system

Abstract

We provide the system. [Solution] A means for collecting images of an object from an image acquisition device, Image processing means for performing noise reduction and quality improvement on the aforementioned image, Analysis means using an artificial intelligence model that identifies the state of an object using the processed image, A display and notification means for displaying the identification results obtained by the aforementioned analysis means and notifying of defective products, A database recording means for recording the aforementioned identification results and managing their history, A system that includes this.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, the shortage of labor has become serious in the manufacturing industry. Especially in production lines that operate 24 hours a day, a large amount of labor is required to maintain the quality of products. However, it is difficult to ensure a constant workforce, and the burden on engineers and workers has increased particularly in simple inspection operations. Therefore, there is a demand to perform product inspections efficiently and accurately while reducing the labor force. To solve this problem, a method for automating the inspection work is necessary.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides a means for collecting images of an object from an image acquisition device and performing image processing to improve quality by removing noise from the images. Furthermore, it has an analysis means that uses an artificial intelligence model with the processed images to accurately identify the state of the object. The identified results are displayed in real time, and a notification is given when a defective product is detected. In addition, all identification results are recorded in a database and used for subsequent quality control. In this way, it is possible to reduce labor and improve the efficiency of inspection work.

[0006] An "image acquisition device" is a device used to capture images of an object and collect them as digital data.

[0007] "Noise reduction" is a process that improves image quality by removing non-essential information and unwanted signals from image data.

[0008] "Quality enhancement" refers to the process of improving the visual characteristics of image data so that details are displayed more clearly.

[0009] "Image processing means" refers to a series of technologies and programs that have the function of performing necessary processing and analysis on image data of an object.

[0010] An "artificial intelligence model" is a model that uses machine learning or deep learning algorithms to learn patterns from data and perform identification and prediction.

[0011] "Analytical means" refers to methods or processes for interpreting data and drawing specific conclusions or results.

[0012] "Display and notification means" refers to a function or device for conveying information to the user visually or audibly.

[0013] A "database recording means" refers to a function or system that structures and stores various types of information, enabling efficient access, retrieval, and updating as needed. [Brief explanation of the drawing]

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

Modes for Carrying Out the Invention

[0015] 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.

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

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

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

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

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

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

[0022] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0035] This invention is a system for streamlining product inspection on a manufacturing line, and includes an image acquisition device, image processing means, analysis means, display and notification means, and database recording means. This allows for the automatic determination of the quality of the target product, specifically aluminum cans.

[0036] Detailed description of the embodiment

[0037] The server first collects real-time images of objects, such as aluminum cans, from image acquisition devices installed on the factory's production line. The image acquisition devices photograph the objects as they move along the rollers and transmit the image data to the server. This allows the server to obtain detailed visual data of the manufactured products in real time.

[0038] Next, the server uses image processing equipment to perform noise reduction and quality improvement on the received image data. Specifically, it adjusts the brightness and saturation of the image and performs edge detection to clearly display fine scratches and dents. This allows for the extraction of the maximum amount of information necessary for quality assessment.

[0039] The processed images are input into an artificial intelligence model on the server. Here, the analysis tool identifies the state of the object. The AI ​​model uses pre-trained characteristics of normal and defective products to perform real-time inspections. For example, it can identify dents or abnormal color differences in aluminum cans.

[0040] The judgment results are immediately sent from the server to the terminal, where they are displayed and notified for the terminal to check. If a defective product is detected, an alert is displayed on the terminal, and the user is notified with a warning sound and a displayed message. Detailed information is also displayed on the screen, such as "defective products detected on a specific shelf at a specific time."

[0041] Ultimately, the server records all inspection results in a database. This allows for data analysis during quality control at a later date, contributing to improvements in the manufacturing process and trend analysis.

[0042] Specific example

[0043] In a 24-hour aluminum can manufacturing line at a certain factory, a user monitors the production process via a monitor. A server continuously acquires images of aluminum cans moving along rollers, and after AI analysis, detects minute dents on the can's surface. This result is immediately transmitted to a terminal, and a notification is sent to the user if a defective product has been found. The user can then take immediate action on the production line, preventing the shipment of unnecessary defective products and maintaining the final product quality.

[0044] In this way, the system automatically performs highly accurate inspections, contributing to improved factory production efficiency and product quality.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The server collects real-time images of aluminum cans moving on rollers from image acquisition devices within the factory. The camera captures a series of images of the cans at regular intervals and immediately transmits this data to the server.

