow as the machine learning library. It also uses OpenCV or Librosa for sentiment analysis. Leveraging these tools, the server has the ability to analyze the emotions of the document creator and adjust the feedback accordingly.

[0553] Users create documents and upload them to the system using a terminal. The terminal is typically an internet-connected computer that accesses the server via a browser or dedicated application. The uploaded documents are transferred to the server using the HTTP protocol.

[0554] The device also acquires user emotion data via its camera and microphone and sends it to the server. The device processes this data in real time, supporting the server in accurately analyzing the user's emotional state. Receiving feedback tailored to the user's emotional state allows for more appropriate revisions to the materials.

[0555] As a concrete example, consider a scenario where a user creates a technical report and requests a review. The server matches the report type to past feedback data and generates appropriate feedback. If the emotion engine determines during this process that the user is stressed, it provides feedback in softer language and encouraging messages.

[0556] As an example of a prompt message, a user could send text to the server such as, "Please review the technical report. I would appreciate feedback in a gentle tone, taking into account past error patterns," to receive better feedback.

[0557] These steps not only streamline the process of improving materials, but also enable the system to provide flexible support tailored to the user's emotions.

[0558] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0559] Step 1:

[0560] The server retrieves data from a storage device that holds past complaint information. Using this data as input, the server trains a machine learning model to learn complaint patterns. A Python dataframe processing library is used for data processing to extract necessary features. The output is the trained machine learning model.

[0561] Step 2:

[0562] The user creates a document and uploads it to the system using a terminal. The terminal sends the document to the server using the HTTP protocol. The input is the document created by the user, and the server receives it and proceeds to the next processing step. The output is the document data received by the server.

[0563] Step 3:

[0564] The server passes the received data to a machine learning model to predict areas for improvement. The server then performs textual analysis of the data to identify errors and areas for improvement. The input consists of the received data and the trained model, while the output includes the areas of concern and specific feedback.

[0565] Step 4:

[0566] The device uses the user's camera and microphone to acquire emotional data in real time. The device sends this data to a server, which is used as input for emotional analysis. The input is the user's emotional data, and the output is the process of sending this data to the server.

[0567] Step 5:

[0568] The server uses an emotion engine to analyze the user's emotional state. A Python emotion analysis library is used to determine whether the user is stressed or relaxed. The input is emotion data sent from the terminal, and the output is information about the analyzed emotional state.

[0569] Step 6:

[0570] The server adjusts the feedback based on the analyzed emotional state. If the user is stressed, the feedback tone becomes gentler; if relaxed, it provides detailed suggestions for improvement. The input is the analyzed emotional state, and the output is the adjusted feedback.

[0571] Step 7:

[0572] The server sends the adjusted feedback to the terminal. The terminal displays the feedback visually, making it easy for the user to understand. The input is the adjusted feedback, and the output is the feedback information displayed to the user.

[0573] (Application Example 2)

[0574] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0575] It is crucial to appropriately analyze the emotional state of factory workers and improve the work environment accordingly. However, conventional systems have not adequately recognized workers' stress and relaxation levels in real time, provided appropriate feedback based on these levels, and reduced work efficiency and psychological burden. Therefore, there is a need to provide a system that customizes feedback based on workers' emotional states and improves the factory work environment.

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

[0577] In this invention, the server includes means for acquiring feedback data from an information recording device that stores past feedback information, means for analyzing the emotional state of the creator and adjusting the feedback according to that state, and means for collecting data for analyzing the emotional state of the worker and generating actions and feedback according to that state. This enables automatic adjustment of feedback and actions according to the emotional state of the worker.

[0578] An "information recording device" is a device that stores past information and data regarding incidents and retrieves it as needed.

[0579] A "machine learning model" is an algorithm that learns from collected data and makes predictions and judgments about new information.

[0580] "Instructor" refers to a person or system whose role is to provide feedback and guidance on document creation and work.

[0581] "Feedback" refers to information that provides comments or suggestions for improvement regarding documents or work.

[0582] "Emotional state" refers to the psychological state or mood of the worker or document creator.

[0583] "Automatic adjustment of operation and feedback" is a process that automatically adjusts the operation of a device or system and the feedback it provides in accordance with the emotional state of the operator.

