system

Abstract

We provide the system. [Solution] A means of inputting verification results, Means for saving the input verification results, A means for automatically generating a report based on the aforementioned saved verification results, A means for generating anticipated questions and answers based on the aforementioned generated report, A means for comparing the previously saved past results with the current verification results, Means for reflecting the aforementioned comparison results in the report 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 performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Describe "Problems to be Solved by the Invention" and "Means for Solving the Problems".

[0005] In recent years, the time required for document creation and review in business has been increasing, and there is a demand for efficiently creating reports. However, conventional methods require a lot of time for manual editing and data entry, making efficient work difficult. In addition, since the preparation of assumed Q&A after report creation and the comparison with past results are also performed manually, an additional burden is imposed. There is a demand for a system that solves these problems and realizes efficient and accurate report creation, generation of assumed Q&A, and comparison with past results.

Means for Solving the Problems

[0006] The present invention provides a system that includes means for inputting verification results, means for saving the inputted verification results, means for automatically generating a report based on the saved verification results, means for generating anticipated questions and answers based on the generated report, means for comparing saved past results with current verification results, and means for reflecting the comparison results in the report. This allows users to efficiently input verification results and proceed with their work based on reports automatically generated based on those results. Furthermore, the system can automatically generate anticipated questions and answers and compare results with past results, significantly improving work efficiency.

[0007] "Verification results" refer to data that shows the results of tests and evaluations conducted on systems, products, processes, etc.

[0008] "Means of input" refers to the methods or devices used by users to input verification results into the system.

[0009] "Means of storage" refers to methods or devices for saving input data to a database or storage device.

[0010] "Methods for automatic generation" refer to methods or devices in which a system mechanically generates reports using a program based on input data.

[0011] A "report" is a document created based on verification results, organizing data according to a specific format and presenting it visually.

[0012] "Anticipated questions and answers" refer to a set of questions and answers that are predicted based on the content of the report.

[0013] "Means of generation" refers to methods or devices for generating specific data or information using programs or algorithms.

[0014] "Past results" refer to data saved as a result of previous verifications or tests.

[0015] The "comparison means" is a method or device for comparing current data with past data to find differences and improvement points.

[0016] The "reflection means" is a method or device for incorporating comparison results into reports or documents.

[0017] A "system" is a collection of a series of methods and devices in which multiple means operate in cooperation.

Brief Explanation of Drawings

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

Mode for Carrying Out the Invention

[0019] 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.

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

[0021] 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.

[0022] 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.

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

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] 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."

[0026] [First Embodiment]

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

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0033] 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.

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

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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".

[0039] This invention relates to a verification result report generation system for improving operational efficiency. This system significantly reduces the user's workload by inputting and saving verification results, automatically generating reports, creating anticipated questions and answers, and comparing them with past results.

[0040] The main components of this system are as follows:

[0041] First, the user accesses a dedicated input screen to enter verification results. The terminal provides this input screen and checks the format of the data entered by the user. If the input data is valid, the terminal sends the data to the server.

[0042] The server saves the received verification data to a database. Next, the server automatically generates a report based on the saved data. Here, a predetermined template is used to format the data and create a visually appealing report.

[0043] Next, the server analyzes the generated report and automatically generates anticipated questions and their answers. Here, by utilizing past question patterns and accumulated data, it is possible to create highly accurate anticipated questions and answers.

[0044] Furthermore, the server retrieves past verification results stored in the database and compares them to current results. This comparison visually shows what performance improvements or problems exist. These comparison results are reflected in a report, providing users with clear areas for improvement.

[0045] The final report generated based on the above process is notified to the user from the server and becomes accessible via a saved link. This allows users to quickly and efficiently create and review documents.

[0046] Specific example

[0047] For example, consider a scenario where a user inputs the durability test results for a product. The user uses a terminal to input "Durability test results for product A." The terminal checks the format of the input data and sends the verification results, "Durability: 95, Failure rate: 0.5%", to the server. The server stores this in a database and generates a report based on the stored data.

[0048] Next, the server analyzes the generated report and automatically generates questions and answers such as, "What were the results of this durability test?". Furthermore, the server retrieves past "durability test results for product A" and compares them with the current results. The server adds the comparison results, such as "The failure rate improved from 0.8% to 0.5%", to the report and notifies the user.

[0049] In this way, this system reduces the burden on users and supports efficient and accurate report creation.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The user accesses the system's input screen and enters the verification results. The terminal automatically checks the format of the entered data and verifies that it is in the correct format.

[0053] Step 2:

[0054] The terminal sends data that has passed the format check to the server. The server temporarily stores the received data and prepares to write it to the database.

[0055] Step 3:

[0056] The server saves the verification results data to the database. If the save is successful, the server generates a save completion message and sends it to the terminal.

[0057] Step 4:

[0058] The server loads a report template based on the validation results stored in the database and embeds the validation results. This automatically generates the initial report.

[0059] Step 5:

[0060] The server analyzes the generated report and predicts anticipated question patterns. It then references a database of past questions to generate relevant questions and their answers.

[0061] Step 6:

[0062] Add the server-generated questions and answers to the report to complete the anticipated Q&A section. This completes the first report.

[0063] Step 7:

[0064] The server retrieves past verification results from the database and compares them with current results. If any new discoveries or areas for improvement are found as a result of the comparison, they are reflected in the report.

[0065] Step 8:

[0066] The server completes the final report and saves the report file. It generates a link to the saved report and notifies the user.

[0067] Step 9:

[0068] The user accesses the completed report using the provided link. The user reviews the report and takes any necessary actions or further feedback.

[0069] This processing flow allows users to quickly and efficiently generate and review verification results reports.

[0070] (Example 1)

[0071] 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."

[0072] Conventional verification result reporting systems often involved manual tasks such as data entry, report generation, and the creation of anticipated questions and answers, resulting in low work efficiency and a heavy burden on users. In particular, when dealing with large amounts of verification data, comparing with historical data and generating highly accurate anticipated questions and answers required considerable time and effort. Furthermore, there was a lack of effective means to notify users of the generated reports, making prompt responses difficult.

[0073] 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.

[0074] In this invention, the server includes means for storing verification results in a database, means for automatically generating a report using a template based on the stored verification results, means for analyzing the generated report and generating anticipated questions and answers using past question patterns, means for comparing past results with current verification results, and means for reflecting the comparison results in the report and notifying the user. As a result, the user can efficiently input verification results, receive automatically generated reports and anticipated questions and answers, and proceed with their work quickly and accurately.

[0075] A "terminal" is a device used by users to input verification results and has a function to check the format of the input data.

[0076] A "server" is a central computer system that stores received verification result data in a database, automatically generates reports based on the stored data, analyzes them, and sends notifications.

[0077] A "database" is a data storage system used by a server to store and manage verification result data.

[0078] A "template" refers to a predetermined format or style that a server uses to automatically generate reports.

[0079] "Anticipated Q&A" refers to a collection of answers created based on the generated report, providing users with anticipated questions and their corresponding answers.

[0080] A "generative AI model" is an artificial intelligence technology that uses past question patterns and validation data to automatically generate highly accurate anticipated questions and answers.

[0081] A "comparison method" is a processing function that allows a server to compare past verification results with current results to identify areas for performance improvement and problems.

[0082] "Notification methods" refer to mechanisms for informing users of generated reports and comparison results, including methods such as email and display on dashboards.

[0083] This invention relates to a system that allows users to efficiently input and manage verification results and automatically generate reports and anticipated questions and answers. The system consists of a server and terminals as its main components.

[0084] First, the user accesses a dedicated input screen. For example, by accessing a specific URL using a web browser, they can input verification results. The input screen provides multiple input fields, such as product name and test results.

[0085] The terminal has a function to check the format of data entered by the user. For example, it checks whether the durability value is within the range of 0 to 100 and whether the failure rate is provided in percentage format. If the data is not valid, it displays an error message and prompts the user to re-enter the data.

[0086] When correct data is entered, the terminal sends that data to the server. The data is sent in JSON format and reaches the server via an HTTP POST request. In this case, the sending endpoint is, for example, " / api / submit_test_result".

[0087] The server saves the received data to an internal database. For example, an SQL database is used, and an INSERT query is executed against the "test_results" table. Storing the data in the database makes it available for future data analysis and report generation.

[0088] The server automatically generates reports based on the stored data. Specifically, it uses a Python script and the Jinja2 template engine to generate reports in HTML format. The templates include a predefined format, which formats the data and results in a visually appealing report.

[0089] Once a report is generated, the server analyzes it and automatically generates anticipated questions and answers. This process uses a generation AI model (e.g., GPT-4®) to create a highly accurate Q&A set by comparing it with past question patterns.

[0090] Furthermore, the server retrieves saved historical validation results and compares them to current results. This comparison clearly shows performance improvements and areas for improvement. A Python script is used to analyze the data and add the comparison results to the report.

[0091] Finally, the generated report is notified to the user from the server. Notification methods include sending a link to the user's email address or displaying a notification on the dashboard that a new report has been added. This allows users to quickly and efficiently create and review documents.

[0092] Specific example

[0093] For example, consider a scenario where a user inputs the results of a durability test for "Product A". The user accesses "http: / / example.com / report_input" from their browser and enters "Durability: 95, Failure Rate: 0.5%" into the input field. The terminal checks the format of this data, confirms that it is valid, and then sends it to the server.

[0094] The server saves this data to a database and generates a report based on the saved data. Then, it uses a generative AI model (e.g., GPT-4) to automatically generate questions such as "What were the results of this durability test?" and their answers. The server also compares the results with past test results and adds information to the report such as "The defect rate improved from 0.8% to 0.5%."

[0095] The generated report is notified to the user, who can access the detailed report via a specified link. This significantly improves the user's work efficiency.

[0096] Example of a prompt

[0097] For example, you can use the following prompt statements:

[0098] "Please enter the durability test results for Product A. Example: Durability: 95, Defect Rate: 0.5%"

[0099] This reduces the burden on users and supports efficient and accurate report creation.

[0100] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0101] Step 1:

[0102] The user accesses a dedicated input screen to enter the verification results. For example, they access "http: / / example.com / report_input" from a web browser and enter "Durability test results for product A," for example, "Durability: 95, Defect rate: 0.5%," into the input field. The input data is provided to the user and formatted on the input screen.

[0103] Step 2:

[0104] The terminal checks the format of the data entered by the user. For example, it verifies that the durability is within the range of 0 to 100 and that the failure rate is in percentage format. This check ensures data consistency and accuracy. Here, it distinguishes between valid and invalid data, and if invalid data is found, the terminal displays an error message to the user and prompts them to re-enter the data.

[0105] Step 3:

[0106] If the terminal receives valid data, it sends that data to the server. For example, it might send data to the " / api / submit_test_result" endpoint using an HTTP POST request. The data is sent in JSON format. The input data is sent to the server, which then receives it.

[0107] Step 4:

[0108] The server saves the received validation results data to a database. For example, it uses an INSERT query to save the data to the "test_results" table in an SQL database. The saved data is then used in subsequent processing. The saved data is stored in the database, which enables later analysis.

[0109] Step 5:

[0110] The server automatically generates reports based on the stored data. For example, it uses a Python script and the Jinja2 template engine to generate HTML reports. This template includes a predefined format, formatting the data and creating a highly readable report. For report generation, the input data is embedded in the template, and the output is generated as an HTML report.

[0111] Step 6:

[0112] The server analyzes the generated report and uses a generation AI model (e.g., GPT-4) to automatically generate anticipated questions and answers. For example, it generates questions and answers such as, "What were the results of this durability test?" By referring to past question patterns, it creates a highly accurate set of questions and answers. In this process, the text data from the report is input, the AI ​​model generates questions and answers, and the output is obtained as anticipated questions and answers.

[0113] Step 7:

[0114] The server retrieves stored historical validation results and compares them to current results. For example, it uses an SQL query to retrieve historical validation data from the "test_results" table and performs a comparison using Python. This comparison visually shows performance improvements and problems. Historical and current data are used as input, and the comparison results are obtained as output.

[0115] Step 8:

[0116] The server notifies the user of the final report, which includes the generated report, anticipated questions and answers, and comparison results. For example, it can send a notification email with a link to the user's email address, or display a notification on the dashboard that a new report has been added. This notification allows the user to quickly access the detailed report. The notification includes a link to the final report, and its output is provided to the user.

[0117] Therefore, this system can reduce the user's workload and support efficient and accurate report creation.

[0118] (Application Example 1)

[0119] 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."

[0120] Conventional verification result reporting systems have faced challenges such as requiring significant time and effort for data entry, storage, and report generation. Furthermore, manual comparison with historical data often led to decreased operational efficiency. Additionally, the lack of automation in the creation of anticipated questions and answers sometimes imposed additional burdens on users. A new system is needed to address these challenges and streamline operational processes in logistics centers and similar facilities.

[0121] 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.

[0122] In this invention, the server includes means for inputting verification results, means for saving the inputted verification results, means for automatically generating a report based on the saved verification results, means for generating anticipated questions and answers based on the generated report, means for comparing the saved past results with the current verification results, means for reflecting the comparison results in the report, means for automatically generating questions and answers using a generation AI model based on past and current verification data, and means for inputting verification results and checking reports using a smart device. As a result, users can efficiently input verification results, generate reports, and compare them with past data, significantly reducing their workload.

[0123] "Verification results" refer to the results of tests and investigations conducted to evaluate the performance and quality of a particular product or service.

[0124] "Means of input" refers to the interface or device that allows users to register verification results in the system.

[0125] "Means of storage" refers to functions or devices for accumulating the entered verification results in a database or storage device.

[0126] "Methods for automatically generating reports" refer to algorithms or programs that automatically create reports based on saved verification results and predetermined templates.

[0127] "Means for generating anticipated questions and answers" refers to engines or software that automatically generate anticipated questions and their answers based on the generated report.

[0128] "Means of comparison" refers to a function that compares past and current verification results and analyzes the differences and areas for improvement.

[0129] "Means of reflection" refers to functions that add comparison results to reports and provide them to users in a visually easy-to-understand format.

[0130] A "generative AI model" refers to an artificial intelligence model that learns from large datasets and is used for natural language processing.

[0131] A "smart device" refers to a portable device, such as a smartphone or tablet, that can connect to the internet and run applications.

[0132] This invention relates to a system for automating the creation of verification result reports at logistics centers. This system significantly improves operational efficiency by efficiently inputting verification results, automatically generating reports, creating anticipated questions and answers, and comparing them with past results.

[0133] System Configuration

[0134] 1. Hardware

[0135] User terminal: A device such as a smartphone, tablet, or PC. The user uses this device to input verification results and review reports.

[0136] Servers: Cloud servers or dedicated servers are used. They are used for data storage, analysis, and execution of generational AI models.

[0137] Specific examples: AWS®, Google® Cloud Platform

[0138] Database: Used to store verification results and generated reports.

[0139] Examples: MySQL (registered trademark), PostgreSQL

[0140] 2. Software

[0141] Data entry form: A web or mobile application for users to enter verification results.

[0142] Frameworks: React Native, Flutter (registered trademark)

[0143] Report generation program: A program that automatically generates reports based on verification result data.

[0144] Data analysis program: A program that compares saved past verification results with current verification results and analyzes the results.

[0145] Generative AI model: An artificial intelligence model used for natural language processing.

[0146] Model: GPT-4, BERT

[0147] Program processing

[0148] Input of verification results

[0149] Users access a dedicated data entry form using their smartphones or tablets. They enter necessary data such as "product ID," "inspection results," and "inventory quantity," and then press the submit button. The smart device checks whether the entered data is correct and sends it to the server.

[0150] Data storage

[0151] The server saves the received verification results data to a database. The data is stored in an appropriate format and used for subsequent analysis and report generation.

[0152] Report generation

[0153] The server automatically generates reports based on the stored data. It uses predefined template files to format the data and create visually appealing reports.

[0154] Generation of anticipated questions and answers

[0155] Based on the generated report, the server automatically generates anticipated questions and their answers. Using a generation AI model, it creates question-and-answer pairs, referencing past question patterns.

[0156] Comparison with past data

[0157] The server compares the current results with previously saved verification results. This comparison visually shows areas for improvement and problems. This information is reflected in reports and notified to the user.

[0158] Specific example

[0159] For example, when a user inputs the durability test results for a product, the user uses a terminal to input "Durability test results for product A." The terminal checks the format of the input data and sends the verification result "Durability: 95, Defect rate: 0.5%" to the server. The server saves this to a database and generates a report based on the saved data. Next, the server analyzes the generated report and automatically generates questions and answers such as "What are the results of this durability test?". Furthermore, the server retrieves past "Durability test results for product A" and compares them with the current results. The server adds the comparison result, such as "The past defect rate improved from 0.8% to 0.5%", to the report and notifies the user.

[0160] Example of a prompt

[0161] Product inspection results:

[0162] Product ID: A123

[0163] Test results: Good

[0164] Quantity in stock: 200

[0165] Please compare the current test data with past test data and generate a report.

[0166] Please also enter any anticipated questions and their answers.

[0167] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0168] Step 1:

[0169] Users input verification results using smart devices (smartphones or tablets). Users access a data entry form and enter necessary information such as "Product ID," "Inspection Result," and "Inventory Quantity." The input data is format-checked on the device, and if there are no errors, it is sent to the server. For example, input data might include "Product ID: A123," "Inspection Result: Good," and "Inventory Quantity: 200."

[0170] Step 2:

[0171] The verification result data sent from the terminal is received by the server. The server saves this verification result data to a database. Specifically, it executes an SQL query to insert the verification result data into the appropriate table in the database. The input is the verification result data (e.g., "Product ID: A123", "Inspection Result: Good", "Inventory Quantity: 200"), and the output is the data saved in the database.

[0172] Step 3:

[0173] The server automatically generates a report based on the stored validation result data. In this process, it formats the validation result data using a predetermined template file. Specifically, it uses a template engine to convert the validation results into an easily readable format. The input is the validation result data retrieved from the database, and the output is the generated report file.

[0174] Step 4:

[0175] Based on the generated report, the server automatically generates anticipated questions and their answers. Here, a generative AI model (e.g., GPT-4) is used for natural language processing. Specifically, the report data is input to the generative AI model, which then generates pairs of anticipated questions and answers. The input is the report data, and the output is the generated question and answer pairs.

[0176] Step 5:

[0177] The server compares the current verification result with previously stored verification results. Specifically, it retrieves past data from the database and uses an algorithm to analyze the differences between it and the current result. The inputs are the current verification result data and the past verification result data, and the output is the comparison result.

[0178] Step 6:

[0179] The server incorporates the comparison results into the generated report. Specifically, it adds the comparison results to the report template and generates a consistent report overall. The inputs are the comparison results and the generated report, and the output is the final report.

[0180] Step 7:

[0181] The server notifies the user of the final report and provides a link that can be accessed from a smart device. Specifically, it sends an email or push notification to the user, including the link to access the report. The input is the URL of the final report, and the output is the notified user.

[0182] 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.

[0183] This invention relates to a system that combines an emotion engine with a verification result report generation system to improve operational efficiency, enabling the system to recognize the user's emotional state and generate reports, anticipated questions and answers, and compare results with past results based on that state. This system provides an optimal report tailored to the user's emotions by combining emotion recognition technology with the process of inputting and saving verification results, automatically generating reports, creating anticipated questions and answers, and comparing results with past results.

[0184] The main components of this system are as follows:

[0185] First, the user accesses a dedicated input screen to enter verification results. The terminal provides this input screen and verifies the format of the data entered by the user. If the input data is correct, the terminal sends the data to the server.