[0048] Step 2:

[0049] The server performs basic image processing on the received image data, such as noise reduction and brightness / saturation correction. This prepares the image for easier analysis. Furthermore, an edge detection algorithm is applied to highlight fine anomalies on the can surface.

[0050] Step 3:

[0051] The server inputs the processed images into an artificial intelligence model to identify the product's condition. The AI ​​model has been pre-trained and operates a comparison algorithm that distinguishes between normal products and defective products (e.g., dents, scratches, foreign objects).

[0052] Step 4:

[0053] The server aggregates the results of the AI ​​analysis, and if a product is identified as defective, it extracts detailed information about it. If a product is determined to be defective, it identifies which part is faulty and how.

[0054] Step 5:

[0055] The server sends the judgment result to the terminal. Based on the received information, the terminal notifies the user in real time. When a defective product is detected, a warning is displayed on the terminal's screen, and if necessary, an audio alert is given to alert the user.

[0056] Step 6:

[0057] The server records all judgment results in a database, accumulating data that can be used for future quality control and statistical analysis. This data is then used to analyze long-term production trends and optimize manufacturing processes.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] Product quality inspection on manufacturing lines is a time-consuming and inefficient process that requires significant manpower. In particular, it is difficult to quickly and accurately identify minute defects and flaws in the products being inspected, leading to increased defect rates and problems in quality assurance. Furthermore, recording and analyzing quality data is time-consuming, making continuous improvement of the manufacturing process difficult.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for collecting information from a device that acquires visual information of an object, image processing means for removing noise and improving the quality of the information, and analysis means using a machine learning model that identifies the characteristics of the object using the processed information. This makes it possible to automatically inspect the quality of products on a manufacturing line in real time and with high accuracy.

[0063] "Target object" refers to the product that is subject to quality inspection on the manufacturing line.

[0064] A "device for acquiring visual information" is a device used to collect image and video data of objects on a manufacturing line.

[0065] "Noise reduction" is the process of removing unwanted background noise from acquired image or video data.

[0066] "Quality improvement" refers to the process of adjusting the visual characteristics of images and video data to clearly identify defects in the object being inspected.

[0067] "Image processing means" refers to technical means for applying noise reduction and quality improvement to visual information.

[0068] A "machine learning model" is an algorithm that uses training data to make predictions and judgments in order to identify the characteristics of an object.

[0069] "Analysis means" refers to technical means for evaluating the state of an object based on processed visual information and identifying its features and defects.

[0070] "Display and warning means" refers to a system function that displays the identification results obtained by the analysis means and, if necessary, alerts the user.

[0071] "Data storage means" refers to technical means for recording analysis results so that they can be referenced later.

[0072] This invention is an automated product inspection system for a manufacturing line, providing a method for efficiently evaluating the quality of the target product. The system includes a device for acquiring visual information of the target object, a server for image processing and analysis, and a terminal for displaying and warning the results.

[0073] The server first collects high-resolution image data from visual information acquisition devices installed on the manufacturing line. These devices accurately capture the details of fast-moving objects and transmit the data to the server in real time.

[0074] Next, the server performs image processing on the acquired visual information to remove noise and improve quality. Specifically, the server uses dedicated software to adjust the brightness and saturation of the image and applies an edge detection algorithm to clearly highlight minute defects in the object.

[0075] Subsequently, the processed image data is analyzed using a generative AI model. The server utilizes a deep learning-based machine learning model to identify patterns between normal and defective products. This allows for highly accurate determination of the object's condition. For example, it can quickly detect minute dents on the surface or abnormal color changes.

[0076] The analysis results are sent from the server to the terminal for user review. The terminal immediately displays the inspection results and issues visual and auditory warnings if defective products are detected. This allows the user to address the problem quickly.

[0077] Furthermore, the server records all inspection results in a data storage system and manages them as a history. This data can be used to continuously improve quality control and optimize the manufacturing process.

[0078] Specific example

[0079] Users can monitor the aluminum can manufacturing production line and quickly adjust the line based on analysis results provided by the server. Defective products are immediately notified via the terminal, helping to improve manufacturing efficiency and maintain high product quality.

[0080] Example of a prompt

[0081] "Please describe a real-time quality inspection system used in the aluminum can manufacturing process. Please explain, with specific examples, how AI is being used on the factory production line."