[0584] The system that implements this application primarily consists of a server, a terminal, and an emotion analysis system. The server retrieves previously accumulated feedback information from an information recording device and generates a machine learning model based on it. This model learns the patterns of feedback given by supervisors to workers and document creators and is used to provide appropriate feedback for new documents and tasks.

[0585] The server also collects data from the worker's terminals and equipment and performs sentiment analysis. Specifically, it uses the camera and microphone installed in the terminal to capture the worker's facial expressions and voice, and analyzes them. This uses technologies such as the OpenCV image processing library and Google Cloud Speech-to-Text for speech recognition. The analyzed data is used through an emotion AI engine to determine the worker's emotional state, and the content of the feedback and the operation of the system are adjusted based on that information.

[0586] For example, while a factory worker is assembling precision parts, the system might detect that the worker looks tired and determine that their stress levels are rising. In this case, the server would generate encouraging feedback for the worker, providing a message such as, "You've worked hard. Maybe you should take a break."

[0587] The generative AI model serves as the foundation for generating feedback and suggestions based on collected data, customizing prompts according to the user's emotional changes. A specific example of a prompt might be, "Analyze the emotional state of workers in the factory and tell me how a robot can assist them if they are feeling stressed."

[0588] This allows terminals and servers to provide personalized feedback based on the worker's emotional state, thereby improving work efficiency and safety.

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] Users upload work data and documents to the server using a terminal. This input includes the worker's facial expressions and voice data. The terminal uses a camera and microphone to capture real-time data of the worker. This data is used later for sentiment analysis.

[0592] Step 2:

[0593] The server receives uploaded documents and related data, and retrieves past issue information from the information recording device. Using this issue data as input, the server uses a machine learning model to predict the areas of concern in the documents and generates feedback data. In this process, the generated AI model outputs optimal feedback based on the characteristics of the documents and data.

[0594] Step 3:

[0595] The server inputs the collected audio and image data into an emotion analysis engine. The server then uses TensorFlow for facial recognition and Google Cloud Speech-to-Text to convert the audio to text. The data is then analyzed by an emotion AI library, and the user's emotional state (e.g., stressed or relaxed) is output.

[0596] Step 4:

[0597] The server combines the generated feedback with the user's emotional state to adjust the final feedback. For example, if the server determines that the user is stressed, it will output feedback that includes gentle language and encouragement. This feedback becomes the final output.

[0598] Step 5:

[0599] The terminal receives feedback from the server and displays it visually to the user. The user then uses this feedback to revise their work or documents. The user's reaction after receiving feedback is also monitored and, if necessary, fed back as data to generate new feedback.

[0600] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0601] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0602] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0603] [Fourth Embodiment]

[0604] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0605] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0606] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0607] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0608] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0609] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0610] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0611] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0612] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0613] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0614] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0615] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0616] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0617] This invention relates to a system that improves the efficiency of feedback from supervisors during document creation. In this system, a server, terminals, and users work together to generate and provide effective feedback.

[0618] System Overview

[0619] First, the server maintains a database that stores past feedback data. This database contains points raised by supervisors during past reviews and the corrections made to those points. This data is regularly updated and managed by the server.

[0620] Next, the server uses a machine learning model to analyze and learn patterns of feedback from supervisors. This process allows the server to predict common points of feedback on documents in advance, based on past review information.

[0621] After the user creates a document, they upload it to their device. The device then sends the document to a server for analysis and requests the generation of preliminary feedback.

[0622] The server applies a pre-trained machine learning model to the received documents to identify areas for improvement. Specifically, it predicts points that require correction based on content consistency, data accuracy, and formatting integrity.

[0623] The server then sends the generated feedback back to the terminal, providing it to the user. The user can then modify the document while referring to this feedback. The feedback is displayed visually and designed to be easily understood and applied by the user.

[0624] Specific example

[0625] For example, consider a scenario where a user creates a sales report. This report includes numerical data and market analysis. After completing the report, the user sends it to a server via their terminal. Based on patterns of feedback from similar past reports, the server generates feedback regarding the consistency of the figures and any missing analysis, and sends it back to the terminal. The user can then use this feedback to correct the figures and enhance the analysis, ultimately submitting a high-quality report to their supervisor.

[0626] By improving quality during the document creation stage in this way, potential issues from superiors can be addressed in advance, and review time can be made more efficient.

[0627] The following describes the processing flow.