[0186] The server saves the received verification data to a database. Next, the server automatically generates a report based on the saved data. Here, a predetermined template is used to format the data and create a visually appealing report.

[0187] Next, the server analyzes the generated report and automatically generates anticipated questions and their answers. Here, by utilizing past question patterns and accumulated data, it is possible to create highly accurate anticipated questions and answers.

[0188] Furthermore, the server retrieves past verification results stored in the database and compares them to current results. This comparison visually shows what performance improvements or problems exist. These comparison results are reflected in a report, providing users with clear areas for improvement.

[0189] Embedding an emotion engine

[0190] This system incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's input data and behavior during operation to recognize their current emotional state. Specifically, it identifies emotions through factors such as key input speed, mouse movements, and facial recognition (when using a webcam).

[0191] The content and wording of the generated reports are adjusted based on the user's emotional state recognized by the emotion engine. For example, if the user is experiencing stress, the report content is made more concise, and negative results are expressed in softer language. This reduces the burden on the user and enables the generation of more adaptable reports.

[0192] Specific example

[0193] For example, consider a scenario where a user inputs the durability test results for a product. The user uses a terminal to input "Durability test results for product A." The terminal checks the format of the input data and sends the verification results, "Durability: 95, Failure rate: 0.5%", to the server. The server stores this in a database and generates a report based on the stored data.

[0194] Next, the server analyzes the generated report and automatically generates questions and answers such as, "What were the results of this durability test?". Furthermore, the server retrieves past "durability test results for product A" and compares them with the current results. The server adds the comparison results, such as "The failure rate improved from 0.8% to 0.5%", to the report and notifies the user.

[0195] In addition, during this process, the emotion engine analyzes the user's emotional state at the time of input, and if the user is experiencing stress or fatigue, it adjusts the report content to be more concise. In this way, it is possible to provide an optimal report tailored to the user's psychological state.

[0196] This system allows users to create and review reports efficiently and accurately, and the inclusion of an emotion engine further reduces the psychological burden on users.

[0197] The following describes the processing flow.

[0198] Step 1:

[0199] The user accesses the system's input screen and enters the verification results. The terminal automatically checks the format of the entered data to ensure it is correct. The emotion engine collects the user's keystroke speed, mouse movements, and, if possible, facial expression information during input.

[0200] Step 2:

[0201] The device sends data that has passed the format check, along with user sentiment data collected by the sentiment engine, to the server. The server temporarily stores the received data and prepares it for writing to the database.

[0202] Step 3:

[0203] The server saves the verification results data to the database. If the save is successful, the server generates a save completion message and sends it to the terminal. Sentiment data is also saved to the database in the same way.

[0204] Step 4:

[0205] The server loads a report template based on the validation results stored in the database and embeds the results. Here, it adjusts the tone and expression of the template, taking into account the user's emotional data collected by the emotion engine. For example, if the user is stressed, the results will be made concise and softer.

[0206] Step 5:

[0207] The server analyzes the generated report and predicts anticipated question patterns. It then references a database of past questions to generate relevant questions and their answers. The generated questions and answers are then refined using sentiment engine data to ensure they are expressed in a way that takes the user's psychological state into account.

[0208] Step 6:

[0209] The server-generated questions and answers are added to the report, completing the anticipated Q&A section. Based on the analysis results from the sentiment engine, the difficulty of the questions and the level of detail in the answers are also adjusted.

[0210] Step 7:

[0211] The server retrieves past test results from the database and compares them to current results. This comparison visually shows what performance improvements and problems exist. The comparison results are reflected in the report, taking into account the sentiment engine data.

[0212] Step 8:

[0213] The server completes the final report and saves the report file. It generates a link to the saved report and notifies the user. The notification message is also adjusted to suit the user's emotional state.

[0214] Step 9:

[0215] The user accesses the completed report using the provided link. The user reviews the report and takes any necessary actions or further feedback.

[0216] This processing flow allows users to quickly and efficiently generate and review verification results, and the integration of an emotion engine further reduces the user's psychological burden.

[0217] (Example 2)

[0218] 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".

[0219] In modern business, there is a demand for rapid and accurate reporting of verification results. However, conventional report generation systems do not take into account the user's emotional state, making them burdensome for users who are stressed or fatigued. Furthermore, the generated reports are formulaic and lack responses to the specific problems and questions that users have. It is necessary to solve these problems and provide a more effective and user-friendly report generation system.

[0220] 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.

[0221] In this invention, the server includes means for inputting verification results, means for saving the inputted verification results, means for automatically generating a report based on the saved verification results, means for generating anticipated questions and answers based on the generated report, means for comparing the saved past results with the current verification results, means for reflecting the comparison results in the report, means for analyzing the user's emotional state, and means for adjusting the content of the report based on the analyzed emotional state. This enables flexible report generation in accordance with the user's emotional state, making it possible to provide highly accurate and specific information while reducing the user's psychological burden.

[0222] "Verification results" refer to numerical data and qualitative evaluation results obtained through tests and experiments.

[0223] "Means of input" refers to an interface or device for the user to provide verification results to the system.

[0224] "Means of storage" refers to a mechanism or device for accumulating the input verification results in a storage device such as a database.

[0225] "Means for automatically generating reports" refers to a mechanism or device that automatically creates reports using a set template or algorithm based on saved verification results.

[0226] "Means for generating anticipated questions and answers" refers to a mechanism or device for automatically creating predictable questions and their answers based on a generated report.

[0227] "Means for comparing past results with current verification results" refers to a mechanism or device for comparing stored past verification data with current data and evaluating the differences or changes between them.

[0228] "Means for reflecting comparison results in the report" refers to a mechanism or device for adding the results obtained from the aforementioned comparison to the content of the report and presenting them in an easily understandable manner.

[0229] "Means for analyzing emotional state" refers to a mechanism or device for determining a user's emotional state from user input, behavior, or facial expressions captured via a webcam.

[0230] "Means for adjusting the report content based on the analyzed emotional state" refers to a mechanism or device for modifying the structure and expression of a report, taking into account the user's emotional state, and providing the report in a format suitable for the user.

[0231] This invention relates to a verification result report generation system for improving work efficiency according to the user's emotional state. This system allows the user to input verification results, automatically generates a report, creates anticipated questions and answers, compares them with past data, and further recognizes the user's emotional state via an emotion engine, adjusting the report based on that recognition.

[0232] Hardware and software used

[0233] (Hardware)

[0234] Terminal (user's PC or smartphone): Providing an input screen

[0235] Server: Data storage, report generation, sentiment recognition processing.

[0236] Webcam (optional): Facial recognition

[0237] (software)

[0238] Input form application: An interface for users to enter validation results.

[0239] Emotion engine (e.g., EmotionAPI): Recognizing user emotions.

[0240] Database (MySQL, PostgreSQL, etc.): Storage of validation result data

[0241] Report generation software (LaTeX, JasperReports, etc.): Report creation

[0242] Data analysis tools (SciPy, Pandas, etc.): Analysis and comparison of validation results

[0243] System operation

[0244] 1. The user logs into the system and accesses a screen for entering verification results. Here, the user enters specific verification result data.

[0245] For example, you would enter data such as "Durability test results for product A," "Durability: 95," and "Defect rate: 0.5%."

[0246] 2. The terminal checks the format of the input data and verifies that it is in the correct format. For example, it checks whether the durability value is 100 or less and the failure rate is 1% or less.

[0247] 3. The terminal sends properly formatted data to the server.

[0248] 4. The server saves the received verification result data to the database. Additional information such as the type of verification result, date and time, and the verifier's ID are also saved at this time.

[0249] 5. The server automatically generates reports using predefined templates based on the stored data. For example, it can create easy-to-read reports using LaTeX or JasperReports.

[0250] 6. The server analyzes the generated report and automatically generates frequently asked questions (FAQs) and their answers. By referring to past question patterns and existing data, it creates highly accurate Q&A.

[0251] 7. The server retrieves past verification results and compares them to current results. Graphs and tables are created to visually represent this comparison and reflected in the report. For example, a statement such as "Past defect rate improved from 0.8% to 0.5%" might be added.

[0252] 8. The emotion engine recognizes the user's emotional state through user actions and webcam footage. For example, it uses key input speed, mouse movements, and facial expression analysis to determine the user's stress level.

[0253] 9. The server adjusts the content and wording of the report based on the recognized emotional state of the user. Specifically, if the user is experiencing stress, the report content will be made more concise.

[0254] 10. The server provides the user with a finalized report. The user reviews this report and decides on their next action.

[0255] Examples of prompt statements

[0256] For example, when prompting a generative AI model, you would use a prompt statement like this:

[0257] "Please prepare a report based on the latest durability test results for Product A. Include past test results and note any improvements made. If users have reported experiencing fatigue, please summarize this concisely in the report."

[0258] This system allows users to create and review reports efficiently and accurately, and the inclusion of an emotion engine further reduces the psychological burden on users.

[0259] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0260] Processing steps

[0261] Step 1:

[0262] The user logs into the system and accesses a screen to enter verification results. Specifically, this involves the user logging into a web application using a browser and accessing an input form.

[0263] Input: The user enters the verification result data (e.g., "Product A durability test results: Durability: 95, Defect rate: 0.5%").

[0264] Output: The input data is sent to the terminal.

[0265] Step 2:

[0266] The terminal checks the format of the input data and verifies that it is in the correct format. Here, the input data is validated based on predefined rules.

[0267] Input: Verification result data submitted by the user.

[0268] Data processing / calculation: Verify that the format of the verification results is appropriate (e.g., whether the numerical value is 100 or less, or whether the defect rate is 1% or less).

[0269] Output: Correct data is sent to the next step, and incorrect data is returned to the user as an error message.

[0270] Step 3:

[0271] The terminal sends data that has passed the format check to the server.

[0272] Input: Verification result data that has been determined to be in the correct format.

[0273] Output: Validation result data sent to the server.

[0274] Step 4:

[0275] The server saves the received verification result data in the database. At this time, metadata such as the type of verification result, date and time, and the ID of the verifier is also saved.

[0276] Input: Verification result data sent from the terminal.

[0277] Data processing / data calculation: Insert the data into an appropriate table in the database (e.g., execute an SQL INSERT statement).

[0278] Output: A confirmation message indicating that the saving was successful.

[0279] Step 5:

[0280] Based on the saved data, the server automatically generates a report using a pre-defined template. In this process, tools such as LaTeX and JasperReports are used.

[0281] Input: Verification result data saved in the database.

[0282] Data processing / data calculation: Generate a visually easy-to-read report by embedding the data in the template (e.g., embedding data in a LaTeX template).

[0283] Output: The generated report file.

[0284] Step 6:

[0285] The server analyzes the generated report and automatically generates frequently asked questions (FAQ) and their answers. It is created by referring to past question patterns and existing data.

[0286] Input: The generated report.

[0287] Data processing / data calculation: Generate FAQ using natural language processing (e.g., apply pre-defined rules or machine learning models).

[0288] Output: A set of automatically generated questions and answers.

[0289] Step 7:

[0290] The server retrieves past validation results and compares them with current results. This comparison is performed using data analysis tools (such as SciPy or Pandas).

[0291] Input: Current validation result data and past validation result data.

[0292] Data processing / data calculations: statistical analysis and graph creation (e.g., manipulating dataframes using Pandas and creating graphs using Matplotlib).

[0293] Output: Comparison results are output in text and graph formats and added to the report.

[0294] Step 8:

[0295] The emotion engine recognizes the user's emotional state through user actions and webcam footage.

[0296] Input: User operation data (key presses and mouse movements) and webcam footage.

[0297] Data processing / data calculation: Analysis using emotion recognition algorithms (e.g., using EmotionAPI).

[0298] Output: Analysis results (user's emotional state).

[0299] Step 9:

[0300] The server adjusts the content and wording of the report based on the recognized emotional state of the user.

[0301] Input: Emotional state data obtained from the emotion engine.

[0302] Data processing / data calculation: Adjust the language and format of the report (e.g., apply rewrite algorithms).

[0303] Output: Adjusted report.

[0304] Step 10:

[0305] The server finally provides the adjusted report to the user.

[0306] Input: Adjusted report.

[0307] Output: Final report provided to the user.

[0308] In this way, the system can provide an accurate and comprehensive verification result report while considering the user's emotional state.

[0309] (Application Example 2)

[0310] Next, Application Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0311] In the conventional verification result report creation system, appropriate responses according to the user's emotional state were not made, and stress and fatigue may have increased. In addition, since the content of the generated report was redundant or complex, it may have hindered the user's understanding. Especially in the verification work in the factory, improvement of efficiency and reduction of the user's psychological burden are required.

[0312] 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. In this invention, the server includes means for inputting verification results, means for saving the inputted verification results, means for automatically generating a report based on the saved verification results, means for generating anticipated questions and answers based on the generated report, means for comparing the saved past results with the current verification results, means for reflecting the comparison results in the report, and means for recognizing the emotional state using emotion recognition technology and adjusting the report content. This makes it possible to adjust the report appropriately according to the user's emotional state, improve the efficiency of the verification work, and reduce the psychological burden.

[0313] "Means for inputting verification results" refers to an interface device for inputting data obtained through inspection work into the system.

[0314] "Means for storing the input verification results" refers to a database or storage device for recording and securely storing the input inspection result data.

[0315] "Means for automatically generating a report based on the saved verification results" refers to an algorithm or software that automatically creates a report using a predetermined template based on the saved data.

[0316] "Means for generating anticipated questions and answers based on the generated report" refers to a program that analyzes the generated report and prepares simulated answers to future questions.

[0317] "Means for comparing the stored past results with current verification results" refers to an analytical tool for comparing previously stored data with current data to identify changes in performance and areas for improvement.

[0318] "Means for reflecting the comparison results in the report" refers to a program or software that integrates the comparison results into the report and presents them in a visually easy-to-understand format.

[0319] "Means for recognizing emotional states and adjusting report content using emotion recognition technology" refers to an emotion engine and its control program for analyzing the user's emotional state and optimizing the content and expression of reports generated based on that analysis.

[0320] System Overview

[0321] This invention provides a system for efficiently managing verification results and providing reports tailored to the user's emotional state. By incorporating emotion recognition technology, this system generates highly accurate verification result reports while reducing the user's psychological burden.

[0322] Hardware and software to be used

[0323] Server: A server for high-performance computing, running software such as databases, emotion engines, report generation engines, comparison tools, and anticipated question and answer generation engines.

[0324] Terminal: A terminal device that provides an interface for users to input verification results, and is equipped with a camera, microphone, and sensors necessary for emotion recognition.

[0325] Database: A database used to store verification results and historical data.

[0326] Emotion recognition engine: Software used to analyze a user's emotional state.

[0327] Report generation engine: Software that generates reports based on templates.

[0328] Comparison tool: Software for comparing and analyzing historical and current data.

[0329] Anticipated Q&A Generation Engine: Software that generates anticipated questions and answers based on the report content.

[0330] Implementation method

[0331] 1. Input of verification results and emotion recognition:

[0332] The user inputs the verification results through the device. At this time, the emotion recognition engine built into the device analyzes the user's emotional state. This determines whether the user is experiencing stress or fatigue.

[0333] 2. Data storage:

[0334] The entered validation results are saved to the database by the server.

[0335] 3. Automatic report generation:

[0336] The server automatically generates reports based on the saved validation results. These reports are efficiently created using template files.

[0337] 4. Generating anticipated questions and answers:

[0338] The generated report is analyzed, and anticipated questions and answers are created using past question patterns. This prepares us for future questions.

[0339] 5. Comparative analysis of data:

[0340] The server retrieves past validation results stored in the database and compares them to the current results. These comparison results are reflected in the report.

[0341] 6. Adjusting reports based on emotions:

[0342] The content and wording of the generated report are adjusted based on the user's emotional state recognized by the emotion recognition engine. For example, if the user is feeling stressed, the report content will be summarized concisely.

[0343] Specific example

[0344] As a concrete example, consider the case of using a factory robot. The factory robot inputs "quality inspection data for product X," analyzes the operator's emotional state using an emotion engine, and generates a report and anticipated questions and answers. It compares this with past inspection results and adjusts the report according to the operator's emotions.

[0345] Example of a prompt

[0346] prompt:

[0347] A factory robot inputs "product X quality inspection data," analyzes the operator's emotional state using an emotion engine, and generates a report and anticipated Q&A. It then compares this with past inspection results and adjusts the report according to the operator's emotions.

[0348] In this way, the present invention enables the provision of verification result reports tailored to the user's emotional state, thereby improving work efficiency within the factory.

[0349] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0350] Processing flow

[0351] Step 1: Input of verification results and emotion recognition

[0352] Input: User-verified data (e.g., quality inspection data for product X)

[0353] Processing: The device receives input data, and at that time, the emotion recognition engine collects data on the user's emotional state. Emotion analysis is performed using the camera, microphone, touch input speed, etc.

[0354] Output: Set of validation data and sentiment data

[0355] Step 2: Saving the verification results

[0356] Input: Set of validation data and sentiment data

[0357] Processing: The server securely stores the received data in the database. The storage process includes verifying the data format and performing error checks.

[0358] Output: Verification data and sentiment data stored in the database

[0359] Step 3: Automatic report generation

[0360] Input: Validation data stored in the database

[0361] Processing: The server uses a report generation engine to automatically generate reports using template files based on the saved verification data.

[0362] Output: Automated report

[0363] Step 4: Generating anticipated questions and answers

[0364] Input: Automated report

[0365] Processing: The server analyzes the generated report and generates questions and answers using a question and answer generation engine, referencing past question patterns.

[0366] Output: Set of anticipated questions and answers (pairs of questions and answers)

[0367] Step 5: Comparison with historical data

[0368] Input: Current validation result data and past validation result data

[0369] Processing: The server uses a comparison tool to analyze and compare current and past test results to identify performance changes and problems.

[0370] Output: Comparison results data (e.g., graphs or numerical data showing performance improvements)

[0371] Step 6: Adjusting the report based on emotions

[0372] Input: Automated reports, sentiment data

[0373] Processing: Based on the emotion data analyzed by the emotion recognition engine, the server uses the report generation engine to appropriately adjust the content and expression of the report. For example, if the user is experiencing stress, the report content will be summarized concisely.

[0374] Output: Optimized report

[0375] Description of each step

[0376] Step 1: Input of verification results and emotion recognition

[0377] The user inputs verification data through the device. The device receives the input data according to the format, and simultaneously, the emotion recognition engine uses the camera, microphone, and touch input speed to analyze the user's emotional state and collect emotion data. This generates a set of verification data and emotion data.

[0378] Step 2: Saving the verification results

[0379] The server saves the set of verification and sentiment data received from the terminal to the database. This saving process includes checking the data format and performing error checks. After saving, the database records the securely stored verification and sentiment data.

[0380] Step 3: Automatic report generation

[0381] The server automatically generates reports by applying template files using a report generation engine based on validation data stored in the database. This process creates visually appealing and easy-to-understand reports.

[0382] Step 4: Generating anticipated questions and answers

[0383] The server analyzes the generated report and automatically generates questions and answers using a question-and-answer generation engine based on past question patterns. This creates question-and-answer pairs, preparing the system for future questions.

[0384] Step 5: Comparison with historical data

[0385] The server retrieves current verification results data and historical verification results data stored in the database, and analyzes and compares them using a comparison tool. This comparison identifies performance changes and problems. The comparison results data is output in visual graphs and numerical formats.