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The server collects image data of aluminum cans as input from a visual information acquisition device installed on the production line. This device is equipped with a high-resolution camera and continuously acquires images as the product moves, transmitting them to the server. The server temporarily stores the received image data in storage in preparation for the next processing step.

[0085] Step 2:

[0086] The server takes the collected image data as input and performs image processing to remove noise and improve quality. Specifically, it uses filters to remove noise from the image as part of data processing, and adjusts brightness and saturation to improve visibility. It also applies an edge detection algorithm to highlight minute scratches and dents on the surface of the aluminum can. As a result, the processed image data is passed to the next process as output.

[0087] Step 3:

[0088] The server feeds the processed image data into the AI ​​model. The AI ​​model uses a deep learning-based machine learning algorithm to analyze the product's health based on past learning results. As part of the data calculation, the model extracts features from the image and determines whether it is a normal or defective product. The analysis results are output, and the process moves to the next step.

[0089] Step 4:

[0090] The server sends the analysis results of the AI ​​model to the terminal. The terminal displays the received identification results as input on its screen, and if a defective product is detected, it warns the user with sound and visual indicators. Specifically, the terminal displays a message saying "Defective product detected" and explains the details of the anomaly (e.g., the degree and location of the dent). The user can also perform additional verification tasks through the terminal's interface.

[0091] Step 5:

[0092] The server records all generated analysis results as input to the data storage system. The data is systematically stored for later reference and includes information such as the date and time of inspection, location, and type of defects detected. This recorded data can then be used as output to generate quality control reports and improve the manufacturing process.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] In modern manufacturing lines, automation of quality inspection is required, but conventional systems require a great deal of manpower and time to perform accurate inspections. Furthermore, if defective products are overlooked, there is a possibility of large-scale product recalls after shipment, which significantly impacts production efficiency. In particular, there is a need for a system that can rapidly control the production line in real time based on inspection results.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes means for collecting images of an object from an image acquisition device, image processing means for performing noise reduction and quality improvement on the images, analysis means using an artificial intelligence algorithm to identify the state of the object using the processed images, and production control means for issuing an instruction to the autonomous machine to stop the production line when the analysis means detects a defective product. This enables automation of product inspection on the manufacturing line, as well as high-precision and real-time control of the production line.

[0098] An "image acquisition device" is a device used to collect visual information of a target object.

[0099] "Noise reduction" is a process that reduces unwanted random fluctuations and errors in order to improve the quality of image data.

[0100] "Quality improvement" refers to a series of processes performed to enhance the visibility and analytical accuracy of image data.

[0101] "Image processing means" refers to a method for optimizing data by applying a specific algorithm to an acquired image.

[0102] An "artificial intelligence algorithm" is a type of computer program used to learn and identify the characteristics of an object.

[0103] "Analysis means" are methods for identifying and evaluating specific characteristics or states based on acquired data.

[0104] "Display and warning means" refers to devices or programs that provide displays and warnings to inform the user of the results of the identification.

[0105] "Information recording means" refers to means for storing identified results and historical data and managing them so that they can be referenced at a later date.

[0106] An "autonomous machine" is a mechanical device that can perform specific actions based on its own judgment.

[0107] "Production control means" are means for managing the progress of the production process and making adjustments as needed.

[0108] In this invention, the server collects images of the product in real time using image acquisition equipment installed on the manufacturing line. The server then performs noise reduction and quality improvement processing on these images to prepare them for checking for minor scratches or dents on the surface of the aluminum cans. Image processing software such as OpenCV is used for this process.

[0109] The processed images are input into an artificial intelligence algorithm on the server. This algorithm uses a generative AI model to analyze the characteristics of good and defective products. By using deep learning frameworks such as TENSORFLOW® and Keras, the product condition can be identified with high accuracy.

[0110] Analysis results are immediately transmitted from the server to the terminal, which displays the results to the user. The terminal functions as a display and warning system, issuing a warning if a defective product is detected. Subsequently, the autonomous machine can stop the production line based on instructions from the server. This collaboration efficiently prevents the shipment of defective products and maintains product quality.

[0111] As a concrete example, in one factory, the system is in operation, and users can monitor the status of the production line in real time. One day, the generative AI model detects a minor defect, the system immediately issues an alert, and an instruction is sent to the autonomous machine to stop the line. As a result, the user can immediately address the problem and adjust the production process. The generative AI system can be improved based on a prompt message such as, "What algorithm would be most effective in exploring new ways to streamline product inspection?"