[0628] Step 1:

[0629] The server retrieves past feedback data from the database. This includes the feedback made by supervisors and the corrections made based on those feedback. This data is then used to create a new training dataset.

[0630] Step 2:

[0631] The server trains a machine learning model based on the created dataset. The model identifies patterns in supervisor feedback and learns what points are most likely to be criticized.

[0632] Step 3:

[0633] The user uploads the created document to their device. The device sends the document specified by the user to the server and requests feedback generation.

[0634] Step 4:

[0635] The server analyzes the received data. It applies a pre-trained machine learning model to identify potential issues in the data and generate specific feedback for improvement.

[0636] Step 5:

[0637] The server sends the generated feedback back to the terminal. The terminal interprets the feedback and presents it visually to the user.

[0638] Step 6:

[0639] Users revise the materials based on the feedback they receive. They finalize the materials by reviewing them again as needed.

[0640] Step 7:

[0641] Finally, once the document is satisfactory to the user, it is submitted directly to the supervisor. This process minimizes additional feedback from the supervisor and ensures efficient document submission.

[0642] (Example 1)

[0643] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0644] A challenge with document creation is the frequent criticism from superiors, which results in significant time and effort spent on revisions. Furthermore, the criticisms are sometimes inconsistent, leading to repeated mistakes and decreased work efficiency. The goal is to resolve these issues, improve document quality, and reduce the time spent on reviews.

[0645] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0646] In this invention, the server includes means for acquiring data from an information resource that stores past feedback information, means for generating a learning model using the data and learning the supervisor's tendency to make criticisms, and means for receiving materials, applying the learning model to predict areas of criticism, and generating a response. This makes it possible to automatically generate high-quality feedback during the material creation stage and to resolve criticisms from supervisors in advance.

[0647] "Feedback information" refers to information resources that include comments and corrections made regarding past documents.

[0648] "Information resources" refers to data sets stored in databases and other similar systems, and includes information pointing out flaws in past documents.

[0649] "Data" refers to specific comments and information about corrections obtained from information resources.

[0650] A "learning model" is an algorithm that uses machine learning to make predictions and classifications for specific tasks, and is used to learn the tendencies of a supervisor's feedback.

[0651] "Tendency to point out flaws" refers to the patterns and characteristics of the types of criticisms a supervisor tends to make about a document.

[0652] "Documents" refer to documents and data that users create and submit for review.

[0653] "Points of concern" refer to sections of the document that are expected to require correction.

[0654] "Response" refers to information that includes specific feedback on the points raised, and is provided to the document creator.

[0655] This invention provides a system that improves the efficiency of feedback from supervisors during document creation. The central components of the system are the server, the terminal, and the user who creates the document.

[0656] The server is responsible for managing information resources that store past feedback data. Specifically, it stores past feedback and correction information in a database and generates a learning model using machine learning algorithms based on that information. This learning model analyzes the supervisor's feedback tendencies and helps predict future areas of concern. The server builds the machine learning model and processes the data using software such as Python or TensorFlow.

[0657] Users create documents and upload them to their devices. The devices then send the documents to the server and request analysis. This allows users to easily provide documents to the server and receive feedback.

[0658] The server applies a pre-trained model to the received material to identify areas for improvement regarding content consistency, data accuracy, and formatting. Natural language processing techniques are used to generate a response for the material creator. The generated response is displayed visually, designed to allow users to easily understand the points that need correction.

[0659] For example, when a user creates a sales report, the report includes numerical data and market analysis. After the user completes the document, they send it to the server via their terminal. Based on patterns of feedback from similar past reports, the server generates feedback regarding the consistency of the figures and any missing analysis, and sends it back to the terminal. This allows the user to revise the document based on the feedback and submit a high-quality report to their supervisor.

[0660] An example of a prompt message might be, "While maintaining consistency between the numerical data in the sales report and the market analysis, use past feedback data to predict potential issues." This system is expected to improve quality during the document creation stage and proactively address potential issues from supervisors.

[0661] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0662] Step 1:

[0663] The server retrieves past feedback information from the database. Its input includes comments and correction history regarding past documents, and its output generates a dataset for analysis. This dataset is then processed to serve as training data for a machine learning model.

