system

Abstract

To provide a system.SOLUTION: A system comprises: means for digitizing, based on a QC flow diagram, quality management information including at least one of an inspection item, a point of view, a point of caution, a posture to be present, an assumed quality risk, a preventive measure against the risk, and a corrective measure for each section; means for creating a tool capable of announcing the quality management information with the usage of a generated AI model based on the digitized quality management information; and means for providing the tool.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] In many cases, quality control efforts in small and medium-sized enterprises are not adequately implemented due to a lack of human resources and specialized knowledge. In addition, there is a huge amount of information on quality control audit items, points to focus on, points to note, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc., and it is difficult to properly manage and utilize this information. [Means for solving the problem]

[0005] Based on the basic QC flow chart related to quality control systems and product manufacturing, the audit items and points of focus for each section, points to note, ideal situations, anticipated quality risks, preventive and corrective measures against risks, etc. are digitized, and based on this information, notifications can be made using chat generation AI.

[0006] We will create a tool that will be marketed as a digital transformation tool for quality control, primarily for small and medium-sized enterprises, to improve the efficiency of quality control and quality. [Brief description of the drawings]

[0007] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14]FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. [Figure 19] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system according to the embodiment 2 of the second embodiment in the case where an emotion engine is combined. [Figure 20] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when combined with an emotion engine. [Figure 21] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the embodiment 3 of the form example 3 in the case where an emotion engine is combined. [Figure 22] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] 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.

[0009] First, the terms used in the following description will be explained.

[0010] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0011] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0012] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0013] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0014] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0015] [First embodiment]

[0016] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (e.g., voice 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 voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0026] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out 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 the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0027] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0028] "Example 1"

[0029] As one embodiment of the present invention, a means is provided for converting the audit items and points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures against risks, etc., for each section into digital data based on a basic QC flow diagram related to a quality control system and product manufacturing. This digitalization is performed taking into consideration, for example, the work procedures and quality check items for each section, the skill levels of workers, etc.

[0030] "Example 2"

[0031] Furthermore, we will create a tool that can make announcements using chat generation AI based on the digitized information.

[0032] This tool has a function to automatically suggest points to note and areas for improvement at each step of quality control, for example. It also has a function to suggest appropriate audit items, points to focus on, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks in response to questions from users.

[0033] "Example 3"

[0034] Furthermore, the created tools will be provided as a means to market them as a digitalization menu for quality control, primarily for small and medium-sized enterprises. For example, this market development could be provided as a cloud service for small and medium-sized enterprises, and companies could use this service to streamline their own quality control and improve quality.

[0035] The process flow of each embodiment will be described below.

[0036] "Example 1"

[0037] Step 1: Refer to the quality control system and basic QC flow diagram related to product manufacturing, and extract the audit items and points of focus for each section, points to note, the ideal state, anticipated quality risks, and preventive and corrective measures for risks.

[0038] Step 2: The extracted information is registered in a database and digitized. This digitization is carried out taking into consideration, for example, the work procedures and quality check items of each section, the skill levels of the workers, etc.

[0039] "Example 2"

[0040] Step 1: Create a tool that can make announcements using chat generation AI based on the digitized information.

[0041] This tool will have the function of automatically suggesting points to note and areas for improvement at each step of quality control.

[0042] Step 2: Add a function that, in response to user questions, presents appropriate audit items, points to focus on, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks.

[0043] "Example 3"

[0044] Step 1: The created tool will be marketed as a digital transformation menu for quality control, primarily to small and medium-sized enterprises. This market deployment will be provided, for example, as a cloud service for small and medium-sized enterprises. Step 2: By using this service, companies can streamline their own quality control and improve quality.

[0045] Example 1

[0046] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal".

[0047] In quality control systems and product manufacturing, there is a demand for a system that can efficiently digitize the audit items, points of interest, cautions, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. for each section, and allow users to easily confirm, correct, and add them. In addition, there is a challenge in providing a tool that uses a generative AI model based on this information to make appropriate announcements in response to user questions.

[0048] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0049] In this invention, the server includes a means for digitizing the audit items, points of interest, cautions, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. for each section based on a basic QC flow chart related to the quality control system and product manufacturing, a means for accessing a database to collect necessary information, and a means for analyzing the collected data and digitizing it while taking into consideration the work procedures, quality check items, and skill levels of workers for each section. This makes it possible to efficiently digitize the audit items, points of interest, cautions, etc. for each section, and for users to easily confirm, correct, and add them.

[0050] A "quality management system" refers to a set of processes and tools for controlling and maintaining the quality of products and services.

[0051] A "QC flow diagram" is a diagram that visually represents each process and procedure in quality control.

[0052] "Audit items" refer to specific items that should be checked or evaluated in quality control or product manufacturing.

[0053] "Points of focus" refers to points that should be given particular attention when conducting an audit or evaluation.

[0054] "Points to note" refers to matters that require special attention when performing work or audits.

[0055] "The ideal state" refers to the ideal or target state in quality control and product manufacturing.

[0056] "Quality risk" refers to factors or circumstances that may affect the quality of a product or service.

[0057] "Preventive measures" refer to measures taken to prevent quality risks.

[0058] "Corrective action" refers to measures taken to resolve a quality problem that has occurred and to prevent its recurrence.

[0059] "Digitization" refers to the process of organizing and storing information in digital form.

[0060] A "generative AI model" refers to a model that uses artificial intelligence technology to generate and analyze data.

[0061] A "prompt" refers to an instruction or question that is input to a generative AI model.

[0062] "Digital transformation" refers to the innovation of business processes and business models through the use of digital technology.

[0063] This invention is a system that digitizes the audit items, points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. for each section based on the basic QC flow chart related to quality control systems and product manufacturing. This system works in cooperation with the server, terminals, and users.

[0064] The server accesses the quality control system database and collects information such as the audit items, points of interest, and points of caution for each section based on the QC flow diagram. Specifically, the server uses a database management system (DBMS) such as MySQL (registered trademark) or PostgreSQL to extract the necessary information with SQL queries.

[0065] Next, the server analyzes the collected data. To do so, it uses a Python data analysis library (e.g., Pandas) to organize the data, taking into account the work procedures and quality check items of each section, the skill level of the workers, etc. The analysis results are digitized and saved in JSON format.

[0066] The server sends the digitized information to the terminal using the HTTP protocol. Specifically, the data is sent through a RESTful API. The terminal uses a general device such as a PC or tablet and receives the data through a web browser or a dedicated quality control application.

[0067] The terminal visually displays the received data to the user. For example, it uses HTML and JavaScript (registered trademark) to display the data in the form of tables, graphs, etc. Using the terminal interface, the user can check the audit items, points of interest, and points of caution for each section, and make corrections or additions as necessary.

[0068] In addition, the server uses a generative AI model based on the digitized information to create a tool that makes appropriate announcements in response to user questions. Based on the prompt text entered by the user, this generative AI model presents appropriate audit items, points of interest, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks.

[0069] As a concrete example, in the product manufacturing section, the following audit items are recorded:

[0070] Checking work procedures: Are the work procedures being followed?

[0071] Quality check items: Checking product dimensions and appearance

[0072] Worker skill level: Do your workers have the required skills?

[0073] The server collects this information from the database and sends it to the terminal. The user can check this information through the terminal and make corrections or additions as necessary.

[0074] Examples of prompts to be input to a generative AI model include:

[0075] "For the quality control of the product manufacturing section, please digitize the following audit items: confirmation of work procedures, quality check items, and worker skill levels."

[0076] By using this prompt sentence, the generative AI model can properly digitize the data and reflect it in the quality control system.

[0077] The above is a specific embodiment for carrying out the present invention.

[0078] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0079] Step 1: Data collection

[0080] The server accesses the quality control system database and collects information such as the audit items, points of interest, and points of caution for each section based on the QC flow diagram. Specifically, the server uses a database management system (DBMS) such as MySQL or PostgreSQL to extract data by executing the SQL query "SELECT FROM qc_flow WHERE section_id = 'product manufacturing'". The input is the database connection information and the SQL query, and the output is the extracted data.

[0081] Step 2: Data analysis

[0082] The server analyzes the collected data. Specifically, it uses a Python data analysis library (e.g. Pandas) to convert the data into a data frame and extracts the work procedures and quality check items for each section, the skill levels of workers, and so on. The input is the collected data, and the output is the analyzed data. For example, a data frame can be used to extract "checking work procedures" and "quality check items."

[0083] Step 3: Digitization

[0084] Based on the parsed data, the server converts the audit items, points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. into JSON format data for each section. The input is the parsed data, and the output is JSON format data. For example, it generates the following JSON data:

[0085] json { "section": "Product Manufacturing", "audit_items": [ { "item": "Check the work procedure", "details": "Are the work instructions being followed?" }, { "item": "Quality check item", "details": "Check product dimensions and appearance" } ], "risk_prevention": "Regular training" }

[0086] Step 4: Send data

[0087] The server transmits the digitized information to the terminal. Specifically, it transmits data through a RESTful API using the HTTP protocol. The input is data in JSON format, and the output is data transmission to the terminal.

[0088] Step 5: Displaying the data

[0089] The terminal receives the data sent from the server and displays it visually to the user. Specifically, it uses HTML and JavaScript to display the data in the form of tables, graphs, etc. The input is the JSON data received from the server, and the output is the visual data that is displayed to the user. For example, to generate a table like this:

[0090] html Audit items detail Check the work procedure Are you following the work instructions? Quality Check Items Checking product dimensions and appearance

[0091] Step 6: User feedback

[0092] Through the terminal, the user checks the audit items, points of focus, and points of caution for each section, and makes corrections or additions as necessary. Specifically, the user uses the terminal interface to edit data and add comments. The input is the user's feedback, and the output is the corrected or added data. For example, the user can modify the details of "quality check items" to "check product dimensions, appearance, and functions."

[0093] Step 7: Leverage generative AI models

[0094] The server uses a generative AI model based on the digitized information to create a tool that makes appropriate announcements in response to user questions. The input is the prompt text entered by the user, and the output is the answer generated by the generative AI model. For example, the following prompt text is used:

[0095] "For the quality control of the product manufacturing section, please digitize the following audit items: confirmation of work procedures, quality check items, and worker skill levels."

[0096] The above is the specific processing flow of the program of this system.

[0097] (Application example 1)

[0098] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0099] In conventional quality control systems, the audit items for each section, prediction of quality risks, and proposal of preventive and corrective measures are often done manually, which is inefficient. In addition, it is difficult to check quality and predict risks in real time, which leads to a problem of reduced accuracy of quality control on the production line. Furthermore, digital transformation of quality control has not progressed well in small and medium-sized enterprises, making effective quality control difficult.

[0100] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0101] In this invention, the server includes: a means for digitizing the audit items, points of interest, points to note, ideal state, expected quality risks, preventive measures and corrective measures for risks for each section based on a basic QC flow diagram related to a quality control system and product manufacturing; a means for creating an announceable tool using a generative AI model based on the digitized information; a means for marketing the created tool as a menu for digital transformation of quality control, mainly for small and medium-sized enterprises; a means for monitoring the work procedures and quality check items of each section in the production line in real time, predicting quality risks, and proposing preventive measures and corrective measures; a means for checking the quality of products using image recognition technology; and a means for predicting quality risks based on past data using a machine learning model. This enables real-time quality control and risk prediction, improves the accuracy of quality control on the production line, and promotes the digital transformation of quality control in small and medium-sized enterprises.

[0102] A "quality control system" is a system that monitors and controls the entire manufacturing process in order to maintain and improve product quality.

[0103] A "QC flow diagram" is a diagram that visually represents each step and process of quality control, and shows the audit items and work procedures for each section.

[0104] "Audit items" are specific items or standards that should be checked for quality control.

[0105] A "point of view" is a point or perspective that requires particular attention in quality control.

[0106] "Points to note" are points that require special attention in each section of quality control.

[0107] "The ideal state" is the standard to be aimed for in quality control.

[0108] A "quality risk" is any factor or situation that may adversely affect the quality of a product.

[0109] "Preventive measures" are measures or procedures to prevent quality risks before they occur.

[0110] "Corrective action" means measures or procedures to resolve a quality problem that has occurred and prevent it from recurring.

[0111] A "generative AI model" is a model that uses artificial intelligence to generate new information and predictions from data.

[0112] An "announceable tool" is a tool that uses a generative AI model to provide appropriate information to users.

[0113] "Digital transformation" refers to the innovation of business processes and business models through the use of digital technology.

[0114] "Real-time monitoring" refers to monitoring the manufacturing process in real time and acquiring and analyzing data instantly.

[0115] "Image recognition technology" is a technology that uses cameras and sensors to analyze images and extract specific information.

[0116] A "machine learning model" is an algorithm that learns patterns based on past data and uses them to make future predictions and classifications.

[0117] As an embodiment of the present invention, a "smart QC robot" equipped with a quality control system will be described as an example.

[0118] System Configuration

[0119] Hardware

[0120] Robot body: A robot installed on a manufacturing line (e.g., an industrial robot)

[0121] Camera sensor: A camera for taking images of the product (e.g. a high-resolution camera)

[0122] Data processing unit: A unit for processing image data and quality data (e.g. high-performance processor).

[0123] software

[0124] Image recognition software: Software for analyzing captured images (e.g. OpenCV)

[0125] Database management system: A system for managing data such as each section's work procedures, quality check items, and worker skill levels (e.g., MySQL)

[0126] Machine learning models: Models for predicting quality risks based on past data (e.g., TENSORFLOW (registered trademark))

[0127] Generative AI model: A model for creating announceable tools based on digitized information

[0128] Program processing explanation

[0129] Data processing and calculation

[0130] 1. Image recognition: Images of products captured by a camera sensor are analyzed using OpenCV to check quality check items. For example, the positional accuracy and mounting strength of parts are monitored in real time.

[0131] 2. Database management: MySQL is used to manage data such as each section's work procedures, quality check items, and worker skill levels, allowing information required for quality control to be managed centrally.

[0132] 3. Machine Learning: Using TensorFlow, predict quality risks based on past data and suggest preventive or corrective measures. For example, if past data shows frequent occurrences of part misalignment, the risk can be predicted and real-time monitoring can be strengthened.

[0133] Examples and prompts

[0134] As a concrete example, the following prompt sentence is input into the generative AI model.

[0135] Example prompt:

[0136] Please check the quality check items in Section A of the production line and suggest preventive measures if there is high risk. Please make your decision based on the following data.

[0137] Procedure: Parts installation

[0138] Quality check items: Part position accuracy, mounting strength

[0139] Worker skill level: Intermediate

[0140] Past quality risk data: Frequent occurrence of part misalignment

[0141] An example of the response generated:

[0142] We have reviewed the quality check items in Section A. Regarding the positional accuracy of parts, past data has revealed that there have been frequent occurrences of misalignment. As a preventative measure, we suggest that you introduce a system that monitors the mounting position in real time and issues an alert immediately if any misalignment occurs. In addition, regarding the mounting strength, we recommend that you regularly check it with a torque wrench.

[0143] In this way, smart QC robots can control quality in real time and suggest preventive and corrective measures to prevent risks, improving the accuracy of quality control on the production line and promoting the digital transformation of quality control in small and medium-sized enterprises.

[0144] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0145] Step 1:

[0146] The server obtains product image data from the camera sensor. The input is image data from the camera sensor, and the output is image data that can be analyzed. In concrete terms, the camera sensor takes a picture of the product on the production line and sends the image data to the server.

[0147] Step 2:

[0148] The server uses image recognition software (e.g. OpenCV) to analyze the acquired image data. The input is the image data acquired in step 1, and the output is the analysis results of the quality check items. In concrete terms, the image recognition software analyzes the positional accuracy and mounting strength of the parts to check for any abnormalities.

[0149] Step 3:

[0150] The server accesses a database management system (e.g. MySQL) and retrieves data such as the work procedures for each section, quality check items, and the skill levels of workers. The input is a query to the database, and the output is the retrieved data. In concrete terms, the server sends a query to the database and retrieves the required data.

[0151] Step 4:

[0152] The server uses a machine learning model (e.g. TensorFlow) to predict quality risks based on past data. The inputs are the data acquired in step 3 and past quality risk data, and the output is the predicted quality risk. In concrete terms, the machine learning model analyzes past data and predicts current quality risks.

[0153] Step 5:

[0154] The server uses the generative AI model to generate prompt sentences that suggest preventive or corrective actions. The input is the quality risk predicted in step 4, and the output is the generated prompt sentence. In concrete terms, the generative AI model generates prompt sentences that suggest appropriate preventive or corrective actions based on the quality risk.

[0155] Step 6:

[0156] The server announces the generated prompt to the user. The input is the prompt generated in step 5, and the output is the announcement to the user. In concrete terms, the server notifies the user of the generated prompt, and the user takes appropriate action based on it.

[0157] In this way, by clarifying the specific actions and inputs / outputs performed at each step, the process flow of the quality control system can be explained in detail.

[0158] Example 2

[0159] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0160] In conventional quality control systems, audit items, points of focus, points of caution, ideal situations, quality risks, and preventive and corrective measures for risks for each section had to be manually digitized, which took time and effort. In addition, specialized knowledge was required to provide appropriate information in response to user questions, making it difficult to respond quickly. Furthermore, the digitalization of quality control had not progressed in small and medium-sized enterprises, making efficient quality control difficult.

[0161] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0162] In this invention, the server includes a means for generating an announcement using a generative AI model based on digitized quality control information, a means for providing the generated announcement to a user, a means for generating a prompt sentence based on a user's question and inputting the prompt sentence to the generative AI model, and a means for receiving the announcement generated from the generative AI model and displaying it to the user. This enables the automation and rapid provision of information on quality control.

[0163] "Digital quality control information" refers to information recorded in digital format, such as quality control audit items, points of focus, points to note, ideal conditions, quality risks, and preventive and corrective measures against risks.

[0164] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to generate appropriate announcements based on input prompt sentences.

[0165] "Means for generating an announcement" refers to the process of using a generative AI model to create an announcement based on digitized quality control information.

[0166] "Means for providing to a user" refers to a method or system for displaying or notifying a user of a generated announcement.

[0167] A "prompt sentence" is an instruction sentence to be input into a generative AI model, and is generated based on the user's question.

[0168] The term "means for generating a prompt sentence based on a user's question" refers to a process for analyzing a question from a user and creating a corresponding prompt sentence.

[0169] "Means for inputting to a generative AI model" refers to a method or system for inputting the generated prompt sentence into a generative AI model to generate an announcement.

[0170] "Means for receiving an announcement generated from a generative AI model and displaying it to a user" refers to a method or system for receiving an announcement output from a generative AI model and displaying it to a user.

[0171] The present invention is a system that automatically digitizes information about quality control and provides appropriate announcements to users using a generative AI model. A specific embodiment of this system will be described below.

[0172] System Configuration

[0173] server

[0174] The server includes a database, a generative AI model, a prompt sentence generation module, an announcement generation module, and a communication module. The server obtains data related to quality control from the database and generates an announcement using the generative AI model.

[0175] Terminal

[0176] The terminal provides an interface for the user to input a question, transmits the user's question to the server, and displays announcements received from the server to the user.

[0177] User

[0178] The user inputs a question about quality control using the terminal, and the user checks the announcement displayed on the terminal to help improve quality control.

[0179] Hardware and Software Used

[0180] Hardware

[0181] Server: A server with a powerful processor and large memory capacity

[0182] Device: User devices such as computers, tablets, and smartphones

[0183] software

[0184] Generative AI model: A generative AI model that uses natural language processing technology (e.g., GPT-4 (registered trademark))

[0185] Database: A database that stores data related to quality control

[0186] Communication module: Software for data communication between the server and the terminal

[0187] Data processing and calculation

[0188] The server retrieves data related to quality control from the database and performs preprocessing. The preprocessed data is used to generate prompt sentences that are input to the generative AI model. The generated prompt sentences are input to the generative AI model to generate appropriate announcements. The generated announcements are provided to the user.

[0189] Examples

[0190] A user uses a terminal to input a question such as "Please tell me what to pay attention to in the product inspection process." The terminal sends this question to the server. The server receives the question and generates a prompt sentence like the following:

[0191] "What should I pay attention to in the product inspection process?"

[0192] The server inputs the generated prompt sentence into the generative AI model, which generates an announcement based on the prompt sentence, such as the following:

[0193] "In the product inspection process, the following points should be noted: 1. Use a detailed checklist based on the inspection standards. 2. When a defect is discovered, identify the cause and take measures to prevent recurrence. 3. Record the inspection results and analyze the data to help improve quality."

[0194] The server transmits the generated announcement to the terminal, which displays it to the user, who can then learn specific points to note and points to improve regarding quality control.

[0195] In this way, quality control information can be automated and provided quickly.

[0196] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0197] Step 1:

[0198] The user enters a question.

[0199] The user uses the terminal interface to input a question about quality control, for example, "Please tell me what points I should pay attention to in the product inspection process." The input question is temporarily stored in the terminal's memory.

[0200] Step 2:

[0201] The terminal sends a question to the server.

[0202] The terminal converts the question entered by the user into JSON format and sends it to the server using an HTTP request. The input is the user's question and the output is the JSON data sent to the server.

[0203] Step 3:

[0204] The server receives the question and generates a prompt.

[0205] The server analyzes the JSON data received from the terminal and extracts the question. It then generates a prompt sentence to input to the generative AI model. For example, it generates a prompt sentence such as, "Please tell me what points to be careful about in the product inspection process." The input is the user's question, and the output is the generated prompt sentence.

[0206] Step 4:

[0207] The server inputs a prompt sentence into the generative AI model.

[0208] The server sends the generated prompt sentence as an API request to the generative AI model. The input is the generated prompt sentence, and the output is the API request sent to the generative AI model.

[0209] Step 5:

[0210] A generative AI model generates the announcements.

[0211] The generative AI model generates announcements about quality control based on the input prompt sentence. For example, it generates an announcement that says, "In the product inspection process, attention should be paid to the following points: 1. Use a detailed checklist based on the inspection criteria. 2. When a defective product is found, identify the cause and take measures to prevent recurrence. 3. Record the inspection results and analyze the data to help improve quality." The input is the prompt sentence, and the output is the generated announcement.

[0212] Step 6:

[0213] The server receives the generated announcement.

[0214] The server receives the announcements returned by the generative AI model and formats them as necessary. The input is the announcement from the generative AI model and the output is the formatted announcement.

[0215] Step 7:

[0216] The server sends the announcement to the terminal.

[0217] The server converts the formatted announcement into JSON format and sends it to the terminal as an HTTP response. The input is the formatted announcement, and the output is the JSON data sent to the terminal.

[0218] Step 8:

[0219] The terminal displays the announcement to the user.