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The server collects images of products from image acquisition equipment installed on the manufacturing line. During this process, the camera continuously photographs moving aluminum cans on the line and transmits the resulting image data to the server. The server receives this data as input.

[0115] Step 2:

[0116] The server performs noise reduction and quality enhancement on the received image data. For noise reduction, it uses OpenCV's Gaussian blur function to smooth the image, and for quality enhancement, it adjusts the brightness and contrast of the image to improve its clarity. The processed image data is then output.

[0117] Step 3:

[0118] The server inputs the processed image data into an artificial intelligence algorithm. Using a generative AI model, the AI ​​analyzes the features in the image and identifies whether the product is good or defective. Based on pre-trained data, the AI ​​detects minute defects on the product. The analysis results are output as identification information.

[0119] Step 4:

[0120] The server sends the identified results to the terminal. The terminal displays the results, allowing the user to check the product quality status in real time. If a defective product is detected, the terminal issues a warning and displays an alert on the screen. This notification is intended to allow the user to take quick action.

[0121] Step 5:

[0122] If a defective product is detected, the server instructs the autonomous machine to stop the production line. This instruction is transmitted to the autonomous machine via communication, and upon receiving it, the machine temporarily suspends the line's operation. This prevents defective products from being shipped.

[0123] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0124] This invention provides a system for streamlining product inspection on a manufacturing line and improving the user experience. It includes an image acquisition device, image processing means, analysis means using an artificial intelligence model, display and notification means, and database recording means, as well as an emotion engine that recognizes user emotions. This system enables a highly automated inspection process, maintains product quality, and provides an interface that considers the user's emotional state.

[0125] Detailed description of the embodiment

[0126] The server uses image acquisition equipment within the factory to capture images of aluminum cans moving along rollers. These images are transmitted to the server in real time, and the server performs quality improvement processing on the received images using noise reduction and edge detection algorithms. The processed image data is input into an artificial intelligence model using deep learning to analyze the presence of defects and the condition of the products. The results of this AI analysis are immediately sent from the server to the terminal.

[0127] The terminal provides real-time notifications to the user based on analysis results received from the server. The display and notification system displays a warning when a defective product is identified and provides an audio alert as needed. This information allows the user to take appropriate action immediately.

[0128] Furthermore, this system integrates an emotion engine, which analyzes data obtained from the user's facial expressions and voice to determine the user's emotional state. For example, if the user shows signs of dissatisfaction or confusion, the system dynamically adjusts the interface display and notification process, and adds supportive information to make it easier for the user to understand.

[0129] The database recording system records inspection results and user interaction history to help improve quality and optimize the user experience in the future. All data is securely stored and contributes to subsequent trend analysis and improvements to the manufacturing process.

[0130] Specific example

[0131] On a production line one day, while a user is monitoring the system, the server acquires images of newly arrived aluminum cans and performs AI-powered defect inspection. The terminal notifies the user of the detected defects, while an emotion engine analyzes the user's facial expressions to detect signs of attention or dissatisfaction. The terminal automatically selects the most appropriate way to display the information for the user, adding detailed instructions and support information to help the user respond quickly.

[0132] In this way, this system contributes to maintaining product quality and improving work efficiency by streamlining the manufacturing process and providing a flexible operating environment that takes user emotions into consideration.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The server continuously acquires images of aluminum cans from image acquisition devices located on the production line. Acquisition is performed in real time, and the image data is immediately sent to the server to prepare it for processing.

[0136] Step 2:

[0137] The server performs image processing on the received image, removing noise and adjusting brightness and contrast. This process improves image visibility, and by applying an edge detection algorithm, it makes it easier to identify fine defects on the can surface.

[0138] Step 3:

[0139] The processed images are input into an artificial intelligence model on the server. The AI ​​model analyzes the images based on pre-trained data and determines whether the product is normal or defective. It can identify abnormalities such as dents and scratches with high accuracy.

[0140] Step 4:

[0141] The server evaluates the analysis results of the artificial intelligence model and records the details if a defective product is identified. The evaluation results immediately lead to the next step.

[0142] Step 5:

[0143] The server sends the analysis results to the terminal. Based on the data received by the terminal, it notifies the user in real time of the detection of defective products.

[0144] Step 6:

[0145] Devices equipped with an emotion engine analyze the user's facial expressions and voice to determine the user's emotional state. If there are signs that the user is dissatisfied or has questions, the content of the conversation and the interface are adjusted accordingly.