[0664] Step 2:

[0665] The server uses the acquired data to train a machine learning model. The dataset is used as input for training, and the output is a model that has learned the supervisor's tendency to give feedback. In this process, natural language processing techniques and algorithms are used to perform data calculations, improving the accuracy of the model.

[0666] Step 3:

[0667] The user uploads the completed document to the terminal. The input data is the document created by the user, and the output is the document sent to the server. The terminal provides a simple interface, creating an environment where users can easily submit documents.

[0668] Step 4:

[0669] The server inputs the received data into a machine learning model for analysis. The input data is the uploaded document, and the output predicts the areas of concern within the document. The data calculation performed involves identifying areas of concern based on the model, and the consistency of the content, the accuracy of the data, and the consistency of the format are evaluated.

[0670] Step 5:

[0671] The server generates feedback based on the analysis results. The input is information about the identified issues, and the output includes visually presented feedback for the user. The server organizes the feedback clearly and outputs it in a highly practical format.

[0672] Step 6:

[0673] Users revise the document based on feedback received on their device. The input is feedback provided by the server, and the output is the improved document. By following the feedback and correcting the indicated areas, users can improve the quality of the document.

[0674] (Application Example 1)

[0675] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0676] In quality control of industrial products, conventional methods have challenges in terms of the accuracy and time efficiency of defect detection. These methods primarily rely on manual verification, often resulting in reactive measures and wasted time and money. There is a need for efficient methods to detect and correct defects before shipment.

[0677] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0678] In this invention, the server includes means for acquiring defect data from a database storing past defect information, means for generating a machine learning model based on the defect data and learning defect patterns, means for receiving quality control activities, predicting defect locations using the machine learning model, and generating feedback, and means for displaying the feedback information on a manufacturing machine. This enables highly accurate and time-efficient detection and improvement of defective products in product quality control.

[0679] 1. "Identification information" refers to records of information and identifications that indicated past improvements needed in the quality control process.

[0680] 2. A "database" is a system for storing and managing information and related data.

[0681] 3. A "machine learning model" refers to an algorithm that learns data patterns and makes predictions and classifications based on new data.

[0682] 4. "Patient feedback patterns" are data extracted from past feedback information that represent specific trends or common signs of defects.

[0683] 5. "Quality control activities" refer to a series of processes carried out to maintain and improve the quality of a product.

[0684] 6. "Feedback" refers to information such as improvement suggestions and points to note that are generated based on the results of analysis and checks.

[0685] 7. A "manufacturing machine" is an automated machine or device used to manufacture products, and it can also display quality control information.

[0686] This invention relates to a system aimed at improving the efficiency and accuracy of quality control. It links a server with manufacturing machinery (robots), analyzes past feedback data, and generates automated feedback.

[0687] The server first retrieves issue data from a database containing past issue information. This data includes records of past product defects and improvement suggestions in quality control. The server then generates a machine learning model based on the issue data and learns specific issue patterns. Machine learning frameworks such as TensorFlow and PyTorch can be used during this process.

[0688] As part of quality control activities, when a product is checked by a manufacturing machine, the data is received by a server. The server applies a trained machine learning model to predict quality issues and generates feedback indicating areas for improvement. This feedback is visually displayed on the manufacturing machine's screen, allowing on-site workers to immediately correct the product.

[0689] For example, when an automotive part is produced on an assembly line, the server uses previous defect data to identify insufficiently tightened bolts and provides immediate feedback. This process enables highly accurate defect detection, contributing to improved product quality.

[0690] An example of a prompt in a generative AI model is, "Please advise on building a feedback system for factory quality control that automatically predicts defective areas based on past data and generates improvement suggestions."

[0691] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0692] Step 1:

[0693] The server retrieves existing issue data from a database that stores past issue information. The input is a database query, and the output is the issue information itself. Specifically, it executes SQL queries in the database management system and aggregates the relevant data.

[0694] Step 2:

[0695] The server generates a machine learning model based on the feedback data obtained in Step 1 and learns the feedback patterns. The input is the feedback data, and the output is a trained machine learning model. Specifically, TensorFlow is used to process the dataset and train the pattern recognition model.

[0696] Step 3:

[0697] The manufacturing machine acquires product quality control information and transmits this data to a server. The input is real-time quality data, and the output, which is the data of the product being inspected, is stored on the server. Specifically, the data is securely transmitted via a communication protocol.