[0220] The terminal analyzes the received JSON data and displays the announcement content on the screen. This allows the user to know specific points to note and areas for improvement regarding quality control. The input is JSON data from the server, and the output is the announcement displayed to the user.

[0221] (Application example 2)

[0222] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0223] In conventional quality control systems, it was necessary to manually manage audit items, points of caution, and preventive measures against risks for each section, which was inefficient and prone to human error. It was also difficult to provide prompt and appropriate answers to user questions, and there was a lack of means to effectively analyze quality control history. This made the entire quality control process inefficient, and there was a possibility that preventive and corrective measures for quality risks would be delayed.

[0224] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means. In this invention, the server includes a means for digitizing the inspection items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks, etc. for each section based on a basic quality control flow chart related to a quality control system and product manufacturing, a means for creating a tool that can be announced by a generative AI model based on the digitized information, a means for installing the created tool in a factory robot and announcing in real time points of caution and improvements at each step of quality control, a means for presenting appropriate inspection items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks in response to questions from a user, and a means for collecting data and recording and analyzing the history of quality control. This allows the quality control process to be automated and performed efficiently and accurately.

[0225] A "quality management system" refers to a set of processes and tools for controlling and maintaining the quality of products and services.

[0226] "Product manufacturing" refers to the process of assembling and processing raw materials and parts to create a final product.

[0227] A "quality control flow diagram" is a diagram that visually represents each step and process of quality control.

[0228] "Audit items" refer to specific items that should be checked in each section of quality control.

[0229] "Point of focus" refers to points that require special attention in quality control.

[0230] "Points to note" refer to matters that require special attention at each step of quality control.

[0231] "The ideal state" refers to the ideal or target state in quality control.

[0232] "Quality risk" refers to a risk that may affect the quality of a product or service.

[0233] "Preventive measures" refer to measures taken to prevent quality risks from occurring.

[0234] "Corrective Action" means a measure taken to resolve a quality problem that has occurred.

[0235] "Digitization" refers to recording and storing information in digital form.

[0236] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate text or information.

[0237] An "announceable tool" refers to a tool that uses a generative AI model to communicate information via voice or text.

[0238] A "factory robot" refers to a mechanical device used to perform automated tasks in a factory.

[0239] "Real-time" refers to immediate processing or response without delay.

[0240] "User" refers to a person or organization that uses a system or tool.

[0241] A "question" refers to an inquiry a user makes to a system or tool.

[0242] "Present" refers to showing information or answers to the user.

[0243] "History" refers to past data or records.

[0244] "Recording" refers to storing information for future reference.

[0245] "Analysis" refers to examining data in detail to find meaning and trends.

[0246] As an embodiment of the present invention, a means is provided for digitizing the audit items and points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. for each section based on a quality control system and a basic quality control flow chart related to product manufacturing. A tool that can be announced by a generative AI model is created based on the digitized information, and this is installed in a factory robot. A specific embodiment is described below.

[0247] Hardware and Software Used

[0248] Hardware: Factory robots (e.g. general industrial robots), computers (installed on the robots)

[0249] Software: Python, OpenAI® API

[0250] Data processing and calculation

[0251] The server digitizes audit items and points of caution for each section of quality control, preventive measures against risks, etc. The digitized information is converted into a format that can be announced using a generative AI model. Specifically, by inputting the following prompt sentences into the generative AI model, appropriate advice and answers are generated.

[0252] Examples of prompt statements

[0253] Prompt for entering quality control step information: "Quality control step: Final inspection of the product. Please let us know any points of concern or improvements you need to make."

[0254] Prompt for inputting user questions: "User question: What are the risks in this process? Please tell us the appropriate audit items, points of focus, points to note, how things should be, anticipated quality risks, and preventive and corrective measures for the risks."

[0255] Processing flow

[0256] 1. Digitization: The server digitizes the audit items and points of attention for each section based on the quality control flow diagram.

[0257] 2. Use of generative AI models: Using digitized information, a generative AI model is used to convert it into a format that can be announced.

[0258] 3. Announcement: Tools installed on factory robots announce in real time the points to note and areas for improvement at each step of quality control.

[0259] 4. Responding to user questions: In response to questions from users, a generative AI model is used to suggest appropriate audit items and risk countermeasures.

[0260] 5. Data collection and analysis: The server records the quality control history and analyzes the data to continuously improve the quality control process.

[0261] Examples

[0262] For example, during final product inspection in a factory, the robot announces, "In this step, we will focus on visual inspection of the product to check for scratches or dirt." When a worker asks, "What are the risks in this process?", the robot responds, "In this process, there is a risk that the product's appearance may be scratched. As a precaution, please wear gloves before the inspection."

[0263] In this way, the quality control process is automated and can be made efficient and accurate.

[0264] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0265] Step 1:

[0266] The server digitizes the audit items, points to note, and preventive measures against risks for each section based on the quality control flow diagram. Specifically, it receives the information from the quality control flow diagram as input and records it in digital form. The digitized information is stored in a database for use in subsequent processes.

[0267] Step 2:

[0268] The server converts the digitized information into a format that can be announced by the generative AI model. Specifically, the server generates prompts containing audit items and points to note for each section and inputs them into the generative AI model. The generative AI model generates appropriate advice and points to note based on the prompts and outputs them in text format.

[0269] Step 3:

[0270] The server sends the generated text to the factory robot, which converts the received text into speech and announces in real time points to note and areas for improvement at each step of quality control. Specifically, the text is input into a speech synthesis engine to generate voice data.

[0271] Step 4:

[0272] If a user has a question at each step of quality control, the user inputs the question to the factory robot. The factory robot sends the user's question in text format to the server. Specifically, the factory robot converts the user's voice into text using a voice recognition engine and sends the text to the server.

[0273] Step 5:

[0274] The server inputs the user's question into the generative AI model and generates appropriate audit items and risk countermeasures. Specifically, the server generates the user's question as a prompt sentence and inputs it into the generative AI model. The generative AI model generates an appropriate answer based on the prompt sentence and outputs it in text format.

[0275] Step 6:

[0276] The server sends the generated answer to the factory robot. The factory robot converts the received text into speech and provides the answer to the user. Specifically, the text is input to a speech synthesis engine to generate speech data.

[0277] Step 7:

[0278] The server records the quality control history and analyzes the data. Specifically, the data generated at each step and the user's questions and answers are stored in a database and used in subsequent analysis processes. A data analysis engine is used to analyze the quality control history data and extract areas for improvement and risk prevention measures.

[0279] In this way, the quality control process is automated and can be made efficient and accurate.

[0280] Example 3

[0281] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0282] In conventional quality control systems, audit items, points of focus, points of caution, ideal situations, quality risks, and preventive and corrective measures for risks for each section had to be manually digitized, which was inefficient and prone to human error. In addition, data analysis and report generation were often done manually, which took time and effort, making it difficult for small and medium-sized enterprises to adopt. Another problem was that it was difficult to quickly provide appropriate information when users had questions.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0284] In this invention, the server includes a means for collecting quality control data from the terminal and transmitting it to the server, a means for inputting the data received by the server into a generative AI model and detecting patterns and anomalies in the data, and a means for generating a report based on the analysis results of the generative AI model and displaying the report on a dashboard so that the user can view it. This enables automatic collection and analysis of quality control data, and realizes efficient and accurate quality control. In addition, by using the generative AI model, it becomes possible to provide prompt and appropriate information in response to a user's question.

[0285] A "quality management system" refers to a set of processes and tools for controlling and maintaining the quality of products and services.

[0286] A "flow diagram" is a visual representation of the flow of a process or system, showing the relationships between each step or element.

[0287] "Audit items" refer to specific items that are subject to evaluation and inspection in quality control.

[0288] "Point of view" refers to a point or perspective that deserves particular attention in quality control.

[0289] "Points to note" refers to matters that require special attention in quality control.

[0290] "The ideal state" refers to the ideal state or standard to aim for in quality control.

[0291] "Quality risk" refers to risk factors that may affect the quality of a product or service.

[0292] "Preventive measures" refer to measures or means to prevent quality risks from occurring.

[0293] "Corrective action" refers to measures or procedures taken to resolve an encountered quality problem.

[0294] A "generative AI model" refers to a model that uses artificial intelligence technology to generate, analyze, and predict data.

[0295] An "announceable tool" refers to a tool that has the ability to provide information to users using a generative AI model.

[0296] "Terminal" refers to a device for collecting and transmitting data to a server.

[0297] "Server" refers to a computer system for receiving, processing, analyzing, and storing data.

[0298] "Dashboard" refers to an interface that allows users to visually view data and reports.

[0299] "Digital transformation" refers to the innovation of business processes and business models through the use of digital technology.

[0300] This invention is a system for improving the efficiency of quality control systems and achieving digital transformation of quality control in small and medium-sized enterprises. This system is composed of a terminal, a server, and a generative AI model.

[0301] First, the terminal collects quality control data. Specifically, it collects data such as product inspection results and the operating status of the production line. For example, as the inspection results for product A, it collects the number of defective products and detailed data for each inspection item.

[0302] Next, the terminal transmits the collected quality control data to a server. The data is transmitted using a secure communication protocol (e.g., HTTPS). The server inputs the received data into a generative AI model. For example, OpenAI's GPT-4 can be used as the generative AI model.

[0303] The server uses the generative AI model to detect patterns and anomalies in the data. To do this, the server inputs prompts like the following into the generative AI model:

[0304] "Please suggest ways to improve quality control based on the inspection data for product A."

[0305] Generative AI models detect patterns and anomalies in data and generate outputs such as:

[0306] "The defect rate for test item B is high, so we need to reevaluate our testing method."

[0307] The server generates a report containing suggestions for improving quality control and streamlining based on the analysis results of the generative AI model. The report includes specific improvement measures and recommended action plans. For example, the server generates a report like the one below:

[0308] "After analyzing the test data for product A, the following improvements were found:

[0309] 1. Review of the inspection process: Because the defect rate for inspection item B is high, the inspection method needs to be reevaluated.

[0310] 2. Adjustment of production line: The operating rate of the production line is declining, so we should work to improve the efficiency of the line.

[0311] The user accesses the dashboard provided by the server and views the generated report. The user can take measures to improve quality control based on the report. For example, the user can reevaluate the inspection method for inspection item B and make necessary adjustments.

[0312] This system enables automatic collection and analysis of quality control data, realizing efficient and accurate quality control. In addition, by using a generative AI model, it becomes possible to provide prompt and appropriate information in response to user questions. The flow of the identification process in the third embodiment will be described with reference to FIG. 15.

[0313] Step 1:

[0314] The terminal collects quality control data. Specifically, it collects data such as product inspection results and the operating status of the production line. For example, as the inspection results for product A, it collects the number of defective products and detailed data for each inspection item.

[0315] Input: Product inspection results and production line operation status

[0316] Output: Collected quality control data

[0317] Step 2:

[0318] The terminal transmits the collected quality control data to the server. The data is transmitted using a secure communication protocol (e.g., HTTPS).

[0319] Input: Collected quality control data

[0320] Output: Data sent to the server

[0321] Step 3:

[0322] The server inputs the received data into a generative AI model, such as OpenAI's GPT-4.

[0323] Input: Quality control data sent to the server

[0324] Output: The data fed into the generative AI model

[0325] Step 4:

[0326] The server uses the generative AI model to detect patterns and anomalies in the data. To do this, the server inputs prompts like the following into the generative AI model:

[0327] "Please suggest ways to improve quality control based on the inspection data for product A."

[0328] Generative AI models detect patterns and anomalies in data and generate outputs such as:

[0329] "The defect rate for test item B is high, so we need to reevaluate our testing method."

[0330] Input: Quality control data fed into the generative AI model

[0331] Output: Patterns and anomalies detected in the data

[0332] Step 5:

[0333] The server generates a report containing suggestions for improving quality control and streamlining based on the analysis results of the generative AI model. The report includes specific improvement measures and recommended action plans. For example, the server generates a report like the one below:

[0334] "After analyzing the test data for product A, the following improvements were found:

[0335] 1. Review of the inspection process: Because the defect rate for inspection item B is high, the inspection method needs to be reevaluated.

[0336] 2. Adjustment of production line: The operating rate of the production line is declining, so we should work to improve the efficiency of the line.

[0337] Input: Data pattern and anomaly detection results

[0338] Output: Report with suggestions for quality control improvements and efficiency improvements

[0339] Step 6:

[0340] The user accesses the dashboard provided by the server and views the generated report. The user can take measures to improve quality control based on the report. For example, the user can reevaluate the inspection method for inspection item B and make necessary adjustments.

[0341] Input: Reports containing suggestions for quality control improvements and efficiencies

[0342] Output: Quality control improvements that users can view and implement.

[0343] (Application example 3)

[0344] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0345] Quality control in small and medium-sized enterprises is currently difficult to carry out efficiently and effectively due to limited resources and lack of expertise. In addition, there is a demand for real-time monitoring of quality data in factories, detection of anomalies, and proposals of specific actions to improve quality, but there is a lack of appropriate tools and systems to achieve this. For this reason, a comprehensive system is needed to support the digital transformation of quality control and improve quality.

[0346] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means. In this invention, the server includes a means for digitizing the audit items and points of interest, points of caution, ideal situations, expected quality risks, preventive measures and corrective measures for risks for each section based on a basic quality control flow diagram related to a quality control system and product manufacturing, a means for creating a tool that can be announced by a generative AI model based on the digitized information, a means for marketing the created tool as a digital transformation menu for quality control mainly for small and medium-sized enterprises, a means for providing a quality control support application to be installed in a factory robot, a means for monitoring quality data in real time and issuing an alert when an abnormality is detected, and a means for analyzing and predicting quality data and proposing specific actions for quality improvement. This makes it possible for even small and medium-sized enterprises to efficiently and effectively perform quality control, thereby improving quality.

[0347] A "quality control system" is a system that manages a series of processes and methods for maintaining and improving the quality of products and services.

[0348] A quality control flow diagram is a visual representation of each process and procedure of quality control, and indicates the audit items, points of focus, and points of caution for each section.

[0349] "Audit items" refer to specific items or standards that should be checked in quality control.

[0350] A "point of view" is a point or perspective to which special attention should be paid in quality control.

[0351] "Points to note" refer to matters or risks that require special attention in quality control.

[0352] "The ideal state" refers to the standard to be aimed for in quality control.

[0353] "Quality risk" refers to a risk or issue that could affect the quality of a product or service.

[0354] "Preventive measures" refer to specific measures or means to prevent quality risks before they occur.

[0355] "Corrective action" refers to specific measures or procedures taken to resolve an encountered quality problem.

[0356] A "generative AI model" is a model that uses artificial intelligence technology to generate and analyze data.

[0357] An "announceable tool" is a tool that uses a generative AI model to provide information to users.

[0358] "Digital transformation" refers to the effort to use digital technology to innovate operational processes and business models in order to improve efficiency and create value.

[0359] A "factory robot" is a robot used to automate work in a factory.

[0360] "Quality control support application" means a software application for supporting quality control.

[0361] "Real-time monitoring" refers to the instantaneous monitoring of ongoing data and situations.

[0362] "Detecting anomalies" refers to discovering conditions or problems that are different from the norm.

[0363] "Issuing an alert" refers to issuing a warning when an abnormality or problem occurs.

[0364] "Analysis and prediction of quality data" refers to analyzing collected quality data and predicting future quality states.

[0365] "Proposing specific actions" refers to proposing specific measures or steps that should be taken to improve quality.

[0366] This invention is a system that supports the digital transformation of quality control for small and medium-sized enterprises, and provides a quality control support application that is installed on factory robots. Based on a basic quality control flow chart related to quality control systems and product manufacturing, this system digitizes the audit items and points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures for risks for each section, etc., and creates tools that can be announced using a generative AI model.

[0367] The server first digitizes the audit items, points of interest, cautions, ideal conditions, quality risks, preventive measures, and corrective measures for each section based on the quality control flow diagram. This digitization process can be automated using AI technology. Next, a generative AI model is built based on the digitized information, and an announceable tool is created to provide appropriate information to users. This tool has the function of automatically presenting appropriate audit items, points of interest, cautions, ideal conditions, quality risks, preventive measures, and corrective measures in response to user questions.

[0368] Furthermore, Sarver will market the tool it created as a digital transformation menu for quality control, primarily for small and medium-sized enterprises, enabling them to efficiently and effectively carry out quality control and improve quality.

[0369] The quality control support application installed on factory robots has the ability to monitor quality data in real time and issue an alert if an abnormality is detected. This application analyzes and predicts quality data and proposes specific actions to improve quality. Specifically, it collects quality data such as temperature, humidity, and pressure, and detects anomalies using a generative AI model. If an abnormality is detected, it issues an alert to the factory manager, urging them to take prompt action.

[0370] For example, the quality data of products manufactured in a factory can be collected in real time and used to detect anomalies. If an anomaly is detected, an alert can be sent to the factory manager to promptly take action.

[0371] Examples of prompts to be input to a generative AI model include the following:

[0372] "Use quality data from within your factory to build an AI model that detects anomalies and suggests specific actions to improve quality. Data includes information such as temperature, humidity, and pressure."

[0373] In this way, by developing a quality control support application to be installed on factory robots, it is possible to make quality control within the factory more efficient and improve quality.

[0374] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0375] Step 1:

[0376] The server digitizes the audit items, points of focus, cautions, ideal conditions, quality risks, preventive measures, and corrective actions for each section based on the quality control flow diagram. Specifically, it analyzes the quality control flow diagram, extracts information from each section, and stores it in a database. This digitization process can be automated using AI technology. The input is the quality control flow diagram, and the output is data such as audit items and points of focus stored in the database.

[0377] Step 2:

[0378] The server builds a generative AI model based on the digitized information. Specifically, it retrieves data such as audit items and points of interest from the database and uses this to train the generative AI model. The input is the data retrieved from the database, and the output is the trained generative AI model.

[0379] Step 3:

[0380] The server uses the generative AI model to create an announceable tool. Specifically, the server uses the generative AI model to develop a tool that has the function of presenting appropriate audit items, points of interest, points of caution, ideal situations, quality risks, preventive measures, and corrective measures in response to user questions. The input is the generative AI model, and the output is the announceable tool.

[0381] Step 4:

[0382] The server will market the created tool as a digital transformation menu for quality control, mainly for small and medium-sized enterprises. Specifically, it will provide it as a cloud service, allowing companies to use the service. The input is an announceable tool, and the output is a tool provided as a cloud service.

[0383] Step 5:

[0384] The factory robot installs the quality control support application. Specifically, the quality control support application provided by the server is downloaded and installed in the robot's system. The input is the quality control support application, and the output is the installed application.

[0385] Step 6:

[0386] Factory robots monitor quality data in real time and detect abnormalities. Specifically, they analyze temperature, humidity, pressure, and other data obtained from sensors in real time and issue an alert if an abnormality is detected. The input is the quality data from the sensors, and the output is an alert that an abnormality has been detected.

[0387] Step 7:

[0388] The factory robot analyzes and predicts quality data and proposes specific actions to improve quality. Specifically, it uses a generative AI model to analyze quality data, predict future quality states, and propose necessary measures. The input is quality data, and the output is a proposal for specific actions to improve quality.

[0389] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0390] "Example 1"

[0391] As one embodiment of the present invention, a system incorporating an emotion engine is provided. This system includes a means for digitizing the audit items and points of interest, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks for each section based on a basic QC flow diagram related to quality control systems and product manufacturing, a means for creating a tool that can be announced via Chat GPT based on the digitized information, and a means for market deployment of the created tool as a quality control DX menu, mainly for small and medium-sized enterprises.

[0392] "Example 2"

[0393] The emotion engine recognizes the user's emotions and presents appropriate audit items, points of focus, cautions, ideal situations, anticipated quality risks, and preventive and corrective measures for risks according to the user's emotional state. For example, if a user is feeling stressed, the emotion engine recognizes that information and presents appropriate preventive and corrective measures to reduce stress.

[0394] "Example 3"

[0395] In addition, the emotion engine adjusts how it presents the quality control digitalization menu according to the user's emotional state. For example, if a user is feeling happy, the emotion engine will recognize that information and present a quality control digitalization menu that amplifies the joy. This enables more effective quality control that takes the user's emotional state into account.

[0396] The process flow of each embodiment will be described below.

[0397] "Example 1"

[0398] Step 1: Based on a basic QC flow diagram related to the quality control system and product manufacturing, digitize the audit items and points of focus for each section, points to note, how things should be, anticipated quality risks, and preventive and corrective measures for risks.

[0399] Step 2: Create a tool that can make announcements using chat generation AI based on the digitized information

[0400] do.

[0401] Step 3: Market the created tool as a quality control digitalization menu, primarily for small and medium-sized enterprises.

[0402] "Example 2"

[0403] Step 1: Recognize the user's emotion using the emotion engine.

[0404] Step 2: The emotion engine presents appropriate audit items, points of focus, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks based on the recognized emotional state.

[0405] "Example 3"

[0406] Step 1: Recognize the user's emotion using the emotion engine.

[0407] Step 2: The emotion engine adjusts how it presents the quality control digitalization menu based on the recognized emotional state.

[0408] Example 1

[0409] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal".

[0410] In conventional quality control systems and product manufacturing, information such as audit items, points of focus, points of caution, ideal situations, quality risks, preventive and corrective measures for risks, etc. for each section had to be managed manually, which was inefficient and prone to human error. In addition, specialized knowledge was required to generate announcements based on this information, which made it difficult for small and medium-sized enterprises to introduce.

[0411] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0412] In this invention, the server includes a means for converting the audit items and points of interest, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks for each section into digital data based on a quality control system and a basic quality control flow chart related to product manufacturing, a means for storing the data using a database management system, and a means for generating announcements using an emotion engine. This enables efficient management of information related to quality control and automatic generation of announcements using generative artificial intelligence.

[0413] A "quality control system" is a system that manages a series of processes and methods for maintaining and improving the quality of products and services.

[0414] "Product manufacturing" is the process of assembling and processing raw materials and parts to create a final product.

[0415] A "quality control flow diagram" is a visual representation of each step or process of quality control, showing the audit items and procedures for each section.

[0416] "Audit items" are specific items or standards that should be checked in quality control and product manufacturing.

[0417] A "point of focus" is a point or perspective that should be given particular attention when conducting an audit or check.

[0418] "Points to note" are matters that require special attention when performing work or audits.

[0419] "The ideal state" is the standard to be aimed for in quality control and product manufacturing.

[0420] A "quality risk" is any factor or situation that can affect quality.

[0421] "Preventive measures" are measures or procedures to prevent quality risks before they occur.

[0422] "Corrective action" means measures or procedures to resolve a quality problem that has occurred and prevent it from recurring.

[0423] "Digitization" is the process of recording and managing information in digital form.

[0424] "Generative artificial intelligence" is an artificial intelligence technology that uses natural language processing and machine learning to generate text and announcements.