[0386] Step 6: Adjusting the report based on emotions

[0387] The server uses the emotion recognition engine to analyze emotional data, and the report generation engine then adjusts the content and presentation of the report. For example, if the user is experiencing stress, the report is made more concise and easier to understand. This results in an optimized report being output.

[0388] The above describes the specific processing steps and content of the system program that implements the application example.

[0389] 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.

[0390] 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.

[0391] 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.

[0392] [Second Embodiment]

[0393] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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).

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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".

[0405] This invention relates to a verification result report generation system for improving operational efficiency. This system significantly reduces the user's workload by inputting and saving verification results, automatically generating reports, creating anticipated questions and answers, and comparing them with past results.

[0406] The main components of this system are as follows:

[0407] First, the user accesses a dedicated input screen to enter verification results. The terminal provides this input screen and checks the format of the data entered by the user. If the input data is valid, the terminal sends the data to the server.

[0408] The server saves the received verification data to a database. Next, the server automatically generates a report based on the saved data. Here, a predetermined template is used to format the data and create a visually appealing report.

[0409] Next, the server analyzes the generated report and automatically generates anticipated questions and their answers. Here, by utilizing past question patterns and accumulated data, it is possible to create highly accurate anticipated questions and answers.

[0410] Furthermore, the server retrieves past verification results stored in the database and compares them to current results. This comparison visually shows what performance improvements or problems exist. These comparison results are reflected in a report, providing users with clear areas for improvement.

[0411] The final report generated based on the above process is notified to the user from the server and becomes accessible via a saved link. This allows users to quickly and efficiently create and review documents.

[0412] Specific example

[0413] For example, consider a scenario where a user inputs the durability test results for a product. The user uses a terminal to input "Durability test results for product A." The terminal checks the format of the input data and sends the verification results, "Durability: 95, Failure rate: 0.5%", to the server. The server stores this in a database and generates a report based on the stored data.

[0414] Next, the server analyzes the generated report and automatically generates questions and answers such as, "What were the results of this durability test?". Furthermore, the server retrieves past "durability test results for product A" and compares them with the current results. The server adds the comparison results, such as "The failure rate improved from 0.8% to 0.5%", to the report and notifies the user.

[0415] In this way, this system reduces the burden on users and supports efficient and accurate report creation.

[0416] The following describes the processing flow.

[0417] Step 1:

[0418] The user accesses the system's input screen and enters the verification results. The terminal automatically checks the format of the entered data and verifies that it is in the correct format.

[0419] Step 2:

[0420] The terminal sends data that has passed the format check to the server. The server temporarily stores the received data and prepares to write it to the database.

[0421] Step 3:

[0422] The server saves the verification results data to the database. If the save is successful, the server generates a save completion message and sends it to the terminal.

[0423] Step 4:

[0424] The server loads a report template based on the validation results stored in the database and embeds the validation results. This automatically generates the initial report.

[0425] Step 5:

[0426] The server analyzes the generated report and predicts anticipated question patterns. It then references a database of past questions to generate relevant questions and their answers.

[0427] Step 6:

[0428] Add the server-generated questions and answers to the report to complete the anticipated Q&A section. This completes the first report.

[0429] Step 7:

[0430] The server retrieves past verification results from the database and compares them with current results. If any new discoveries or areas for improvement are found as a result of the comparison, they are reflected in the report.

[0431] Step 8:

[0432] The server completes the final report and saves the report file. It generates a link to the saved report and notifies the user.

[0433] Step 9:

[0434] The user accesses the completed report using the provided link. The user reviews the report and takes any necessary actions or further feedback.

[0435] This processing flow allows users to quickly and efficiently generate and review verification results reports.

[0436] (Example 1)

[0437] 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."

[0438] Conventional verification result reporting systems often involved manual tasks such as data entry, report generation, and the creation of anticipated questions and answers, resulting in low work efficiency and a heavy burden on users. In particular, when dealing with large amounts of verification data, comparing with historical data and generating highly accurate anticipated questions and answers required considerable time and effort. Furthermore, there was a lack of effective means to notify users of the generated reports, making prompt responses difficult.

[0439] 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.

[0440] In this invention, the server includes means for storing verification results in a database, means for automatically generating a report using a template based on the stored verification results, means for analyzing the generated report and generating anticipated questions and answers using past question patterns, means for comparing past results with current verification results, and means for reflecting the comparison results in the report and notifying the user. As a result, the user can efficiently input verification results, receive automatically generated reports and anticipated questions and answers, and proceed with their work quickly and accurately.

[0441] A "terminal" is a device used by users to input verification results and has a function to check the format of the input data.

[0442] A "server" is a central computer system that stores received verification result data in a database, automatically generates reports based on the stored data, analyzes them, and sends notifications.

[0443] A "database" is a data storage system used by a server to store and manage verification result data.

[0444] A "template" refers to a predetermined format or style that a server uses to automatically generate reports.

[0445] "Anticipated Q&A" refers to a collection of answers created based on the generated report, providing users with anticipated questions and their corresponding answers.

[0446] A "generative AI model" is an artificial intelligence technology that uses past question patterns and validation data to automatically generate highly accurate anticipated questions and answers.

[0447] A "comparison method" is a processing function that allows a server to compare past verification results with current results to identify areas for performance improvement and problems.

[0448] "Notification methods" refer to mechanisms for informing users of generated reports and comparison results, including methods such as email and display on dashboards.

[0449] This invention relates to a system that allows users to efficiently input and manage verification results and automatically generate reports and anticipated questions and answers. The system consists of a server and terminals as its main components.

[0450] First, the user accesses a dedicated input screen. For example, by accessing a specific URL using a web browser, they can input verification results. The input screen provides multiple input fields, such as product name and test results.

[0451] The terminal has a function to check the format of data entered by the user. For example, it checks whether the durability value is within the range of 0 to 100 and whether the failure rate is provided in percentage format. If the data is not valid, it displays an error message and prompts the user to re-enter the data.

[0452] When correct data is entered, the terminal sends that data to the server. The data is sent in JSON format and reaches the server via an HTTP POST request. In this case, the sending endpoint is, for example, " / api / submit_test_result".

[0453] The server saves the received data to an internal database. For example, an SQL database is used, and an INSERT query is executed against the "test_results" table. Storing the data in the database makes it available for future data analysis and report generation.

[0454] The server automatically generates reports based on the stored data. Specifically, it uses a Python script and the Jinja2 template engine to generate reports in HTML format. The templates include a predefined format, which formats the data and results in a visually appealing report.

[0455] Once a report is generated, the server analyzes it and automatically generates anticipated questions and answers. This process uses a generation AI model (e.g., GPT-4) to create a highly accurate set of questions and answers by comparing them with past question patterns.

[0456] Furthermore, the server retrieves saved historical validation results and compares them to current results. This comparison clearly shows performance improvements and areas for improvement. A Python script is used to analyze the data and add the comparison results to the report.

[0457] Finally, the generated report is notified to the user from the server. Notification methods include sending a link to the user's email address or displaying a notification on the dashboard that a new report has been added. This allows users to quickly and efficiently create and review documents.

[0458] Specific example

[0459] For example, consider a scenario where a user inputs the results of a durability test for "Product A". The user accesses "http: / / example.com / report_input" from their browser and enters "Durability: 95, Failure Rate: 0.5%" into the input field. The terminal checks the format of this data, confirms that it is valid, and then sends it to the server.

[0460] The server saves this data to a database and generates a report based on the saved data. Then, it uses a generative AI model (e.g., GPT-4) to automatically generate questions such as "What were the results of this durability test?" and their answers. The server also compares the results with past test results and adds information to the report such as "The defect rate improved from 0.8% to 0.5%."

[0461] The generated report is notified to the user, who can access the detailed report via a specified link. This significantly improves the user's work efficiency.

[0462] Example of a prompt

[0463] For example, you can use the following prompt statements:

[0464] "Please enter the durability test results for Product A. Example: Durability: 95, Defect Rate: 0.5%"

[0465] This reduces the burden on users and supports efficient and accurate report creation.

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

[0467] Step 1:

[0468] The user accesses a dedicated input screen to enter the verification results. For example, they access "http: / / example.com / report_input" from a web browser and enter "Durability test results for product A," for example, "Durability: 95, Defect rate: 0.5%," into the input field. The input data is provided to the user and formatted on the input screen.

[0469] Step 2:

[0470] The terminal checks the format of the data entered by the user. For example, it verifies that the durability is within the range of 0 to 100 and that the failure rate is in percentage format. This check ensures data consistency and accuracy. Here, it distinguishes between valid and invalid data, and if invalid data is found, the terminal displays an error message to the user and prompts them to re-enter the data.

[0471] Step 3:

[0472] If the terminal receives valid data, it sends that data to the server. For example, it might send data to the " / api / submit_test_result" endpoint using an HTTP POST request. The data is sent in JSON format. The input data is sent to the server, which then receives it.

[0473] Step 4:

[0474] The server saves the received validation results data to a database. For example, it uses an INSERT query to save the data to the "test_results" table in an SQL database. The saved data is then used in subsequent processing. The saved data is stored in the database, which enables later analysis.

[0475] Step 5:

[0476] The server automatically generates reports based on the stored data. For example, it uses a Python script and the Jinja2 template engine to generate HTML reports. This template includes a predefined format, formatting the data and creating a highly readable report. For report generation, the input data is embedded in the template, and the output is generated as an HTML report.

[0477] Step 6:

[0478] The server analyzes the generated report and uses a generation AI model (e.g., GPT-4) to automatically generate anticipated questions and answers. For example, it generates questions and answers such as, "What were the results of this durability test?" By referring to past question patterns, it creates a highly accurate set of questions and answers. In this process, the text data from the report is input, the AI ​​model generates questions and answers, and the output is obtained as anticipated questions and answers.

[0479] Step 7:

[0480] The server retrieves stored historical validation results and compares them to current results. For example, it uses an SQL query to retrieve historical validation data from the "test_results" table and performs a comparison using Python. This comparison visually shows performance improvements and problems. Historical and current data are used as input, and the comparison results are obtained as output.

[0481] Step 8:

[0482] The server notifies the user of the final report, which includes the generated report, anticipated questions and answers, and comparison results. For example, it can send a notification email with a link to the user's email address, or display a notification on the dashboard that a new report has been added. This notification allows the user to quickly access the detailed report. The notification includes a link to the final report, and its output is provided to the user.

[0483] Therefore, this system can reduce the user's workload and support efficient and accurate report creation.

[0484] (Application Example 1)

[0485] 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 glasses 214 will be referred to as the "terminal."

[0486] Conventional verification result reporting systems have faced challenges such as requiring significant time and effort for data entry, storage, and report generation. Furthermore, manual comparison with historical data often led to decreased operational efficiency. Additionally, the lack of automation in the creation of anticipated questions and answers sometimes imposed additional burdens on users. A new system is needed to address these challenges and streamline operational processes in logistics centers and similar facilities.

[0487] 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.

[0488] In this invention, the server includes means for inputting verification results, means for saving the inputted verification results, means for automatically generating a report based on the saved verification results, means for generating anticipated questions and answers based on the generated report, means for comparing the saved past results with the current verification results, means for reflecting the comparison results in the report, means for automatically generating questions and answers using a generation AI model based on past and current verification data, and means for inputting verification results and checking reports using a smart device. As a result, users can efficiently input verification results, generate reports, and compare them with past data, significantly reducing their workload.

[0489] "Verification results" refer to the results of tests and investigations conducted to evaluate the performance and quality of a particular product or service.

[0490] "Means of input" refers to the interface or device that allows users to register verification results in the system.

[0491] "Means of storage" refers to functions or devices for accumulating the entered verification results in a database or storage device.

[0492] "Methods for automatically generating reports" refer to algorithms or programs that automatically create reports based on saved verification results and predetermined templates.

[0493] "Means for generating anticipated questions and answers" refers to engines or software that automatically generate anticipated questions and their answers based on the generated report.

[0494] "Means of comparison" refers to a function that compares past and current verification results and analyzes the differences and areas for improvement.

[0495] "Means of reflection" refers to functions that add comparison results to reports and provide them to users in a visually easy-to-understand format.

[0496] A "generative AI model" refers to an artificial intelligence model that learns from large datasets and is used for natural language processing.

[0497] A "smart device" refers to a portable device, such as a smartphone or tablet, that can connect to the internet and run applications.

[0498] This invention relates to a system for automating the creation of verification result reports at logistics centers. This system significantly improves operational efficiency by efficiently inputting verification results, automatically generating reports, creating anticipated questions and answers, and comparing them with past results.

[0499] System Configuration

[0500] 1. Hardware

[0501] User terminal: A device such as a smartphone, tablet, or PC. The user uses this device to input verification results and review reports.

[0502] Servers: Cloud servers or dedicated servers are used. They are used for data storage, analysis, and execution of generational AI models.

[0503] Specific examples: AWS, Google Cloud Platform

[0504] Database: Used to store verification results and generated reports.

[0505] Examples: MySQL, PostgreSQL

[0506] 2. Software

[0507] Data entry form: A web or mobile application for users to enter verification results.

[0508] Frameworks: React Native, Flutter

[0509] Report generation program: A program that automatically generates reports based on verification result data.

[0510] Data analysis program: A program that compares saved past verification results with current verification results and analyzes the results.

[0511] Generative AI model: An artificial intelligence model used for natural language processing.

[0512] Model: GPT-4, BERT

[0513] Program processing

[0514] Input of verification results

[0515] Users access a dedicated data entry form using their smartphones or tablets. They enter necessary data such as "product ID," "inspection results," and "inventory quantity," and then press the submit button. The smart device checks whether the entered data is correct and sends it to the server.

[0516] Data storage

[0517] The server saves the received verification results data to a database. The data is stored in an appropriate format and used for subsequent analysis and report generation.

[0518] Report generation

[0519] The server automatically generates reports based on the stored data. It uses predefined template files to format the data and create visually appealing reports.

[0520] Generation of anticipated questions and answers

[0521] Based on the generated report, the server automatically generates anticipated questions and their answers. Using a generation AI model, it creates question-and-answer pairs, referencing past question patterns.

[0522] Comparison with past data

[0523] The server compares the current results with previously saved verification results. This comparison visually shows areas for improvement and problems. This information is reflected in reports and notified to the user.

[0524] Specific example

[0525] For example, when a user inputs the durability test results for a product, the user uses a terminal to input "Durability test results for product A." The terminal checks the format of the input data and sends the verification result "Durability: 95, Defect rate: 0.5%" to the server. The server saves this to a database and generates a report based on the saved data. Next, the server analyzes the generated report and automatically generates questions and answers such as "What are the results of this durability test?". Furthermore, the server retrieves past "Durability test results for product A" and compares them with the current results. The server adds the comparison result, such as "The past defect rate improved from 0.8% to 0.5%", to the report and notifies the user.

[0526] Example of a prompt

[0527] Product inspection results:

[0528] Product ID: A123

[0529] Test results: Good

[0530] Quantity in stock: 200

[0531] Please compare the current test data with past test data and generate a report.

[0532] Please also enter any anticipated questions and their answers.

[0533] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0534] Step 1:

[0535] Users input verification results using smart devices (smartphones or tablets). Users access a data entry form and enter necessary information such as "Product ID," "Inspection Result," and "Inventory Quantity." The input data is format-checked on the device, and if there are no errors, it is sent to the server. For example, input data might include "Product ID: A123," "Inspection Result: Good," and "Inventory Quantity: 200."

[0536] Step 2:

[0537] The verification result data sent from the terminal is received by the server. The server saves this verification result data to a database. Specifically, it executes an SQL query to insert the verification result data into the appropriate table in the database. The input is the verification result data (e.g., "Product ID: A123", "Inspection Result: Good", "Inventory Quantity: 200"), and the output is the data saved in the database.

[0538] Step 3:

[0539] The server automatically generates a report based on the stored validation result data. In this process, it formats the validation result data using a predetermined template file. Specifically, it uses a template engine to convert the validation results into an easily readable format. The input is the validation result data retrieved from the database, and the output is the generated report file.

[0540] Step 4:

[0541] Based on the generated report, the server automatically generates anticipated questions and their answers. Here, a generative AI model (e.g., GPT-4) is used for natural language processing. Specifically, the report data is input to the generative AI model, which then generates pairs of anticipated questions and answers. The input is the report data, and the output is the generated question and answer pairs.

[0542] Step 5:

[0543] The server compares the current verification result with previously stored verification results. Specifically, it retrieves past data from the database and uses an algorithm to analyze the differences between it and the current result. The inputs are the current verification result data and the past verification result data, and the output is the comparison result.

[0544] Step 6:

[0545] The server incorporates the comparison results into the generated report. Specifically, it adds the comparison results to the report template and generates a consistent report overall. The inputs are the comparison results and the generated report, and the output is the final report.

[0546] Step 7:

[0547] The server notifies the user of the final report and provides a link that can be accessed from a smart device. Specifically, it sends an email or push notification to the user, including the link to access the report. The input is the URL of the final report, and the output is the notified user.

[0548] 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.

[0549] This invention relates to a system that combines an emotion engine with a verification result report generation system to improve operational efficiency, enabling the system to recognize the user's emotional state and generate reports, anticipated questions and answers, and compare results with past results based on that state. This system provides an optimal report tailored to the user's emotions by combining emotion recognition technology with the process of inputting and saving verification results, automatically generating reports, creating anticipated questions and answers, and comparing results with past results.

[0550] The main components of this system are as follows:

[0551] First, the user accesses a dedicated input screen to enter verification results. The terminal provides this input screen and verifies the format of the data entered by the user. If the input data is correct, the terminal sends the data to the server.

[0552] The server saves the received verification data to a database. Next, the server automatically generates a report based on the saved data. Here, a predetermined template is used to format the data and create a visually appealing report.

[0553] Next, the server analyzes the generated report and automatically generates anticipated questions and their answers. Here, by utilizing past question patterns and accumulated data, it is possible to create highly accurate anticipated questions and answers.

[0554] Furthermore, the server retrieves past verification results stored in the database and compares them to current results. This comparison visually shows what performance improvements or problems exist. These comparison results are reflected in a report, providing users with clear areas for improvement.

[0555] Embedding an emotion engine

[0556] This system incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's input data and behavior during operation to recognize their current emotional state. Specifically, it identifies emotions through factors such as key input speed, mouse movements, and facial recognition (when using a webcam).

[0557] The content and wording of the generated reports are adjusted based on the user's emotional state recognized by the emotion engine. For example, if the user is experiencing stress, the report content is made more concise, and negative results are expressed in softer language. This reduces the burden on the user and enables the generation of more adaptable reports.

[0558] Specific example

[0559] For example, consider a scenario where a user inputs the durability test results for a product. The user uses a terminal to input "Durability test results for product A." The terminal checks the format of the input data and sends the verification results, "Durability: 95, Failure rate: 0.5%", to the server. The server stores this in a database and generates a report based on the stored data.

[0560] Next, the server analyzes the generated report and automatically generates questions and answers such as, "What were the results of this durability test?". Furthermore, the server retrieves past "durability test results for product A" and compares them with the current results. The server adds the comparison results, such as "The failure rate improved from 0.8% to 0.5%", to the report and notifies the user.

[0561] In addition, during this process, the emotion engine analyzes the user's emotional state at the time of input, and if the user is experiencing stress or fatigue, it adjusts the report content to be more concise. In this way, it is possible to provide an optimal report tailored to the user's psychological state.