[0698] Step 4:

[0699] The server applies a pre-trained machine learning model to quality control data transmitted from manufacturing machines to predict areas of concern. The input is quality control data, and the output is the predicted areas of concern. Specifically, the model is executed to analyze the data.

[0700] Step 5:

[0701] The server generates feedback based on the prediction in step 4. The input is the prediction result, and the output is feedback information with improvement suggestions. The specific action is to convert the feedback content into a format that is easy to visually interpret.

[0702] Step 6:

[0703] The server sends the generated feedback back to the manufacturing machine for display. The input is feedback information, and the output is the feedback displayed on the manufacturing machine's screen. Specifically, it is visualized based on UI / UX design and provided in a way that is easy for the user to understand.

[0704] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0705] This invention relates to a system that, in addition to improving the efficiency of feedback in document creation, recognizes the user's emotional state and provides appropriate support accordingly. The central elements are a server, a terminal, and an emotion engine that analyzes the user's emotions.

[0706] System Overview

[0707] First, the server maintains a database of past feedback data and uses it to train a machine learning model. The model adapts to the patterns of feedback from supervisors and provides a foundation for making predictions based on documents submitted by users.

[0708] When a user creates a document and uploads it to the system via their device, the server receives the document, uses a machine learning model to predict areas for improvement, and generates specific feedback. In this process, the server also uses an emotion engine to analyze the user's current emotional state. The emotion engine analyzes data obtained from the user (e.g., facial recognition and voice data) to determine whether the user is stressed or relaxed.

[0709] In generating feedback, the server considers the results of the emotion engine and makes adjustments according to the user's emotional state. For example, if the user is experiencing high levels of stress, the feedback is rephrased in gentler language; conversely, if the user is relaxed, more detailed suggestions for improvement are provided.

[0710] The generated feedback is sent back to the device, which visually displays it to the user. The user then revises the material based on the feedback. If necessary, the sentiment engine monitors the user's emotional changes after receiving the feedback to determine if further support is needed.

[0711] Specific example

[0712] For example, suppose a user is writing a technical report and wants it reviewed by the system before submitting it. The server detects that this report is the type that has been flagged for many errors in the past and generates feedback. In this process, if the sentiment engine determines that the user is feeling stressed before submission, the user will be provided with feedback in a softer tone, along with an encouraging message.

[0713] In this way, document creators can efficiently revise their documents while receiving support that takes their emotional state into consideration. This system improves the quality of feedback and reduces the mental burden on users.

[0714] The following describes the processing flow.

[0715] Step 1:

[0716] The user creates a document and saves the document file to their device. Once the document is complete, they upload it to the system using their device.

[0717] Step 2:

[0718] The device sends the uploaded data to the server and requests the generation of feedback. This request includes a signal to initiate the feedback process.

[0719] Step 3:

[0720] The server receives the document file and first analyzes its contents based on a machine learning model. The model identifies areas where issues are predicted to occur, based on patterns learned from past feedback data.

[0721] Step 4:

[0722] The server generates specific feedback based on the analysis results. This feedback includes areas for improvement and recommended revisions within the document.

[0723] Step 5:

[0724] The server simultaneously monitors the user's current emotional state using an emotion engine. This is done by analyzing the user's voice and video data transmitted from the device, and based on the results, it determines whether the user is tense or relaxed.

[0725] Step 6:

[0726] The server adjusts the generated feedback according to the user's emotional state. If the user is feeling stressed, the feedback is changed to gentler language, and messages are added to alleviate the user's anxiety.

[0727] Step 7:

[0728] The server sends the adjusted feedback to the device. The device displays the feedback visually, presenting it in a way that is easy for the user to understand.

[0729] Step 8:

[0730] Users revise their materials while referring to feedback. After completing the revisions, they can re-upload the materials and request new feedback if necessary.

[0731] Step 9:

[0732] Once the user has completed the final document, they formally submit it to their supervisor or relevant department. This process improves the quality of the document and ensures the user's emotional support.

[0733] (Example 2)

[0734] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0735] In the current document creation process, feedback is often mechanical and fails to consider the creator's emotional state, which can cause significant stress. Furthermore, inaccurate feedback makes it difficult to efficiently improve the document.