[0425] An "announceable tool" is a tool that uses generative artificial intelligence to automatically provide information.

[0426] "Digital transformation" refers to the effort to use digital technology to innovate operational processes and business models in order to improve efficiency and create value.

[0427] A "database management system" is a system for efficiently storing, managing, and searching data.

[0428] An "emotion engine" is a technology that analyzes emotions from text and voice and generates appropriate responses.

[0429] This invention is a system that uses a quality control system and a basic quality control flow diagram related to product manufacturing to digitize the audit items, points of focus, points of caution, ideal situations, anticipated quality risks, preventive and corrective measures against risks, etc. for each section, and generates announcements using generative artificial intelligence.

[0430] System Configuration

[0431] Data collection

[0432] Based on the quality control system and basic quality control flow chart related to product manufacturing, users input information such as audit items for each section, points to focus on, points to note, ideal situations, anticipated quality risks, preventive and corrective measures against risks, etc. Input is done using a dedicated input form.

[0433] Data storage

[0434] The server takes the information entered by the user and stores it using a database management system (e.g., MySQL). The server runs SQL queries to insert the entered information into the appropriate tables.

[0435] Generate an announcement

[0436] The server generates announcements using generative artificial intelligence (e.g., ChatGPT (registered trademark) by OpenAI) based on the information stored in the database. The server retrieves necessary information from the database and generates a prompt sentence for the generative artificial intelligence.

[0437] Creating tools

[0438] The server creates tools based on the generated announcements to be marketed as quality control digital transformation menus for small and medium-sized enterprises. The server develops the tools as web applications using programming languages ​​such as Python and JavaScript.

[0439] Examples

[0440] Section: Product Inspection

[0441] Audit item: Compliance with inspection procedures

[0442] Focus: Does the inspection procedure follow standard operating procedures?

[0443] Important points: Are test results recorded accurately?

[0444] What should happen: All testing is done according to standard operating procedures and is accurately recorded.

[0445] Potential quality risks: Non-compliance with inspection procedures resulting in the release of defective products

[0446] Preventive measures against risks: Regular review and education of inspection procedures

[0447] Corrective Action: Immediate correction when non-compliance with inspection procedures is discovered

[0448] Example prompt:

[0449] "What are the audit items in the product inspection section? Also, please tell us about the points to focus on and points to note regarding compliance with the inspection procedures, the ideal situation, anticipated quality risks, and preventive and corrective measures for risks."

[0450] In this way, the user generates the system's program, and the server executes the program to collect data, store it in the database, generate announcements using generative AI, and create tools. Using concrete examples and prompt sentences makes it easier to input data into the generative AI model.

[0451] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0452] Step 1: Data collection

[0453] Input: Based on the quality control system and basic quality control flow diagram related to product manufacturing, the user inputs information such as the audit items, points of focus, points of caution, ideal state, anticipated quality risks, and preventive and corrective measures for risks for each section.

[0454] Specific operation: The user enters information for each section using a dedicated input form. For example, the user enters "Compliance with inspection procedures" as an audit item in the product inspection section.

[0455] Output: The entered information is sent to the server.

[0456] Step 2: Save your data

[0457] Input: The server receives information entered by the user.

[0458] What Happens: The server uses a database management system (e.g., MySQL) to execute a SQL query that inserts the received information into the appropriate tables, for example "INSERT INTO qc_data (section, audit_item, focus_point, caution, ideal_state, risk, preventive_action, corrective_action) VALUES (...)".

[0459] Output: The information is stored in a database.

[0460] Step 3: Generate an announcement

[0461] Input: The server retrieves information stored in a database.

[0462] Specific operation: The server retrieves the necessary information from the database and generates a prompt for generative artificial intelligence (e.g., ChatGPT of OpenAI). For example, it generates a prompt such as "What are the audit items in the product inspection section?" and sends it to ChatGPT.

[0463] Output: The generated announcement from ChatGPT is returned.

[0464] Step 4: Creating the tool

[0465] Input: The server receives the generated announcement.

[0466] Specific operation: The server develops tools as web applications using programming languages ​​such as Python and JavaScript. For example, it uses the Django framework to create a dashboard where users can check announcements.

[0467] Output: The finished tool is generated.

[0468] Step 5: Market launch

[0469] Input: The user receives the completed tool.

[0470] Specific Actions: The user demonstrates the tool and explains the benefits of its implementation to the company, for example emphasizing that the tool will improve the efficiency of quality control.

[0471] Output: The tools are provided to SMEs and deployed in the market.

[0472] (Application example 1)

[0473] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0474] Traditional quality control systems and the management of audit items and quality risks based on QC flow charts in product manufacturing are often done manually, which is inefficient and prone to human error. Feedback to workers is also one-way, making it difficult to provide appropriate guidance based on the worker's emotions and situation. Furthermore, digital transformation (DX) of quality control has not progressed well in small and medium-sized enterprises, raising concerns about a decline in competitiveness. To solve these issues, a system that allows for real-time monitoring and feedback is needed.

[0475] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0476] In this invention, the server includes a means for digitizing the audit items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks for each section based on a basic QC flow diagram related to the quality control system and product manufacturing, a means for creating a tool that can be announced by generative AI based on the digitized information, a means for market deployment of the created tool as a quality control DX menu mainly for small and medium-sized enterprises, a means for being installed in a factory robot and monitoring work procedures and quality check items in real time, a means for providing appropriate feedback to workers using an emotion engine, and a means for making announcements and instructions to workers using generative AI. This makes it possible to improve the efficiency and accuracy of quality control, provide appropriate feedback to workers, and DX quality control in small and medium-sized enterprises.

[0477] A "quality control system" is a system for monitoring and controlling the manufacturing process and product quality in order to maintain and improve product quality.

[0478] "Product manufacturing" is the process of assembling or processing raw materials and parts to create a final product.

[0479] A "QC flow diagram" is a visual representation of the procedures and processes for quality control, and is intended to clarify the audit items and work procedures for each section.

[0480] An "audit item" is an item in quality control or product manufacturing that is evaluated or inspected based on specific standards or specifications.

[0481] A "point of focus" is a point that should be given special attention or observed in quality control or product manufacturing.

[0482] "Points to note" are areas in quality control or product manufacturing where mistakes or problems are likely to occur, or matters that require special attention.

[0483] "The ideal state" refers to the ideal state or standard to aim for in quality control and product manufacturing.

[0484] A "quality risk" is any factor or situation that may affect the quality of a product.

[0485] "Preventive measures" are measures or procedures taken to prevent quality risks before they occur.

[0486] "Corrective action" means measures or procedures taken to resolve an existing quality problem and prevent its recurrence.

[0487] "Digitization" is the process of recording and storing information or data in a digital format.

[0488] "Generative AI" is an artificial intelligence technology that uses natural language processing and machine learning to generate text, speech, and other data.

[0489] An "announceable tool" is a tool that uses generative AI to automatically convey specific information or instructions to users.

[0490] The "DX Menu" is a list of specific measures and services to promote digital transformation.

[0491] A "factory robot" is a robot used to automate tasks in a manufacturing environment.

[0492] "Real-time monitoring" is a function that allows you to instantly monitor and check ongoing processes and situations.

[0493] An "emotion engine" is an artificial intelligence technology that generates appropriate feedback based on the user's emotions and situation.

[0494] "Feedback" is evaluation, criticism, or advice given in response to a specific action or result.

[0495] An "announcement" is the act of conveying specific information or instructions to a user.

[0496] As an embodiment of the present invention, we provide a system that digitizes the audit items and points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures against risks, etc. for each section based on a basic QC flow chart related to quality control systems and product manufacturing. A specific embodiment of this system is described below.

[0497] System Configuration

[0498] 1. Data collection method

[0499] Based on the quality control system and basic QC flow charts related to product manufacturing, the server digitizes the audit items, points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. for each section. This includes automated data processing using AI technology.

[0500] 2. How to create generative AI tools

[0501] The server uses the digitized information to create tools that can be announced using generative AI. These tools have the ability to automatically present appropriate audit items, points of interest, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks in response to user questions.

[0502] 3. Digital transformation menu development methods

[0503] Sarver will market the tool it created as a digitalization menu for quality control, primarily for small and medium-sized enterprises. This menu aims to improve the efficiency and accuracy of quality control.

[0504] 4. Real-time monitoring methods

[0505] The factory robot monitors each section's work procedures and quality check items in real time, including collecting data using cameras and sensors.

[0506] 5. Emotion Engine Feedback Measures

[0507] The factory robot uses an emotion engine to provide appropriate feedback to workers, for example by gently pointing out mistakes and suggesting ways to improve.

[0508] 6. Generative AI Announcement Methods

[0509] The server uses generative AI to make announcements and give instructions to workers, allowing them to receive appropriate instructions in real time.

[0510] Hardware and Software Used

[0511] Hardware: Factory robots, cameras, sensors

[0512] Software: AI technology (e.g. ChatGPT by OpenAI), emotion engine

[0513] Examples

[0514] For example, if a worker is working in a dark environment in a factory, the factory robot's camera will detect the brightness of the frame and gently point it out using the emotion engine. Specifically, it will generate a prompt sentence like the following:

[0515] Examples of prompt statements

[0516] Communicate the following message to workers in a gentle tone: The lighting is too dim. Please adjust the lighting.

[0517] In this way, the system can perform quality control in real time and provide appropriate feedback to workers, which will improve the efficiency and accuracy of quality control, provide appropriate feedback to workers, and enable digital transformation of quality control in small and medium-sized enterprises.

[0518] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0519] Step 1:

[0520] The server digitizes the audit items, points of interest, points to note, ideal conditions, anticipated quality risks, and preventive and corrective measures for risks for each section based on the quality control system and basic QC flow diagram related to product manufacturing. It receives the QC flow diagram and related data as input, and uses AI technology to record and store this information in digital format. The output is the digitized audit items and risk information.

[0521] Step 2:

[0522] The server creates tools that can be announced using generative AI based on the digitized information. It receives digitized audit items and risk information as input, and uses a generative AI model (e.g., OpenAI's ChatGPT) to generate tools that automatically present appropriate audit items, points of interest, cautions, ideal situations, quality risks, and preventive and corrective actions in response to user questions. The announceable tool is obtained as output.

[0523] Step 3:

[0524] The server will market the created tools as a DX menu for quality control, primarily to small and medium-sized enterprises. It will receive announceable tools as input and provide them to small and medium-sized enterprises through marketing strategies and sales channels. As output, the DX menu will be marketed.

[0525] Step 4:

[0526] The factory robot monitors the work procedures and quality check items of each section in real time. It receives data from cameras and sensors as input, processes images and analyzes the sensor data, and obtains real-time monitoring data as output.

[0527] Step 5:

[0528] The factory robot uses an emotion engine to provide appropriate feedback to workers. It receives real-time monitoring data as input and uses the emotion engine to generate feedback according to the worker's situation. As an output, a feedback message for the worker is obtained.

[0529] Step 6:

[0530] The server uses generative AI to make announcements and instructions to the workers. It receives feedback messages as input and uses a generative AI model to generate specific announcements and instructions. As output, it obtains announcements and instructions for the workers.

[0531] Specifically, for example, if a worker is working in a dark environment in a factory, the factory robot's camera detects the brightness of the frame in step 4, and in step 5 uses the emotion engine to generate a gentle feedback message saying, "The lighting is too dim. Please adjust the lighting." In step 6, the server uses generative AI to announce this message to the worker.

[0532] Example 2

[0533] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0534] In conventional quality control systems and product manufacturing processes, it was necessary to manually digitize the audit items, points of interest, points of caution, ideal situations, anticipated risks, and preventive and corrective measures for risks for each section, which was inefficient and prone to human error. In addition, it was difficult to quickly provide appropriate information in response to questions from users, especially when a response based on the user's emotional state was required. This led to the slow progress of digital transformation of quality control, and there was an issue that its introduction was delayed, especially in small and medium-sized enterprises.

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

[0536] In this invention, the server includes a means for digitizing the audit items, points of interest, points of caution, ideal situations, anticipated risks, preventive measures and corrective measures for risks for each section based on a basic flow diagram related to the quality control system and product manufacturing, a means for creating a tool that can be announced by the generative AI model based on the digitized information, and a means for receiving and analyzing user input, recognizing the user's emotions with an emotion engine, sending prompt sentences to the generative AI model, receiving a response from the generative AI model, and presenting the response to the user. This makes it possible to automatically present points of caution and improvements at each step of quality control and quickly provide appropriate information in response to user questions. It also makes it possible to respond according to the user's emotional state, making it easier to advance the digital transformation of quality control. Its introduction is particularly promoted in small and medium-sized enterprises.

[0537] A "quality management system" refers to a set of processes and tools for controlling and maintaining the quality of products and services.

[0538] "Product manufacturing" refers to the series of processes that assemble raw materials and parts to create a final product.

[0539] A "flow diagram" is a visual representation of the flow of a process or system.

[0540] "Audit items" refer to specific points that should be checked in quality control and product manufacturing.

[0541] "Points of focus" refers to points that should be given special attention during an audit or evaluation.

[0542] "Points to note" refers to things that should be taken into consideration in a particular process or task.

[0543] "The way things should be" refers to an ideal or targeted state.

[0544] "Potential risk" refers to problems or dangers that may occur in a particular process or situation.

[0545] "Preventive measures" refer to specific measures taken to prevent risks from occurring.

[0546] "Corrective action" refers to a specific measure taken to correct an existing problem or defect.

[0547] "Digitization" refers to recording and storing information in digital form.

[0548] A "generative AI model" refers to a model that is trained using artificial intelligence techniques to perform a specific task.

[0549] "Announceable Tool" refers to a tool that uses a generative AI model to provide information to a user.

[0550] An "emotion engine" refers to technology that recognizes a user's emotional state and responds accordingly.

[0551] A "prompt" refers to text containing instructions or questions that are input to a generative AI model.

[0552] "Digital transformation" refers to the innovation of business processes and business models through the use of digital technology.

[0553] The term "small and medium-sized enterprises" refers to relatively small businesses, generally defined in terms of the number of employees and sales.

[0554] This invention is a system that converts the audit items and points of interest, points to note, ideal situations, anticipated risks, preventive and corrective measures against risks, etc. for each section into digital data based on basic flow charts related to quality control systems and product manufacturing, and provides appropriate information to users using a generative AI model. A specific embodiment of this system is described below.

[0555] Based on the quality control system and basic flow diagrams related to product manufacturing, the server digitizes the audit items and points of focus for each section, points to note, ideal situations, anticipated risks, and preventive and corrective measures for risks. This digitization can be automated using artificial intelligence technology. For example, natural language processing (NLP) technology can be used to extract necessary information from documents and store it in a database.

[0556] Next, the server uses a generative AI model (e.g., OpenAI's GPT-4) based on the digitized information to create a tool that can be announced to the user. This tool has the functions of receiving and analyzing the user's input, recognizing the user's emotions with an emotion engine, sending prompt sentences to the generative AI model, receiving responses from the generative AI model, and presenting the responses to the user.

[0557] As a concrete example, if a user uses a terminal to input "What are the quality risks of this product?", the server receives this input and analyzes it using NLP technology. Based on the analysis results and the emotion recognition results of the emotion engine, it sends the following prompt sentence to the generative AI model.

[0558] Example prompt:

[0559] User: What are the quality risks of this product?

[0560] The generative AI model analyzes the prompt sentence and generates an appropriate response, for example, "Possible quality risks for this product include defects during the manufacturing process, poor quality raw materials, and an inappropriate storage environment. As preventive measures against these risks, it is important to regularly audit the manufacturing process, inspect the quality of raw materials, and maintain an appropriate storage environment."

[0561] The server receives the response from the generative AI model, sends it to the terminal and displays it on the user's screen, allowing the user to quickly obtain specific information about quality control.

[0562] Also, if the user is feeling stressed, the emotion engine will recognize that information and suggest appropriate preventive or corrective measures to reduce stress. For example, if a user types, "I've been feeling stressed lately because of my quality control job," the generative AI model will generate a response like this:

[0563] Example prompt:

[0564] User: I've been feeling stressed lately in my quality control job.

[0565] Example response of the generative AI model:

[0566] Server: It sounds like you're stressed. Try these preventative measures:

[0567] 1. Reprioritize your work and focus on the tasks that matter

[0568] 2. Take regular breaks and make time to refresh

[0569] 3. Communicate with your team members and ask for support

[0570] These measures may help reduce stress.

[0571] In this way, the system operates in cooperation with the server, terminals, and users, automatically presenting points of caution and areas for improvement at each step of quality control, and making it possible to quickly provide appropriate information in response to user questions. It also makes it possible to respond according to the user's emotional state, making it easier to advance the digital transformation of quality control. This will encourage its adoption especially in small and medium-sized enterprises.

[0572] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0573] Step 1:

[0574] Receiving user input

[0575] A user uses a terminal to input a question or comment about quality control. For example, the user inputs "What are the quality risks of this product?" and clicks the send button. The input data is sent from the terminal to the server.

[0576] Step 2:

[0577] Parsing input data

[0578] The server analyzes the input data received from the user. Specifically, it uses natural language processing (NLP) technology to understand the content and intent of the question. For example, it extracts the keyword "quality risk" and understands the intent of the question. The input data is in text format, and the output is structured data as the analysis result.

[0579] Step 3:

[0580] Recognize user emotions with an emotion engine

[0581] The server uses an emotion engine to recognize the user's emotional state from the input. For example, it may determine that the user is feeling stressed based on the tone and context of the words in the input sentence. The input data is the parsed text and the emotion recognition algorithm, and the output is data that indicates the user's emotional state.

[0582] Step 4:

[0583] Sending prompts to generative AI models

[0584] The server sends a prompt sentence to the generative AI model based on the analysis results and the emotional state. The prompt sentence includes the user's question and emotional state. For example, a prompt sentence containing information such as "The user is asking about quality risks and is feeling stressed" is generated. The input data is the analysis results and the emotional state data, and the output is the generated prompt sentence.

[0585] Step 5:

[0586] Receiving responses from generative AI models

[0587] The generative AI model generates an appropriate response based on the prompt sentence and returns it to the server. For example, it generates a response that reads, "Possible quality risks for this product include defects during the manufacturing process, poor quality raw materials, and an inappropriate storage environment. As preventive measures against these risks, it is important to regularly audit the manufacturing process, inspect the quality of raw materials, and maintain an appropriate storage environment." The input data is the prompt sentence, and the output is the generated response sentence.

[0588] Step 6:

[0589] Present the response to the user

[0590] The server presents the response received from the generative AI model to the user. Specifically, the user can check the answer by viewing it on the screen of the device. The input data is the generated response sentence, and the output is the text displayed on the user's device.

[0591] In this way, the system works in cooperation with the server, terminal, and user, automatically suggesting points to note and areas for improvement at each step of quality control, and making it possible to quickly provide appropriate information in response to user questions.

[0592] (Application example 2)

[0593] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0594] In conventional quality control systems, it was necessary to manually manage the audit items, points of focus, points of caution, ideal situations, anticipated quality risks, and preventive and corrective measures for risks for each section, which was inefficient and prone to human error.In addition, there was also the issue of not being able to provide appropriate information according to the user's emotional state, making it difficult to provide appropriate support to users who felt stressed or anxious.

[0595] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0596] In this invention, the server includes a means for digitizing the audit items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks for each section based on a basic QC flow diagram related to quality control systems and product manufacturing, a means for creating a tool that can be announced by a chat generation AI based on the digitized information, a means for market deployment of the created tool as a quality control DX menu mainly for small and medium-sized enterprises, and a means for presenting appropriate audit items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks according to the user's emotional state using an emotion recognition engine. This makes it possible to improve the efficiency of quality control and provide appropriate information according to the user's emotional state.

[0597] A "quality control system" refers to the management methods and processes for maintaining and improving the quality of products and services.

[0598] A "QC flow diagram" is a visual representation of each step or process of quality control.

[0599] "Audit items" refer to specific items that should be checked in each section of quality control.

[0600] "Point of focus" refers to points that require special attention in quality control.

[0601] "Points to note" refers to matters that require special attention at each step of quality control.

[0602] "The ideal state" refers to the ideal or target state in quality control.

[0603] "Quality risk" refers to factors that may adversely affect the quality of a product or service.

[0604] "Preventive measures" refer to measures taken to prevent quality risks from occurring.

[0605] "Corrective Action" means a measure taken to resolve a quality problem that has occurred.

[0606] "Digitization" refers to recording and storing information in digital form.

[0607] "Chat generation AI" refers to artificial intelligence that uses natural language processing technology to generate dialogue with users.

[0608] "Emotion recognition engine" refers to technology for analyzing and recognizing a user's emotional state.

[0609] The "DX menu" refers to specific measures and plans for promoting digital transformation.

[0610] The following system configuration is necessary to implement this invention. The server has a means for digitizing the audit items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks for each section based on the quality control system and basic QC flow diagram related to product manufacturing. It also includes a means for creating a tool that can be announced by a chat generation AI based on the digitized information. In addition, it has a means for market deployment of the created tool as a quality control DX menu, mainly for small and medium-sized enterprises. It also includes a means for presenting appropriate audit items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks according to the user's emotional state using an emotion recognition engine.

[0611] The server uses a database management system (DBMS) to digitize the audit items, points of interest, and points of caution required for each section of the quality control system. The digitized information is passed through a generative AI model (e.g., OpenAI's API) that uses natural language processing technology to provide appropriate announcements to users. An emotion recognition engine (e.g., EmotionRecognizer) is used to recognize the user's emotional state.

[0612] As a specific example, if a user asks, "What are the quality risks of this product?" and the emotion recognition engine determines that the user is stressed, the generated advice might be, "Possible quality risks for this product include wear of parts and defects in the manufacturing process. To reduce stress, we recommend that you perform regular maintenance and quality checks."

[0613] An example of a prompt is:

[0614] User Question: What are the quality risks of this product?

[0615] User Emotion: Stress

[0616] Please present appropriate audit items, points of focus, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks.

[0617] This system will enable more efficient quality control and provide appropriate information according to the user's emotional state.

[0618] The flow of the identification process in the application example 2 will be described with reference to FIG.

[0619] Step 1:

[0620] The server digitizes the audit items and points of interest for each section, points to note, ideal conditions, anticipated quality risks, and preventive and corrective measures for risks, based on the quality control system and basic QC flow diagram related to product manufacturing. The input required is the QC flow diagram and related quality control data, and the output is information such as audit items and points of interest stored in a digital format in a database. Specifically, the server analyzes the QC flow diagram, extracts information for each section, and stores it in the database.