[0146] Step 7:

[0147] The device adjusts the displayed content according to the user's emotional state. It presents information in a format that is easy for the user to understand, and adds supplementary explanations and support information as needed to facilitate smooth communication.

[0148] Step 8:

[0149] The server records all test results and user feedback data in a database. This enables analysis aimed at improving the efficiency of the manufacturing line and enhancing the user experience.

[0150] (Example 2)

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

[0152] Modern manufacturing lines demand improved inspection accuracy and process efficiency in product inspection. However, conventional technologies lack high-precision defect inspection systems that integrate image processing and artificial intelligence, resulting in insufficient automation and cost reduction in quality control. Furthermore, there are insufficient means to reduce the burden on users and improve the user experience. Therefore, there is a need to provide a system that solves these problems and enhances the efficiency of the entire manufacturing process.

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

[0154] In this invention, the server includes means for collecting images of an object from an image acquisition device, image processing means for applying noise reduction and edge detection algorithms to the images, and analysis means for using a generative AI model to identify the state of the object using the processed images. This enables high-precision and efficient product inspection, as well as dynamic adjustment of the interface according to the user's emotional state.

[0155] An "image acquisition device" is a device used to collect images of an object, and specifically refers to a device capable of acquiring images of products moving along a manufacturing line in real time.

[0156] "Noise reduction" is the process of removing unwanted information from a digital image in order to improve image quality.

[0157] An "edge detection algorithm" is a processing technique used to detect the contours of objects in an image, and is used to clarify the shape and boundaries of objects.

[0158] A "generative AI model" is a pre-trained model designed to analyze the features of images and data using artificial intelligence technology and to identify the state of an object.

[0159] "Analysis means" refers to methods and processes for determining whether an object is defective or identifying its condition based on processed image data.

[0160] "Display and notification means" refers to a system for visually or audibly communicating the results of the analysis to the user, thereby encouraging the user to take prompt action.

[0161] A "database recording system" is a data management system that securely stores data such as analysis results and user operation history, and uses it for future quality control and system improvement.

[0162] "Dynamic interface adjustment" is the process of appropriately changing the displayed content and notification methods according to the user's emotional state and operating environment.

[0163] This invention is a system for highly automating product inspection on a manufacturing line and improving efficiency. The following describes the embodiments for implementing this system.

[0164] The server collects images of the target object, aluminum cans, through an image acquisition device. This image acquisition device is a camera installed on the manufacturing line that captures images of products moving in real time. The server then applies noise reduction and edge detection algorithms to the collected images using Python and OpenCV to improve image quality. A Gaussian filter is used for noise reduction, and the Canny method is used for edge detection.

[0165] Next, the server inputs the improved image quality into an AI model, specifically a deep learning model using TensorFlow. This model uses a convolutional neural network (CNN) to extract features from the image data and identify whether or not there are defective products and to determine the product's condition.

[0166] The identification results are sent from the server to the terminal. Based on these results, the terminal notifies the user in real time. Specifically, it displays a warning of defective product detection on the display and issues an audio alert if necessary, enabling the user to respond quickly.

[0167] Furthermore, the device has an integrated emotion engine that determines the user's emotional state based on data acquired from the camera and microphone. For example, it uses the Emotion API to analyze facial expressions and voice tone, and if the user is showing signs of dissatisfaction or confusion, it dynamically adjusts the interface display and adds personalized support information.

[0168] Inspection results and user interaction history are recorded in a database. This data is securely stored using an SQL database and used for trend analysis to improve quality and enhance manufacturing processes.

[0169] As a concrete example, a server acquires an image of an aluminum can, performs a defect inspection using an AI model, and sends the results to a terminal. The terminal receives the defect information and notifies the user. If the user shows signs of dissatisfaction, the terminal adjusts its interface and displays detailed instructions on how to resolve the issue.

[0170] An example of a prompt is: "Design a system that uses image processing and an AI model to inspect products on a manufacturing line and notifies the user of the results in real time. The system should recognize the user's emotional state and dynamically adjust the interface." By using an AI model generated based on such prompts, it is possible to achieve efficient product inspection and improve the user's work environment.

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] The server controls the image acquisition device to capture images of aluminum cans, which are the target objects on the manufacturing line. The image acquisition device uses a high-resolution camera and continuously captures multiple images in real time. The input is the manufacturing line through which the aluminum cans move, and the output is the acquired raw image data. This makes it possible to accurately record the current state of the target objects.