[0736] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0737] In this invention, the server includes means for acquiring feedback data from a storage device that stores past feedback information, means for generating a machine learning model based on the feedback data and learning the feedback patterns of higher-ranking users, means for receiving materials, predicting areas for feedback using the machine learning model, and generating feedback, means for analyzing the emotional state of the material creator and adjusting the feedback according to that emotional state, and means for providing the feedback to the material creator. This makes it possible to provide feedback that takes the emotions of the material creator into consideration, reducing stress and enabling efficient material improvement.

[0738] "Information gathering data" refers to a collection of data that shows past feedback and revision history regarding a document.

[0739] A "memory device" is a general term for a device that has the function of storing and retaining data such as pointed-out information.

[0740] A "machine learning model" is an algorithm or mechanism that learns from feedback data and understands the feedback patterns of top performers.

[0741] A "senior" is someone responsible for evaluating the materials and providing feedback on their content.

[0742] "Emotional state" refers to the psychological state of the document creator and is a concept that encompasses multiple emotions, including stress and relaxation.

[0743] "Feedback" refers to information, including suggestions for improvement and evaluations, that is provided regarding a document, and is primarily received by the document creator.

[0744] "Means of adjustment" refers to procedures and mechanisms for modifying the content and expression of feedback, taking into account the emotional state of the document creator.

[0745] A "document creator" is a user who creates documents and receives feedback through the system.

[0746] This system is designed to streamline feedback during document creation and provide support that takes into account the user's emotional state. A specific implementation is described below.

[0747] The server retrieves data from a storage device that has accumulated past feedback information and learns feedback patterns using a machine learning model. The server uses this model to generate predictions and feedback for documents, often employing Python as the programming language and TensorFlow as the machine learning library. It also uses OpenCV or Librosa for sentiment analysis. Leveraging these tools, the server has the ability to analyze the emotions of the document creator and adjust the feedback accordingly.

[0748] Users create documents and upload them to the system using a terminal. The terminal is typically an internet-connected computer that accesses the server via a browser or dedicated application. The uploaded documents are transferred to the server using the HTTP protocol.

[0749] The device also acquires user emotion data via its camera and microphone and sends it to the server. The device processes this data in real time, supporting the server in accurately analyzing the user's emotional state. Receiving feedback tailored to the user's emotional state allows for more appropriate revisions to the materials.

[0750] As a concrete example, consider a scenario where a user creates a technical report and requests a review. The server matches the report type to past feedback data and generates appropriate feedback. If the emotion engine determines during this process that the user is stressed, it provides feedback in softer language and encouraging messages.

[0751] As an example of a prompt message, a user could send text to the server such as, "Please review the technical report. I would appreciate feedback in a gentle tone, taking into account past error patterns," to receive better feedback.

[0752] These steps not only streamline the process of improving materials, but also enable the system to provide flexible support tailored to the user's emotions.

[0753] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0754] Step 1:

[0755] The server retrieves data from a storage device that holds past complaint information. Using this data as input, the server trains a machine learning model to learn complaint patterns. A Python dataframe processing library is used for data processing to extract necessary features. The output is the trained machine learning model.

[0756] Step 2:

[0757] The user creates a document and uploads it to the system using a terminal. The terminal sends the document to the server using the HTTP protocol. The input is the document created by the user, and the server receives it and proceeds to the next processing step. The output is the document data received by the server.

[0758] Step 3:

[0759] The server passes the received data to a machine learning model to predict areas for improvement. The server then performs textual analysis of the data to identify errors and areas for improvement. The input consists of the received data and the trained model, while the output includes the areas of concern and specific feedback.

[0760] Step 4:

[0761] The device uses the user's camera and microphone to acquire emotional data in real time. The device sends this data to a server, which is used as input for emotional analysis. The input is the user's emotional data, and the output is the process of sending this data to the server.

[0762] Step 5:

[0763] The server uses an emotion engine to analyze the user's emotional state. A Python emotion analysis library is used to determine whether the user is stressed or relaxed. The input is emotion data sent from the terminal, and the output is information about the analyzed emotional state.

[0764] Step 6:

[0765] The server adjusts the feedback based on the analyzed emotional state. If the user is stressed, the feedback tone becomes gentler; if relaxed, it provides detailed suggestions for improvement. The input is the analyzed emotional state, and the output is the adjusted feedback.