[0621] Step 2:

[0622] The server creates a tool that can make announcements using chat generation AI based on the digitized information. The input requires information such as the audit items and points of interest digitized in step 1, and the output is a generative AI model for making appropriate announcements to users. In concrete terms, the server retrieves the necessary information from the database and generates the announcement content using the generative AI model (for example, OpenAI's API).

[0623] Step 3:

[0624] The user recognizes the user's emotional state using an emotion recognition engine. The user's voice and facial expression data are required as input, and the user's emotional state (e.g., stress, joy, etc.) is obtained as output. In concrete terms, the device captures the user's voice and facial expression using a microphone and camera, and analyzes the emotional state using an emotion recognition engine (e.g., EmotionRecognizer).

[0625] Step 4:

[0626] The user inputs a question, and the server presents appropriate audit items, points of interest, cautions, ideal conditions, anticipated quality risks, and preventive and corrective measures for risks based on the question and emotional state. The input requires the user's question and emotional state, and the output provides advice such as appropriate audit items and points of interest. Specifically, the server converts the user's question and emotional state into a prompt sentence, generates an answer using a generative AI model, and presents it to the user.

[0627] Step 5:

[0628] The server will market the created tool as a quality control DX menu, mainly for small and medium-sized enterprises. The inputs will be the completed tool and strategic information for market deployment, and the output will be companies and users that adopt the tool. In concrete terms, the server will create marketing materials and propose and introduce the tool to small and medium-sized enterprises through sales activities.

[0629] Example 3

[0630] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0631] In conventional quality control systems, audit items and risk management for each section are often performed manually, which is inefficient. In addition, it is not possible to provide a quality control menu that takes into account the emotional state of the user, which results in low user satisfaction and effectiveness. Furthermore, in small and medium-sized enterprises, digital transformation (DX) of quality control has not progressed, making efficient quality control difficult.

[0632] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0633] In this invention, the server includes a means for digitizing the audit items, points of interest, points to note, ideal situations, anticipated risks, and preventive and corrective measures for risks for each section based on a basic flow chart related to the quality control system and product manufacturing, a means for creating a tool that can be announced by generative artificial intelligence based on the digitized information, a means for marketing the created tool as a digital transformation menu for quality control, mainly for small and medium-sized enterprises, a means for inputting and analyzing the emotional state of a user, a means for generating an appropriate quality control menu using generative artificial intelligence based on the analysis result, and a means for providing the generated menu to a user. This enables efficient quality control and effective quality control that takes into account the emotional state of the user.

[0634] A "quality control system" is a system that manages a series of processes and methods for maintaining and improving the quality of products and services.

[0635] A "flow diagram" is a visual representation of a process or procedure, showing the flow and relationships of each step.

[0636] "Audit items" are specific items or standards that should be checked in quality control.

[0637] A "point of view" is a point or perspective that should be given particular attention when conducting an audit or evaluation.

[0638] "Points to note" are matters or risks that require special attention in quality control.

[0639] "The way things should be" is the ideal state or the standard of quality to be targeted.

[0640] "Risk" refers to factors or uncertainties that may affect quality.

[0641] A "preventive measure" is a measure taken to reduce or avoid the effects of a risk before it occurs.

[0642] "Corrective action" is a measure taken to correct an existing problem or defect and to prevent its recurrence.

[0643] "Generative AI" is AI that has the ability to generate new information or content based on input data or prompts.

[0644] An "announceable tool" is a tool that uses generative artificial intelligence to provide information to users.

[0645] "Digital transformation" refers to the effort to use digital technology to innovate operational processes and business models in order to improve efficiency and create value.

[0646] An "emotional state" is a state that indicates a user's current emotions or mood.

[0647] "Analysis" is the process of analyzing data to extract meaning and patterns.

[0648] A "menu" is a list of options or functions offered to a user.

[0649] This invention is a cloud service that supports the digital transformation (DX) of quality control for small and medium-sized enterprises. It is equipped with an emotion engine that adjusts the DX menu of quality control according to the user's emotional state.

[0650] System Overview

[0651] This system consists of three main components: a server, terminals, and users. The server runs on the cloud and provides a quality control digitalization menu. The terminals are the users' PCs or smartphones, and access the cloud service to use the quality control menu. Users access the system through their terminals and use the menu to make their company's quality control more efficient.

[0652] Server Processing

[0653] The server provides a quality control digitalization menu that runs on the cloud. Specifically, it uses AWS (registered trademark) (Amazon Web Services) to manage databases (Amazon RDS) and computing resources (Amazon EC2). The server receives requests from users, generates and provides appropriate quality control menus. It uses a generative AI model (e.g., GPT-4) to generate the optimal quality control menu according to the user's emotional state.

[0654] Terminal handling

[0655] The terminal accesses the cloud service and uses the quality control digitalization menu. The terminal provides an interface for inputting the user's emotional state. For example, the terminal uses a camera and microphone to analyze the user's facial expressions and voice to estimate the emotional state. Libraries and services such as OpenCV and Google (registered trademark) Cloud Speech-to-Text API are used for the analysis.

[0656] User Action

[0657] Users access the cloud service through their devices and use a menu to streamline their company's quality control. The user inputs their emotional state and selects from the menu provided by the system. For example, if the user is feeling happy, the emotion engine recognizes that information and provides a menu that amplifies the happiness.

[0658] Examples

[0659] For example, consider the case where a quality control manager of a small or medium-sized enterprise accesses a cloud service and uses a menu for digitalization of quality control. If the manager is feeling happy, the emotion engine will recognize that information and provide a menu that will amplify the manager's happiness. Specifically, the menu will include sharing of success stories and positive feedback.

[0660] Examples of prompt statements

[0661] Examples of prompt sentences to be input to a generative AI model include the following:

[0662] "If users are happy, what kind of content should we offer as part of our quality control digital transformation menu?"

[0663] By using this prompt sentence, the generative AI model can propose an optimal quality control menu according to the user's emotional state. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0664] Step 1:

[0665] A user logs in to a cloud service.

[0666] A user accesses a cloud service using their own device (PC or smartphone) and enters their user ID and password on the login screen. The device then sends this information to the server for authentication. The input is the user ID and password, and the output is the authentication result. In concrete terms, the user opens a browser and enters the URL of the cloud service to access it. The login screen is displayed, and the user enters their user ID and password and clicks the "Login" button.

[0667] Step 2:

[0668] The user inputs an emotional state.

[0669] After logging in, the user accesses an interface for inputting an emotional state. For example, the user may use a camera to capture a facial expression or a microphone to record a voice. The user may also input an emotional state in text. The input is the user's emotional state, and the output is emotion data. In concrete terms, the user clicks an "emotion input" button, which starts the camera. The user smiles at the camera and clicks the capture button. Or, the user may say into the microphone, "I'm very happy today."

[0670] Step 3:

[0671] The device analyzes the emotional state.

[0672] The device analyzes the emotion data input by the user. For example, it analyzes facial expression data captured by a camera using libraries such as OpenCV to estimate the user's emotional state. In the case of voice data, it uses the Google Cloud Speech-to-Text API to convert the voice to text and perform emotion analysis. The input is emotion data, and the output is the analysis result. In concrete terms, the device analyzes the captured image with OpenCV and quantifies the degree of smile. The voice data is converted to text using the Google Cloud Speech-to-Text API, and the keyword "happy" is extracted.

[0673] Step 4:

[0674] The server receives the analysis results and generates an appropriate quality control digitalization menu.

[0675] The terminal sends the analysis results to the server. The server uses a generative AI model (e.g., GPT-4) to generate an appropriate quality control digitalization menu based on the received emotion data. The input is the analysis result, and the output is the generated menu. In concrete terms, the terminal sends the analysis results to the server in JSON format. The server inputs a prompt sentence into the generative AI model based on the received data, and generates an appropriate menu.

[0676] Step 5:

[0677] The server sends the generated menu to the terminal.

[0678] The server sends the generated menu to the terminal. The data is securely transferred using the HTTPS protocol. The input is the generated menu, and the output is the result of sending it to the terminal. In concrete terms, the server sends the generated menu to the terminal in JSON format. The terminal analyzes the received data and displays it to the user.

[0679] Step 6:

[0680] The user utilizes the provided menu.

[0681] The user checks and uses the quality control digitalization menu displayed on the device. For example, a menu including sharing success stories and positive feedback may be displayed. The input is the provided menu, and the output is the user's actions. Specifically, the user checks the menu displayed on the device and clicks the "Share success stories" link. The user reads the displayed success stories and uses them to help with their own company's quality control.

[0682] (Application example 3)

[0683] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0684] In conventional quality control systems, audit items and risk management for each section are often done manually, which is inefficient. In addition, feedback and support that takes into account the user's emotional state is not provided, which can lead to a decrease in worker motivation and work efficiency. This leads to the issue that the effectiveness of quality control is not fully realized.

[0685] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0686] In this invention, the server includes a means for digitizing the audit items, points of interest, cautions, ideal situations, anticipated risks, and preventive and corrective measures for risks for each section based on a basic flow chart related to a quality control system and product manufacturing, a means for creating a tool that can be announced by a generative AI based on the digitized information, a means for market deployment of the created tool as a digital transformation menu for quality control, mainly for small and medium-sized enterprises, a means for recognizing the emotional state of a user using an emotion engine and adjusting feedback and support content according to the emotional state, and a means for providing positive feedback based on the emotional state. This enables efficient quality control and effective feedback that takes into account the emotional state of the user.

[0687] A "quality control system" is a system that manages a series of processes and methods for maintaining and improving the quality of products and services.

[0688] "Product manufacturing" is the process of assembling raw materials and parts to create a final product.

[0689] A "flow diagram" is a visual representation of a process or procedure, showing the order and relationships of the steps.

[0690] "Audit items" are specific items that should be checked in quality control and product manufacturing.

[0691] A "point of focus" is a point that should be given particular attention when conducting an audit or evaluation.

[0692] "Points to note" are things that you should pay special attention to when proceeding with a task or process.

[0693] "The way things should be" is an ideal state or a standard to aim for.

[0694] A "risk" is a problem or failure that may occur in the quality or manufacturing of a product.

[0695] A "preventive measure" is a measure taken to prevent a risk before it occurs.

[0696] A "corrective action" is a measure taken to correct or improve a problem or risk that has already occurred.

[0697] "Digitization" means recording and storing information in digital form.

[0698] "Generative AI" is a system that uses artificial intelligence technology to generate and process data and information.

[0699] An "announceable tool" is a tool that notifies and presents generated information and data to users.

[0700] "Digital transformation" refers to the innovation of business processes and business models through the use of digital technology.

[0701] An "emotion engine" is a technology that recognizes the user's emotional state and provides appropriate feedback and support.

[0702] "Feedback" means evaluations or advice provided to a User.

[0703] "Positive feedback" is feedback that positively evaluates and encourages a user's actions or achievements.

[0704] As an embodiment of the present invention, the following system configuration and processing procedure will be described.

[0705] System Configuration

[0706] 1. Hardware:

[0707] Camera: Used to capture the face of the worker.

[0708] Server: processes and stores data.

[0709] Terminal: The device used by the worker (e.g. computer, tablet).

[0710] 2. Software:

[0711] OpenCV: A library for image processing.

[0712] EmotionRecognizer: A model for emotion recognition.

[0713] QualityManagementService: Quality management cloud service.

[0714] Generative AI: Artificial intelligence techniques for generating and processing data and information.

[0715] Processing flow

[0716] 1. Data capture:

[0717] The worker's face is captured in real time using a camera connected to the terminal.

[0718] The captured image data is transmitted to a server.

[0719] 2. Emotion recognition:

[0720] The server recognizes the worker's emotional state from the captured images using EmotionRecognizer.

[0721] The recognized emotion data is sent to a quality control cloud service.

[0722] 3. Processing of quality control data:

[0723] Based on basic flow diagrams related to quality control systems and product manufacturing, the server digitizes the audit items and points of focus for each section, points to note, how things should be, anticipated risks, and preventive and corrective measures against risks.

[0724] The digitized information will be created into an announceable tool using generative AI.

[0725] 4. Providing Feedback:

[0726] The server uses an emotion engine to recognize the user's emotional state and adjusts the feedback and support content according to the emotional state.

[0727] Provide positive feedback based on the worker's emotional state. For example, if the worker is happy, show a message like, "Great job! Keep it up."

[0728] Examples

[0729] Consider a scenario in which a worker on a manufacturing line collaborates with a robot to perform quality control: if the worker is happy, the robot will recognize that emotion and provide positive feedback, such as a message like, "Great job! Keep it up."

[0730] Examples of prompt statements

[0731] Program a robot to recognize the emotional state of workers on a production line and provide appropriate feedback. Use a camera for emotion recognition and send quality control data to a cloud service. If a worker is happy, show positive feedback.

[0732] In this way, a system can be realized that enables efficient quality control and effective feedback that takes into account the user's emotional state.

[0733] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0734] Step 1:

[0735] The worker's face is captured in real time using a camera connected to the terminal.

[0736] Input: Camera image

[0737] Data processing: Acquire image data using OpenCV

[0738] Output: Captured image data

[0739] Step 2:

[0740] The server receives the captured image data and recognizes the worker's emotional state using the EmotionRecognizer.

[0741] Input: Captured image data

[0742] Data computation: Applying emotion recognition algorithms using EmotionRecognizer

[0743] Output: Recognized emotion data (e.g., happy, sad, angry, etc.)

[0744] Step 3:

[0745] The server sends the recognized emotion data to a quality control cloud service.

[0746] Input: Recognized emotion data

[0747] Data processing: data format conversion and transmission

[0748] Output: Emotion data stored in a cloud service

[0749] Step 4:

[0750] Based on basic flow diagrams related to quality control systems and product manufacturing, the server digitizes the audit items and points of focus for each section, points to note, how things should be, anticipated risks, and preventive and corrective measures against risks.

[0751] Input: Flow diagram and related data

[0752] Data processing: Automate and organize data using generative AI

[0753] Output: Digitalized audit items and risk management information

[0754] Step 5:

[0755] The server uses generative AI to create tools that can make announcements based on the digitized information.

[0756] Input: Digitalized audit items and risk management information

[0757] Data processing: Generate announcement content using generative AI

[0758] Output: Announcable tools

[0759] Step 6:

[0760] The server uses an emotion engine to recognize the user's emotional state and adjusts the feedback and support content according to the emotional state.

[0761] Input: Recognized emotion data

[0762] Data Computation: Generate feedback content using emotion engine

[0763] Output: Adjusted feedback content

[0764] Step 7:

[0765] The server provides positive feedback based on the worker's emotional state: for example, if the worker is happy, it displays a message like "Great job! Keep it up."

[0766] Input: Adjusted feedback

[0767] Data processing: generating and displaying feedback messages

[0768] Output: A positive feedback message provided to the worker.

[0769] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0770] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0771] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0772] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0773] [Second embodiment]

[0774] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0775] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0776] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0777] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0778] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0779] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0780] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0781] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0782] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0783] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0784] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0785] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0786] "Example 1"

[0787] As one embodiment of the present invention, a means is provided for converting the audit items and points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures against risks, etc., for each section into digital data based on a basic QC flow diagram related to a quality control system and product manufacturing. This digitalization is performed taking into consideration, for example, the work procedures and quality check items for each section, the skill levels of workers, etc.

[0788] "Example 2"

[0789] Furthermore, we will create a tool that can make announcements using chat generation AI based on the digitized information.

[0790] This tool has a function to automatically suggest points to note and areas for improvement at each step of quality control, for example. It also has a function to suggest appropriate audit items, points to focus on, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks in response to questions from users.

[0791] "Example 3"

[0792] Furthermore, the created tools will be provided as a means to market them as a digitalization menu for quality control, primarily for small and medium-sized enterprises. For example, this market development could be provided as a cloud service for small and medium-sized enterprises, and companies could use this service to streamline their own quality control and improve quality.

[0793] The process flow of each embodiment will be described below.

[0794] "Example 1"

[0795] Step 1: Refer to the quality control system and basic QC flow diagram related to product manufacturing, and extract the audit items and points of focus for each section, points to note, the ideal state, anticipated quality risks, and preventive and corrective measures for risks.

[0796] Step 2: The extracted information is registered in a database and digitized. This digitization is carried out taking into consideration, for example, the work procedures and quality check items of each section, the skill levels of the workers, etc.

[0797] "Example 2"

[0798] Step 1: Create a tool that can make announcements using chat generation AI based on the digitized information.

[0799] This tool will have the function of automatically suggesting points to note and areas for improvement at each step of quality control.

[0800] Step 2: Add a function that, in response to user questions, presents appropriate audit items, points to focus on, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks.

[0801] "Example 3"

[0802] Step 1: The created tool will be marketed as a digital transformation menu for quality control, primarily to small and medium-sized enterprises. This market deployment will be provided, for example, as a cloud service for small and medium-sized enterprises. Step 2: By using this service, companies can streamline their own quality control and improve quality.

[0803] Example 1

[0804] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0805] In quality control systems and product manufacturing, there is a demand for a system that can efficiently digitize the audit items, points of interest, cautions, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. for each section, and allow users to easily confirm, correct, and add them. In addition, there is a challenge in providing a tool that uses a generative AI model based on this information to make appropriate announcements in response to user questions.

[0806] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0807] In this invention, the server includes a means for digitizing the audit items, points of interest, cautions, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. for each section based on a basic QC flow chart related to the quality control system and product manufacturing, a means for accessing a database to collect necessary information, and a means for analyzing the collected data and digitizing it while taking into consideration the work procedures, quality check items, and skill levels of workers for each section. This makes it possible to efficiently digitize the audit items, points of interest, cautions, etc. for each section, and for users to easily confirm, correct, and add them.

[0808] A "quality management system" refers to a set of processes and tools for controlling and maintaining the quality of products and services.

[0809] A "QC flow diagram" is a diagram that visually represents each process and procedure in quality control.

[0810] "Audit items" refer to specific items that should be checked or evaluated in quality control or product manufacturing.

[0811] "Points of focus" refers to points that should be given particular attention when conducting an audit or evaluation.

[0812] "Points to note" refers to matters that require special attention when performing work or audits.

[0813] "The ideal state" refers to the ideal or target state in quality control and product manufacturing.

[0814] "Quality risk" refers to factors or circumstances that may affect the quality of a product or service.

[0815] "Preventive measures" refer to measures taken to prevent quality risks.

[0816] "Corrective action" refers to measures taken to resolve a quality problem that has occurred and to prevent its recurrence.

[0817] "Digitization" refers to the process of organizing and storing information in digital form.

[0818] A "generative AI model" refers to a model that uses artificial intelligence technology to generate and analyze data.

[0819] A "prompt" refers to an instruction or question that is input to a generative AI model.

[0820] "Digital transformation" refers to the innovation of business processes and business models through the use of digital technology.

[0821] This invention is a system that digitizes the audit items, points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. for each section based on the basic QC flow chart related to quality control systems and product manufacturing. This system works in cooperation with the server, terminals, and users.

[0822] The server accesses the quality control system database and collects information such as the audit items, points of interest, and points of caution for each section based on the QC flow diagram. Specifically, the server uses a database management system (DBMS) such as MySQL or PostgreSQL to extract the necessary information with SQL queries.

[0823] Next, the server analyzes the collected data. To do so, it uses a Python data analysis library (e.g., Pandas) to organize the data, taking into account the work procedures and quality check items of each section, the skill level of the workers, etc. The analysis results are digitized and saved in JSON format.

[0824] The server sends the digitized information to the terminal using the HTTP protocol. Specifically, the data is sent through a RESTful API. The terminal uses a general device such as a PC or tablet and receives the data through a web browser or a dedicated quality control application.

[0825] The terminal visually displays the received data to the user. For example, it uses HTML and JavaScript to display the data in the form of tables, graphs, etc. Using the terminal interface, the user can check the audit items, points of interest, and points of caution for each section and make corrections or additions as necessary.

[0826] In addition, the server uses a generative AI model based on the digitized information to create a tool that makes appropriate announcements in response to user questions. Based on the prompt text entered by the user, this generative AI model presents appropriate audit items, points of interest, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks.

[0827] As a concrete example, in the product manufacturing section, the following audit items are recorded:

[0828] Checking work procedures: Are the work procedures being followed?

[0829] Quality check items: Checking product dimensions and appearance

[0830] Worker skill level: Do your workers have the required skills?

[0831] The server collects this information from the database and sends it to the terminal. The user can check this information through the terminal and make corrections or additions as necessary.

[0832] Examples of prompts to be input to a generative AI model include:

[0833] "For the quality control of the product manufacturing section, please digitize the following audit items: confirmation of work procedures, quality check items, and worker skill levels."

[0834] By using this prompt sentence, the generative AI model can properly digitize the data and reflect it in the quality control system.

[0835] The above is a specific embodiment for carrying out the present invention.

[0836] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0837] Step 1: Data collection

[0838] The server accesses the quality control system database and collects information such as the audit items, points of interest, and points of caution for each section based on the QC flow diagram. Specifically, the server uses a database management system (DBMS) such as MySQL or PostgreSQL to extract data by executing the SQL query "SELECT FROM qc_flow WHERE section_id = 'product manufacturing'". The input is the database connection information and the SQL query, and the output is the extracted data.

[0839] Step 2: Data analysis

[0840] The server analyzes the collected data. Specifically, it uses a Python data analysis library (e.g. Pandas) to convert the data into a data frame and extracts the work procedures and quality check items for each section, the skill levels of workers, and so on. The input is the collected data, and the output is the analyzed data. For example, a data frame can be used to extract "checking work procedures" and "quality check items."

[0841] Step 3: Digitization

[0842] Based on the parsed data, the server converts the audit items, points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. into JSON format data for each section. The input is the parsed data, and the output is JSON format data. For example, it generates the following JSON data:

[0843] json { "section": "Product Manufacturing", "audit_items": [ { "item": "Check the work procedure", "details": "Are the work instructions being followed?" }, { "item": "Quality check item", "details": "Check product dimensions and appearance" } ], "risk_prevention": "Regular training" }

[0844] Step 4: Send data

[0845] The server transmits the digitized information to the terminal. Specifically, it transmits data through a RESTful API using the HTTP protocol. The input is data in JSON format, and the output is data transmission to the terminal.

[0846] Step 5: Displaying the data

[0847] The terminal receives the data sent from the server and displays it visually to the user. Specifically, it uses HTML and JavaScript to display the data in the form of tables, graphs, etc. The input is the JSON data received from the server, and the output is the visual data that is displayed to the user. For example, to generate a table like this:

[0848] html Audit items detail Check the work procedure Are you following the work instructions? Quality Check Items Checking product dimensions and appearance

[0849] Step 6: User feedback

[0850] Through the terminal, the user checks the audit items, points of focus, and points of caution for each section, and makes corrections or additions as necessary. Specifically, the user uses the terminal interface to edit data and add comments. The input is the user's feedback, and the output is the corrected or added data. For example, the user can modify the details of "quality check items" to "check product dimensions, appearance, and functions."