[0562] This system allows users to create and review reports efficiently and accurately, and the inclusion of an emotion engine further reduces the psychological burden on users.

[0563] The following describes the processing flow.

[0564] Step 1:

[0565] The user accesses the system's input screen and enters the verification results. The terminal automatically checks the format of the entered data to ensure it is correct. The emotion engine collects the user's keystroke speed, mouse movements, and, if possible, facial expression information during input.

[0566] Step 2:

[0567] The device sends data that has passed the format check, along with user sentiment data collected by the sentiment engine, to the server. The server temporarily stores the received data and prepares it for writing to the database.

[0568] Step 3:

[0569] The server saves the verification results data to the database. If the save is successful, the server generates a save completion message and sends it to the terminal. Sentiment data is also saved to the database in the same way.

[0570] Step 4:

[0571] The server loads a report template based on the validation results stored in the database and embeds the results. Here, it adjusts the tone and expression of the template, taking into account the user's emotional data collected by the emotion engine. For example, if the user is stressed, the results will be made concise and softer.

[0572] Step 5:

[0573] The server analyzes the generated report and predicts anticipated question patterns. It then references a database of past questions to generate relevant questions and their answers. The generated questions and answers are then refined using sentiment engine data to ensure they are expressed in a way that takes the user's psychological state into account.

[0574] Step 6:

[0575] The server-generated questions and answers are added to the report, completing the anticipated Q&A section. Based on the analysis results from the sentiment engine, the difficulty of the questions and the level of detail in the answers are also adjusted.

[0576] Step 7:

[0577] The server retrieves past test results from the database and compares them to current results. This comparison visually shows what performance improvements and problems exist. The comparison results are reflected in the report, taking into account the sentiment engine data.

[0578] Step 8:

[0579] The server completes the final report and saves the report file. It generates a link to the saved report and notifies the user. The notification message is also adjusted to suit the user's emotional state.

[0580] Step 9:

[0581] The user accesses the completed report using the provided link. The user reviews the report and takes any necessary actions or further feedback.

[0582] This processing flow allows users to quickly and efficiently generate and review verification results, and the integration of an emotion engine further reduces the user's psychological burden.

[0583] (Example 2)

[0584] 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".

[0585] In modern business, there is a demand for rapid and accurate reporting of verification results. However, conventional report generation systems do not take into account the user's emotional state, making them burdensome for users who are stressed or fatigued. Furthermore, the generated reports are formulaic and lack responses to the specific problems and questions that users have. It is necessary to solve these problems and provide a more effective and user-friendly report generation system.

[0586] 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.

[0587] In this invention, the server includes means for inputting verification results, means for saving the inputted verification results, means for automatically generating a report based on the saved verification results, means for generating anticipated questions and answers based on the generated report, means for comparing the saved past results with the current verification results, means for reflecting the comparison results in the report, means for analyzing the user's emotional state, and means for adjusting the content of the report based on the analyzed emotional state. This enables flexible report generation in accordance with the user's emotional state, making it possible to provide highly accurate and specific information while reducing the user's psychological burden.

[0588] "Verification results" refer to numerical data and qualitative evaluation results obtained through tests and experiments.

[0589] "Means of input" refers to an interface or device for the user to provide verification results to the system.

[0590] "Means of storage" refers to a mechanism or device for accumulating the input verification results in a storage device such as a database.

[0591] "Means for automatically generating reports" refers to a mechanism or device that automatically creates reports using a set template or algorithm based on saved verification results.

[0592] "Means for generating anticipated questions and answers" refers to a mechanism or device for automatically creating predictable questions and their answers based on a generated report.

[0593] "Means for comparing past results with current verification results" refers to a mechanism or device for comparing stored past verification data with current data and evaluating the differences or changes between them.

[0594] "Means for reflecting comparison results in the report" refers to a mechanism or device for adding the results obtained from the aforementioned comparison to the content of the report and presenting them in an easily understandable manner.

[0595] "Means for analyzing emotional state" refers to a mechanism or device for determining a user's emotional state from user input, behavior, or facial expressions captured via a webcam.

[0596] "Means for adjusting the report content based on the analyzed emotional state" refers to a mechanism or device for modifying the structure and expression of a report, taking into account the user's emotional state, and providing the report in a format suitable for the user.

[0597] This invention relates to a verification result report generation system for improving work efficiency according to the user's emotional state. This system allows the user to input verification results, automatically generates a report, creates anticipated questions and answers, compares them with past data, and further recognizes the user's emotional state via an emotion engine, adjusting the report based on that recognition.

[0598] Hardware and software used

[0599] (Hardware)

[0600] Terminal (user's PC or smartphone): Providing an input screen

[0601] Server: Data storage, report generation, sentiment recognition processing.

[0602] Webcam (optional): Facial recognition

[0603] (software)

[0604] Input form application: An interface for users to enter validation results.

[0605] Emotion engine (e.g., EmotionAPI): Recognizing user emotions.

[0606] Database (MySQL, PostgreSQL, etc.): Storage of validation result data

[0607] Report generation software (LaTeX, JasperReports, etc.): Report creation

[0608] Data analysis tools (SciPy, Pandas, etc.): Analysis and comparison of validation results

[0609] System operation

[0610] 1. The user logs into the system and accesses a screen for entering verification results. Here, the user enters specific verification result data.

[0611] For example, you would enter data such as "Durability test results for product A," "Durability: 95," and "Defect rate: 0.5%."

[0612] 2. The terminal checks the format of the input data and verifies that it is in the correct format. For example, it checks whether the durability value is 100 or less and the failure rate is 1% or less.

[0613] 3. The terminal sends properly formatted data to the server.

[0614] 4. The server saves the received verification result data to the database. Additional information such as the type of verification result, date and time, and the verifier's ID are also saved at this time.

[0615] 5. The server automatically generates reports using predefined templates based on the stored data. For example, it can create easy-to-read reports using LaTeX or JasperReports.

[0616] 6. The server analyzes the generated report and automatically generates frequently asked questions (FAQs) and their answers. By referring to past question patterns and existing data, it creates highly accurate Q&A.

[0617] 7. The server retrieves past verification results and compares them to current results. Graphs and tables are created to visually represent this comparison and reflected in the report. For example, a statement such as "Past defect rate improved from 0.8% to 0.5%" might be added.

[0618] 8. The emotion engine recognizes the user's emotional state through user actions and webcam footage. For example, it uses key input speed, mouse movements, and facial expression analysis to determine the user's stress level.

[0619] 9. The server adjusts the content and wording of the report based on the recognized emotional state of the user. Specifically, if the user is experiencing stress, the report content will be made more concise.

[0620] 10. The server provides the user with a finalized report. The user reviews this report and decides on their next action.

[0621] Examples of prompt statements

[0622] For example, when prompting a generative AI model, you would use a prompt statement like this:

[0623] "Please prepare a report based on the latest durability test results for Product A. Include past test results and note any improvements made. If users have reported experiencing fatigue, please summarize this concisely in the report."

[0624] This system allows users to create and review reports efficiently and accurately, and the inclusion of an emotion engine further reduces the psychological burden on users.

[0625] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0626] Processing steps

[0627] Step 1:

[0628] The user logs into the system and accesses a screen to enter verification results. Specifically, this involves the user logging into a web application using a browser and accessing an input form.

[0629] Input: The user enters the verification result data (e.g., "Product A durability test results: Durability: 95, Defect rate: 0.5%").

[0630] Output: The input data is sent to the terminal.

[0631] Step 2:

[0632] The terminal checks the format of the input data and verifies that it is in the correct format. Here, the input data is validated based on predefined rules.

[0633] Input: Verification result data submitted by the user.

[0634] Data processing / calculation: Verify that the format of the verification results is appropriate (e.g., whether the numerical value is 100 or less, or whether the defect rate is 1% or less).

[0635] Output: Correct data is sent to the next step, and incorrect data is returned to the user as an error message.

[0636] Step 3:

[0637] The terminal sends data that has passed the format check to the server.

[0638] Input: Verification result data that has been determined to be in the correct format.

[0639] Output: Validation result data sent to the server.

[0640] Step 4:

[0641] The server saves the received validation result data to a database. At this time, metadata such as the type of validation result, date and time, and the verifier's ID are also saved.

[0642] Input: Verification result data sent from the terminal.

[0643] Data processing / data calculation: Inserting data into the appropriate table in the database (e.g., executing an SQL INSERT statement).

[0644] Output: A confirmation message indicating that saving was successful.

[0645] Step 5:

[0646] The server automatically generates reports using predefined templates based on the stored data. This process utilizes tools such as LaTeX and JasperReports.

[0647] Input: Validation result data stored in the database.

[0648] Data processing / data calculation: Generate visually easy-to-understand reports by embedding data into templates (e.g., embedding data into LaTeX templates).

[0649] Output: The generated report file.

[0650] Step 6:

[0651] The server analyzes the generated report and automatically generates frequently asked questions (FAQs) and their answers. These are created by referencing past question patterns and existing data.

[0652] Input: Generated report.

[0653] Data processing / data computation: Generate FAQs using natural language processing (e.g., applying predefined rules or machine learning models).

[0654] Output: A set of automatically generated questions and answers.

[0655] Step 7:

[0656] The server retrieves past validation results and compares them with current results. This comparison is performed using data analysis tools (such as SciPy or Pandas).

[0657] Input: Current validation result data and past validation result data.

[0658] Data processing / data calculations: statistical analysis and graph creation (e.g., manipulating dataframes using Pandas and creating graphs using Matplotlib).

[0659] Output: Comparison results are output in text and graph formats and added to the report.

[0660] Step 8:

[0661] The emotion engine recognizes the user's emotional state through user actions and webcam footage.

[0662] Input: User operation data (key presses and mouse movements) and webcam footage.

[0663] Data processing / data calculation: Analysis using emotion recognition algorithms (e.g., using EmotionAPI).

[0664] Output: Analysis results (user's emotional state).

[0665] Step 9:

[0666] The server adjusts the content and wording of the report based on the recognized emotional state of the user.

[0667] Input: Emotional state data obtained from the emotion engine.

[0668] Data processing / data calculation: Adjusting the wording and format of reports (e.g., applying rewriting algorithms).

[0669] Output: Adjusted report.

[0670] Step 10:

[0671] The server then provides the user with a finalized report.

[0672] Input: Adjusted report.

[0673] Output: The final report provided to the user.

[0674] This allows the system to provide accurate and comprehensive verification reports while taking into account the user's emotional state.

[0675] (Application Example 2)

[0676] 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."

[0677] Conventional verification result reporting systems often failed to provide appropriate responses to users' emotional states, leading to increased stress and fatigue. Furthermore, the generated reports were sometimes redundant or complex, hindering user comprehension. In particular, in factory verification work, there is a need for both increased efficiency and reduced psychological burden on users.

[0678] 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. In this invention, the server includes means for inputting verification results, means for saving the inputted verification results, means for automatically generating a report based on the saved verification results, means for generating anticipated questions and answers based on the generated report, means for comparing the saved past results with the current verification results, means for reflecting the comparison results in the report, and means for recognizing the emotional state using emotion recognition technology and adjusting the report content. This makes it possible to adjust the report appropriately according to the user's emotional state, improve the efficiency of the verification work, and reduce the psychological burden.

[0679] "Means for inputting verification results" refers to an interface device for inputting data obtained through inspection work into the system.

[0680] "Means for storing the input verification results" refers to a database or storage device for recording and securely storing the input inspection result data.

[0681] "Means for automatically generating a report based on the saved verification results" refers to an algorithm or software that automatically creates a report using a predetermined template based on the saved data.

[0682] "Means for generating anticipated questions and answers based on the generated report" refers to a program that analyzes the generated report and prepares simulated answers to future questions.

[0683] "Means for comparing the stored past results with current verification results" refers to an analytical tool for comparing previously stored data with current data to identify changes in performance and areas for improvement.

[0684] "Means for reflecting the comparison results in the report" refers to a program or software that integrates the comparison results into the report and presents them in a visually easy-to-understand format.

[0685] "Means for recognizing emotional states and adjusting report content using emotion recognition technology" refers to an emotion engine and its control program for analyzing the user's emotional state and optimizing the content and expression of reports generated based on that analysis.

[0686] System Overview

[0687] This invention provides a system for efficiently managing verification results and providing reports tailored to the user's emotional state. By incorporating emotion recognition technology, this system generates highly accurate verification result reports while reducing the user's psychological burden.

[0688] Hardware and software to be used

[0689] Server: A server for high-performance computing, running software such as databases, emotion engines, report generation engines, comparison tools, and anticipated question and answer generation engines.

[0690] Terminal: A terminal device that provides an interface for users to input verification results, and is equipped with a camera, microphone, and sensors necessary for emotion recognition.

[0691] Database: A database used to store verification results and historical data.

[0692] Emotion recognition engine: Software used to analyze a user's emotional state.

[0693] Report generation engine: Software that generates reports based on templates.

[0694] Comparison tool: Software for comparing and analyzing historical and current data.

[0695] Anticipated Q&A Generation Engine: Software that generates anticipated questions and answers based on the report content.

[0696] Implementation method

[0697] 1. Input of verification results and emotion recognition:

[0698] The user inputs the verification results through the device. At this time, the emotion recognition engine built into the device analyzes the user's emotional state. This determines whether the user is experiencing stress or fatigue.

[0699] 2. Data storage:

[0700] The entered validation results are saved to the database by the server.

[0701] 3. Automatic report generation:

[0702] The server automatically generates reports based on the saved validation results. These reports are efficiently created using template files.

[0703] 4. Generating anticipated questions and answers:

[0704] The generated report is analyzed, and anticipated questions and answers are created using past question patterns. This prepares us for future questions.

[0705] 5. Comparative analysis of data:

[0706] The server retrieves past validation results stored in the database and compares them to the current results. These comparison results are reflected in the report.

[0707] 6. Adjusting reports based on emotions:

[0708] The content and wording of the generated report are adjusted based on the user's emotional state recognized by the emotion recognition engine. For example, if the user is feeling stressed, the report content will be summarized concisely.

[0709] Specific example

[0710] As a concrete example, consider the case of using a factory robot. The factory robot inputs "quality inspection data for product X," analyzes the operator's emotional state using an emotion engine, and generates a report and anticipated questions and answers. It compares this with past inspection results and adjusts the report according to the operator's emotions.

[0711] Example of a prompt

[0712] prompt:

[0713] A factory robot inputs "product X quality inspection data," analyzes the operator's emotional state using an emotion engine, and generates a report and anticipated Q&A. It then compares this with past inspection results and adjusts the report according to the operator's emotions.

[0714] In this way, the present invention enables the provision of verification result reports tailored to the user's emotional state, thereby improving work efficiency within the factory.

[0715] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0716] Processing flow

[0717] Step 1: Input of verification results and emotion recognition

[0718] Input: User-verified data (e.g., quality inspection data for product X)

[0719] Processing: The device receives input data, and at that time, the emotion recognition engine collects data on the user's emotional state. Emotion analysis is performed using the camera, microphone, touch input speed, etc.

[0720] Output: Set of validation data and sentiment data

[0721] Step 2: Saving the verification results

[0722] Input: Set of validation data and sentiment data

[0723] Processing: The server securely stores the received data in the database. The storage process includes verifying the data format and performing error checks.

[0724] Output: Verification data and sentiment data stored in the database

[0725] Step 3: Automatic report generation

[0726] Input: Validation data stored in the database

[0727] Processing: The server uses a report generation engine to automatically generate reports using template files based on the saved verification data.

[0728] Output: Automated report

[0729] Step 4: Generating anticipated questions and answers

[0730] Input: Automated report

[0731] Processing: The server analyzes the generated report and generates questions and answers using a question and answer generation engine, referencing past question patterns.

[0732] Output: Set of anticipated questions and answers (pairs of questions and answers)

[0733] Step 5: Comparison with historical data

[0734] Input: Current validation result data and past validation result data

[0735] Processing: The server uses a comparison tool to analyze and compare current and past test results to identify performance changes and problems.

[0736] Output: Comparison results data (e.g., graphs or numerical data showing performance improvements)

[0737] Step 6: Adjusting the report based on emotions

[0738] Input: Automated reports, sentiment data

[0739] Processing: Based on the emotion data analyzed by the emotion recognition engine, the server uses the report generation engine to appropriately adjust the content and expression of the report. For example, if the user is experiencing stress, the report content will be summarized concisely.

[0740] Output: Optimized report

[0741] Description of each step

[0742] Step 1: Input of verification results and emotion recognition

[0743] The user inputs verification data through the device. The device receives the input data according to the format, and simultaneously, the emotion recognition engine uses the camera, microphone, and touch input speed to analyze the user's emotional state and collect emotion data. This generates a set of verification data and emotion data.

[0744] Step 2: Saving the verification results

[0745] The server saves the set of verification and sentiment data received from the terminal to the database. This saving process includes checking the data format and performing error checks. After saving, the database records the securely stored verification and sentiment data.

[0746] Step 3: Automatic report generation

[0747] The server automatically generates reports by applying template files using a report generation engine based on validation data stored in the database. This process creates visually appealing and easy-to-understand reports.

[0748] Step 4: Generating anticipated questions and answers

[0749] The server analyzes the generated report and automatically generates questions and answers using a question-and-answer generation engine based on past question patterns. This creates question-and-answer pairs, preparing the system for future questions.

[0750] Step 5: Comparison with historical data

[0751] The server retrieves current verification results data and historical verification results data stored in the database, and analyzes and compares them using a comparison tool. This comparison identifies performance changes and problems. The comparison results data is output in visual graphs and numerical formats.

[0752] Step 6: Adjusting the report based on emotions

[0753] The server uses the emotion recognition engine to analyze emotional data, and the report generation engine then adjusts the content and presentation of the report. For example, if the user is experiencing stress, the report is made more concise and easier to understand. This results in an optimized report being output.

[0754] The above describes the specific processing steps and content of the system program that implements the application example.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] [Third Embodiment]

[0759] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0760] 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.

[0761] 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).

[0762] 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.

[0763] 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.

[0764] 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).

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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".

[0771] This invention relates to a verification result report generation system for improving operational efficiency. This system significantly reduces the user's workload by inputting and saving verification results, automatically generating reports, creating anticipated questions and answers, and comparing them with past results.

[0772] The main components of this system are as follows:

[0773] First, the user accesses a dedicated input screen to enter verification results. The terminal provides this input screen and checks the format of the data entered by the user. If the input data is valid, the terminal sends the data to the server.

[0774] The server saves the received verification data to a database. Next, the server automatically generates a report based on the saved data. Here, a predetermined template is used to format the data and create a visually appealing report.

[0775] Next, the server analyzes the generated report and automatically generates anticipated questions and their answers. Here, by utilizing past question patterns and accumulated data, it is possible to create highly accurate anticipated questions and answers.

[0776] Furthermore, the server retrieves past verification results stored in the database and compares them to current results. This comparison visually shows what performance improvements or problems exist. These comparison results are reflected in a report, providing users with clear areas for improvement.

[0777] The final report generated based on the above process is notified to the user from the server and becomes accessible via a saved link. This allows users to quickly and efficiently create and review documents.

[0778] Specific example

[0779] For example, consider a scenario where a user inputs the durability test results for a product. The user uses a terminal to input "Durability test results for product A." The terminal checks the format of the input data and sends the verification results, "Durability: 95, Failure rate: 0.5%", to the server. The server stores this in a database and generates a report based on the stored data.