[0766] Step 7:

[0767] The server sends the adjusted feedback to the terminal. The terminal displays the feedback visually, making it easy for the user to understand. The input is the adjusted feedback, and the output is the feedback information displayed to the user.

[0768] (Application Example 2)

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

[0770] It is crucial to appropriately analyze the emotional state of factory workers and improve the work environment accordingly. However, conventional systems have not adequately recognized workers' stress and relaxation levels in real time, provided appropriate feedback based on these levels, and reduced work efficiency and psychological burden. Therefore, there is a need to provide a system that customizes feedback based on workers' emotional states and improves the factory work environment.

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

[0772] In this invention, the server includes means for acquiring feedback data from an information recording device that stores past feedback information, means for analyzing the emotional state of the creator and adjusting the feedback according to that state, and means for collecting data for analyzing the emotional state of the worker and generating actions and feedback according to that state. This enables automatic adjustment of feedback and actions according to the emotional state of the worker.

[0773] An "information recording device" is a device that stores past information and data regarding incidents and retrieves it as needed.

[0774] A "machine learning model" is an algorithm that learns from collected data and makes predictions and judgments about new information.

[0775] "Instructor" refers to a person or system whose role is to provide feedback and guidance on document creation and work.

[0776] "Feedback" refers to information that provides comments or suggestions for improvement regarding documents or work.

[0777] "Emotional state" refers to the psychological state or mood of the worker or document creator.

[0778] "Automatic adjustment of operation and feedback" is a process that automatically adjusts the operation of a device or system and the feedback it provides in accordance with the emotional state of the operator.

[0779] The system that implements this application primarily consists of a server, a terminal, and an emotion analysis system. The server retrieves previously accumulated feedback information from an information recording device and generates a machine learning model based on it. This model learns the patterns of feedback given by supervisors to workers and document creators and is used to provide appropriate feedback for new documents and tasks.

[0780] The server also collects data from the worker's terminals and equipment and performs sentiment analysis. Specifically, it uses the camera and microphone installed in the terminal to capture the worker's facial expressions and voice, and analyzes them. This uses technologies such as the OpenCV image processing library and Google Cloud Speech-to-Text for speech recognition. The analyzed data is used through an emotion AI engine to determine the worker's emotional state, and the content of the feedback and the operation of the system are adjusted based on that information.

[0781] For example, while a factory worker is assembling precision parts, the system might detect that the worker looks tired and determine that their stress levels are rising. In this case, the server would generate encouraging feedback for the worker, providing a message such as, "You've worked hard. Maybe you should take a break."

[0782] The generative AI model serves as the foundation for generating feedback and suggestions based on collected data, customizing prompts according to the user's emotional changes. A specific example of a prompt might be, "Analyze the emotional state of workers in the factory and tell me how a robot can assist them if they are feeling stressed."

[0783] This allows terminals and servers to provide personalized feedback based on the worker's emotional state, thereby improving work efficiency and safety.

[0784] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0785] Step 1:

[0786] Users upload work data and documents to the server using a terminal. This input includes the worker's facial expressions and voice data. The terminal uses a camera and microphone to capture real-time data of the worker. This data is used later for sentiment analysis.

[0787] Step 2:

[0788] The server receives uploaded documents and related data, and retrieves past issue information from the information recording device. Using this issue data as input, the server uses a machine learning model to predict the areas of concern in the documents and generates feedback data. In this process, the generated AI model outputs optimal feedback based on the characteristics of the documents and data.

[0789] Step 3:

[0790] The server inputs the collected audio and image data into an emotion analysis engine. The server then uses TensorFlow for facial recognition and Google Cloud Speech-to-Text to convert the audio to text. The data is then analyzed by an emotion AI library, and the user's emotional state (e.g., stressed or relaxed) is output.

[0791] Step 4:

[0792] The server combines the generated feedback with the user's emotional state to adjust the final feedback. For example, if the server determines that the user is stressed, it will output feedback that includes gentle language and encouragement. This feedback becomes the final output.

[0793] Step 5:

[0794] The terminal receives feedback from the server and displays it visually to the user. The user then uses this feedback to revise their work or documents. The user's reaction after receiving feedback is also monitored and, if necessary, fed back as data to generate new feedback.

[0795] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0796] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0797] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0798] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0799] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0800] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0801] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0802] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0803] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0804] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0805] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0806] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0807] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0808] 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.