[0851] Step 7: Leverage generative AI models

[0852] The server uses a generative AI model based on the digitized information to create a tool that makes appropriate announcements in response to user questions. The input is the prompt text entered by the user, and the output is the answer generated by the generative AI model. For example, the following prompt text is used:

[0853] "For the quality control of the product manufacturing section, please digitize the following audit items: confirmation of work procedures, quality check items, and worker skill levels."

[0854] The above is the specific processing flow of the program of this system.

[0855] (Application example 1)

[0856] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0857] In conventional quality control systems, the audit items for each section, prediction of quality risks, and proposal of preventive and corrective measures are often done manually, which is inefficient. In addition, it is difficult to check quality and predict risks in real time, which leads to a problem of reduced accuracy of quality control on the production line. Furthermore, digital transformation of quality control has not progressed well in small and medium-sized enterprises, making effective quality control difficult.

[0858] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0859] In this invention, the server includes: a means for digitizing the audit items, points of interest, points to note, ideal state, expected quality risks, preventive measures and corrective measures for risks for each section based on a basic QC flow diagram related to a quality control system and product manufacturing; a means for creating an announceable tool using a generative AI model based on the digitized information; a means for marketing the created tool as a menu for digital transformation of quality control, mainly for small and medium-sized enterprises; a means for monitoring the work procedures and quality check items of each section in the production line in real time, predicting quality risks, and proposing preventive measures and corrective measures; a means for checking the quality of products using image recognition technology; and a means for predicting quality risks based on past data using a machine learning model. This enables real-time quality control and risk prediction, improves the accuracy of quality control on the production line, and promotes the digital transformation of quality control in small and medium-sized enterprises.

[0860] A "quality control system" is a system that monitors and controls the entire manufacturing process in order to maintain and improve product quality.

[0861] A "QC flow diagram" is a diagram that visually represents each step and process of quality control, and shows the audit items and work procedures for each section.

[0862] "Audit items" are specific items or standards that should be checked for quality control.

[0863] A "point of view" is a point or perspective that requires particular attention in quality control.

[0864] "Points to note" are points that require special attention in each section of quality control.

[0865] "The ideal state" is the standard to be aimed for in quality control.

[0866] A "quality risk" is any factor or situation that may adversely affect the quality of a product.

[0867] "Preventive measures" are measures or procedures to prevent quality risks before they occur.

[0868] "Corrective action" means measures or procedures to resolve a quality problem that has occurred and prevent it from recurring.

[0869] A "generative AI model" is a model that uses artificial intelligence to generate new information and predictions from data.

[0870] An "announceable tool" is a tool that uses a generative AI model to provide appropriate information to users.

[0871] "Digital transformation" refers to the innovation of business processes and business models through the use of digital technology.

[0872] "Real-time monitoring" refers to monitoring the manufacturing process in real time and acquiring and analyzing data instantly.

[0873] "Image recognition technology" is a technology that uses cameras and sensors to analyze images and extract specific information.

[0874] A "machine learning model" is an algorithm that learns patterns based on past data and uses them to make future predictions and classifications.

[0875] As an embodiment of the present invention, a "smart QC robot" equipped with a quality control system will be described as an example.

[0876] System Configuration

[0877] Hardware

[0878] Robot body: A robot installed on a manufacturing line (e.g., an industrial robot)

[0879] Camera sensor: A camera for taking images of the product (e.g. a high-resolution camera)

[0880] Data processing unit: A unit for processing image data and quality data (e.g. high-performance processor).

[0881] software

[0882] Image recognition software: Software for analyzing captured images (e.g. OpenCV)

[0883] Database management system: A system for managing data such as each section's work procedures, quality check items, and worker skill levels (e.g., MySQL)

[0884] Machine learning models: Models for predicting quality risks based on past data (e.g. TensorFlow)

[0885] Generative AI model: A model for creating announceable tools based on digitized information

[0886] Program processing explanation

[0887] Data processing and calculation

[0888] 1. Image recognition: Images of products captured by a camera sensor are analyzed using OpenCV to check quality check items. For example, the positional accuracy and mounting strength of parts are monitored in real time.

[0889] 2. Database management: MySQL is used to manage data such as each section's work procedures, quality check items, and worker skill levels, allowing information required for quality control to be managed centrally.

[0890] 3. Machine Learning: Using TensorFlow, predict quality risks based on past data and suggest preventive or corrective measures. For example, if past data shows frequent occurrences of part misalignment, the risk can be predicted and real-time monitoring can be strengthened.

[0891] Examples and prompts

[0892] As a concrete example, the following prompt sentence is input into the generative AI model.

[0893] Example prompt:

[0894] Please check the quality check items in Section A of the production line and suggest preventive measures if there is high risk. Please make your decision based on the following data.

[0895] Procedure: Parts installation

[0896] Quality check items: Part position accuracy, mounting strength

[0897] Worker skill level: Intermediate

[0898] Past quality risk data: Frequent occurrence of part misalignment

[0899] An example of the response generated:

[0900] We have reviewed the quality check items in Section A. Regarding the positional accuracy of parts, past data has revealed that there have been frequent occurrences of misalignment. As a preventative measure, we suggest that you introduce a system that monitors the mounting position in real time and issues an alert immediately if any misalignment occurs. In addition, regarding the mounting strength, we recommend that you regularly check it with a torque wrench.

[0901] In this way, smart QC robots can control quality in real time and suggest preventive and corrective measures to prevent risks, improving the accuracy of quality control on the production line and promoting the digital transformation of quality control in small and medium-sized enterprises.

[0902] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0903] Step 1:

[0904] The server obtains product image data from the camera sensor. The input is image data from the camera sensor, and the output is image data that can be analyzed. In concrete terms, the camera sensor takes a picture of the product on the production line and sends the image data to the server.

[0905] Step 2:

[0906] The server uses image recognition software (e.g. OpenCV) to analyze the acquired image data. The input is the image data acquired in step 1, and the output is the analysis results of the quality check items. In concrete terms, the image recognition software analyzes the positional accuracy and mounting strength of the parts to check for any abnormalities.

[0907] Step 3:

[0908] The server accesses a database management system (e.g. MySQL) and retrieves data such as the work procedures for each section, quality check items, and the skill levels of workers. The input is a query to the database, and the output is the retrieved data. In concrete terms, the server sends a query to the database and retrieves the required data.

[0909] Step 4:

[0910] The server uses a machine learning model (e.g. TensorFlow) to predict quality risks based on past data. The inputs are the data acquired in step 3 and past quality risk data, and the output is the predicted quality risk. In concrete terms, the machine learning model analyzes past data and predicts current quality risks.

[0911] Step 5:

[0912] The server uses the generative AI model to generate prompt sentences that suggest preventive or corrective actions. The input is the quality risk predicted in step 4, and the output is the generated prompt sentence. In concrete terms, the generative AI model generates prompt sentences that suggest appropriate preventive or corrective actions based on the quality risk.

[0913] Step 6:

[0914] The server announces the generated prompt to the user. The input is the prompt generated in step 5, and the output is the announcement to the user. In concrete terms, the server notifies the user of the generated prompt, and the user takes appropriate action based on it.

[0915] In this way, by clarifying the specific actions and inputs / outputs performed at each step, the process flow of the quality control system can be explained in detail.

[0916] Example 2

[0917] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0918] In conventional quality control systems, audit items, points of focus, points of caution, ideal situations, quality risks, and preventive and corrective measures for risks for each section had to be manually digitized, which took time and effort. In addition, specialized knowledge was required to provide appropriate information in response to user questions, making it difficult to respond quickly. Furthermore, the digitalization of quality control had not progressed in small and medium-sized enterprises, making efficient quality control difficult.

[0919] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0920] In this invention, the server includes a means for generating an announcement using a generative AI model based on digitized quality control information, a means for providing the generated announcement to a user, a means for generating a prompt sentence based on a user's question and inputting the prompt sentence to the generative AI model, and a means for receiving the announcement generated from the generative AI model and displaying it to the user. This enables the automation and rapid provision of information on quality control.

[0921] "Digital quality control information" refers to information recorded in digital format, such as quality control audit items, points of focus, points to note, ideal conditions, quality risks, and preventive and corrective measures against risks.

[0922] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to generate appropriate announcements based on input prompt sentences.

[0923] "Means for generating an announcement" refers to the process of using a generative AI model to create an announcement based on digitized quality control information.

[0924] "Means for providing to a user" refers to a method or system for displaying or notifying a user of a generated announcement.

[0925] A "prompt sentence" is an instruction sentence to be input into a generative AI model, and is generated based on the user's question.

[0926] The term "means for generating a prompt sentence based on a user's question" refers to a process for analyzing a question from a user and creating a corresponding prompt sentence.

[0927] "Means for inputting to a generative AI model" refers to a method or system for inputting the generated prompt sentence into a generative AI model to generate an announcement.

[0928] "Means for receiving an announcement generated from a generative AI model and displaying it to a user" refers to a method or system for receiving an announcement output from a generative AI model and displaying it to a user.

[0929] The present invention is a system that automatically digitizes information about quality control and provides appropriate announcements to users using a generative AI model. A specific embodiment of this system will be described below.

[0930] System Configuration

[0931] server

[0932] The server includes a database, a generative AI model, a prompt sentence generation module, an announcement generation module, and a communication module. The server obtains data related to quality control from the database and generates an announcement using the generative AI model.

[0933] Terminal

[0934] The terminal provides an interface for the user to input a question, transmits the user's question to the server, and displays announcements received from the server to the user.

[0935] User

[0936] The user inputs a question about quality control using the terminal, and the user checks the announcement displayed on the terminal to help improve quality control.

[0937] Hardware and Software Used

[0938] Hardware

[0939] Server: A server with a powerful processor and large memory capacity

[0940] Device: User devices such as computers, tablets, and smartphones

[0941] software

[0942] Generative AI model: A generative AI model that uses natural language processing technology (e.g. GPT-4)

[0943] Database: A database that stores data related to quality control

[0944] Communication module: Software for data communication between the server and the terminal

[0945] Data processing and calculation

[0946] The server retrieves data related to quality control from the database and performs preprocessing. The preprocessed data is used to generate prompt sentences that are input to the generative AI model. The generated prompt sentences are input to the generative AI model to generate appropriate announcements. The generated announcements are provided to the user.

[0947] Examples

[0948] A user uses a terminal to input a question such as "Please tell me what to pay attention to in the product inspection process." The terminal sends this question to the server. The server receives the question and generates a prompt sentence like the following:

[0949] "What should I pay attention to in the product inspection process?"

[0950] The server inputs the generated prompt sentence into the generative AI model, which generates an announcement based on the prompt sentence, such as the following:

[0951] "In the product inspection process, the following points should be noted: 1. Use a detailed checklist based on the inspection standards. 2. When a defect is discovered, identify the cause and take measures to prevent recurrence. 3. Record the inspection results and analyze the data to help improve quality."

[0952] The server transmits the generated announcement to the terminal, which displays it to the user, who can then learn specific points to note and points to improve regarding quality control.

[0953] In this way, quality control information can be automated and provided quickly.

[0954] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0955] Step 1:

[0956] The user enters a question.

[0957] The user uses the terminal interface to input a question about quality control, for example, "Please tell me what points I should pay attention to in the product inspection process." The input question is temporarily stored in the terminal's memory.

[0958] Step 2:

[0959] The terminal sends a question to the server.

[0960] The terminal converts the question entered by the user into JSON format and sends it to the server using an HTTP request. The input is the user's question and the output is the JSON data sent to the server.

[0961] Step 3:

[0962] The server receives the question and generates a prompt.

[0963] The server analyzes the JSON data received from the terminal and extracts the question. It then generates a prompt sentence to input to the generative AI model. For example, it generates a prompt sentence such as, "Please tell me what points to be careful about in the product inspection process." The input is the user's question, and the output is the generated prompt sentence.

[0964] Step 4:

[0965] The server inputs a prompt sentence into the generative AI model.

[0966] The server sends the generated prompt sentence as an API request to the generative AI model. The input is the generated prompt sentence, and the output is the API request sent to the generative AI model.

[0967] Step 5:

[0968] A generative AI model generates the announcements.

[0969] The generative AI model generates announcements about quality control based on the input prompt sentence. For example, it generates an announcement that says, "In the product inspection process, attention should be paid to the following points: 1. Use a detailed checklist based on the inspection criteria. 2. When a defective product is found, identify the cause and take measures to prevent recurrence. 3. Record the inspection results and analyze the data to help improve quality." The input is the prompt sentence, and the output is the generated announcement.

[0970] Step 6:

[0971] The server receives the generated announcement.

[0972] The server receives the announcements returned by the generative AI model and formats them as necessary. The input is the announcement from the generative AI model and the output is the formatted announcement.

[0973] Step 7:

[0974] The server sends the announcement to the terminal.

[0975] The server converts the formatted announcement into JSON format and sends it to the terminal as an HTTP response. The input is the formatted announcement, and the output is the JSON data sent to the terminal.

[0976] Step 8:

[0977] The terminal displays the announcement to the user.

[0978] The terminal analyzes the received JSON data and displays the announcement content on the screen. This allows the user to know specific points to note and areas for improvement regarding quality control. The input is JSON data from the server, and the output is the announcement displayed to the user.

[0979] (Application example 2)

[0980] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the smart glasses 214 will be referred to as a "terminal".

[0981] In conventional quality control systems, it was necessary to manually manage audit items, points of caution, and preventive measures against risks for each section, which was inefficient and prone to human error. It was also difficult to provide prompt and appropriate answers to user questions, and there was a lack of means to effectively analyze quality control history. This made the entire quality control process inefficient, and there was a possibility that preventive and corrective measures for quality risks would be delayed.

[0982] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means. In this invention, the server includes a means for digitizing the inspection items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks, etc. for each section based on a basic quality control flow chart related to a quality control system and product manufacturing, a means for creating a tool that can be announced by a generative AI model based on the digitized information, a means for installing the created tool in a factory robot and announcing in real time points of caution and improvements at each step of quality control, a means for presenting appropriate inspection items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks in response to questions from a user, and a means for collecting data and recording and analyzing the history of quality control. This allows the quality control process to be automated and performed efficiently and accurately.

[0983] A "quality management system" refers to a set of processes and tools for controlling and maintaining the quality of products and services.

[0984] "Product manufacturing" refers to the process of assembling and processing raw materials and parts to create a final product.

[0985] A "quality control flow diagram" is a diagram that visually represents each step and process of quality control.

[0986] "Audit items" refer to specific items that should be checked in each section of quality control.

[0987] "Point of focus" refers to points that require special attention in quality control.

[0988] "Points to note" refer to matters that require special attention at each step of quality control.

[0989] "The ideal state" refers to the ideal or target state in quality control.

[0990] "Quality risk" refers to a risk that may affect the quality of a product or service.

[0991] "Preventive measures" refer to measures taken to prevent quality risks from occurring.

[0992] "Corrective Action" means a measure taken to resolve a quality problem that has occurred.

[0993] "Digitization" refers to recording and storing information in digital form.

[0994] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate text or information.

[0995] An "announceable tool" refers to a tool that uses a generative AI model to communicate information via voice or text.

[0996] A "factory robot" refers to a mechanical device used to perform automated tasks in a factory.

[0997] "Real-time" refers to immediate processing or response without delay.

[0998] "User" refers to a person or organization that uses a system or tool.

[0999] A "question" refers to an inquiry a user makes to a system or tool.

[1000] "Present" refers to showing information or answers to the user.

[1001] "History" refers to past data or records.

[1002] "Recording" refers to storing information for future reference.

[1003] "Analysis" refers to examining data in detail to find meaning and trends.

[1004] As an embodiment of the present invention, a means is provided for digitizing the audit items and points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. for each section based on a quality control system and a basic quality control flow chart related to product manufacturing. A tool that can be announced by a generative AI model is created based on the digitized information, and this is installed in a factory robot. A specific embodiment is described below.

[1005] Hardware and Software Used

[1006] Hardware: Factory robots (e.g. general industrial robots), computers (installed on the robots)

[1007] Software: Python, OpenAI API

[1008] Data processing and calculation

[1009] The server digitizes audit items and points of caution for each section of quality control, preventive measures against risks, etc. The digitized information is converted into a format that can be announced using a generative AI model. Specifically, by inputting the following prompt sentences into the generative AI model, appropriate advice and answers are generated.

[1010] Examples of prompt statements

[1011] Prompt for entering quality control step information: "Quality control step: Final inspection of the product. Please let us know any points of concern or improvements you need to make."

[1012] Prompt for inputting user questions: "User question: What are the risks in this process? Please tell us the appropriate audit items, points of focus, points to note, how things should be, anticipated quality risks, and preventive and corrective measures for the risks."

[1013] Processing flow

[1014] 1. Digitization: The server digitizes the audit items and points of attention for each section based on the quality control flow diagram.

[1015] 2. Use of generative AI models: Using digitized information, a generative AI model is used to convert it into a format that can be announced.

[1016] 3. Announcement: Tools installed on factory robots announce in real time the points to note and areas for improvement at each step of quality control.

[1017] 4. Responding to user questions: In response to questions from users, a generative AI model is used to suggest appropriate audit items and risk countermeasures.

[1018] 5. Data collection and analysis: The server records the quality control history and analyzes the data to continuously improve the quality control process.

[1019] Examples

[1020] For example, during final product inspection in a factory, the robot announces, "In this step, we will focus on visual inspection of the product to check for scratches or dirt." When a worker asks, "What are the risks in this process?", the robot responds, "In this process, there is a risk that the product's appearance may be scratched. As a precaution, please wear gloves before the inspection."

[1021] In this way, the quality control process is automated and can be made efficient and accurate.

[1022] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1023] Step 1:

[1024] The server digitizes the audit items, points to note, and preventive measures against risks for each section based on the quality control flow diagram. Specifically, it receives the information from the quality control flow diagram as input and records it in digital form. The digitized information is stored in a database for use in subsequent processes.

[1025] Step 2:

[1026] The server converts the digitized information into a format that can be announced by the generative AI model. Specifically, the server generates prompts containing audit items and points to note for each section and inputs them into the generative AI model. The generative AI model generates appropriate advice and points to note based on the prompts and outputs them in text format.

[1027] Step 3:

[1028] The server sends the generated text to the factory robot, which converts the received text into speech and announces in real time points to note and areas for improvement at each step of quality control. Specifically, the text is input into a speech synthesis engine to generate voice data.

[1029] Step 4:

[1030] If a user has a question at each step of quality control, the user inputs the question to the factory robot. The factory robot sends the user's question in text format to the server. Specifically, the factory robot converts the user's voice into text using a voice recognition engine and sends the text to the server.

[1031] Step 5:

[1032] The server inputs the user's question into the generative AI model and generates appropriate audit items and risk countermeasures. Specifically, the server generates the user's question as a prompt sentence and inputs it into the generative AI model. The generative AI model generates an appropriate answer based on the prompt sentence and outputs it in text format.

[1033] Step 6:

[1034] The server sends the generated answer to the factory robot. The factory robot converts the received text into speech and provides the answer to the user. Specifically, the text is input to a speech synthesis engine to generate speech data.

[1035] Step 7:

[1036] The server records the quality control history and analyzes the data. Specifically, the data generated at each step and the user's questions and answers are stored in a database and used in subsequent analysis processes. A data analysis engine is used to analyze the quality control history data and extract areas for improvement and risk prevention measures.

[1037] In this way, the quality control process is automated and can be made efficient and accurate.

[1038] Example 3

[1039] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[1040] In conventional quality control systems, audit items, points of focus, points of caution, ideal situations, quality risks, and preventive and corrective measures for risks for each section had to be manually digitized, which was inefficient and prone to human error. In addition, data analysis and report generation were often done manually, which took time and effort, making it difficult for small and medium-sized enterprises to adopt. Another problem was that it was difficult to quickly provide appropriate information when users had questions.

[1041] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1042] In this invention, the server includes a means for collecting quality control data from the terminal and transmitting it to the server, a means for inputting the data received by the server into a generative AI model and detecting patterns and anomalies in the data, and a means for generating a report based on the analysis results of the generative AI model and displaying the report on a dashboard so that the user can view it. This enables automatic collection and analysis of quality control data, and realizes efficient and accurate quality control. In addition, by using the generative AI model, it becomes possible to provide prompt and appropriate information in response to a user's question.

[1043] A "quality management system" refers to a set of processes and tools for controlling and maintaining the quality of products and services.

[1044] A "flow diagram" is a visual representation of the flow of a process or system, showing the relationships between each step or element.

[1045] "Audit items" refer to specific items that are subject to evaluation and inspection in quality control.

[1046] "Point of view" refers to a point or perspective that deserves particular attention in quality control.

[1047] "Points to note" refers to matters that require special attention in quality control.

[1048] "The ideal state" refers to the ideal state or standard to aim for in quality control.

[1049] "Quality risk" refers to risk factors that may affect the quality of a product or service.

[1050] "Preventive measures" refer to measures or means to prevent quality risks from occurring.

[1051] "Corrective action" refers to measures or procedures taken to resolve an encountered quality problem.

[1052] A "generative AI model" refers to a model that uses artificial intelligence technology to generate, analyze, and predict data.

[1053] An "announceable tool" refers to a tool that has the ability to provide information to users using a generative AI model.

[1054] "Terminal" refers to a device for collecting and transmitting data to a server.

[1055] "Server" refers to a computer system for receiving, processing, analyzing, and storing data.

[1056] "Dashboard" refers to an interface that allows users to visually view data and reports.

[1057] "Digital transformation" refers to the innovation of business processes and business models through the use of digital technology.

[1058] This invention is a system for improving the efficiency of quality control systems and achieving digital transformation of quality control in small and medium-sized enterprises. This system is composed of a terminal, a server, and a generative AI model.

[1059] First, the terminal collects quality control data. Specifically, it collects data such as product inspection results and the operating status of the production line. For example, as the inspection results for product A, it collects the number of defective products and detailed data for each inspection item.

[1060] Next, the terminal transmits the collected quality control data to a server. The data is transmitted using a secure communication protocol (e.g., HTTPS). The server inputs the received data into a generative AI model. For example, OpenAI's GPT-4 can be used as the generative AI model.

[1061] The server uses the generative AI model to detect patterns and anomalies in the data. To do this, the server inputs prompts like the following into the generative AI model:

[1062] "Please suggest ways to improve quality control based on the inspection data for product A."

[1063] Generative AI models detect patterns and anomalies in data and generate outputs such as:

[1064] "The defect rate for test item B is high, so we need to reevaluate our testing method."