[0780] Next, the server analyzes the generated report and automatically generates questions and answers such as, "What were the results of this durability test?". Furthermore, the server retrieves past "durability test results for product A" and compares them with the current results. The server adds the comparison results, such as "The failure rate improved from 0.8% to 0.5%", to the report and notifies the user.

[0781] In this way, this system reduces the burden on users and supports efficient and accurate report creation.

[0782] The following describes the processing flow.

[0783] Step 1:

[0784] The user accesses the system's input screen and enters the verification results. The terminal automatically checks the format of the entered data and verifies that it is in the correct format.

[0785] Step 2:

[0786] The terminal sends data that has passed the format check to the server. The server temporarily stores the received data and prepares to write it to the database.

[0787] Step 3:

[0788] The server saves the verification results data to the database. If the save is successful, the server generates a save completion message and sends it to the terminal.

[0789] Step 4:

[0790] The server loads a report template based on the validation results stored in the database and embeds the validation results. This automatically generates the initial report.

[0791] Step 5:

[0792] The server analyzes the generated report and predicts anticipated question patterns. It then references a database of past questions to generate relevant questions and their answers.

[0793] Step 6:

[0794] Add the server-generated questions and answers to the report to complete the anticipated Q&A section. This completes the first report.

[0795] Step 7:

[0796] The server retrieves past verification results from the database and compares them with current results. If any new discoveries or areas for improvement are found as a result of the comparison, they are reflected in the report.

[0797] Step 8:

[0798] The server completes the final report and saves the report file. It generates a link to the saved report and notifies the user.

[0799] Step 9:

[0800] The user accesses the completed report using the provided link. The user reviews the report and takes any necessary actions or further feedback.

[0801] This processing flow allows users to quickly and efficiently generate and review verification results reports.

[0802] (Example 1)

[0803] 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."

[0804] Conventional verification result reporting systems often involved manual tasks such as data entry, report generation, and the creation of anticipated questions and answers, resulting in low work efficiency and a heavy burden on users. In particular, when dealing with large amounts of verification data, comparing with historical data and generating highly accurate anticipated questions and answers required considerable time and effort. Furthermore, there was a lack of effective means to notify users of the generated reports, making prompt responses difficult.

[0805] 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.

[0806] In this invention, the server includes means for storing verification results in a database, means for automatically generating a report using a template based on the stored verification results, means for analyzing the generated report and generating anticipated questions and answers using past question patterns, means for comparing past results with current verification results, and means for reflecting the comparison results in the report and notifying the user. As a result, the user can efficiently input verification results, receive automatically generated reports and anticipated questions and answers, and proceed with their work quickly and accurately.

[0807] A "terminal" is a device used by users to input verification results and has a function to check the format of the input data.

[0808] A "server" is a central computer system that stores received verification result data in a database, automatically generates reports based on the stored data, analyzes them, and sends notifications.

[0809] A "database" is a data storage system used by a server to store and manage verification result data.

[0810] A "template" refers to a predetermined format or style that a server uses to automatically generate reports.

[0811] "Anticipated Q&A" refers to a collection of answers created based on the generated report, providing users with anticipated questions and their corresponding answers.

[0812] A "generative AI model" is an artificial intelligence technology that uses past question patterns and validation data to automatically generate highly accurate anticipated questions and answers.

[0813] A "comparison method" is a processing function that allows a server to compare past verification results with current results to identify areas for performance improvement and problems.

[0814] "Notification methods" refer to mechanisms for informing users of generated reports and comparison results, including methods such as email and display on dashboards.

[0815] This invention relates to a system that allows users to efficiently input and manage verification results and automatically generate reports and anticipated questions and answers. The system consists of a server and terminals as its main components.

[0816] First, the user accesses a dedicated input screen. For example, by accessing a specific URL using a web browser, they can input verification results. The input screen provides multiple input fields, such as product name and test results.

[0817] The terminal has a function to check the format of data entered by the user. For example, it checks whether the durability value is within the range of 0 to 100 and whether the failure rate is provided in percentage format. If the data is not valid, it displays an error message and prompts the user to re-enter the data.

[0818] When correct data is entered, the terminal sends that data to the server. The data is sent in JSON format and reaches the server via an HTTP POST request. In this case, the sending endpoint is, for example, " / api / submit_test_result".

[0819] The server saves the received data to an internal database. For example, an SQL database is used, and an INSERT query is executed against the "test_results" table. Storing the data in the database makes it available for future data analysis and report generation.

[0820] The server automatically generates reports based on the stored data. Specifically, it uses a Python script and the Jinja2 template engine to generate reports in HTML format. The templates include a predefined format, which formats the data and results in a visually appealing report.

[0821] Once a report is generated, the server analyzes it and automatically generates anticipated questions and answers. This process uses a generation AI model (e.g., GPT-4) to create a highly accurate set of questions and answers by comparing them with past question patterns.

[0822] Furthermore, the server retrieves saved historical validation results and compares them to current results. This comparison clearly shows performance improvements and areas for improvement. A Python script is used to analyze the data and add the comparison results to the report.

[0823] Finally, the generated report is notified to the user from the server. Notification methods include sending a link to the user's email address or displaying a notification on the dashboard that a new report has been added. This allows users to quickly and efficiently create and review documents.

[0824] Specific example

[0825] For example, consider a scenario where a user inputs the results of a durability test for "Product A". The user accesses "http: / / example.com / report_input" from their browser and enters "Durability: 95, Failure Rate: 0.5%" into the input field. The terminal checks the format of this data, confirms that it is valid, and then sends it to the server.

[0826] The server saves this data to a database and generates a report based on the saved data. Then, it uses a generative AI model (e.g., GPT-4) to automatically generate questions such as "What were the results of this durability test?" and their answers. The server also compares the results with past test results and adds information to the report such as "The defect rate improved from 0.8% to 0.5%."

[0827] The generated report is notified to the user, who can access the detailed report via a specified link. This significantly improves the user's work efficiency.

[0828] Example of a prompt

[0829] For example, you can use the following prompt statements:

[0830] "Please enter the durability test results for Product A. Example: Durability: 95, Defect Rate: 0.5%"

[0831] This reduces the burden on users and supports efficient and accurate report creation.

[0832] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0833] Step 1:

[0834] The user accesses a dedicated input screen to enter the verification results. For example, they access "http: / / example.com / report_input" from a web browser and enter "Durability test results for product A," for example, "Durability: 95, Defect rate: 0.5%," into the input field. The input data is provided to the user and formatted on the input screen.

[0835] Step 2:

[0836] The terminal checks the format of the data entered by the user. For example, it verifies that the durability is within the range of 0 to 100 and that the failure rate is in percentage format. This check ensures data consistency and accuracy. Here, it distinguishes between valid and invalid data, and if invalid data is found, the terminal displays an error message to the user and prompts them to re-enter the data.

[0837] Step 3:

[0838] If the terminal receives valid data, it sends that data to the server. For example, it might send data to the " / api / submit_test_result" endpoint using an HTTP POST request. The data is sent in JSON format. The input data is sent to the server, which then receives it.

[0839] Step 4:

[0840] The server saves the received validation results data to a database. For example, it uses an INSERT query to save the data to the "test_results" table in an SQL database. The saved data is then used in subsequent processing. The saved data is stored in the database, which enables later analysis.

[0841] Step 5:

[0842] The server automatically generates reports based on the stored data. For example, it uses a Python script and the Jinja2 template engine to generate HTML reports. This template includes a predefined format, formatting the data and creating a highly readable report. For report generation, the input data is embedded in the template, and the output is generated as an HTML report.

[0843] Step 6:

[0844] The server analyzes the generated report and uses a generation AI model (e.g., GPT-4) to automatically generate anticipated questions and answers. For example, it generates questions and answers such as, "What were the results of this durability test?" By referring to past question patterns, it creates a highly accurate set of questions and answers. In this process, the text data from the report is input, the AI ​​model generates questions and answers, and the output is obtained as anticipated questions and answers.

[0845] Step 7:

[0846] The server retrieves stored historical validation results and compares them to current results. For example, it uses an SQL query to retrieve historical validation data from the "test_results" table and performs a comparison using Python. This comparison visually shows performance improvements and problems. Historical and current data are used as input, and the comparison results are obtained as output.

[0847] Step 8:

[0848] The server notifies the user of the final report, which includes the generated report, anticipated questions and answers, and comparison results. For example, it can send a notification email with a link to the user's email address, or display a notification on the dashboard that a new report has been added. This notification allows the user to quickly access the detailed report. The notification includes a link to the final report, and its output is provided to the user.

[0849] Therefore, this system can reduce the user's workload and support efficient and accurate report creation.

[0850] (Application Example 1)

[0851] 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."

[0852] Conventional verification result reporting systems have faced challenges such as requiring significant time and effort for data entry, storage, and report generation. Furthermore, manual comparison with historical data often led to decreased operational efficiency. Additionally, the lack of automation in the creation of anticipated questions and answers sometimes imposed additional burdens on users. A new system is needed to address these challenges and streamline operational processes in logistics centers and similar facilities.

[0853] 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.

[0854] In this invention, the server includes means for inputting verification results, means for saving the inputted verification results, means for automatically generating a report based on the saved verification results, means for generating anticipated questions and answers based on the generated report, means for comparing the saved past results with the current verification results, means for reflecting the comparison results in the report, means for automatically generating questions and answers using a generation AI model based on past and current verification data, and means for inputting verification results and checking reports using a smart device. As a result, users can efficiently input verification results, generate reports, and compare them with past data, significantly reducing their workload.

[0855] "Verification results" refer to the results of tests and investigations conducted to evaluate the performance and quality of a particular product or service.

[0856] "Means of input" refers to the interface or device that allows users to register verification results in the system.

[0857] "Means of storage" refers to functions or devices for accumulating the entered verification results in a database or storage device.

[0858] "Methods for automatically generating reports" refer to algorithms or programs that automatically create reports based on saved verification results and predetermined templates.

[0859] "Means for generating anticipated questions and answers" refers to engines or software that automatically generate anticipated questions and their answers based on the generated report.

[0860] "Means of comparison" refers to a function that compares past and current verification results and analyzes the differences and areas for improvement.

[0861] "Means of reflection" refers to functions that add comparison results to reports and provide them to users in a visually easy-to-understand format.

[0862] A "generative AI model" refers to an artificial intelligence model that learns from large datasets and is used for natural language processing.

[0863] A "smart device" refers to a portable device, such as a smartphone or tablet, that can connect to the internet and run applications.

[0864] This invention relates to a system for automating the creation of verification result reports at logistics centers. This system significantly improves operational efficiency by efficiently inputting verification results, automatically generating reports, creating anticipated questions and answers, and comparing them with past results.

[0865] System Configuration

[0866] 1. Hardware

[0867] User terminal: A device such as a smartphone, tablet, or PC. The user uses this device to input verification results and review reports.

[0868] Servers: Cloud servers or dedicated servers are used. They are used for data storage, analysis, and execution of generational AI models.

[0869] Specific examples: AWS, Google Cloud Platform

[0870] Database: Used to store verification results and generated reports.

[0871] Examples: MySQL, PostgreSQL

[0872] 2. Software

[0873] Data entry form: A web or mobile application for users to enter verification results.

[0874] Frameworks: React Native, Flutter

[0875] Report generation program: A program that automatically generates reports based on verification result data.

[0876] Data analysis program: A program that compares saved past verification results with current verification results and analyzes the results.

[0877] Generative AI model: An artificial intelligence model used for natural language processing.

[0878] Model: GPT-4, BERT

[0879] Program processing

[0880] Input of verification results

[0881] Users access a dedicated data entry form using their smartphones or tablets. They enter necessary data such as "product ID," "inspection results," and "inventory quantity," and then press the submit button. The smart device checks whether the entered data is correct and sends it to the server.

[0882] Data storage

[0883] The server saves the received verification results data to a database. The data is stored in an appropriate format and used for subsequent analysis and report generation.

[0884] Report generation

[0885] The server automatically generates reports based on the stored data. It uses predefined template files to format the data and create visually appealing reports.

[0886] Generation of anticipated questions and answers

[0887] Based on the generated report, the server automatically generates anticipated questions and their answers. Using a generation AI model, it creates question-and-answer pairs, referencing past question patterns.

[0888] Comparison with past data

[0889] The server compares the current results with previously saved verification results. This comparison visually shows areas for improvement and problems. This information is reflected in reports and notified to the user.

[0890] Specific example

[0891] For example, when a user inputs the durability test results for a product, the user uses a terminal to input "Durability test results for product A." The terminal checks the format of the input data and sends the verification result "Durability: 95, Defect rate: 0.5%" to the server. The server saves this to a database and generates a report based on the saved data. Next, the server analyzes the generated report and automatically generates questions and answers such as "What are the results of this durability test?". Furthermore, the server retrieves past "Durability test results for product A" and compares them with the current results. The server adds the comparison result, such as "The past defect rate improved from 0.8% to 0.5%", to the report and notifies the user.

[0892] Example of a prompt

[0893] Product inspection results:

[0894] Product ID: A123

[0895] Test results: Good

[0896] Quantity in stock: 200

[0897] Please compare the current test data with past test data and generate a report.

[0898] Please also enter any anticipated questions and their answers.

[0899] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0900] Step 1:

[0901] Users input verification results using smart devices (smartphones or tablets). Users access a data entry form and enter necessary information such as "Product ID," "Inspection Result," and "Inventory Quantity." The input data is format-checked on the device, and if there are no errors, it is sent to the server. For example, input data might include "Product ID: A123," "Inspection Result: Good," and "Inventory Quantity: 200."

[0902] Step 2:

[0903] The verification result data sent from the terminal is received by the server. The server saves this verification result data to a database. Specifically, it executes an SQL query to insert the verification result data into the appropriate table in the database. The input is the verification result data (e.g., "Product ID: A123", "Inspection Result: Good", "Inventory Quantity: 200"), and the output is the data saved in the database.

[0904] Step 3:

[0905] The server automatically generates a report based on the stored validation result data. In this process, it formats the validation result data using a predetermined template file. Specifically, it uses a template engine to convert the validation results into an easily readable format. The input is the validation result data retrieved from the database, and the output is the generated report file.

[0906] Step 4:

[0907] Based on the generated report, the server automatically generates anticipated questions and their answers. Here, a generative AI model (e.g., GPT-4) is used for natural language processing. Specifically, the report data is input to the generative AI model, which then generates pairs of anticipated questions and answers. The input is the report data, and the output is the generated question and answer pairs.

[0908] Step 5:

[0909] The server compares the current verification result with previously stored verification results. Specifically, it retrieves past data from the database and uses an algorithm to analyze the differences between it and the current result. The inputs are the current verification result data and the past verification result data, and the output is the comparison result.

[0910] Step 6:

[0911] The server incorporates the comparison results into the generated report. Specifically, it adds the comparison results to the report template and generates a consistent report overall. The inputs are the comparison results and the generated report, and the output is the final report.

[0912] Step 7:

[0913] The server notifies the user of the final report and provides a link that can be accessed from a smart device. Specifically, it sends an email or push notification to the user, including the link to access the report. The input is the URL of the final report, and the output is the notified user.

[0914] 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.

[0915] This invention relates to a system that combines an emotion engine with a verification result report generation system to improve operational efficiency, enabling the system to recognize the user's emotional state and generate reports, anticipated questions and answers, and compare results with past results based on that state. This system provides an optimal report tailored to the user's emotions by combining emotion recognition technology with the process of inputting and saving verification results, automatically generating reports, creating anticipated questions and answers, and comparing results with past results.

[0916] The main components of this system are as follows:

[0917] First, the user accesses a dedicated input screen to enter verification results. The terminal provides this input screen and verifies the format of the data entered by the user. If the input data is correct, the terminal sends the data to the server.

[0918] The server saves the received verification data to a database. Next, the server automatically generates a report based on the saved data. Here, a predetermined template is used to format the data and create a visually appealing report.

[0919] Next, the server analyzes the generated report and automatically generates anticipated questions and their answers. Here, by utilizing past question patterns and accumulated data, it is possible to create highly accurate anticipated questions and answers.

[0920] Furthermore, the server retrieves past verification results stored in the database and compares them to current results. This comparison visually shows what performance improvements or problems exist. These comparison results are reflected in a report, providing users with clear areas for improvement.

[0921] Embedding an emotion engine

[0922] This system incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's input data and behavior during operation to recognize their current emotional state. Specifically, it identifies emotions through factors such as key input speed, mouse movements, and facial recognition (when using a webcam).

[0923] The content and wording of the generated reports are adjusted based on the user's emotional state recognized by the emotion engine. For example, if the user is experiencing stress, the report content is made more concise, and negative results are expressed in softer language. This reduces the burden on the user and enables the generation of more adaptable reports.

[0924] Specific example

[0925] For example, consider a scenario where a user inputs the durability test results for a product. The user uses a terminal to input "Durability test results for product A." The terminal checks the format of the input data and sends the verification results, "Durability: 95, Failure rate: 0.5%", to the server. The server stores this in a database and generates a report based on the stored data.

[0926] Next, the server analyzes the generated report and automatically generates questions and answers such as, "What were the results of this durability test?". Furthermore, the server retrieves past "durability test results for product A" and compares them with the current results. The server adds the comparison results, such as "The failure rate improved from 0.8% to 0.5%", to the report and notifies the user.

[0927] In addition, during this process, the emotion engine analyzes the user's emotional state at the time of input, and if the user is experiencing stress or fatigue, it adjusts the report content to be more concise. In this way, it is possible to provide an optimal report tailored to the user's psychological state.

[0928] This system allows users to create and review reports efficiently and accurately, and the inclusion of an emotion engine further reduces the psychological burden on users.

[0929] The following describes the processing flow.

[0930] Step 1:

[0931] The user accesses the system's input screen and enters the verification results. The terminal automatically checks the format of the entered data to ensure it is correct. The emotion engine collects the user's keystroke speed, mouse movements, and, if possible, facial expression information during input.

[0932] Step 2:

[0933] The device sends data that has passed the format check, along with user sentiment data collected by the sentiment engine, to the server. The server temporarily stores the received data and prepares it for writing to the database.

[0934] Step 3:

[0935] The server saves the verification results data to the database. If the save is successful, the server generates a save completion message and sends it to the terminal. Sentiment data is also saved to the database in the same way.

[0936] Step 4:

[0937] The server loads a report template based on the validation results stored in the database and embeds the results. Here, it adjusts the tone and expression of the template, taking into account the user's emotional data collected by the emotion engine. For example, if the user is stressed, the results will be made concise and softer.

[0938] Step 5:

[0939] The server analyzes the generated report and predicts anticipated question patterns. It then references a database of past questions to generate relevant questions and their answers. The generated questions and answers are then refined using sentiment engine data to ensure they are expressed in a way that takes the user's psychological state into account.

[0940] Step 6:

[0941] The server-generated questions and answers are added to the report, completing the anticipated Q&A section. Based on the analysis results from the sentiment engine, the difficulty of the questions and the level of detail in the answers are also adjusted.

[0942] Step 7:

[0943] The server retrieves past test results from the database and compares them to current results. This comparison visually shows what performance improvements and problems exist. The comparison results are reflected in the report, taking into account the sentiment engine data.

[0944] Step 8:

[0945] The server completes the final report and saves the report file. It generates a link to the saved report and notifies the user. The notification message is also adjusted to suit the user's emotional state.

[0946] Step 9:

[0947] The user accesses the completed report using the provided link. The user reviews the report and takes any necessary actions or further feedback.

[0948] This processing flow allows users to quickly and efficiently generate and review verification results, and the integration of an emotion engine further reduces the user's psychological burden.