[0174] Step 2:

[0175] The server receives the acquired image data, and denoising is performed using Python and OpenCV. Specifically, a Gaussian filter is applied to reduce unwanted noise in the image. The input is the raw image data acquired in step 1, and the output is the denoised image data. This process lays the foundation for more accurate subsequent analysis.

[0176] Step 3:

[0177] The server performs edge detection on the denoised image. The Canny method of OpenCV is used to clarify the image contours. The input is the denoised image data, and the output is image data with enhanced contours. This process clarifies the shape of objects, enabling highly accurate analysis by AI models.

[0178] Step 4:

[0179] The server inputs edge-detected image data into an AI model, specifically a deep learning model using TensorFlow. A convolutional neural network (CNN) is used to extract features from the image data. The input is edge-enhanced image data, and the output is information about the presence or absence of defects and the condition of the product as an inspection result. During this process, the visual features of the image are analyzed to determine whether it is normal or defective.

[0180] Step 5:

[0181] The server sends the obtained inspection results to the terminal. The terminal notifies the user of these analysis results. Specifically, it displays a warning message for defective products on the display and plays an audio alert if necessary. The input is the inspection results from the AI ​​model, and the output is the visual and auditory information provided to the user. This step allows the user to immediately understand the situation on the production line.

[0182] Step 6:

[0183] The device uses an emotion engine to recognize the user's emotional state. It analyzes the user's facial expressions and voice tone captured by the camera and microphone. The input is the user's facial expression data and voice data, and the output is an evaluation of the user's emotional state. Using the Emotion API, it can determine if the user is showing dissatisfaction or confusion and dynamically change the notification content based on that.

[0184] Step 7:

[0185] The server stores all inspection results and user interaction history in a database. An SQL database is used to securely record the information and utilize it for future analysis and process improvement. Inputs are inspection result data and user interaction logs, and output is a database containing this organized information. This database contributes to the continuous optimization of product quality and user experience.

[0186] (Application Example 2)

[0187] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0188] There is a need to automate and streamline quality inspection on manufacturing lines while simultaneously improving the user experience. Conventional systems require human resources for inspecting defective products and struggle to respond to users' emotional states. To address this challenge, it is necessary to automatically identify the product's condition with high accuracy, while simultaneously analyzing user emotions and reactions in real time to dynamically adjust the interface.

[0189] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0190] In this invention, the server includes a device for collecting target video from an image acquisition function, an image manipulation device for edge detection and improvement, an analysis device using an artificial intelligence model for identifying the state of the target, and an emotion engine for analyzing the user's emotional state and dynamically adjusting the interface. This enables the automation of quality inspection and improvement of the user experience.

[0191] An "image acquisition function" refers to a device or process for collecting video footage of a target into the system.

[0192] Edge detection is a processing technique that identifies boundaries in an image and uses them to improve image quality.

[0193] An "image manipulation device" is a device or software that applies various processing to an image to improve its quality.

[0194] An "artificial intelligence model" is an algorithm or structure that learns from data and automatically performs a specific task; in this context, it is used to identify the state of the target.

[0195] An "analytical device" is a device used to examine data or information in detail and output the results.

[0196] The "emotion engine" is a function that analyzes the user's emotional state and automatically adjusts the system interface accordingly.

[0197] "User experience" refers to the overall experience and feelings a user has when using a product or service.

[0198] In this invention, the server uses multiple devices and software to perform quality inspections on the manufacturing line and improve the user experience. Specifically, an image acquisition function, an image manipulation device, an artificial intelligence model, an analysis device, and an emotion engine work together.

[0199] The image acquisition function captures images of the product in real time and sends the data to a server. This image data is processed by an image manipulation device for noise reduction and edge detection. The OpenCV library is often used for this process. The processed images are then input into an artificial intelligence model using TensorFlow or PyTorch to determine the product's condition and identify defective products.

[0200] The analysis results are transmitted in real time to the user's device, providing the user with notifications of defective products and operating guides. The device also uses an emotion engine to analyze the user's facial expressions and voice, recognizing their emotional state. By utilizing services such as Microsoft® Azure® Face API, the notification and information presentation methods can be dynamically adjusted in response to the user's reactions.