[1065] The server generates a report containing suggestions for improving quality control and streamlining based on the analysis results of the generative AI model. The report includes specific improvement measures and recommended action plans. For example, the server generates a report like the one below:

[1066] "After analyzing the test data for product A, the following improvements were found:

[1067] 1. Review of the inspection process: Because the defect rate for inspection item B is high, the inspection method needs to be reevaluated.

[1068] 2. Adjustment of production line: The operating rate of the production line is declining, so we should work to improve the efficiency of the line.

[1069] The user accesses the dashboard provided by the server and views the generated report. The user can take measures to improve quality control based on the report. For example, the user can reevaluate the inspection method for inspection item B and make necessary adjustments.

[1070] This system enables automatic collection and analysis of quality control data, realizing efficient and accurate quality control. In addition, by using a generative AI model, it becomes possible to provide prompt and appropriate information in response to user questions. The flow of the identification process in the third embodiment will be described with reference to FIG. 15.

[1071] Step 1:

[1072] The terminal collects quality control data. Specifically, it collects data such as product inspection results and the operating status of the production line. For example, as the inspection results for product A, it collects the number of defective products and detailed data for each inspection item.

[1073] Input: Product inspection results and production line operation status

[1074] Output: Collected quality control data

[1075] Step 2:

[1076] The terminal transmits the collected quality control data to the server. The data is transmitted using a secure communication protocol (e.g., HTTPS).

[1077] Input: Collected quality control data

[1078] Output: Data sent to the server

[1079] Step 3:

[1080] The server inputs the received data into a generative AI model, such as OpenAI's GPT-4.

[1081] Input: Quality control data sent to the server

[1082] Output: The data fed into the generative AI model

[1083] Step 4:

[1084] The server uses the generative AI model to detect patterns and anomalies in the data. To do this, the server inputs prompts like the following into the generative AI model:

[1085] "Please suggest ways to improve quality control based on the inspection data for product A."

[1086] Generative AI models detect patterns and anomalies in data and generate outputs such as:

[1087] "The defect rate for test item B is high, so we need to reevaluate our testing method."

[1088] Input: Quality control data fed into the generative AI model

[1089] Output: Patterns and anomalies detected in the data

[1090] Step 5:

[1091] The server generates a report containing suggestions for improving quality control and streamlining based on the analysis results of the generative AI model. The report includes specific improvement measures and recommended action plans. For example, the server generates a report like the one below:

[1092] "After analyzing the test data for product A, the following improvements were found:

[1093] 1. Review of the inspection process: Because the defect rate for inspection item B is high, the inspection method needs to be reevaluated.

[1094] 2. Adjustment of production line: The operating rate of the production line is declining, so we should work to improve the efficiency of the line.

[1095] Input: Data pattern and anomaly detection results

[1096] Output: Report with suggestions for quality control improvements and efficiency improvements

[1097] Step 6:

[1098] The user accesses the dashboard provided by the server and views the generated report. The user can take measures to improve quality control based on the report. For example, the user can reevaluate the inspection method for inspection item B and make necessary adjustments.

[1099] Input: Reports containing suggestions for quality control improvements and efficiencies

[1100] Output: Quality control improvements that users can view and implement.

[1101] (Application example 3)

[1102] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server", and the smart glasses 214 will be referred to as a "terminal".

[1103] Quality control in small and medium-sized enterprises is currently difficult to carry out efficiently and effectively due to limited resources and lack of expertise. In addition, there is a demand for real-time monitoring of quality data in factories, detection of anomalies, and proposals of specific actions to improve quality, but there is a lack of appropriate tools and systems to achieve this. For this reason, a comprehensive system is needed to support the digital transformation of quality control and improve quality.

[1104] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means. In this invention, the server includes a means for digitizing the audit items and points of interest, points of caution, ideal situations, expected quality risks, preventive measures and corrective measures for risks for each section based on a basic quality control flow diagram related to a quality control system and product manufacturing, a means for creating a tool that can be announced by a generative AI model based on the digitized information, a means for marketing the created tool as a digital transformation menu for quality control mainly for small and medium-sized enterprises, a means for providing a quality control support application to be installed in a factory robot, a means for monitoring quality data in real time and issuing an alert when an abnormality is detected, and a means for analyzing and predicting quality data and proposing specific actions for quality improvement. This makes it possible for even small and medium-sized enterprises to efficiently and effectively perform quality control, thereby improving quality.

[1105] A "quality control system" is a system that manages a series of processes and methods for maintaining and improving the quality of products and services.

[1106] A quality control flow diagram is a visual representation of each process and procedure of quality control, and indicates the audit items, points of focus, and points of caution for each section.

[1107] "Audit items" refer to specific items or standards that should be checked in quality control.

[1108] A "point of view" is a point or perspective to which special attention should be paid in quality control.

[1109] "Points to note" refer to matters or risks that require special attention in quality control.

[1110] "The ideal state" refers to the standard to be aimed for in quality control.

[1111] "Quality risk" refers to a risk or issue that could affect the quality of a product or service.

[1112] "Preventive measures" refer to specific measures or means to prevent quality risks before they occur.

[1113] "Corrective action" refers to specific measures or procedures taken to resolve an encountered quality problem.

[1114] A "generative AI model" is a model that uses artificial intelligence technology to generate and analyze data.

[1115] An "announceable tool" is a tool that uses a generative AI model to provide information to users.

[1116] "Digital transformation" refers to the effort to use digital technology to innovate operational processes and business models in order to improve efficiency and create value.

[1117] A "factory robot" is a robot used to automate work in a factory.

[1118] "Quality control support application" means a software application for supporting quality control.

[1119] "Real-time monitoring" refers to the instantaneous monitoring of ongoing data and situations.

[1120] "Detecting anomalies" refers to discovering conditions or problems that are different from the norm.

[1121] "Issuing an alert" refers to issuing a warning when an abnormality or problem occurs.

[1122] "Analysis and prediction of quality data" refers to analyzing collected quality data and predicting future quality states.

[1123] "Proposing specific actions" refers to proposing specific measures or steps that should be taken to improve quality.

[1124] This invention is a system that supports the digital transformation of quality control for small and medium-sized enterprises, and provides a quality control support application that is installed on factory robots. Based on a basic quality control flow chart related to quality control systems and product manufacturing, this system digitizes the audit items and points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures for risks for each section, etc., and creates tools that can be announced using a generative AI model.

[1125] The server first digitizes the audit items, points of interest, cautions, ideal conditions, quality risks, preventive measures, and corrective measures for each section based on the quality control flow diagram. This digitization process can be automated using AI technology. Next, a generative AI model is built based on the digitized information, and an announceable tool is created to provide appropriate information to users. This tool has the function of automatically presenting appropriate audit items, points of interest, cautions, ideal conditions, quality risks, preventive measures, and corrective measures in response to user questions.

[1126] Furthermore, Sarver will market the tool it created as a digital transformation menu for quality control, primarily for small and medium-sized enterprises, enabling them to efficiently and effectively carry out quality control and improve quality.

[1127] The quality control support application installed on factory robots has the ability to monitor quality data in real time and issue an alert if an abnormality is detected. This application analyzes and predicts quality data and proposes specific actions to improve quality. Specifically, it collects quality data such as temperature, humidity, and pressure, and detects anomalies using a generative AI model. If an abnormality is detected, it issues an alert to the factory manager, urging them to take prompt action.

[1128] For example, the quality data of products manufactured in a factory can be collected in real time and used to detect anomalies. If an anomaly is detected, an alert can be sent to the factory manager to promptly take action.

[1129] Examples of prompts to be input to a generative AI model include the following:

[1130] "Use quality data from within your factory to build an AI model that detects anomalies and suggests specific actions to improve quality. Data includes information such as temperature, humidity, and pressure."

[1131] In this way, by developing a quality control support application to be installed on factory robots, it is possible to make quality control within the factory more efficient and improve quality.

[1132] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1133] Step 1:

[1134] The server digitizes the audit items, points of focus, cautions, ideal conditions, quality risks, preventive measures, and corrective actions for each section based on the quality control flow diagram. Specifically, it analyzes the quality control flow diagram, extracts information from each section, and stores it in a database. This digitization process can be automated using AI technology. The input is the quality control flow diagram, and the output is data such as audit items and points of focus stored in the database.

[1135] Step 2:

[1136] The server builds a generative AI model based on the digitized information. Specifically, it retrieves data such as audit items and points of interest from the database and uses this to train the generative AI model. The input is the data retrieved from the database, and the output is the trained generative AI model.

[1137] Step 3:

[1138] The server uses the generative AI model to create an announceable tool. Specifically, the server uses the generative AI model to develop a tool that has the function of presenting appropriate audit items, points of interest, points of caution, ideal situations, quality risks, preventive measures, and corrective measures in response to user questions. The input is the generative AI model, and the output is the announceable tool.

[1139] Step 4:

[1140] The server will market the created tool as a digital transformation menu for quality control, mainly for small and medium-sized enterprises. Specifically, it will provide it as a cloud service, allowing companies to use the service. The input is an announceable tool, and the output is a tool provided as a cloud service.

[1141] Step 5:

[1142] The factory robot installs the quality control support application. Specifically, the quality control support application provided by the server is downloaded and installed in the robot's system. The input is the quality control support application, and the output is the installed application.

[1143] Step 6:

[1144] Factory robots monitor quality data in real time and detect abnormalities. Specifically, they analyze temperature, humidity, pressure, and other data obtained from sensors in real time and issue an alert if an abnormality is detected. The input is the quality data from the sensors, and the output is an alert that an abnormality has been detected.

[1145] Step 7:

[1146] The factory robot analyzes and predicts quality data and proposes specific actions to improve quality. Specifically, it uses a generative AI model to analyze quality data, predict future quality states, and propose necessary measures. The input is quality data, and the output is a proposal for specific actions to improve quality.

[1147] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[1148] "Example 1"

[1149] As one embodiment of the present invention, a system incorporating an emotion engine is provided. This system includes a means for digitizing the audit items and points of interest, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks for each section based on a basic QC flow diagram related to quality control systems and product manufacturing, a means for creating a tool that can be announced via Chat GPT based on the digitized information, and a means for market deployment of the created tool as a quality control DX menu, mainly for small and medium-sized enterprises.

[1150] "Example 2"

[1151] The emotion engine recognizes the user's emotions and presents appropriate audit items, points of focus, cautions, ideal situations, anticipated quality risks, and preventive and corrective measures for risks according to the user's emotional state. For example, if a user is feeling stressed, the emotion engine recognizes that information and presents appropriate preventive and corrective measures to reduce stress.

[1152] "Example 3"

[1153] In addition, the emotion engine adjusts how it presents the quality control digitalization menu according to the user's emotional state. For example, if a user is feeling happy, the emotion engine will recognize that information and present a quality control digitalization menu that amplifies the joy. This enables more effective quality control that takes the user's emotional state into account.

[1154] The process flow of each embodiment will be described below.

[1155] "Example 1"

[1156] Step 1: Based on a basic QC flow diagram related to the quality control system and product manufacturing, digitize the audit items and points of focus for each section, points to note, how things should be, anticipated quality risks, and preventive and corrective measures for risks.

[1157] Step 2: Create a tool that can make announcements using chat generation AI based on the digitized information

[1158] do.

[1159] Step 3: Market the created tool as a quality control digitalization menu, primarily for small and medium-sized enterprises.

[1160] "Example 2"

[1161] Step 1: Recognize the user's emotion using the emotion engine.

[1162] Step 2: The emotion engine presents appropriate audit items, points of focus, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks based on the recognized emotional state.

[1163] "Example 3"

[1164] Step 1: Recognize the user's emotion using the emotion engine.

[1165] Step 2: The emotion engine adjusts how it presents the quality control digitalization menu based on the recognized emotional state.

[1166] Example 1

[1167] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[1168] In conventional quality control systems and product manufacturing, information such as audit items, points of focus, points of caution, ideal situations, quality risks, preventive and corrective measures for risks, etc. for each section had to be managed manually, which was inefficient and prone to human error. In addition, specialized knowledge was required to generate announcements based on this information, which made it difficult for small and medium-sized enterprises to introduce.

[1169] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1170] In this invention, the server includes a means for converting the audit items and points of interest, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks for each section into digital data based on a quality control system and a basic quality control flow chart related to product manufacturing, a means for storing the data using a database management system, and a means for generating announcements using an emotion engine. This enables efficient management of information related to quality control and automatic generation of announcements using generative artificial intelligence.

[1171] A "quality control system" is a system that manages a series of processes and methods for maintaining and improving the quality of products and services.

[1172] "Product manufacturing" is the process of assembling and processing raw materials and parts to create a final product.

[1173] A "quality control flow diagram" is a visual representation of each step or process of quality control, showing the audit items and procedures for each section.

[1174] "Audit items" are specific items or standards that should be checked in quality control and product manufacturing.

[1175] A "point of focus" is a point or perspective that should be given particular attention when conducting an audit or check.

[1176] "Points to note" are matters that require special attention when performing work or audits.

[1177] "The ideal state" is the standard to be aimed for in quality control and product manufacturing.

[1178] A "quality risk" is any factor or situation that can affect quality.

[1179] "Preventive measures" are measures or procedures to prevent quality risks before they occur.

[1180] "Corrective action" means measures or procedures to resolve a quality problem that has occurred and prevent it from recurring.

[1181] "Digitization" is the process of recording and managing information in digital form.

[1182] "Generative artificial intelligence" is an artificial intelligence technology that uses natural language processing and machine learning to generate text and announcements.

[1183] An "announceable tool" is a tool that uses generative artificial intelligence to automatically provide information.

[1184] "Digital transformation" refers to the effort to use digital technology to innovate operational processes and business models in order to improve efficiency and create value.

[1185] A "database management system" is a system for efficiently storing, managing, and searching data.

[1186] An "emotion engine" is a technology that analyzes emotions from text and voice and generates appropriate responses.

[1187] This invention is a system that uses a quality control system and a basic quality control flow diagram related to product manufacturing to digitize the audit items, points of focus, points of caution, ideal situations, anticipated quality risks, preventive and corrective measures against risks, etc. for each section, and generates announcements using generative artificial intelligence.

[1188] System Configuration

[1189] Data collection

[1190] Based on the quality control system and basic quality control flow chart related to product manufacturing, users input information such as audit items for each section, points to focus on, points to note, ideal situations, anticipated quality risks, preventive and corrective measures against risks, etc. Input is done using a dedicated input form.

[1191] Data storage

[1192] The server takes the information entered by the user and stores it using a database management system (e.g., MySQL). The server runs SQL queries to insert the entered information into the appropriate tables.

[1193] Generate an announcement

[1194] The server generates announcements using generative AI (e.g., ChatGPT by OpenAI) based on the information stored in the database. The server retrieves the necessary information from the database and generates a prompt for the generative AI.

[1195] Creating tools

[1196] The server creates tools based on the generated announcements to be marketed as quality control digital transformation menus for small and medium-sized enterprises. The server develops the tools as web applications using programming languages ​​such as Python and JavaScript.

[1197] Examples

[1198] Section: Product Inspection

[1199] Audit item: Compliance with inspection procedures

[1200] Focus: Does the inspection procedure follow standard operating procedures?

[1201] Important points: Are test results recorded accurately?

[1202] What should happen: All testing is done according to standard operating procedures and is accurately recorded.

[1203] Potential quality risks: Non-compliance with inspection procedures resulting in the release of defective products

[1204] Preventive measures against risks: Regular review and education of inspection procedures

[1205] Corrective Action: Immediate correction when non-compliance with inspection procedures is discovered

[1206] Example prompt:

[1207] "What are the audit items in the product inspection section? Also, please tell us about the points to focus on and points to note regarding compliance with the inspection procedures, the ideal situation, anticipated quality risks, and preventive and corrective measures for risks."

[1208] In this way, the user generates the system's program, and the server executes the program to collect data, store it in the database, generate announcements using generative AI, and create tools. Using concrete examples and prompt sentences makes it easier to input data into the generative AI model.

[1209] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1210] Step 1: Data collection

[1211] Input: Based on the quality control system and basic quality control flow diagram related to product manufacturing, the user inputs information such as the audit items, points of focus, points of caution, ideal state, anticipated quality risks, and preventive and corrective measures for risks for each section.

[1212] Specific operation: The user enters information for each section using a dedicated input form. For example, the user enters "Compliance with inspection procedures" as an audit item in the product inspection section.

[1213] Output: The entered information is sent to the server.

[1214] Step 2: Save your data

[1215] Input: The server receives information entered by the user.

[1216] What Happens: The server uses a database management system (e.g., MySQL) to execute a SQL query that inserts the received information into the appropriate tables, for example "INSERT INTO qc_data (section, audit_item, focus_point, caution, ideal_state, risk, preventive_action, corrective_action) VALUES (...)".

[1217] Output: The information is stored in a database.

[1218] Step 3: Generate an announcement

[1219] Input: The server retrieves information stored in a database.

[1220] Specific operation: The server retrieves the necessary information from the database and generates a prompt for generative artificial intelligence (e.g., ChatGPT of OpenAI). For example, it generates a prompt such as "What are the audit items in the product inspection section?" and sends it to ChatGPT.

[1221] Output: The generated announcement from ChatGPT is returned.

[1222] Step 4: Creating the tool

[1223] Input: The server receives the generated announcement.

[1224] Specific operation: The server develops tools as web applications using programming languages ​​such as Python and JavaScript. For example, it uses the Django framework to create a dashboard where users can check announcements.

[1225] Output: The finished tool is generated.

[1226] Step 5: Market launch

[1227] Input: The user receives the completed tool.

[1228] Specific Actions: The user demonstrates the tool and explains the benefits of its implementation to the company, for example emphasizing that the tool will improve the efficiency of quality control.

[1229] Output: The tools are provided to SMEs and deployed in the market.

[1230] (Application example 1)

[1231] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[1232] Traditional quality control systems and the management of audit items and quality risks based on QC flow charts in product manufacturing are often done manually, which is inefficient and prone to human error. Feedback to workers is also one-way, making it difficult to provide appropriate guidance based on the worker's emotions and situation. Furthermore, digital transformation (DX) of quality control has not progressed well in small and medium-sized enterprises, raising concerns about a decline in competitiveness. To solve these issues, a system that allows for real-time monitoring and feedback is needed.

[1233] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1234] In this invention, the server includes a means for digitizing the audit items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks for each section based on a basic QC flow diagram related to the quality control system and product manufacturing, a means for creating a tool that can be announced by generative AI based on the digitized information, a means for market deployment of the created tool as a quality control DX menu mainly for small and medium-sized enterprises, a means for being installed in a factory robot and monitoring work procedures and quality check items in real time, a means for providing appropriate feedback to workers using an emotion engine, and a means for making announcements and instructions to workers using generative AI. This makes it possible to improve the efficiency and accuracy of quality control, provide appropriate feedback to workers, and DX quality control in small and medium-sized enterprises.

[1235] A "quality control system" is a system for monitoring and controlling the manufacturing process and product quality in order to maintain and improve product quality.

[1236] "Product manufacturing" is the process of assembling or processing raw materials and parts to create a final product.

[1237] A "QC flow diagram" is a visual representation of the procedures and processes for quality control, and is intended to clarify the audit items and work procedures for each section.

[1238] An "audit item" is an item in quality control or product manufacturing that is evaluated or inspected based on specific standards or specifications.

[1239] A "point of focus" is a point that should be given special attention or observed in quality control or product manufacturing.

[1240] "Points to note" are areas in quality control or product manufacturing where mistakes or problems are likely to occur, or matters that require special attention.

[1241] "The ideal state" refers to the ideal state or standard to aim for in quality control and product manufacturing.

[1242] A "quality risk" is any factor or situation that may affect the quality of a product.

[1243] "Preventive measures" are measures or procedures taken to prevent quality risks before they occur.

[1244] "Corrective action" means measures or procedures taken to resolve an existing quality problem and prevent its recurrence.

[1245] "Digitization" is the process of recording and storing information or data in a digital format.

[1246] "Generative AI" is an artificial intelligence technology that uses natural language processing and machine learning to generate text, speech, and other data.

[1247] An "announceable tool" is a tool that uses generative AI to automatically convey specific information or instructions to users.

[1248] The "DX Menu" is a list of specific measures and services to promote digital transformation.

[1249] A "factory robot" is a robot used to automate tasks in a manufacturing environment.

[1250] "Real-time monitoring" is a function that allows you to instantly monitor and check ongoing processes and situations.

[1251] An "emotion engine" is an artificial intelligence technology that generates appropriate feedback based on the user's emotions and situation.

[1252] "Feedback" is evaluation, criticism, or advice given in response to a specific action or result.

[1253] An "announcement" is the act of conveying specific information or instructions to a user.

[1254] As an embodiment of the present invention, we provide a system that digitizes the audit items and points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures against risks, etc. for each section based on a basic QC flow chart related to quality control systems and product manufacturing. A specific embodiment of this system is described below.

[1255] System Configuration

[1256] 1. Data collection method

[1257] Based on the quality control system and basic QC flow charts related to product manufacturing, the server digitizes the audit items, points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. for each section. This includes automated data processing using AI technology.

[1258] 2. How to create generative AI tools

[1259] The server uses the digitized information to create tools that can be announced using generative AI. These tools have the ability to automatically present appropriate audit items, points of interest, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks in response to user questions.

[1260] 3. Digital transformation menu development methods

[1261] Sarver will market the tool it created as a digitalization menu for quality control, primarily for small and medium-sized enterprises. This menu aims to improve the efficiency and accuracy of quality control.

[1262] 4. Real-time monitoring methods

[1263] The factory robot monitors each section's work procedures and quality check items in real time, including collecting data using cameras and sensors.

[1264] 5. Emotion Engine Feedback Measures

[1265] The factory robot uses an emotion engine to provide appropriate feedback to workers, for example by gently pointing out mistakes and suggesting ways to improve.

[1266] 6. Generative AI Announcement Methods

[1267] The server uses generative AI to make announcements and give instructions to workers, allowing them to receive appropriate instructions in real time.

[1268] Hardware and Software Used

[1269] Hardware: Factory robots, cameras, sensors

[1270] Software: AI technology (e.g. ChatGPT by OpenAI), emotion engine

[1271] Examples

[1272] For example, if a worker is working in a dark environment in a factory, the factory robot's camera will detect the brightness of the frame and gently point it out using the emotion engine. Specifically, it will generate a prompt sentence like the following:

[1273] Examples of prompt statements

[1274] Communicate the following message to workers in a gentle tone: The lighting is too dim. Please adjust the lighting.

[1275] In this way, the system can perform quality control in real time and provide appropriate feedback to workers, which will improve the efficiency and accuracy of quality control, provide appropriate feedback to workers, and enable digital transformation of quality control in small and medium-sized enterprises.