[0809] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0810] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0811] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0812] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0813] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0814] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0815] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0816] The following is further disclosed regarding the embodiments described above.

[0817] (Claim 1)

[0818] A means of retrieving error data from a database that stores past error information,

[0819] A means to generate a machine learning model based on the aforementioned data of criticisms and to learn the patterns of criticisms made by superiors,

[0820] A means for receiving data, predicting areas for improvement using the machine learning model, and generating feedback,

[0821] Means for providing the aforementioned feedback to the document creator,

[0822] A system that includes this.

[0823] (Claim 2)

[0824] The system according to claim 1, further comprising means for analyzing the content of the comments related to the document and identifying frequently occurring points for correction.

[0825] (Claim 3)

[0826] The system according to claim 1, further comprising means for the feedback to be visually displayed on the terminal of the document creator.

[0827] "Example 1"

[0828] (Claim 1)

[0829] A means of obtaining data from information resources that have accumulated past feedback information,

[0830] A means of generating a learning model using the aforementioned data and learning the supervisor's tendency to make criticisms,

[0831] A means for receiving data, applying the learning model to infer the points of concern, and generating a response,

[0832] Means for supplying the aforementioned response to the creator,

[0833] A system that includes this.

[0834] (Claim 2)

[0835] The system according to claim 1, further comprising means for analyzing the content of the comments related to the document and identifying frequently occurring points for correction.

[0836] (Claim 3)

[0837] The system according to claim 1, further comprising means for the response to be visually presented on the creator's terminal.

[0838] "Application Example 1"

[0839] (Claim 1)

[0840] A means of retrieving error data from a database that stores past error information,

[0841] A means for generating a machine learning model based on the aforementioned data and learning the patterns of the identified issues,

[0842] A means for receiving quality control activity, predicting areas of concern using the machine learning model, and generating feedback,

[0843] Means for providing the aforementioned feedback to the user,

[0844] A means of displaying feedback information on a manufacturing machine,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, further comprising means for analyzing the content of the comments related to product information and identifying frequently occurring points for correction.

[0848] (Claim 3)

[0849] The system according to claim 1, further comprising means for visually displaying the feedback in a quality control machine.

[0850] "Example 2 of combining an emotion engine"

[0851] (Claim 1)

[0852] A means of obtaining error data from a storage device that stores past error information,

[0853] A means for generating a machine learning model based on the aforementioned data of criticisms and learning the criticism patterns of top performers,

[0854] A means for receiving data, predicting areas for improvement using the machine learning model, and generating feedback,

[0855] A means of analyzing the emotional state of the document creator and adjusting the feedback according to that emotional state,

[0856] Means for providing the aforementioned feedback to the document creator,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, further comprising means for analyzing the content of the comments related to the document and identifying frequently occurring points for correction.

[0860] (Claim 3)

[0861] The system according to claim 1, further comprising means for the feedback to be visually displayed on the terminal of the document creator.

[0862] "Application example 2 when combining with an emotional engine"

[0863] (Claim 1)

[0864] A means for obtaining error data from an information recording device that stores past error information,

[0865] A means for generating a machine learning model based on the aforementioned feedback data and learning the feedback patterns of instructors,

[0866] A means for receiving data, predicting areas for improvement using the machine learning model, and generating feedback,

[0867] Means for providing the aforementioned feedback to the document creator,

[0868] A means to analyze the creator's emotional state and adjust the feedback according to that state,

[0869] A means for collecting data to analyze the emotional state of workers and generating actions and feedback corresponding to that state,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, further comprising means for analyzing the content of the comments related to the document and identifying frequently occurring points for correction.

[0873] (Claim 3)

[0874] The system according to claim 1, further comprising means for the feedback to be visually displayed on the terminal of the document creator. [Explanation of symbols]

[0875] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of retrieving error data from a database that stores past error information, A means to generate a machine learning model based on the aforementioned data of criticisms and to learn the patterns of criticisms made by superiors, A means for receiving data, predicting areas for improvement using the machine learning model, and generating feedback, Means for providing the aforementioned feedback to the document creator, A system that includes this.

2. The system according to claim 1, further comprising means for analyzing the content of the comments related to the document and identifying frequently occurring points for correction.

3. The system according to claim 1, further comprising means for the feedback to be visually displayed on the terminal of the document creator.

Images