[0949] (Example 2)

[0950] 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."

[0951] In modern business, there is a demand for rapid and accurate reporting of verification results. However, conventional report generation systems do not take into account the user's emotional state, making them burdensome for users who are stressed or fatigued. Furthermore, the generated reports are formulaic and lack responses to the specific problems and questions that users have. It is necessary to solve these problems and provide a more effective and user-friendly report generation system.

[0952] 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.

[0953] In this invention, the server includes means for inputting verification results, means for saving the inputted verification results, means for automatically generating a report based on the saved verification results, means for generating anticipated questions and answers based on the generated report, means for comparing the saved past results with the current verification results, means for reflecting the comparison results in the report, means for analyzing the user's emotional state, and means for adjusting the content of the report based on the analyzed emotional state. This enables flexible report generation in accordance with the user's emotional state, making it possible to provide highly accurate and specific information while reducing the user's psychological burden.

[0954] "Verification results" refer to numerical data and qualitative evaluation results obtained through tests and experiments.

[0955] "Means of input" refers to an interface or device for the user to provide verification results to the system.

[0956] "Means of storage" refers to a mechanism or device for accumulating the input verification results in a storage device such as a database.

[0957] "Means for automatically generating reports" refers to a mechanism or device that automatically creates reports using a set template or algorithm based on saved verification results.

[0958] "Means for generating anticipated questions and answers" refers to a mechanism or device for automatically creating predictable questions and their answers based on a generated report.

[0959] "Means for comparing past results with current verification results" refers to a mechanism or device for comparing stored past verification data with current data and evaluating the differences or changes between them.

[0960] "Means for reflecting comparison results in the report" refers to a mechanism or device for adding the results obtained from the aforementioned comparison to the content of the report and presenting them in an easily understandable manner.

[0961] "Means for analyzing emotional state" refers to a mechanism or device for determining a user's emotional state from user input, behavior, or facial expressions captured via a webcam.

[0962] "Means for adjusting the report content based on the analyzed emotional state" refers to a mechanism or device for modifying the structure and expression of a report, taking into account the user's emotional state, and providing the report in a format suitable for the user.

[0963] This invention relates to a verification result report generation system for improving work efficiency according to the user's emotional state. This system allows the user to input verification results, automatically generates a report, creates anticipated questions and answers, compares them with past data, and further recognizes the user's emotional state via an emotion engine, adjusting the report based on that recognition.

[0964] Hardware and software used

[0965] (Hardware)

[0966] Terminal (user's PC or smartphone): Providing an input screen

[0967] Server: Data storage, report generation, sentiment recognition processing.

[0968] Webcam (optional): Facial recognition

[0969] (software)

[0970] Input form application: An interface for users to enter validation results.

[0971] Emotion engine (e.g., EmotionAPI): Recognizing user emotions.

[0972] Database (MySQL, PostgreSQL, etc.): Storage of validation result data

[0973] Report generation software (LaTeX, JasperReports, etc.): Report creation

[0974] Data analysis tools (SciPy, Pandas, etc.): Analysis and comparison of validation results

[0975] System operation

[0976] 1. The user logs into the system and accesses a screen for entering verification results. Here, the user enters specific verification result data.

[0977] For example, you would enter data such as "Durability test results for product A," "Durability: 95," and "Defect rate: 0.5%."

[0978] 2. The terminal checks the format of the input data and verifies that it is in the correct format. For example, it checks whether the durability value is 100 or less and the failure rate is 1% or less.

[0979] 3. The terminal sends properly formatted data to the server.

[0980] 4. The server saves the received verification result data to the database. Additional information such as the type of verification result, date and time, and the verifier's ID are also saved at this time.

[0981] 5. The server automatically generates reports using predefined templates based on the stored data. For example, it can create easy-to-read reports using LaTeX or JasperReports.

[0982] 6. The server analyzes the generated report and automatically generates frequently asked questions (FAQs) and their answers. By referring to past question patterns and existing data, it creates highly accurate Q&A.

[0983] 7. The server retrieves past verification results and compares them to current results. Graphs and tables are created to visually represent this comparison and reflected in the report. For example, a statement such as "Past defect rate improved from 0.8% to 0.5%" might be added.

[0984] 8. The emotion engine recognizes the user's emotional state through user actions and webcam footage. For example, it uses key input speed, mouse movements, and facial expression analysis to determine the user's stress level.

[0985] 9. The server adjusts the content and wording of the report based on the recognized emotional state of the user. Specifically, if the user is experiencing stress, the report content will be made more concise.

[0986] 10. The server provides the user with a finalized report. The user reviews this report and decides on their next action.

[0987] Examples of prompt statements

[0988] For example, when prompting a generative AI model, you would use a prompt statement like this:

[0989] "Please prepare a report based on the latest durability test results for Product A. Include past test results and note any improvements made. If users have reported experiencing fatigue, please summarize this concisely in the report."

[0990] This system allows users to create and review reports efficiently and accurately, and the inclusion of an emotion engine further reduces the psychological burden on users.

[0991] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0992] Processing steps

[0993] Step 1:

[0994] The user logs into the system and accesses a screen to enter verification results. Specifically, this involves the user logging into a web application using a browser and accessing an input form.

[0995] Input: The user enters the verification result data (e.g., "Product A durability test results: Durability: 95, Defect rate: 0.5%").

[0996] Output: The input data is sent to the terminal.

[0997] Step 2:

[0998] The terminal checks the format of the input data and verifies that it is in the correct format. Here, the input data is validated based on predefined rules.

[0999] Input: Verification result data submitted by the user.

[1000] Data processing / calculation: Verify that the format of the verification results is appropriate (e.g., whether the numerical value is 100 or less, or whether the defect rate is 1% or less).

[1001] Output: Correct data is sent to the next step, and incorrect data is returned to the user as an error message.

[1002] Step 3:

[1003] The terminal sends data that has passed the format check to the server.

[1004] Input: Verification result data that has been determined to be in the correct format.

[1005] Output: Validation result data sent to the server.

[1006] Step 4:

[1007] The server saves the received validation result data to a database. At this time, metadata such as the type of validation result, date and time, and the verifier's ID are also saved.

[1008] Input: Verification result data sent from the terminal.

[1009] Data processing / data calculation: Inserting data into the appropriate table in the database (e.g., executing an SQL INSERT statement).

[1010] Output: A confirmation message indicating that saving was successful.

[1011] Step 5:

[1012] The server automatically generates reports using predefined templates based on the stored data. This process utilizes tools such as LaTeX and JasperReports.

[1013] Input: Validation result data stored in the database.

[1014] Data processing / data calculation: Generate visually easy-to-understand reports by embedding data into templates (e.g., embedding data into LaTeX templates).

[1015] Output: The generated report file.

[1016] Step 6:

[1017] The server analyzes the generated report and automatically generates frequently asked questions (FAQs) and their answers. These are created by referencing past question patterns and existing data.

[1018] Input: Generated report.

[1019] Data processing / data computation: Generate FAQs using natural language processing (e.g., applying predefined rules or machine learning models).

[1020] Output: A set of automatically generated questions and answers.

[1021] Step 7:

[1022] The server retrieves past validation results and compares them with current results. This comparison is performed using data analysis tools (such as SciPy or Pandas).

[1023] Input: Current validation result data and past validation result data.

[1024] Data processing / data calculations: statistical analysis and graph creation (e.g., manipulating dataframes using Pandas and creating graphs using Matplotlib).

[1025] Output: Comparison results are output in text and graph formats and added to the report.

[1026] Step 8:

[1027] The emotion engine recognizes the user's emotional state through user actions and webcam footage.

[1028] Input: User operation data (key presses and mouse movements) and webcam footage.

[1029] Data processing / data calculation: Analysis using emotion recognition algorithms (e.g., using EmotionAPI).

[1030] Output: Analysis results (user's emotional state).

[1031] Step 9:

[1032] The server adjusts the content and wording of the report based on the recognized emotional state of the user.

[1033] Input: Emotional state data obtained from the emotion engine.

[1034] Data processing / data calculation: Adjusting the wording and format of reports (e.g., applying rewriting algorithms).

[1035] Output: Adjusted report.

[1036] Step 10:

[1037] The server then provides the user with a finalized report.

[1038] Input: Adjusted report.

[1039] Output: The final report provided to the user.

[1040] This allows the system to provide accurate and comprehensive verification reports while taking into account the user's emotional state.

[1041] (Application Example 2)

[1042] 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."

[1043] Conventional verification result reporting systems often failed to provide appropriate responses to users' emotional states, leading to increased stress and fatigue. Furthermore, the generated reports were sometimes redundant or complex, hindering user comprehension. In particular, in factory verification work, there is a need for both increased efficiency and reduced psychological burden on users.

[1044] 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. In this invention, the server includes means for inputting verification results, means for saving the inputted verification results, means for automatically generating a report based on the saved verification results, means for generating anticipated questions and answers based on the generated report, means for comparing the saved past results with the current verification results, means for reflecting the comparison results in the report, and means for recognizing the emotional state using emotion recognition technology and adjusting the report content. This makes it possible to adjust the report appropriately according to the user's emotional state, improve the efficiency of the verification work, and reduce the psychological burden.

[1045] "Means for inputting verification results" refers to an interface device for inputting data obtained through inspection work into the system.

[1046] "Means for storing the input verification results" refers to a database or storage device for recording and securely storing the input inspection result data.

[1047] "Means for automatically generating a report based on the saved verification results" refers to an algorithm or software that automatically creates a report using a predetermined template based on the saved data.

[1048] "Means for generating anticipated questions and answers based on the generated report" refers to a program that analyzes the generated report and prepares simulated answers to future questions.

[1049] "Means for comparing the stored past results with current verification results" refers to an analytical tool for comparing previously stored data with current data to identify changes in performance and areas for improvement.

[1050] "Means for reflecting the comparison results in the report" refers to a program or software that integrates the comparison results into the report and presents them in a visually easy-to-understand format.

[1051] "Means for recognizing emotional states and adjusting report content using emotion recognition technology" refers to an emotion engine and its control program for analyzing the user's emotional state and optimizing the content and expression of reports generated based on that analysis.

[1052] System Overview

[1053] This invention provides a system for efficiently managing verification results and providing reports tailored to the user's emotional state. By incorporating emotion recognition technology, this system generates highly accurate verification result reports while reducing the user's psychological burden.

[1054] Hardware and software to be used

[1055] Server: A server for high-performance computing, running software such as databases, emotion engines, report generation engines, comparison tools, and anticipated question and answer generation engines.

[1056] Terminal: A terminal device that provides an interface for users to input verification results, and is equipped with a camera, microphone, and sensors necessary for emotion recognition.

[1057] Database: A database used to store verification results and historical data.

[1058] Emotion recognition engine: Software used to analyze a user's emotional state.

[1059] Report generation engine: Software that generates reports based on templates.

[1060] Comparison tool: Software for comparing and analyzing historical and current data.

[1061] Anticipated Q&A Generation Engine: Software that generates anticipated questions and answers based on the report content.

[1062] Implementation method

[1063] 1. Input of verification results and emotion recognition:

[1064] The user inputs the verification results through the device. At this time, the emotion recognition engine built into the device analyzes the user's emotional state. This determines whether the user is experiencing stress or fatigue.

[1065] 2. Data storage:

[1066] The entered validation results are saved to the database by the server.

[1067] 3. Automatic report generation:

[1068] The server automatically generates reports based on the saved validation results. These reports are efficiently created using template files.

[1069] 4. Generating anticipated questions and answers:

[1070] The generated report is analyzed, and anticipated questions and answers are created using past question patterns. This prepares us for future questions.

[1071] 5. Comparative analysis of data:

[1072] The server retrieves past validation results stored in the database and compares them to the current results. These comparison results are reflected in the report.

[1073] 6. Adjusting reports based on emotions:

[1074] The content and wording of the generated report are adjusted based on the user's emotional state recognized by the emotion recognition engine. For example, if the user is feeling stressed, the report content will be summarized concisely.

[1075] Specific example

[1076] As a concrete example, consider the case of using a factory robot. The factory robot inputs "quality inspection data for product X," analyzes the operator's emotional state using an emotion engine, and generates a report and anticipated questions and answers. It compares this with past inspection results and adjusts the report according to the operator's emotions.

[1077] Example of a prompt

[1078] prompt:

[1079] A factory robot inputs "product X quality inspection data," analyzes the operator's emotional state using an emotion engine, and generates a report and anticipated Q&A. It then compares this with past inspection results and adjusts the report according to the operator's emotions.

[1080] In this way, the present invention enables the provision of verification result reports tailored to the user's emotional state, thereby improving work efficiency within the factory.

[1081] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1082] Processing flow

[1083] Step 1: Input of verification results and emotion recognition

[1084] Input: User-verified data (e.g., quality inspection data for product X)

[1085] Processing: The device receives input data, and at that time, the emotion recognition engine collects data on the user's emotional state. Emotion analysis is performed using the camera, microphone, touch input speed, etc.

[1086] Output: Set of validation data and sentiment data

[1087] Step 2: Saving the verification results

[1088] Input: Set of validation data and sentiment data

[1089] Processing: The server securely stores the received data in the database. The storage process includes verifying the data format and performing error checks.

[1090] Output: Verification data and sentiment data stored in the database

[1091] Step 3: Automatic report generation

[1092] Input: Validation data stored in the database

[1093] Processing: The server uses a report generation engine to automatically generate reports using template files based on the saved verification data.

[1094] Output: Automated report

[1095] Step 4: Generating anticipated questions and answers

[1096] Input: Automated report

[1097] Processing: The server analyzes the generated report and generates questions and answers using a question and answer generation engine, referencing past question patterns.

[1098] Output: Set of anticipated questions and answers (pairs of questions and answers)

[1099] Step 5: Comparison with historical data

[1100] Input: Current validation result data and past validation result data

[1101] Processing: The server uses a comparison tool to analyze and compare current and past test results to identify performance changes and problems.

[1102] Output: Comparison results data (e.g., graphs or numerical data showing performance improvements)

[1103] Step 6: Adjusting the report based on emotions

[1104] Input: Automated reports, sentiment data

[1105] Processing: Based on the emotion data analyzed by the emotion recognition engine, the server uses the report generation engine to appropriately adjust the content and expression of the report. For example, if the user is experiencing stress, the report content will be summarized concisely.

[1106] Output: Optimized report

[1107] Description of each step

[1108] Step 1: Input of verification results and emotion recognition

[1109] The user inputs verification data through the device. The device receives the input data according to the format, and simultaneously, the emotion recognition engine uses the camera, microphone, and touch input speed to analyze the user's emotional state and collect emotion data. This generates a set of verification data and emotion data.

[1110] Step 2: Saving the verification results

[1111] The server saves the set of verification and sentiment data received from the terminal to the database. This saving process includes checking the data format and performing error checks. After saving, the database records the securely stored verification and sentiment data.

[1112] Step 3: Automatic report generation

[1113] The server automatically generates reports by applying template files using a report generation engine based on validation data stored in the database. This process creates visually appealing and easy-to-understand reports.

[1114] Step 4: Generating anticipated questions and answers

[1115] The server analyzes the generated report and automatically generates questions and answers using a question-and-answer generation engine based on past question patterns. This creates question-and-answer pairs, preparing the system for future questions.

[1116] Step 5: Comparison with historical data

[1117] The server retrieves current verification results data and historical verification results data stored in the database, and analyzes and compares them using a comparison tool. This comparison identifies performance changes and problems. The comparison results data is output in visual graphs and numerical formats.

[1118] Step 6: Adjusting the report based on emotions

[1119] The server uses the emotion recognition engine to analyze emotional data, and the report generation engine then adjusts the content and presentation of the report. For example, if the user is experiencing stress, the report is made more concise and easier to understand. This results in an optimized report being output.

[1120] The above describes the specific processing steps and content of the system program that implements the application example.

[1121] 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.

[1122] 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.

[1123] 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.

[1124] [Fourth Embodiment]

[1125] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1126] 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.

[1127] 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).

[1128] 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.

[1129] 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.

[1130] 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).

[1131] 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.

[1132] 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.

[1133] 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.

[1134] 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.

[1135] 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.

[1136] 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.

[1137] 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".

[1138] This invention relates to a verification result report generation system for improving operational efficiency. This system significantly reduces the user's workload by inputting and saving verification results, automatically generating reports, creating anticipated questions and answers, and comparing them with past results.

[1139] The main components of this system are as follows:

[1140] First, the user accesses a dedicated input screen to enter verification results. The terminal provides this input screen and checks the format of the data entered by the user. If the input data is valid, the terminal sends the data to the server.

[1141] The server saves the received verification data to a database. Next, the server automatically generates a report based on the saved data. Here, a predetermined template is used to format the data and create a visually appealing report.

[1142] Next, the server analyzes the generated report and automatically generates anticipated questions and their answers. Here, by utilizing past question patterns and accumulated data, it is possible to create highly accurate anticipated questions and answers.

[1143] Furthermore, the server retrieves past verification results stored in the database and compares them to current results. This comparison visually shows what performance improvements or problems exist. These comparison results are reflected in a report, providing users with clear areas for improvement.

[1144] The final report generated based on the above process is notified to the user from the server and becomes accessible via a saved link. This allows users to quickly and efficiently create and review documents.

[1145] Specific example

[1146] For example, consider a scenario where a user inputs the durability test results for a product. The user uses a terminal to input "Durability test results for product A." The terminal checks the format of the input data and sends the verification results, "Durability: 95, Failure rate: 0.5%", to the server. The server stores this in a database and generates a report based on the stored data.

[1147] Next, the server analyzes the generated report and automatically generates questions and answers such as, "What were the results of this durability test?". Furthermore, the server retrieves past "durability test results for product A" and compares them with the current results. The server adds the comparison results, such as "The failure rate improved from 0.8% to 0.5%", to the report and notifies the user.

[1148] In this way, this system reduces the burden on users and supports efficient and accurate report creation.

[1149] The following describes the processing flow.

[1150] Step 1:

[1151] The user accesses the system's input screen and enters the verification results. The terminal automatically checks the format of the entered data and verifies that it is in the correct format.

[1152] Step 2:

[1153] The terminal sends data that has passed the format check to the server. The server temporarily stores the received data and prepares to write it to the database.

[1154] Step 3:

[1155] The server saves the verification results data to the database. If the save is successful, the server generates a save completion message and sends it to the terminal.

[1156] Step 4:

[1157] The server loads a report template based on the validation results stored in the database and embeds the validation results. This automatically generates the initial report.

[1158] Step 5:

[1159] The server analyzes the generated report and predicts anticipated question patterns. It then references a database of past questions to generate relevant questions and their answers.

[1160] Step 6:

[1161] Add the server-generated questions and answers to the report to complete the anticipated Q&A section. This completes the first report.

[1162] Step 7:

[1163] The server retrieves past verification results from the database and compares them with current results. If any new discoveries or areas for improvement are found as a result of the comparison, they are reflected in the report.

[1164] Step 8:

[1165] The server completes the final report and saves the report file. It generates a link to the saved report and notifies the user.

[1166] Step 9:

[1167] The user accesses the completed report using the provided link. The user reviews the report and takes any necessary actions or further feedback.

[1168] This processing flow allows users to quickly and efficiently generate and review verification results reports.

[1169] (Example 1)

[1170] 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".