[1276] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1277] Step 1:

[1278] The server digitizes the audit items, points of interest, points to note, ideal conditions, anticipated quality risks, and preventive and corrective measures for risks for each section based on the quality control system and basic QC flow diagram related to product manufacturing. It receives the QC flow diagram and related data as input, and uses AI technology to record and store this information in digital format. The output is the digitized audit items and risk information.

[1279] Step 2:

[1280] The server creates tools that can be announced using generative AI based on the digitized information. It receives digitized audit items and risk information as input, and uses a generative AI model (e.g., OpenAI's ChatGPT) to generate tools that automatically present appropriate audit items, points of interest, cautions, ideal situations, quality risks, and preventive and corrective actions in response to user questions. The announceable tool is obtained as output.

[1281] Step 3:

[1282] The server will market the created tools as a DX menu for quality control, primarily to small and medium-sized enterprises. It will receive announceable tools as input and provide them to small and medium-sized enterprises through marketing strategies and sales channels. As output, the DX menu will be marketed.

[1283] Step 4:

[1284] The factory robot monitors the work procedures and quality check items of each section in real time. It receives data from cameras and sensors as input, processes images and analyzes the sensor data, and obtains real-time monitoring data as output.

[1285] Step 5:

[1286] The factory robot uses an emotion engine to provide appropriate feedback to workers. It receives real-time monitoring data as input and uses the emotion engine to generate feedback according to the worker's situation. As an output, a feedback message for the worker is obtained.

[1287] Step 6:

[1288] The server uses generative AI to make announcements and instructions to the workers. It receives feedback messages as input and uses a generative AI model to generate specific announcements and instructions. As output, it obtains announcements and instructions for the workers.

[1289] Specifically, for example, if a worker is working in a dark environment in a factory, the factory robot's camera detects the brightness of the frame in step 4, and in step 5 uses the emotion engine to generate a gentle feedback message saying, "The lighting is too dim. Please adjust the lighting." In step 6, the server uses generative AI to announce this message to the worker.

[1290] Example 2

[1291] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[1292] In conventional quality control systems and product manufacturing processes, it was necessary to manually digitize the audit items, points of interest, points of caution, ideal situations, anticipated risks, and preventive and corrective measures for risks for each section, which was inefficient and prone to human error. In addition, it was difficult to quickly provide appropriate information in response to questions from users, especially when a response based on the user's emotional state was required. This led to the slow progress of digital transformation of quality control, and there was an issue that its introduction was delayed, especially in small and medium-sized enterprises.

[1293] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1294] In this invention, the server includes a means for digitizing the audit items, points of interest, points of caution, ideal situations, anticipated risks, preventive measures and corrective measures for risks for each section based on a basic flow diagram related to the quality control system and product manufacturing, a means for creating a tool that can be announced by the generative AI model based on the digitized information, and a means for receiving and analyzing user input, recognizing the user's emotions with an emotion engine, sending prompt sentences to the generative AI model, receiving a response from the generative AI model, and presenting the response to the user. This makes it possible to automatically present points of caution and improvements at each step of quality control and quickly provide appropriate information in response to user questions. It also makes it possible to respond according to the user's emotional state, making it easier to advance the digital transformation of quality control. Its introduction is particularly promoted in small and medium-sized enterprises.

[1295] A "quality management system" refers to a set of processes and tools for controlling and maintaining the quality of products and services.

[1296] "Product manufacturing" refers to the series of processes that assemble raw materials and parts to create a final product.

[1297] A "flow diagram" is a visual representation of the flow of a process or system.

[1298] "Audit items" refer to specific points that should be checked in quality control and product manufacturing.

[1299] "Points of focus" refers to points that should be given special attention during an audit or evaluation.

[1300] "Points to note" refers to things that should be taken into consideration in a particular process or task.

[1301] "The way things should be" refers to an ideal or targeted state.

[1302] "Potential risk" refers to problems or dangers that may occur in a particular process or situation.

[1303] "Preventive measures" refer to specific measures taken to prevent risks from occurring.

[1304] "Corrective action" refers to a specific measure taken to correct an existing problem or defect.

[1305] "Digitization" refers to recording and storing information in digital form.

[1306] A "generative AI model" refers to a model that is trained using artificial intelligence techniques to perform a specific task.

[1307] "Announceable Tool" refers to a tool that uses a generative AI model to provide information to a user.

[1308] An "emotion engine" refers to technology that recognizes a user's emotional state and responds accordingly.

[1309] A "prompt" refers to text containing instructions or questions that are input to a generative AI model.

[1310] "Digital transformation" refers to the innovation of business processes and business models through the use of digital technology.

[1311] The term "small and medium-sized enterprises" refers to relatively small businesses, generally defined in terms of the number of employees and sales.

[1312] This invention is a system that converts the audit items and points of interest, points to note, ideal situations, anticipated risks, preventive and corrective measures against risks, etc. for each section into digital data based on basic flow charts related to quality control systems and product manufacturing, and provides appropriate information to users using a generative AI model. A specific embodiment of this system is described below.

[1313] Based on the quality control system and basic flow diagrams related to product manufacturing, the server digitizes the audit items and points of focus for each section, points to note, ideal situations, anticipated risks, and preventive and corrective measures for risks. This digitization can be automated using artificial intelligence technology. For example, natural language processing (NLP) technology can be used to extract necessary information from documents and store it in a database.

[1314] Next, the server uses a generative AI model (e.g., OpenAI's GPT-4) based on the digitized information to create a tool that can be announced to the user. This tool has the functions of receiving and analyzing the user's input, recognizing the user's emotions with an emotion engine, sending prompt sentences to the generative AI model, receiving responses from the generative AI model, and presenting the responses to the user.

[1315] As a concrete example, if a user uses a terminal to input "What are the quality risks of this product?", the server receives this input and analyzes it using NLP technology. Based on the analysis results and the emotion recognition results of the emotion engine, it sends the following prompt sentence to the generative AI model.

[1316] Example prompt:

[1317] User: What are the quality risks of this product?

[1318] The generative AI model analyzes the prompt sentence and generates an appropriate response, for example, "Possible quality risks for this product include defects during the manufacturing process, poor quality raw materials, and an inappropriate storage environment. As preventive measures against these risks, it is important to regularly audit the manufacturing process, inspect the quality of raw materials, and maintain an appropriate storage environment."

[1319] The server receives the response from the generative AI model, sends it to the terminal and displays it on the user's screen, allowing the user to quickly obtain specific information about quality control.

[1320] Also, if the user is feeling stressed, the emotion engine will recognize that information and suggest appropriate preventive or corrective measures to reduce stress. For example, if a user types, "I've been feeling stressed lately because of my quality control job," the generative AI model will generate a response like this:

[1321] Example prompt:

[1322] User: I've been feeling stressed lately in my quality control job.

[1323] Example response of the generative AI model:

[1324] Server: It sounds like you're stressed. Try these preventative measures:

[1325] 1. Reprioritize your work and focus on the tasks that matter

[1326] 2. Take regular breaks and make time to refresh

[1327] 3. Communicate with your team members and ask for support

[1328] These measures may help reduce stress.

[1329] In this way, the system operates in cooperation with the server, terminals, and users, automatically presenting points of caution and areas for improvement at each step of quality control, and making it possible to quickly provide appropriate information in response to user questions. It also makes it possible to respond according to the user's emotional state, making it easier to advance the digital transformation of quality control. This will encourage its adoption especially in small and medium-sized enterprises.

[1330] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1331] Step 1:

[1332] Receiving user input

[1333] A user uses a terminal to input a question or comment about quality control. For example, the user inputs "What are the quality risks of this product?" and clicks the send button. The input data is sent from the terminal to the server.

[1334] Step 2:

[1335] Parsing input data

[1336] The server analyzes the input data received from the user. Specifically, it uses natural language processing (NLP) technology to understand the content and intent of the question. For example, it extracts the keyword "quality risk" and understands the intent of the question. The input data is in text format, and the output is structured data as the analysis result.

[1337] Step 3:

[1338] Recognize user emotions with an emotion engine

[1339] The server uses an emotion engine to recognize the user's emotional state from the input. For example, it may determine that the user is feeling stressed based on the tone and context of the words in the input sentence. The input data is the parsed text and the emotion recognition algorithm, and the output is data that indicates the user's emotional state.

[1340] Step 4:

[1341] Sending prompts to generative AI models

[1342] The server sends a prompt sentence to the generative AI model based on the analysis results and the emotional state. The prompt sentence includes the user's question and emotional state. For example, a prompt sentence containing information such as "The user is asking about quality risks and is feeling stressed" is generated. The input data is the analysis results and the emotional state data, and the output is the generated prompt sentence.

[1343] Step 5:

[1344] Receiving responses from generative AI models

[1345] The generative AI model generates an appropriate response based on the prompt sentence and returns it to the server. For example, it generates a response that reads, "Possible quality risks for this product include defects during the manufacturing process, poor quality raw materials, and an inappropriate storage environment. As preventive measures against these risks, it is important to regularly audit the manufacturing process, inspect the quality of raw materials, and maintain an appropriate storage environment." The input data is the prompt sentence, and the output is the generated response sentence.

[1346] Step 6:

[1347] Present the response to the user

[1348] The server presents the response received from the generative AI model to the user. Specifically, the user can check the answer by viewing it on the screen of the device. The input data is the generated response sentence, and the output is the text displayed on the user's device.

[1349] In this way, the system works in cooperation with the server, terminal, and user, automatically suggesting points to note and areas for improvement at each step of quality control, and making it possible to quickly provide appropriate information in response to user questions.

[1350] (Application example 2)

[1351] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the smart glasses 214 will be referred to as a "terminal".

[1352] In conventional quality control systems, it was necessary to manually manage the audit items, points of focus, points of caution, ideal situations, anticipated quality risks, and preventive and corrective measures for risks for each section, which was inefficient and prone to human error.In addition, there was also the issue of not being able to provide appropriate information according to the user's emotional state, making it difficult to provide appropriate support to users who felt stressed or anxious.

[1353] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1354] In this invention, the server includes a means for digitizing the audit items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks for each section based on a basic QC flow diagram related to quality control systems and product manufacturing, a means for creating a tool that can be announced by a chat generation AI based on the digitized information, a means for market deployment of the created tool as a quality control DX menu mainly for small and medium-sized enterprises, and a means for presenting appropriate audit items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks according to the user's emotional state using an emotion recognition engine. This makes it possible to improve the efficiency of quality control and provide appropriate information according to the user's emotional state.

[1355] A "quality control system" refers to the management methods and processes for maintaining and improving the quality of products and services.

[1356] A "QC flow diagram" is a visual representation of each step or process of quality control.

[1357] "Audit items" refer to specific items that should be checked in each section of quality control.

[1358] "Point of focus" refers to points that require special attention in quality control.

[1359] "Points to note" refers to matters that require special attention at each step of quality control.

[1360] "The ideal state" refers to the ideal or target state in quality control.

[1361] "Quality risk" refers to factors that may adversely affect the quality of a product or service.

[1362] "Preventive measures" refer to measures taken to prevent quality risks from occurring.

[1363] "Corrective Action" means a measure taken to resolve a quality problem that has occurred.

[1364] "Digitization" refers to recording and storing information in digital form.

[1365] "Chat generation AI" refers to artificial intelligence that uses natural language processing technology to generate dialogue with users.

[1366] "Emotion recognition engine" refers to technology for analyzing and recognizing a user's emotional state.

[1367] The "DX menu" refers to specific measures and plans for promoting digital transformation.

[1368] The following system configuration is necessary to implement this invention. The server has a means for digitizing the audit items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks for each section based on the quality control system and basic QC flow diagram related to product manufacturing. It also includes a means for creating a tool that can be announced by a chat generation AI based on the digitized information. In addition, it has a means for market deployment of the created tool as a quality control DX menu, mainly for small and medium-sized enterprises. It also includes a means for presenting appropriate audit items, points of interest, cautions, ideal state, expected quality risks, preventive measures and corrective measures for risks according to the user's emotional state using an emotion recognition engine.

[1369] The server uses a database management system (DBMS) to digitize the audit items, points of interest, and points of caution required for each section of the quality control system. The digitized information is passed through a generative AI model (e.g., OpenAI's API) that uses natural language processing technology to provide appropriate announcements to users. An emotion recognition engine (e.g., EmotionRecognizer) is used to recognize the user's emotional state.

[1370] As a specific example, if a user asks, "What are the quality risks of this product?" and the emotion recognition engine determines that the user is stressed, the generated advice might be, "Possible quality risks for this product include wear of parts and defects in the manufacturing process. To reduce stress, we recommend that you perform regular maintenance and quality checks."

[1371] An example of a prompt is:

[1372] User Question: What are the quality risks of this product?

[1373] User Emotion: Stress

[1374] Please present appropriate audit items, points of focus, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks.

[1375] This system will enable more efficient quality control and provide appropriate information according to the user's emotional state.

[1376] The flow of the identification process in the application example 2 will be described with reference to FIG.

[1377] Step 1:

[1378] The server digitizes the audit items and points of interest for each section, points to note, ideal conditions, anticipated quality risks, and preventive and corrective measures for risks, based on the quality control system and basic QC flow diagram related to product manufacturing. The input required is the QC flow diagram and related quality control data, and the output is information such as audit items and points of interest stored in a digital format in a database. Specifically, the server analyzes the QC flow diagram, extracts information for each section, and stores it in the database.

[1379] Step 2:

[1380] The server creates a tool that can make announcements using chat generation AI based on the digitized information. The input requires information such as the audit items and points of interest digitized in step 1, and the output is a generative AI model for making appropriate announcements to users. In concrete terms, the server retrieves the necessary information from the database and generates the announcement content using the generative AI model (for example, OpenAI's API).

[1381] Step 3:

[1382] The user recognizes the user's emotional state using an emotion recognition engine. The user's voice and facial expression data are required as input, and the user's emotional state (e.g., stress, joy, etc.) is obtained as output. In concrete terms, the device captures the user's voice and facial expression using a microphone and camera, and analyzes the emotional state using an emotion recognition engine (e.g., EmotionRecognizer).

[1383] Step 4:

[1384] The user inputs a question, and the server presents appropriate audit items, points of interest, cautions, ideal conditions, anticipated quality risks, and preventive and corrective measures for risks based on the question and emotional state. The input requires the user's question and emotional state, and the output provides advice such as appropriate audit items and points of interest. Specifically, the server converts the user's question and emotional state into a prompt sentence, generates an answer using a generative AI model, and presents it to the user.

[1385] Step 5:

[1386] The server will market the created tool as a quality control DX menu, mainly for small and medium-sized enterprises. The inputs will be the completed tool and strategic information for market deployment, and the output will be companies and users that adopt the tool. In concrete terms, the server will create marketing materials and propose and introduce the tool to small and medium-sized enterprises through sales activities.

[1387] Example 3

[1388] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[1389] In conventional quality control systems, audit items and risk management for each section are often performed manually, which is inefficient. In addition, it is not possible to provide a quality control menu that takes into account the emotional state of the user, which results in low user satisfaction and effectiveness. Furthermore, in small and medium-sized enterprises, digital transformation (DX) of quality control has not progressed, making efficient quality control difficult.

[1390] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1391] In this invention, the server includes a means for digitizing the audit items, points of interest, points to note, ideal situations, anticipated risks, and preventive and corrective measures for risks for each section based on a basic flow chart related to the quality control system and product manufacturing, a means for creating a tool that can be announced by generative artificial intelligence based on the digitized information, a means for marketing the created tool as a digital transformation menu for quality control, mainly for small and medium-sized enterprises, a means for inputting and analyzing the emotional state of a user, a means for generating an appropriate quality control menu using generative artificial intelligence based on the analysis result, and a means for providing the generated menu to a user. This enables efficient quality control and effective quality control that takes into account the emotional state of the user.

[1392] A "quality control system" is a system that manages a series of processes and methods for maintaining and improving the quality of products and services.

[1393] A "flow diagram" is a visual representation of a process or procedure, showing the flow and relationships of each step.

[1394] "Audit items" are specific items or standards that should be checked in quality control.

[1395] A "point of view" is a point or perspective that should be given particular attention when conducting an audit or evaluation.

[1396] "Points to note" are matters or risks that require special attention in quality control.

[1397] "The way things should be" is the ideal state or the standard of quality to be targeted.

[1398] "Risk" refers to factors or uncertainties that may affect quality.

[1399] A "preventive measure" is a measure taken to reduce or avoid the effects of a risk before it occurs.

[1400] "Corrective action" is a measure taken to correct an existing problem or defect and to prevent its recurrence.

[1401] "Generative AI" is AI that has the ability to generate new information or content based on input data or prompts.

[1402] An "announceable tool" is a tool that uses generative artificial intelligence to provide information to users.

[1403] "Digital transformation" refers to the effort to use digital technology to innovate operational processes and business models in order to improve efficiency and create value.

[1404] An "emotional state" is a state that indicates a user's current emotions or mood.

[1405] "Analysis" is the process of analyzing data to extract meaning and patterns.

[1406] A "menu" is a list of options or functions offered to a user.

[1407] This invention is a cloud service that supports the digital transformation (DX) of quality control for small and medium-sized enterprises. It is equipped with an emotion engine that adjusts the DX menu of quality control according to the user's emotional state.

[1408] System Overview

[1409] This system consists of three main components: a server, terminals, and users. The server runs on the cloud and provides a quality control digitalization menu. The terminals are the users' PCs or smartphones, and access the cloud service to use the quality control menu. Users access the system through their terminals and use the menu to make their company's quality control more efficient.

[1410] Server Processing

[1411] The server provides a quality control digitalization menu that runs on the cloud. Specifically, it uses AWS (Amazon Web Services) to manage databases (Amazon RDS) and computing resources (Amazon EC2). The server receives requests from users, generates and provides appropriate quality control menus. It uses a generative AI model (e.g., GPT-4) to generate the optimal quality control menu according to the user's emotional state.

[1412] Terminal handling

[1413] The terminal accesses the cloud service and uses the quality control digitalization menu. The terminal provides an interface for inputting the user's emotional state. For example, the terminal uses a camera and microphone to analyze the user's facial expressions and voice to estimate the emotional state. Libraries and services such as OpenCV and Google Cloud Speech-to-Text API are used for the analysis.

[1414] User Action

[1415] Users access the cloud service through their devices and use a menu to streamline their company's quality control. The user inputs their emotional state and selects from the menu provided by the system. For example, if the user is feeling happy, the emotion engine recognizes that information and provides a menu that amplifies the happiness.

[1416] Examples

[1417] For example, consider the case where a quality control manager of a small or medium-sized enterprise accesses a cloud service and uses a menu for digitalization of quality control. If the manager is feeling happy, the emotion engine will recognize that information and provide a menu that will amplify the manager's happiness. Specifically, the menu will include sharing of success stories and positive feedback.

[1418] Examples of prompt statements

[1419] Examples of prompt sentences to be input to a generative AI model include the following:

[1420] "If users are happy, what kind of content should we offer as part of our quality control digital transformation menu?"

[1421] By using this prompt sentence, the generative AI model can propose an optimal quality control menu according to the user's emotional state. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1422] Step 1:

[1423] A user logs in to a cloud service.

[1424] A user accesses a cloud service using their own device (PC or smartphone) and enters their user ID and password on the login screen. The device then sends this information to the server for authentication. The input is the user ID and password, and the output is the authentication result. In concrete terms, the user opens a browser and enters the URL of the cloud service to access it. The login screen is displayed, and the user enters their user ID and password and clicks the "Login" button.

[1425] Step 2:

[1426] The user inputs an emotional state.

[1427] After logging in, the user accesses an interface for inputting an emotional state. For example, the user may use a camera to capture a facial expression or a microphone to record a voice. The user may also input an emotional state in text. The input is the user's emotional state, and the output is emotion data. In concrete terms, the user clicks an "emotion input" button, which starts the camera. The user smiles at the camera and clicks the capture button. Or, the user may say into the microphone, "I'm very happy today."

[1428] Step 3:

[1429] The device analyzes the emotional state.

[1430] The device analyzes the emotion data input by the user. For example, it analyzes facial expression data captured by a camera using libraries such as OpenCV to estimate the user's emotional state. In the case of voice data, it uses the Google Cloud Speech-to-Text API to convert the voice to text and perform emotion analysis. The input is emotion data, and the output is the analysis result. In concrete terms, the device analyzes the captured image with OpenCV and quantifies the degree of smile. The voice data is converted to text using the Google Cloud Speech-to-Text API, and the keyword "happy" is extracted.

[1431] Step 4:

[1432] The server receives the analysis results and generates an appropriate quality control digitalization menu.

[1433] The terminal sends the analysis results to the server. The server uses a generative AI model (e.g., GPT-4) to generate an appropriate quality control digitalization menu based on the received emotion data. The input is the analysis result, and the output is the generated menu. In concrete terms, the terminal sends the analysis results to the server in JSON format. The server inputs a prompt sentence into the generative AI model based on the received data, and generates an appropriate menu.

[1434] Step 5:

[1435] The server sends the generated menu to the terminal.

[1436] The server sends the generated menu to the terminal. The data is securely transferred using the HTTPS protocol. The input is the generated menu, and the output is the result of sending it to the terminal. In concrete terms, the server sends the generated menu to the terminal in JSON format. The terminal analyzes the received data and displays it to the user.

[1437] Step 6:

[1438] The user utilizes the provided menu.

[1439] The user checks and uses the quality control digitalization menu displayed on the device. For example, a menu including sharing success stories and positive feedback may be displayed. The input is the provided menu, and the output is the user's actions. Specifically, the user checks the menu displayed on the device and clicks the "Share success stories" link. The user reads the displayed success stories and uses them to help with their own company's quality control.

[1440] (Application example 3)

[1441] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server", and the smart glasses 214 will be referred to as a "terminal".

[1442] In conventional quality control systems, audit items and risk management for each section are often done manually, which is inefficient. In addition, feedback and support that takes into account the user's emotional state is not provided, which can lead to a decrease in worker motivation and work efficiency. This leads to the issue that the effectiveness of quality control is not fully realized.

[1443] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1444] In this invention, the server includes a means for digitizing the audit items, points of interest, cautions, ideal situations, anticipated risks, and preventive and corrective measures for risks for each section based on a basic flow chart related to a quality control system and product manufacturing, a means for creating a tool that can be announced by a generative AI based on the digitized information, a means for market deployment of the created tool as a digital transformation menu for quality control, mainly for small and medium-sized enterprises, a means for recognizing the emotional state of a user using an emotion engine and adjusting feedback and support content according to the emotional state, and a means for providing positive feedback based on the emotional state. This enables efficient quality control and effective feedback that takes into account the emotional state of the user.

[1445] A "quality control system" is a system that manages a series of processes and methods for maintaining and improving the quality of products and services.

[1446] "Product manufacturing" is the process of assembling raw materials and parts to create a final product.

[1447] A "flow diagram" is a visual representation of a process or procedure, showing the order and relationships of the steps.

[1448] "Audit items" are specific items that should be checked in quality control and product manufacturing.

[1449] A "point of focus" is a point that should be given particular attention when conducting an audit or evaluation.

[1450] "Points to note" are things that you should pay special attention to when proceeding with a task or process.

[1451] "The way things should be" is an ideal state or a standard to aim for.

[1452] A "risk" is a problem or failure that may occur in the quality or manufacturing of a product.

[1453] A "preventive measure" is a measure taken to prevent a risk before it occurs.

[1454] A "corrective action" is a measure taken to correct or improve a problem or risk that has already occurred.

[1455] "Digitization" means recording and storing information in digital form.

[1456] "Generative AI" is a system that uses artificial intelligence technology to generate and process data and information.

[1457] An "announceable tool" is a tool that notifies and presents generated information and data to users.

[1458] "Digital transformation" refers to the innovation of business processes and business models through the use of digital technology.

[1459] An "emotion engine" is a technology that recognizes the user's emotional state and provides appropriate feedback and support.

[1460] "Feedback" means evaluations or advice provided to a User.

[1461] "Positive feedback" is feedback that positively evaluates and encourages a user's actions or achievements.

[1462] As an embodiment of the present invention, the following system configuration and processing procedure will be described.

[1463] System Configuration

[1464] 1. Hardware:

[1465] Camera: Used to capture the face of the worker.

[1466] Server: processes and stores data.

[1467] Terminal: The device used by the worker (e.g. computer, tablet).

[1468] 2. Software:

[1469] OpenCV: A library for image processing.

[1470] EmotionRecognizer: A model for emotion recognition.

[1471] QualityManagementService: Quality management cloud service.

[1472] Generative AI: Artificial intelligence techniques for generating and processing data and information.

[1473] Processing flow

[1474] 1. Data capture:

[1475] The worker's face is captured in real time using a camera connected to the terminal.

[1476] The captured image data is transmitted to a server.

[1477] 2. Emotion recognition:

[1478] The server recognizes the worker's emotional state from the captured images using EmotionRecognizer.

[1479] The recognized emotion data is sent to a quality control cloud service.

[1480] 3. Processing of quality control data:

[1481] Based on basic flow diagrams related to quality control systems and product manufacturing, the server digitizes the audit items and points of focus for each section, points to note, how things should be, anticipated risks, and preventive and corrective measures against risks.

[1482] The digitized information will be created into an announceable tool using generative AI.

[1483] 4. Providing Feedback:

[1484] The server uses an emotion engine to recognize the user's emotional state and adjusts the feedback and support content according to the emotional state.

[1485] Provide positive feedback based on the worker's emotional state. For example, if the worker is happy, show a message like, "Great job! Keep it up."

[1486] Examples

[1487] Consider a scenario in which a worker on a manufacturing line collaborates with a robot to perform quality control: if the worker is happy, the robot will recognize that emotion and provide positive feedback, such as a message like, "Great job! Keep it up."

[1488] Examples of prompt statements

[1489] Program a robot to recognize the emotional state of workers on a production line and provide appropriate feedback. Use a camera for emotion recognition and send quality control data to a cloud service. If a worker is happy, show positive feedback.

[1490] In this way, a system can be realized that enables efficient quality control and effective feedback that takes into account the user's emotional state.

[1491] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1492] Step 1:

[1493] The worker's face is captured in real time using a camera connected to the terminal.

[1494] Input: Camera image

[1495] Data processing: Acquire image data using OpenCV

[1496] Output: Captured image data

[1497] Step 2:

[1498] The server receives the captured image data and recognizes the worker's emotional state using the EmotionRecognizer.

[1499] Input: Captured image data

[1500] Data computation: Applying emotion recognition algorithms using EmotionRecognizer

[1501] Output: Recognized emotion data (e.g., happy, sad, angry, etc.)

[1502] Step 3:

[1503] The server sends the recognized emotion data to a quality control cloud service.

[1504] Input: Recognized emotion data

[1505] Data processing: data format conversion and transmission

[1506] Output: Emotion data stored in a cloud service

[1507] Step 4:

[1508] Based on basic flow diagrams related to quality control systems and product manufacturing, the server digitizes the audit items and points of focus for each section, points to note, how things should be, anticipated risks, and preventive and corrective measures against risks.

[1509] Input: Flow diagram and related data

[1510] Data processing: Automate and organize data using generative AI

[1511] Output: Digitalized audit items and risk management information

[1512] Step 5:

[1513] The server uses generative AI to create tools that can make announcements based on the digitized information.

[1514] Input: Digitalized audit items and risk management information

[1515] Data processing: Generate announcement content using generative AI

[1516] Output: Announcable tools

[1517] Step 6:

[1518] The server uses an emotion engine to recognize the user's emotional state and adjusts the feedback and support content according to the emotional state.

[1519] Input: Recognized emotion data

[1520] Data Computation: Generate feedback content using emotion engine

[1521] Output: Adjusted feedback content

[1522] Step 7:

[1523] The server provides positive feedback based on the worker's emotional state: for example, if the worker is happy, it displays a message like "Great job! Keep it up."

[1524] Input: Adjusted feedback

[1525] Data processing: generating and displaying feedback messages

[1526] Output: A positive feedback message provided to the worker.

[1527] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1528] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1529] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1530] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1531] [Third embodiment]

[1532] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1533] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1534] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[1535] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1536] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[1537] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1538] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1539] Fig. 6 shows an example of main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1540] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1541] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1542] In the headset type terminal 314, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1543] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1544] "Example 1"

[1545] As one embodiment of the present invention, a means is provided for converting the audit items and points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures against risks, etc., for each section into digital data based on a basic QC flow diagram related to a quality control system and product manufacturing. This digitalization is performed taking into consideration, for example, the work procedures and quality check items for each section, the skill levels of workers, etc.

[1546] "Example 2"

[1547] Furthermore, we will create a tool that can make announcements using chat generation AI based on the digitized information.

[1548] This tool has a function to automatically suggest points to note and areas for improvement at each step of quality control, for example. It also has a function to suggest appropriate audit items, points to focus on, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks in response to questions from users.

[1549] "Example 3"

[1550] Furthermore, the created tools will be provided as a means to market them as a digitalization menu for quality control, primarily for small and medium-sized enterprises. For example, this market development could be provided as a cloud service for small and medium-sized enterprises, and companies could use this service to streamline their own quality control and improve quality.

[1551] The process flow of each embodiment will be described below.

[1552] "Example 1"

[1553] Step 1: Refer to the quality control system and basic QC flow diagram related to product manufacturing, and extract the audit items and points of focus for each section, points to note, the ideal state, anticipated quality risks, and preventive and corrective measures for risks.

[1554] Step 2: The extracted information is registered in a database and digitized. This digitization is carried out taking into consideration, for example, the work procedures and quality check items of each section, the skill levels of the workers, etc.

[1555] "Example 2"

[1556] Step 1: Create a tool that can make announcements using chat generation AI based on the digitized information.

[1557] This tool will have the function of automatically suggesting points to note and areas for improvement at each step of quality control.

[1558] Step 2: Add a function that, in response to user questions, presents appropriate audit items, points to focus on, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks.

[1559] "Example 3"

[1560] Step 1: The created tool will be marketed as a digital transformation menu for quality control, primarily to small and medium-sized enterprises. This market deployment will be provided, for example, as a cloud service for small and medium-sized enterprises. Step 2: By using this service, companies can streamline their own quality control and improve quality.

[1561] Example 1

[1562] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1563] In quality control systems and product manufacturing, there is a demand for a system that can efficiently digitize the audit items, points of interest, cautions, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. for each section, and allow users to easily confirm, correct, and add them. In addition, there is a challenge in providing a tool that uses a generative AI model based on this information to make appropriate announcements in response to user questions.

[1564] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1565] In this invention, the server includes a means for digitizing the audit items, points of interest, cautions, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. for each section based on a basic QC flow chart related to the quality control system and product manufacturing, a means for accessing a database to collect necessary information, and a means for analyzing the collected data and digitizing it while taking into consideration the work procedures, quality check items, and skill levels of workers for each section. This makes it possible to efficiently digitize the audit items, points of interest, cautions, etc. for each section, and for users to easily confirm, correct, and add them.

[1566] A "quality management system" refers to a set of processes and tools for controlling and maintaining the quality of products and services.

[1567] A "QC flow diagram" is a diagram that visually represents each process and procedure in quality control.

[1568] "Audit items" refer to specific items that should be checked or evaluated in quality control or product manufacturing.

[1569] "Points of focus" refers to points that should be given particular attention when conducting an audit or evaluation.

[1570] "Points to note" refers to matters that require special attention when performing work or audits.

[1571] "The ideal state" refers to the ideal or target state in quality control and product manufacturing.

[1572] "Quality risk" refers to factors or circumstances that may affect the quality of a product or service.

[1573] "Preventive measures" refer to measures taken to prevent quality risks.

[1574] "Corrective action" refers to measures taken to resolve a quality problem that has occurred and to prevent its recurrence.

[1575] "Digitization" refers to the process of organizing and storing information in digital form.

[1576] A "generative AI model" refers to a model that uses artificial intelligence technology to generate and analyze data.

[1577] A "prompt" refers to an instruction or question that is input to a generative AI model.

[1578] "Digital transformation" refers to the innovation of business processes and business models through the use of digital technology.

[1579] This invention is a system that digitizes the audit items, points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. for each section based on the basic QC flow chart related to quality control systems and product manufacturing. This system works in cooperation with the server, terminals, and users.

[1580] The server accesses the quality control system database and collects information such as the audit items, points of interest, and points of caution for each section based on the QC flow diagram. Specifically, the server uses a database management system (DBMS) such as MySQL or PostgreSQL to extract the necessary information with SQL queries.

[1581] Next, the server analyzes the collected data. To do so, it uses a Python data analysis library (e.g., Pandas) to organize the data, taking into account the work procedures and quality check items of each section, the skill level of the workers, etc. The analysis results are digitized and saved in JSON format.

[1582] The server sends the digitized information to the terminal using the HTTP protocol. Specifically, the data is sent through a RESTful API. The terminal uses a general device such as a PC or tablet and receives the data through a web browser or a dedicated quality control application.

[1583] The terminal visually displays the received data to the user. For example, it uses HTML and JavaScript to display the data in the form of tables, graphs, etc. Using the terminal interface, the user can check the audit items, points of interest, and points of caution for each section and make corrections or additions as necessary.

[1584] In addition, the server uses a generative AI model based on the digitized information to create a tool that makes appropriate announcements in response to user questions. Based on the prompt text entered by the user, this generative AI model presents appropriate audit items, points of interest, points to note, ideal situations, anticipated quality risks, and preventive and corrective measures for risks.

[1585] As a concrete example, in the product manufacturing section, the following audit items are recorded:

[1586] Checking work procedures: Are the work procedures being followed?

[1587] Quality check items: Checking product dimensions and appearance

[1588] Worker skill level: Do your workers have the required skills?

[1589] The server collects this information from the database and sends it to the terminal. The user can check this information through the terminal and make corrections or additions as necessary.

[1590] Examples of prompts to be input to a generative AI model include:

[1591] "For the quality control of the product manufacturing section, please digitize the following audit items: confirmation of work procedures, quality check items, and worker skill levels."

[1592] By using this prompt sentence, the generative AI model can properly digitize the data and reflect it in the quality control system.

[1593] The above is a specific embodiment for carrying out the present invention.

[1594] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1595] Step 1: Data collection

[1596] The server accesses the quality control system database and collects information such as the audit items, points of interest, and points of caution for each section based on the QC flow diagram. Specifically, the server uses a database management system (DBMS) such as MySQL or PostgreSQL to extract data by executing the SQL query "SELECT FROM qc_flow WHERE section_id = 'product manufacturing'". The input is the database connection information and the SQL query, and the output is the extracted data.

[1597] Step 2: Data analysis

[1598] The server analyzes the collected data. Specifically, it uses a Python data analysis library (e.g. Pandas) to convert the data into a data frame and extracts the work procedures and quality check items for each section, the skill levels of workers, and so on. The input is the collected data, and the output is the analyzed data. For example, a data frame can be used to extract "checking work procedures" and "quality check items."

[1599] Step 3: Digitization

[1600] Based on the parsed data, the server converts the audit items, points of interest, points to note, ideal situations, anticipated quality risks, preventive and corrective measures for risks, etc. into JSON format data for each section. The input is the parsed data, and the output is JSON format data. For example, it generates the following JSON data:

[1601] json { "section": "Product Manufacturing", "audit_items": [ { "item": "Check the work procedure", "details": "Are the work instructions being followed?" }, { "item": "Quality check item", "details": "Check product dimensions and appearance" } ], "risk_prevention": "Regular training" }

[1602] Step 4: Send data

[1603] The server transmits the digitized information to the terminal. Specifically, it transmits data through a RESTful API using the HTTP protocol. The input is data in JSON format, and the output is data transmission to the terminal.

[1604] Step 5: Displaying the data

[1605] The terminal receives the data sent from the server and displays it visually to the user. Specifically, it uses HTML and JavaScript to display the data in the form of tables, graphs, etc. The input is the JSON data received from the server, and the output is the visual data that is displayed to the user. For example, to generate a table like this:

[1606] html Audit items detail Check the work procedure Are you following the work instructions? Quality Check Items Checking product dimensions and appearance

[1607] Step 6: User feedback

[1608] Through the terminal, the user checks the audit items, points of focus, and points of caution for each section, and makes corrections or additions as necessary. Specifically, the user uses the terminal interface to edit data and add comments. The input is the user's feedback, and the output is the corrected or added data. For example, the user can modify the details of "quality check items" to "check product dimensions, appearance, and functions."

[1609] Step 7: Leverage generative AI models

[1610] The server uses a generative AI model based on the digitized information to create a tool that makes appropriate announcements in response to user questions. The input is the prompt text entered by the user, and the output is the answer generated by the generative AI model. For example, the following prompt text is used:

[1611] "For the quality control of the product manufacturing section, please digitize the following audit items: confirmation of work procedures, quality check items, and worker skill levels."

[1612] The above is the specific processing flow of the program of this system.

[1613] (Application example 1)

[1614] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1615] In conventional quality control systems, the audit items for each section, prediction of quality risks, and proposal of preventive and corrective measures are often done manually, which is inefficient. In addition, it is difficult to check quality and predict risks in real time, which leads to a problem of reduced accuracy of quality control on the production line. Furthermore, digital transformation of quality control has not progressed well in small and medium-sized enterprises, making effective quality control difficult.

[1616] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1617] In this invention, the server includes: a means for digitizing the audit items, points of interest, points to note, ideal state, expected quality risks, preventive measures and corrective measures for risks for each section based on a basic QC flow diagram related to a quality control system and product manufacturing; a means for creating an announceable tool using a generative AI model based on the digitized information; a means for marketing the created tool as a menu for digital transformation of quality control, mainly for small and medium-sized enterprises; a means for monitoring the work procedures and quality check items of each section in the production line in real time, predicting quality risks, and proposing preventive measures and corrective measures; a means for checking the quality of products using image recognition technology; and a means for predicting quality risks based on past data using a machine learning model. This enables real-time quality control and risk prediction, improves the accuracy of quality control on the production line, and promotes the digital transformation of quality control in small and medium-sized enterprises.

[1618] A "quality control system" is a system that monitors and controls the entire manufacturing process in order to maintain and improve product quality.

[1619] A "QC flow diagram" is a diagram that visually represents each step and process of quality control, and shows the audit items and work procedures for each section.

[1620] "Audit items" are specific items or standards that should be checked for quality control.

[1621] A "point of view" is a point or perspective that requires particular attention in quality control.

[1622] "Points to note" are points that require special attention in each section of quality control.

[1623] "The ideal state" is the standard to be aimed for in quality control.

[1624] A "quality risk" is any factor or situation that may adversely affect the quality of a product.

[1625] "Preventive measures" are measures or procedures to prevent quality risks before they occur.

[1626] "Corrective action" means measures or procedures to resolve a quality problem that has occurred and prevent it from recurring.

[1627] A "generative AI model" is a model that uses artificial intelligence to generate new information and predictions from data.

[1628] An "announceable tool" is a tool that uses a generative AI model to provide appropriate information to users.

[1629] "Digital transformation" refers to the innovation of business processes and business models through the use of digital technology.

[1630] "Real-time monitoring" refers to monitoring the manufacturing process in real time and acquiring and analyzing data instantly.

[1631] "Image recognition technology" is a technology that uses cameras and sensors to analyze images and extract specific information.

[1632] A "machine learning model" is an algorithm that learns patterns based on past data and uses them to make future predictions and classifications.

[1633] As an embodiment of the present invention, a "smart QC robot" equipped with a quality control system will be described as an example.

[1634] System Configuration

[1635] Hardware

[1636] Robot body: A robot installed on a manufacturing line (e.g., an industrial robot)

[1637] Camera sensor: A camera for taking images of the product (e.g. a high-resolution camera)

[1638] Data processing unit: A unit for processing image data and quality data (e.g. high-performance processor).

[1639] software

[1640] Image recognition software: Software for analyzing captured images (e.g. OpenCV)

[1641] Database management system: A system for managing data such as each section's work procedures, quality check items, and worker skill levels (e.g., MySQL)

[1642] Machine learning models: Models for predicting quality risks based on past data (e.g. TensorFlow)

[1643] Generative AI model: A model for creating announceable tools based on digitized information

[1644] Program processing explanation

[1645] Data processing and calculation

[1646] 1. Image recognition: Images of products captured by a camera sensor are analyzed using OpenCV to check quality check items. For example, the positional accuracy and mounting strength of parts are monitored in real time.

[1647] 2. Database management: MySQL is used to manage data such as each section's work procedures, quality check items, and worker skill levels, allowing information required for quality control to be managed centrally.

[1648] 3. Machine Learning: Using TensorFlow, predict quality risks based on past data and suggest preventive or corrective measures. For example, if past data shows frequent occurrences of part misalignment, the risk can be predicted and real-time monitoring can be strengthened.

[1649] Examples and prompts

[1650] As a concrete example, the following prompt sentence is input into the generative AI model.

[1651] Example prompt:

[1652] Please check the quality check items in Section A of the production line and suggest preventive measures if there is high risk. Please make your decision based on the following data.

[1653] Procedure: Parts installation

[1654] Quality check items: Part position accuracy, mounting strength

[1655] Worker skill level: Intermediate

[1656] Past quality risk data: Frequent occurrence of part misalignment

[1657] An example of the response generated:

[1658] We have reviewed the quality check items in Section A. Regarding the positional accuracy of parts, past data has revealed that there have been frequent occurrences of misalignment. As a preventative measure, we suggest that you introduce a system that monitors the mounting position in real time and issues an alert immediately if any misalignment occurs. In addition, regarding the mounting strength, we recommend that you regularly check it with a torque wrench.

[1659] In this way, smart QC robots can control quality in real time and suggest preventive and corrective measures to prevent risks, improving the accuracy of quality control on the production line and promoting the digital transformation of quality control in small and medium-sized enterprises.

[1660] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1661] Step 1:

[1662] The server obtains product image data from the camera sensor. The input is image data from the camera sensor, and the output is image data that can be analyzed. In concrete terms, the camera sensor takes a picture of the product on the production line and sends the image data to the server.

[1663] Step 2:

[1664] The server uses image recognition software (e.g. OpenCV) to analyze the acquired image data. The input is the image data acquired in step 1, and the output is the analysis results of the quality check items. In concrete terms, the image recognition software analyzes the positional accuracy and mounting strength of the parts to check for any abnormalities.

[1665] Step 3:

[1666] The server accesses a database management system (e.g. MySQL) and retrieves data such as the work procedures for each section, quality check items, and the skill levels of workers. The input is a query to the database, and the output is the retrieved data. In concrete terms, the server sends a query to the database and retrieves the required data.

[1667] Step 4:

[1668] The server uses a machine learning model (e.g. TensorFlow) to predict quality risks based on past data. The inputs are the data acquired in step 3 and past quality risk data, and the output is the predicted quality risk. In concrete terms, the machine learning model analyzes past data and predicts current quality risks.

[1669] Step 5:

[1670] The server uses the generative AI model to generate prompt sentences that suggest preventive or corrective actions. The input is the quality risk predicted in step 4, and the output is the generated prompt sentence. In concrete terms, the generative AI model generates prompt sentences that suggest appropriate preventive or corrective actions based on the quality risk.

[1671] Step 6:

[1672] The server announces the generated prompt to the user. The input is the prompt generated in step 5, and the output is the announcement to the user. In concrete terms, the server notifies the user of the generated prompt, and the user takes appropriate action based on it.

[1673] In this way, by clarifying the specific actions and inputs / outputs performed at each step, the process flow of the quality control system can be explained in detail.

[1674] Example 2

[1675] Next, a second embodiment of the second form will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1676] In conventional quality control systems, audit items, points of focus, points of caution, ideal situations, quality risks, and preventive and corrective measures for risks for each section had to be manually digitized, which took time and effort. In addition, specialized knowledge was required to provide appropriate information in response to user questions, making it difficult to respond quickly. Furthermore, the digitalization of quality control had not progressed in small and medium-sized enterprises, making efficient quality control difficult.

[1677] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1678] In this invention, the server includes a means for generating an announcement using a generative AI model based on digitized quality control information, a means for providing the generated announcement to a user, a means for generating a prompt sentence based on a user's question and inputting the prompt sentence to the generative AI model, and a means for receiving the announcement generated from the generative AI model and displaying it to the user. This enables the automation and rapid provision of information on quality control.

[1679] "Digital quality control information" refers to information recorded in digital format, such as quality control audit items, points of focus, points to note, ideal conditions, quality risks, and preventive and corrective measures against risks.

[1680] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to generate appropriate announcements based on input prompt sentences.

[1681] "Means for generating an announcement" refers to the process of using a generative AI model to create an announcement based on digitized quality control information.

[1682] "Means for providing to a user" refers to a method or system for displaying or notifying a user of a generated announcement.

[1683] A "prompt sentence" is an instruction sentence to b...

Claims

1. A means for digitalizing quality control information including at least one of the following for each section based on the QC flow chart: audit items, points of interest, points of caution, ideal state, anticipated quality risks, preventive measures against risks, and corrective measures; A means for creating a tool capable of announcing the quality control information using a generative AI model based on the digitized quality control information; and a means for providing said tool. system.

2. The system further includes a means for installing the created tool on a factory robot, monitoring quality in each section of quality control in real time, and issuing an alert when an abnormality is detected. The system of claim 1 .

3. A means for generating a prompt sentence based on a user's question and inputting the prompt sentence into the generative AI model; and means for receiving and displaying to a user the announcement generated from the generative AI model. The system of claim 1 .

Images