[1171] Conventional verification result reporting systems often involved manual tasks such as data entry, report generation, and the creation of anticipated questions and answers, resulting in low work efficiency and a heavy burden on users. In particular, when dealing with large amounts of verification data, comparing with historical data and generating highly accurate anticipated questions and answers required considerable time and effort. Furthermore, there was a lack of effective means to notify users of the generated reports, making prompt responses difficult.

[1172] 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.

[1173] In this invention, the server includes means for storing verification results in a database, means for automatically generating a report using a template based on the stored verification results, means for analyzing the generated report and generating anticipated questions and answers using past question patterns, means for comparing past results with current verification results, and means for reflecting the comparison results in the report and notifying the user. As a result, the user can efficiently input verification results, receive automatically generated reports and anticipated questions and answers, and proceed with their work quickly and accurately.

[1174] A "terminal" is a device used by users to input verification results and has a function to check the format of the input data.

[1175] A "server" is a central computer system that stores received verification result data in a database, automatically generates reports based on the stored data, analyzes them, and sends notifications.

[1176] A "database" is a data storage system used by a server to store and manage verification result data.

[1177] A "template" refers to a predetermined format or style that a server uses to automatically generate reports.

[1178] "Anticipated Q&A" refers to a collection of answers created based on the generated report, providing users with anticipated questions and their corresponding answers.

[1179] A "generative AI model" is an artificial intelligence technology that uses past question patterns and validation data to automatically generate highly accurate anticipated questions and answers.

[1180] A "comparison method" is a processing function that allows a server to compare past verification results with current results to identify areas for performance improvement and problems.

[1181] "Notification methods" refer to mechanisms for informing users of generated reports and comparison results, including methods such as email and display on dashboards.

[1182] This invention relates to a system that allows users to efficiently input and manage verification results and automatically generate reports and anticipated questions and answers. The system consists of a server and terminals as its main components.

[1183] First, the user accesses a dedicated input screen. For example, by accessing a specific URL using a web browser, they can input verification results. The input screen provides multiple input fields, such as product name and test results.

[1184] The terminal has a function to check the format of data entered by the user. For example, it checks whether the durability value is within the range of 0 to 100 and whether the failure rate is provided in percentage format. If the data is not valid, it displays an error message and prompts the user to re-enter the data.

[1185] When correct data is entered, the terminal sends that data to the server. The data is sent in JSON format and reaches the server via an HTTP POST request. In this case, the sending endpoint is, for example, " / api / submit_test_result".

[1186] The server saves the received data to an internal database. For example, an SQL database is used, and an INSERT query is executed against the "test_results" table. Storing the data in the database makes it available for future data analysis and report generation.

[1187] The server automatically generates reports based on the stored data. Specifically, it uses a Python script and the Jinja2 template engine to generate reports in HTML format. The templates include a predefined format, which formats the data and results in a visually appealing report.

[1188] Once a report is generated, the server analyzes it and automatically generates anticipated questions and answers. This process uses a generation AI model (e.g., GPT-4) to create a highly accurate set of questions and answers by comparing them with past question patterns.

[1189] Furthermore, the server retrieves saved historical validation results and compares them to current results. This comparison clearly shows performance improvements and areas for improvement. A Python script is used to analyze the data and add the comparison results to the report.

[1190] Finally, the generated report is notified to the user from the server. Notification methods include sending a link to the user's email address or displaying a notification on the dashboard that a new report has been added. This allows users to quickly and efficiently create and review documents.

[1191] Specific example

[1192] For example, consider a scenario where a user inputs the results of a durability test for "Product A". The user accesses "http: / / example.com / report_input" from their browser and enters "Durability: 95, Failure Rate: 0.5%" into the input field. The terminal checks the format of this data, confirms that it is valid, and then sends it to the server.

[1193] The server saves this data to a database and generates a report based on the saved data. Then, it uses a generative AI model (e.g., GPT-4) to automatically generate questions such as "What were the results of this durability test?" and their answers. The server also compares the results with past test results and adds information to the report such as "The defect rate improved from 0.8% to 0.5%."

[1194] The generated report is notified to the user, who can access the detailed report via a specified link. This significantly improves the user's work efficiency.

[1195] Example of a prompt

[1196] For example, you can use the following prompt statements:

[1197] "Please enter the durability test results for Product A. Example: Durability: 95, Defect Rate: 0.5%"

[1198] This reduces the burden on users and supports efficient and accurate report creation.

[1199] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1200] Step 1:

[1201] The user accesses a dedicated input screen to enter the verification results. For example, they access "http: / / example.com / report_input" from a web browser and enter "Durability test results for product A," for example, "Durability: 95, Defect rate: 0.5%," into the input field. The input data is provided to the user and formatted on the input screen.

[1202] Step 2:

[1203] The terminal checks the format of the data entered by the user. For example, it verifies that the durability is within the range of 0 to 100 and that the failure rate is in percentage format. This check ensures data consistency and accuracy. Here, it distinguishes between valid and invalid data, and if invalid data is found, the terminal displays an error message to the user and prompts them to re-enter the data.

[1204] Step 3:

[1205] If the terminal receives valid data, it sends that data to the server. For example, it might send data to the " / api / submit_test_result" endpoint using an HTTP POST request. The data is sent in JSON format. The input data is sent to the server, which then receives it.

[1206] Step 4:

[1207] The server saves the received validation results data to a database. For example, it uses an INSERT query to save the data to the "test_results" table in an SQL database. The saved data is then used in subsequent processing. The saved data is stored in the database, which enables later analysis.

[1208] Step 5:

[1209] The server automatically generates reports based on the stored data. For example, it uses a Python script and the Jinja2 template engine to generate HTML reports. This template includes a predefined format, formatting the data and creating a highly readable report. For report generation, the input data is embedded in the template, and the output is generated as an HTML report.

[1210] Step 6:

[1211] The server analyzes the generated report and uses a generation AI model (e.g., GPT-4) to automatically generate anticipated questions and answers. For example, it generates questions and answers such as, "What were the results of this durability test?" By referring to past question patterns, it creates a highly accurate set of questions and answers. In this process, the text data from the report is input, the AI ​​model generates questions and answers, and the output is obtained as anticipated questions and answers.

[1212] Step 7:

[1213] The server retrieves stored historical validation results and compares them to current results. For example, it uses an SQL query to retrieve historical validation data from the "test_results" table and performs a comparison using Python. This comparison visually shows performance improvements and problems. Historical and current data are used as input, and the comparison results are obtained as output.

[1214] Step 8:

[1215] The server notifies the user of the final report, which includes the generated report, anticipated questions and answers, and comparison results. For example, it can send a notification email with a link to the user's email address, or display a notification on the dashboard that a new report has been added. This notification allows the user to quickly access the detailed report. The notification includes a link to the final report, and its output is provided to the user.

[1216] Therefore, this system can reduce the user's workload and support efficient and accurate report creation.

[1217] (Application Example 1)

[1218] 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".

[1219] Conventional verification result reporting systems have faced challenges such as requiring significant time and effort for data entry, storage, and report generation. Furthermore, manual comparison with historical data often led to decreased operational efficiency. Additionally, the lack of automation in the creation of anticipated questions and answers sometimes imposed additional burdens on users. A new system is needed to address these challenges and streamline operational processes in logistics centers and similar facilities.

[1220] 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.

[1221] In this invention, the server includes means for inputting verification results, means for saving the inputted verification results, means for automatically generating a report based on the saved verification results, means for generating anticipated questions and answers based on the generated report, means for comparing the saved past results with the current verification results, means for reflecting the comparison results in the report, means for automatically generating questions and answers using a generation AI model based on past and current verification data, and means for inputting verification results and checking reports using a smart device. As a result, users can efficiently input verification results, generate reports, and compare them with past data, significantly reducing their workload.

[1222] "Verification results" refer to the results of tests and investigations conducted to evaluate the performance and quality of a particular product or service.

[1223] "Means of input" refers to the interface or device that allows users to register verification results in the system.

[1224] "Means of storage" refers to functions or devices for accumulating the entered verification results in a database or storage device.

[1225] "Methods for automatically generating reports" refer to algorithms or programs that automatically create reports based on saved verification results and predetermined templates.

[1226] "Means for generating anticipated questions and answers" refers to engines or software that automatically generate anticipated questions and their answers based on the generated report.

[1227] "Means of comparison" refers to a function that compares past and current verification results and analyzes the differences and areas for improvement.

[1228] "Means of reflection" refers to functions that add comparison results to reports and provide them to users in a visually easy-to-understand format.

[1229] A "generative AI model" refers to an artificial intelligence model that learns from large datasets and is used for natural language processing.

[1230] A "smart device" refers to a portable device, such as a smartphone or tablet, that can connect to the internet and run applications.

[1231] This invention relates to a system for automating the creation of verification result reports at logistics centers. This system significantly improves operational efficiency by efficiently inputting verification results, automatically generating reports, creating anticipated questions and answers, and comparing them with past results.

[1232] System Configuration

[1233] 1. Hardware

[1234] User terminal: A device such as a smartphone, tablet, or PC. The user uses this device to input verification results and review reports.

[1235] Servers: Cloud servers or dedicated servers are used. They are used for data storage, analysis, and execution of generational AI models.

[1236] Specific examples: AWS, Google Cloud Platform

[1237] Database: Used to store verification results and generated reports.

[1238] Examples: MySQL, PostgreSQL

[1239] 2. Software

[1240] Data entry form: A web or mobile application for users to enter verification results.

[1241] Frameworks: React Native, Flutter

[1242] Report generation program: A program that automatically generates reports based on verification result data.

[1243] Data analysis program: A program that compares saved past verification results with current verification results and analyzes the results.

[1244] Generative AI model: An artificial intelligence model used for natural language processing.

[1245] Model: GPT-4, BERT

[1246] Program processing

[1247] Input of verification results

[1248] Users access a dedicated data entry form using their smartphones or tablets. They enter necessary data such as "product ID," "inspection results," and "inventory quantity," and then press the submit button. The smart device checks whether the entered data is correct and sends it to the server.

[1249] Data storage

[1250] The server saves the received verification results data to a database. The data is stored in an appropriate format and used for subsequent analysis and report generation.

[1251] Report generation

[1252] The server automatically generates reports based on the stored data. It uses predefined template files to format the data and create visually appealing reports.

[1253] Generation of anticipated questions and answers

[1254] Based on the generated report, the server automatically generates anticipated questions and their answers. Using a generation AI model, it creates question-and-answer pairs, referencing past question patterns.

[1255] Comparison with past data

[1256] The server compares the current results with previously saved verification results. This comparison visually shows areas for improvement and problems. This information is reflected in reports and notified to the user.

[1257] Specific example

[1258] For example, when a user inputs the durability test results for a product, the user uses a terminal to input "Durability test results for product A." The terminal checks the format of the input data and sends the verification result "Durability: 95, Defect rate: 0.5%" to the server. The server saves this to a database and generates a report based on the saved data. Next, the server analyzes the generated report and automatically generates questions and answers such as "What are the results of this durability test?". Furthermore, the server retrieves past "Durability test results for product A" and compares them with the current results. The server adds the comparison result, such as "The past defect rate improved from 0.8% to 0.5%", to the report and notifies the user.

[1259] Example of a prompt

[1260] Product inspection results:

[1261] Product ID: A123

[1262] Test results: Good

[1263] Quantity in stock: 200

[1264] Please compare the current test data with past test data and generate a report.

[1265] Please also enter any anticipated questions and their answers.

[1266] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1267] Step 1:

[1268] Users input verification results using smart devices (smartphones or tablets). Users access a data entry form and enter necessary information such as "Product ID," "Inspection Result," and "Inventory Quantity." The input data is format-checked on the device, and if there are no errors, it is sent to the server. For example, input data might include "Product ID: A123," "Inspection Result: Good," and "Inventory Quantity: 200."

[1269] Step 2:

[1270] The verification result data sent from the terminal is received by the server. The server saves this verification result data to a database. Specifically, it executes an SQL query to insert the verification result data into the appropriate table in the database. The input is the verification result data (e.g., "Product ID: A123", "Inspection Result: Good", "Inventory Quantity: 200"), and the output is the data saved in the database.

[1271] Step 3:

[1272] The server automatically generates a report based on the stored validation result data. In this process, it formats the validation result data using a predetermined template file. Specifically, it uses a template engine to convert the validation results into an easily readable format. The input is the validation result data retrieved from the database, and the output is the generated report file.

[1273] Step 4:

[1274] Based on the generated report, the server automatically generates anticipated questions and their answers. Here, a generative AI model (e.g., GPT-4) is used for natural language processing. Specifically, the report data is input to the generative AI model, which then generates pairs of anticipated questions and answers. The input is the report data, and the output is the generated question and answer pairs.

[1275] Step 5:

[1276] The server compares the current verification result with previously stored verification results. Specifically, it retrieves past data from the database and uses an algorithm to analyze the differences between it and the current result. The inputs are the current verification result data and the past verification result data, and the output is the comparison result.

[1277] Step 6:

[1278] The server incorporates the comparison results into the generated report. Specifically, it adds the comparison results to the report template and generates a consistent report overall. The inputs are the comparison results and the generated report, and the output is the final report.

[1279] Step 7:

[1280] The server notifies the user of the final report and provides a link that can be accessed from a smart device. Specifically, it sends an email or push notification to the user, including the link to access the report. The input is the URL of the final report, and the output is the notified user.

[1281] 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.

[1282] This invention relates to a system that combines an emotion engine with a verification result report generation system to improve operational efficiency, enabling the system to recognize the user's emotional state and generate reports, anticipated questions and answers, and compare results with past results based on that state. This system provides an optimal report tailored to the user's emotions by combining emotion recognition technology with the process of inputting and saving verification results, automatically generating reports, creating anticipated questions and answers, and comparing results with past results.

[1283] The main components of this system are as follows:

[1284] First, the user accesses a dedicated input screen to enter verification results. The terminal provides this input screen and verifies the format of the data entered by the user. If the input data is correct, the terminal sends the data to the server.

[1285] The server saves the received verification data to a database. Next, the server automatically generates a report based on the saved data. Here, a predetermined template is used to format the data and create a visually appealing report.

[1286] Next, the server analyzes the generated report and automatically generates anticipated questions and their answers. Here, by utilizing past question patterns and accumulated data, it is possible to create highly accurate anticipated questions and answers.

[1287] Furthermore, the server retrieves past verification results stored in the database and compares them to current results. This comparison visually shows what performance improvements or problems exist. These comparison results are reflected in a report, providing users with clear areas for improvement.

[1288] Embedding an emotion engine

[1289] This system incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's input data and behavior during operation to recognize their current emotional state. Specifically, it identifies emotions through factors such as key input speed, mouse movements, and facial recognition (when using a webcam).

[1290] The content and wording of the generated reports are adjusted based on the user's emotional state recognized by the emotion engine. For example, if the user is experiencing stress, the report content is made more concise, and negative results are expressed in softer language. This reduces the burden on the user and enables the generation of more adaptable reports.

[1291] Specific example

[1292] For example, consider a scenario where a user inputs the durability test results for a product. The user uses a terminal to input "Durability test results for product A." The terminal checks the format of the input data and sends the verification results, "Durability: 95, Failure rate: 0.5%", to the server. The server stores this in a database and generates a report based on the stored data.

[1293] Next, the server analyzes the generated report and automatically generates questions and answers such as, "What were the results of this durability test?". Furthermore, the server retrieves past "durability test results for product A" and compares them with the current results. The server adds the comparison results, such as "The failure rate improved from 0.8% to 0.5%", to the report and notifies the user.

[1294] In addition, during this process, the emotion engine analyzes the user's emotional state at the time of input, and if the user is experiencing stress or fatigue, it adjusts the report content to be more concise. In this way, it is possible to provide an optimal report tailored to the user's psychological state.

[1295] This system allows users to create and review reports efficiently and accurately, and the inclusion of an emotion engine further reduces the psychological burden on users.

[1296] The following describes the processing flow.

[1297] Step 1:

[1298] The user accesses the system's input screen and enters the verification results. The terminal automatically checks the format of the entered data to ensure it is correct. The emotion engine collects the user's keystroke speed, mouse movements, and, if possible, facial expression information during input.

[1299] Step 2:

[1300] The device sends data that has passed the format check, along with user sentiment data collected by the sentiment engine, to the server. The server temporarily stores the received data and prepares it for writing to the database.

[1301] Step 3:

[1302] The server saves the verification results data to the database. If the save is successful, the server generates a save completion message and sends it to the terminal. Sentiment data is also saved to the database in the same way.

[1303] Step 4:

[1304] The server loads a report template based on the validation results stored in the database and embeds the results. Here, it adjusts the tone and expression of the template, taking into account the user's emotional data collected by the emotion engine. For example, if the user is stressed, the results will be made concise and softer.

[1305] Step 5:

[1306] The server analyzes the generated report and predicts anticipated question patterns. It then references a database of past questions to generate relevant questions and their answers. The generated questions and answers are then refined using sentiment engine data to ensure they are expressed in a way that takes the user's psychological state into account.

[1307] Step 6:

[1308] The server-generated questions and answers are added to the report, completing the anticipated Q&A section. Based on the analysis results from the sentiment engine, the difficulty of the questions and the level of detail in the answers are also adjusted.

[1309] Step 7:

[1310] The server retrieves past test results from the database and compares them to current results. This comparison visually shows what performance improvements and problems exist. The comparison results are reflected in the report, taking into account the sentiment engine data.

[1311] Step 8:

[1312] The server completes the final report and saves the report file. It generates a link to the saved report and notifies the user. The notification message is also adjusted to suit the user's emotional state.

[1313] Step 9:

[1314] The user accesses the completed report using the provided link. The user reviews the report and takes any necessary actions or further feedback.

[1315] This processing flow allows users to quickly and efficiently generate and review verification results, and the integration of an emotion engine further reduces the user's psychological burden.

[1316] (Example 2)

[1317] 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".

[1318] In modern business, there is a demand for rapid and accurate reporting of verification results. However, conventional report generation systems do not take into account the user's emotional state, making them burdensome for users who are stressed or fatigued. Furthermore, the generated reports are formulaic and lack responses to the specific problems and questions that users have. It is necessary to solve these problems and provide a more effective and user-friendly report generation system.

[1319] 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.

[1320] In this invention, the server includes means for inputting verification results, means for saving the inputted verification results, means for automatically generating a report based on the saved verification results, means for generating anticipated questions and answers based on the generated report, means for comparing the saved past results with the current verification results, means for reflecting the comparison results in the report, means for analyzing the user's emotional state, and means for adjusting the content of the report based on the analyzed emotional state. This enables flexible report generation in accordance with the user's emotional state, making it possible to provide highly accurate and specific information while reducing the user's psychological burden.

[1321] "Verification results" refer to numerical data and qualitative evaluation results obtained through tests and experiments.

[1322] "Means of input" refers to an interface or device for the user to provide verification results to the system.

[1323] "Means of storage" refers to a mechanism or device for accumulating the input verification results in a storage device such as a database.

[1324] "Means for automatically generating reports" refers to a mechanism or device that automatically creates reports using a set template or algorithm based on saved verification results.

[1325] "Means for generating anticipated questions and answers" refers to a mechanism or device for automatically creating predictable questions and their answers based on a generated report.

[1326] "Means for comparing past results with current verification results" refers to a mechanism or device for comparing stored past verification data with current data and evaluating the differences or changes between them.

[1327] "Means for reflecting comparison results in the report" refers to a mechanism or device for adding the results obtained from the aforementioned comparison to the content of the report and presenting them in an easily understandable manner.

[1328] "Means for analyzing emotional state" refers to a mechanism or device for determining a user's emotional state from user input, behavior, or facial expressions captured via a webcam.

[1329] "Means for adjusting the report content based on the analyzed emotional state" refers to a mechanism or device for modifying the structure and expression of a report, taking into account the user's emotional state, and providing the report in a format suitable for the user.

[1330] This invention relates to a verification result report generation system for improving work efficiency according to the user's emotional state. This system allows the user to input verification results, automatically generates a report, creates anticipated questions and answers, compares them with past data, and further recognizes the user's emotional state via an emotion engine, adjusting the report based on that recognition.

[1331] Hardware and software used

[1332] (Hardware)

[1333] Terminal (user's PC or smartphone): Providing an input screen

[1334] Server: Data storage, report generation, sentiment recognition processing.

[1335] Webcam (optional): Facial recognition

[1336] (software)

[1337] Input form application: An interface for users to enter validation results.

[1338] Emotion engine (e.g., EmotionAPI): Recognizing user emotions.

[1339] Database (MySQL, PostgreSQL, etc.): Storage of validation result data

[1340] Report generation software (LaTeX, JasperReports, etc.): Report creation

[1341] Data analysis tools (SciPy, Pandas, etc.): Analysis and comparison of validation results

[1342] System operation

[1343] 1. The user logs into the system and accesses a screen for entering verification results. Here, the user enters specific verification result data.

[1344] For example, you would enter data such as "Durability test results for product A," "Durability: 95," and "Defect rate: 0.5%."

[1345] 2. The terminal checks the format of the input data and verifies that it is in the correct format. For example, it checks whether the durability value is 100 or less and the failure rate is 1% or less.

[1346] 3. The terminal sends properly formatted data to the server.

[1347] 4. The server saves the received verification result data to the database. Additional information such as the type of verification result, date and time, and the verifier's ID are also saved at this time.

[1348] 5. The server automatically generates reports using predefined templates based on the stored data. For example, it can create easy-to-read reports using LaTeX or JasperReports.

[1349] 6. The server analyzes the generated report and automatically generates frequently asked questions (FAQs) and their answers. By referring to past question patterns and existing data, it creates highly accurate Q&A.

[1350] 7. The server retrieves past verification results and compares them to current results. Graphs and tables are created to visually represent this comparison and reflected in the report. For example, a statement such as "Past defect rate improved from 0.8% to 0.5%" might be added.

[1351] 8. The emotion engine recognizes the user's emotional state through user actions and webcam footage. For example, it uses key input speed, mouse movements, and facial expression analysis to determine the user's stress level.

[1352] 9. The server adjusts the content and wording of the report based on the recognized emotional state of the user. Specifically, if the user is experiencing stress, the report content will be made more concise.

[1353] 10. The server provides the user with a finalized report. The user reviews this report and decides on their next action.

[1354] Examples of prompt statements

[1355] For example, when prompting a generative AI model, you would use a prompt statement like this:

[1356] "Please prepare a report based on the latest durability test results for Product A. Include past test results and note any improvements made. If users have reported experiencing fatigue, please summarize this concisely in the report."

[1357] This system allows users to create and review reports efficiently and accurately, and the inclusion of an emotion engine further reduces the psychological burden on users.

[1358] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1359] Processing steps

[1360] Step 1:

[1361] The user logs into the system and accesses a screen to enter verification results. Specifically, this involves the user logging into a web application using a browser and accessing an input form.

[1362] Input: The user enters the verification result data (e.g., "Product A durability test results: Durability: 95, Defect rate: 0.5%").

[1363] Output: The input data is sent to the terminal.

[1364] Step 2:

[1365] The terminal checks the format of the input data and verifies that it is in the correct format. Here, the input data is validated based on predefined rules.

[1366] Input: Verification result data submitted by the user.

[1367] Data processing / calculation: Verify that the format of the verification results is appropriate (e.g., whether the numerical value is 100 or less, or whether the defect rate is 1% or less).

[1368] Output: Correct data is sent to the next step, and incorrect data is returned to the user as an error message.

[1369] Step 3:

[1370] The terminal sends data that has passed the format check to the server.

[1371] Input: Verification result data that has been determined to be in the correct format.

[1372] Output: Validation result data sent to the server.

[1373] Step 4:

[1374] The server saves the received validation result data to a database. At this time, metadata such as the type of validation result, date and time, and the verifier's ID are also saved.

[1375] Input: Verification result data sent from the terminal.

[1376] Data processing / data calculation: Inserting data into the appropriate table in the database (e.g., executing an SQL INSERT statement).

[1377] Output: A confirmation message indicating that saving was successful.

[1378] Step 5:

[1379] The server automatically generates reports using predefined templates based on the stored data. This process utilizes tools such as LaTeX and JasperReports.

[1380] Input: Validation result data stored in the database.

[1381] Data processing / data calculation: Generate visually easy-to-understand reports by embedding data into templates (e.g., embedding data into LaTeX templates).

[1382] Output: The generated report file.

[1383] Step 6:

[1384] The server analyzes the generated report and automatically generates frequently asked questions (FAQs) and their answers. These are created by referencing past question patterns and existing data.

[1385] Input: Generated report.

[1386] Data processing / data computation: Generate FAQs using natural language processing (e.g., applying predefined rules or machine learning models).

[1387] Output: A set of automatically generated questions and answers.

[1388] Step 7:

[1389] The server retrieves past validation results and compares them with current results. This comparison is performed using data analysis tools (such as SciPy or Pandas).

[1390] Input: Current validation result data and past validation result data.

[1391] Data processing / data calculations: statistical analysis and graph creation (e.g., manipulating dataframes using Pandas and creating graphs using Matplotlib).

[1392] Output: Comparison results are output in text and graph formats and added to the report.

[1393] Step 8:

[1394] The emotion engine recognizes the user's emotional state through user actions and webcam footage.

[1395] Input: User operation data (key presses and mouse movements) and webcam footage.

[1396] Data processing / data calculation: Analysis using emotion recognition algorithms (e.g., using EmotionAPI).

[1397] Output: Analysis results (user's emotional state).

[1398] Step 9:

[1399] The server adjusts the content and wording of the report based on the recognized emotional state of the user.

[1400] Input: Emotional state data obtained from the emotion engine.

[1401] Data processing / data calculation: Adjusting the wording and format of reports (e.g., applying rewriting algorithms).

[1402] Output: Adjusted report.

[1403] Step 10:

[1404] The server then provides the user with a finalized report.

[1405] Input: Adjusted report.

[1406] Output: The final report provided to the user.

[1407] This allows the system to provide accurate and comprehensive verification reports while taking into account the user's emotional state.

[1408] (Application Example 2)

[1409] 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".

[1410] Conventional verification result reporting systems often failed to provide appropriate responses to users' emotional states, leading to increased stress and fatigue. Furthermore, the generated reports were sometimes redundant or complex, hindering user comprehension. In particular, in factory verification work, there is a need for both increased efficiency and reduced psychological burden on users.

[1411] 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. In this invention, the server includes means for inputting verification results, means for saving the inputted verification results, means for automatically generating a report based on the saved verification results, means for generating anticipated questions and answers based on the generated report, means for comparing the saved past results with the current verification results, means for reflecting the comparison results in the report, and means for recognizing the emotional state using emotion recognition technology and adjusting the report content. This makes it possible to adjust the report appropriately according to the user's emotional state, improve the efficiency of the verification work, and reduce the psychological burden.

[1412] "Means for inputting verification results" refers to an interface device for inputting data obtained through inspection work into the system.

[1413] "Means for storing the input verification results" refers to a database or storage device for recording and securely storing the input inspection result data.

[1414] "Means for automatically generating a report based on the saved verification results" refers to an algorithm or software that automatically creates a report using a predetermined template based on the saved data.

[1415] "Means for generating anticipated questions and answers based on the generated report" refers to a program that analyzes the generated report and prepares simulated answers to future questions.

[1416] "Means for comparing the stored past results with current verification results" refers to an analytical tool for comparing previously stored data with current data to identify changes in performance and areas for improvement.

[1417] "Means for reflecting the comparison results in the report" refers to a program or software that integrates the comparison results into the report and presents them in a visually easy-to-understand format.

[1418] "Means for recognizing emotional states and adjusting report content using emotion recognition technology" refers to an emotion engine and its control program for analyzing the user's emotional state and optimizing the content and expression of reports generated based on that analysis.

[1419] System Overview

[1420] This invention provides a system for efficiently managing verification results and providing reports tailored to the user's emotional state. By incorporating emotion recognition technology, this system generates highly accurate verification result reports while reducing the user's psychological burden.

[1421] Hardware and software to be used

[1422] Server: A server for high-performance computing, running software such as databases, emotion engines, report generation engines, comparison tools, and anticipated question and answer generation engines.

[1423] Terminal: A terminal device that provides an interface for users to input verification results, and is equipped with a camera, microphone, and sensors necessary for emotion recognition.

[1424] Database: A database used to store verification results and historical data.

[1425] Emotion recognition engine: Software used to analyze a user's emotional state.

[1426] Report generation engine: Software that generates reports based on templates.

[1427] Comparison tool: Software for comparing and analyzing historical and current data.

[1428] Anticipated Q&A Generation Engine: Software that generates anticipated questions and answers based on the report content.

[1429] Implementation method

[1430] 1. Input of verification results and emotion recognition:

[1431] The user inputs the verification results through the device. At this time, the emotion recognition engine built into the device analyzes the user's emotional state. This determines whether the user is experiencing stress or fatigue.

[1432] 2. Data storage:

[1433] The entered validation results are saved to the database by the server.

[1434] 3. Automatic report generation:

[1435] The server automatically generates reports based on the saved validation results. These reports are efficiently created using template files.

[1436] 4. Generating anticipated questions and answers:

[1437] The generated report is analyzed, and anticipated questions and answers are created using past question patterns. This prepares us for future questions.

[1438] 5. Comparative analysis of data:

[1439] The server retrieves past validation results stored in the database and compares them to the current results. These comparison results are reflected in the report.

[1440] 6. Adjusting reports based on emotions:

[1441] The content and wording of the generated report are adjusted based on the user's emotional state recognized by the emotion recognition engine. For example, if the user is feeling stressed, the report content will be summarized concisely.

[1442] Specific example

[1443] As a concrete example, consider the case of using a factory robot. The factory robot inputs "quality inspection data for product X," analyzes the operator's emotional state using an emotion engine, and generates a report and anticipated questions and answers. It compares this with past inspection results and adjusts the report according to the operator's emotions.

[1444] Example of a prompt

[1445] prompt:

[1446] A factory robot inputs "product X quality inspection data," analyzes the operator's emotional state using an emotion engine, and generates a report and anticipated Q&A. It then compares this with past inspection results and adjusts the report according to the operator's emotions.

[1447] In this way, the present invention enables the provision of verification result reports tailored to the user's emotional state, thereby improving work efficiency within the factory.

[1448] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1449] Processing flow

[1450] Step 1: Input of verification results and emotion recognition

[1451] Input: User-verified data (e.g., quality inspection data for product X)

[1452] Processing: The device receives input data, and at that time, the emotion recognition engine collects data on the user's emotional state. Emotion analysis is performed using the camera, microphone, touch input speed, etc.

[1453] Output: Set of validation data and sentiment data

[1454] Step 2: Saving the verification results

[1455] Input: Set of validation data and sentiment data

[1456] Processing: The server securely stores the received data in the database. The storage process includes verifying the data format and performing error checks.

[1457] Output: Verification data and sentiment data stored in the database

[1458] Step 3: Automatic report generation

[1459] Input: Validation data stored in the database

[1460] Processing: The server uses a report generation engine to automatically generate reports using template files based on the saved verification data.

[1461] Output: Automated report

[1462] Step 4: Generating anticipated questions and answers

[1463] Input: Automated report

[1464] Processing: The server analyzes the generated report and generates questions and answers using a question and answer generation engine, referencing past question patterns.

[1465] Output: Set of anticipated questions and answers (pairs of questions and answers)

[1466] Step 5: Comparison with historical data

[1467] Input: Current validation result data and past validation result data

[1468] Processing: The server uses a comparison tool to analyze and compare current and past test results to identify performance changes and problems.

[1469] Output: Comparison results data (e.g., graphs or numerical data showing performance improvements)

[1470] Step 6: Adjusting the report based on emotions

[1471] Input: Automated reports, sentiment data

[1472] Processing: Based on the emotion data analyzed by the emotion recognition engine, the server uses the report generation engine to appropriately adjust the content and expression of the report. For example, if the user is experiencing stress, the report content will be summarized concisely.

[1473] Output: Optimized report

[1474] Description of each step

[1475] Step 1: Input of verification results and emotion recognition

[1476] The user inputs verification data through the device. The device receives the input data according to the format, and simultaneously, the emotion recognition engine uses the camera, microphone, and touch input speed to analyze the user's emotional state and collect emotion data. This generates a set of verification data and emotion data.

[1477] Step 2: Saving the verification results

[1478] The server saves the set of verification and sentiment data received from the terminal to the database. This saving process includes checking the data format and performing error checks. After saving, the database records the securely stored verification and sentiment data.

[1479] Step 3: Automatic report generation

[1480] The server automatically generates reports by applying template files using a report generation engine based on validation data stored in the database. This process creates visually appealing and easy-to-understand reports.

[1481] Step 4: Generating anticipated questions and answers

[1482] The server analyzes the generated report and automatically generates questions and answers using a question-and-answer generation engine based on past question patterns. This creates question-and-answer pairs, preparing the system for future questions.

[1483] Step 5: Comparison with historical data

[1484] The server retrieves current verification results data and historical verification results data stored in the database, and analyzes and compares them using a comparison tool. This comparison identifies performance changes and problems. The comparison results data is output in visual graphs and numerical formats.

[1485] Step 6: Adjusting the report based on emotions

[1486] The server uses the emotion recognition engine to analyze emotional data, and the report generation engine then adjusts the content and presentation of the report. For example, if the user is experiencing stress, the report is made more concise and easier to understand. This results in an optimized report being output.

[1487] The above describes the specific processing steps and content of the system program that implements the application example.

[1488] 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.

[1489] 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.

[1490] 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 robot 414.

[1491] 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.

[1492] 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.

[1493] 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.

[1494] 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.

[1495] 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.

[1496] 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."

[1497] 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.

[1498] 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.

[1499] 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.

[1500] 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.

[1501] 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.

[1502] 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.

[1503] 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.

[1504] 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.

[1505] 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.

[1506] 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.

[1507] 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.

[1508] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1509] The following is further disclosed regarding the embodiments described above.

[1510] (Claim 1)

[1511] A means of inputting verification results,

[1512] Means for saving the input verification results,

[1513] A means for automatically generating a report based on the aforementioned saved verification results,

[1514] A means for generating anticipated questions and answers based on the aforementioned generated report,

[1515] A means for comparing the previously saved past results with the current verification results,

[1516] Means for reflecting the aforementioned comparison results in the report

[1517] A system that includes this.

[1518] (Claim 2)

[1519] The system according to claim 1, wherein the means for generating the anticipated questions and answers generates the anticipated questions and answers using past question patterns.

[1520] (Claim 3)

[1521] The system according to claim 1, wherein the means for automatically generating the aforementioned report is to generate the report using a template file.

[1522] (Claim 4)

[1523] The system according to claim 1, wherein the means for reflecting the comparison results in the report is to compare the main parameters of past verification results and current verification results and add the results to the report.

[1524] "Example 1"

[1525] (Claim 1)

[1526] A terminal for entering verification results,

[1527] A means for checking the format of the input verification result and sending the appropriate data to the server,

[1528] The server provides means for saving the input verification results to a database,

[1529] A means by which the server automatically generates a report using a template based on the saved verification results,

[1530] The server analyzes the generated report and generates anticipated questions and answers using past question patterns,

[1531] The server provides means for comparing the previously saved past results with the current verification results,

[1532] A means of reflecting the aforementioned comparison results in a report and notifying the user.

[1533] A system that includes this.

[1534] (Claim 2)

[1535] The system according to claim 1, wherein the means for generating the anticipated questions and answers uses a generation AI model to generate the anticipated questions and answers.

[1536] (Claim 3)

[1537] The system according to claim 1, wherein the means for notifying the user of the report displays that a new report has been added to the user's dashboard.

[1538] "Application Example 1"

[1539] (Claim 1)

[1540] A means of inputting verification results,

[1541] Means for saving the input verification results,

[1542] A means for automatically generating a report based on the aforementioned saved verification results,

[1543] A means for generating anticipated questions and answers based on the aforementioned generated report,

[1544] A means for comparing the previously saved past results with the current verification results,

[1545] A means of reflecting the aforementioned comparison results in the report,

[1546] A method for automatically generating questions and answers using a generative AI model based on past and current validation data,

[1547] A means of inputting verification results and checking reports using a smart device,

[1548] A system that includes this.

[1549] (Claim 2)

[1550] The system according to claim 1, wherein the means for generating the anticipated questions and answers generates the anticipated questions and answers using past question patterns.

[1551] (Claim 3)

[1552] The system according to claim 1, wherein the means for automatically generating the aforementioned report is to generate the report using a template file.

[1553] "Example 2 of combining an emotion engine"

[1554] (Claim 1)

[1555] A means of inputting verification results,

[1556] Means for saving the input verification results,

[1557] A means for automatically generating a report based on the aforementioned saved verification results,

[1558] A means for generating anticipated questions and answers based on the aforementioned generated report,

[1559] A means for comparing the previously saved past results with the current verification results,

[1560] A means of reflecting the aforementioned comparison results in the report,

[1561] A means of analyzing the user's emotional state,

[1562] Means for adjusting the content of the report based on the analyzed emotional state,

[1563] A system that includes this.

[1564] (Claim 2)

[1565] The system according to claim 1, wherein the means for generating the anticipated questions and answers generates the anticipated questions and answers using past question patterns.

[1566] (Claim 3)

[1567] The system according to claim 1, wherein the means for automatically generating the aforementioned report is to generate the report using a template file.

[1568] "Application example 2 when combining with an emotional engine"

[1569] (Claim 1)

[1570] A means of inputting verification results,

[1571] Means for saving the input verification results,

[1572] A means for automatically generating a report based on the aforementioned saved verification results,

[1573] A means for generating anticipated questions and answers based on the aforementioned generated report,

[1574] A means for comparing the previously saved past results with the current verification results,

[1575] A means of reflecting the aforementioned comparison results in the report,

[1576] A means of recognizing emotional states using emotion recognition technology and adjusting the report content,

[1577] A system that includes this.

[1578] (Claim 2)

[1579] The system according to claim 1, wherein the means for generating the anticipated questions and answers generates the anticipated questions and answers using past question patterns.

[1580] (Claim 3)

[1581] The system according to claim 1, wherein the means for automatically generating the aforementioned report is to generate the report using a template file. [Explanation of symbols]

[1582] 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 inputting verification results, Means for saving the input verification results, A means for automatically generating a report based on the aforementioned saved verification results, A means for generating anticipated questions and answers based on the aforementioned generated report, A means for comparing the previously saved past results with the current verification results, Means for reflecting the aforementioned comparison results in the report A system that includes this.

2. The system according to claim 1, wherein the means for generating the anticipated questions and answers generates the anticipated questions and answers using past question patterns.

3. The system according to claim 1, wherein the means for automatically generating the aforementioned report is to generate the report using a template file.

4. The system according to claim 1, wherein the means for reflecting the comparison results in the report is to compare the main parameters of past verification results and current verification results and add the results to the report.

Images