[0201] As a concrete example, in one factory, a server analyzes images of bottled beverages and notifies workers whenever a defective product is found. If the system determines that the worker is dissatisfied, detailed instructions are displayed on the terminal. In this way, the invented system enables quality control and rapid response to users.

[0202] An example of an input prompt for the generating AI model would be: "Analyze the following set of images to check for defective products. Also, check the user's facial expression image and select the appropriate notification method. If the user appears confused, provide additional guidance."

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] The server uses its image acquisition function to capture video of the product and receives the data in real time. This input data is raw video and is stored for subsequent processing.

[0206] Step 2:

[0207] The server performs noise reduction and edge detection on the video data received by the image manipulation device. The input is the video data from step 1, and by using the OpenCV library to remove unwanted noise and highlight important edges, it outputs highly accurate processed image data.

[0208] Step 3:

[0209] The server inputs the processed image data into an artificial intelligence model to identify the product's condition. Here, TensorFlow or PyTorch is used, employing deep learning techniques to identify defective products and outputting the results.

[0210] Step 4:

[0211] The server sends the analysis results to the terminal and notifies the user in real time whether there are any defective products. The output from step 3 becomes the input, and the terminal provides the information to the user visually or audibly.

[0212] Step 5:

[0213] The device analyzes facial expressions and voice data acquired from the user using an emotion engine to recognize the user's emotional state. This process utilizes Microsoft Azure's Face API, and the input data represents the user's current emotional state.

[0214] Step 6:

[0215] Based on the notification in step 4, the device dynamically adjusts the display and information delivery methods according to the user's emotional state. The input is the emotion analysis result from step 5, and the output is the adjusted display method for notifications and support information.

[0216] Step 7:

[0217] Users perform product quality control and corrections based on notifications and support information from the system. In this step, users operate the terminal and take appropriate action according to the displayed information.

[0218] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0219] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0220] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0221] [Second Embodiment]

[0222] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0223] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0224] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0225] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0226] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0227] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0228] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0229] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0230] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0231] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0232] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0233] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0234] This invention is a system for streamlining product inspection on a manufacturing line, and includes an image acquisition device, image processing means, analysis means, display and notification means, and database recording means. This allows for the automatic determination of the quality of the target product, specifically aluminum cans.

[0235] Detailed description of the embodiment

[0236] The server first collects real-time images of objects, such as aluminum cans, from image acquisition devices installed on the factory's production line. The image acquisition devices photograph the objects as they move along the rollers and transmit the image data to the server. This allows the server to obtain detailed visual data of the manufactured products in real time.

[0237] Next, the server uses image processing equipment to perform noise reduction and quality improvement on the received image data. Specifically, it adjusts the brightness and saturation of the image and performs edge detection to clearly display fine scratches and dents. This allows for the extraction of the maximum amount of information necessary for quality assessment.

[0238] The processed images are input into an artificial intelligence model on the server. Here, the analysis tool identifies the state of the object. The AI ​​model uses pre-trained characteristics of normal and defective products to perform real-time inspections. For example, it can identify dents or abnormal color differences in aluminum cans.

[0239] The judgment results are immediately sent from the server to the terminal, where they are displayed and notified for the terminal to check. If a defective product is detected, an alert is displayed on the terminal, and the user is notified with a warning sound and a displayed message. Detailed information is also displayed on the screen, such as "defective products detected on a specific shelf at a specific time."

[0240] Ultimately, the server records all inspection results in a database. This allows for data analysis during quality control at a later date, contributing to improvements in the manufacturing process and trend analysis.

[0241] Specific example

[0242] In a 24-hour aluminum can manufacturing line at a certain factory, a user monitors the production process via a monitor. A server continuously acquires images of aluminum cans moving along rollers, and after AI analysis, detects minute dents on the can's surface. This result is immediately transmitted to a terminal, and a notification is sent to the user if a defective product has been found. The user can then take immediate action on the production line, preventing the shipment of unnecessary defective products and maintaining the final product quality.

[0243] In this way, the system automatically performs highly accurate inspections, contributing to improved factory production efficiency and product quality.

[0244] The following describes the processing flow.

[0245] Step 1:

[0246] The server collects real-time images of aluminum cans moving on rollers from image acquisition devices within the factory. The camera captures a series of images of the cans at regular intervals and immediately transmits this data to the server.

[0247] Step 2:

[0248] The server performs basic image processing on the received image data, such as noise reduction and brightness / saturation correction. This prepares the image for easier analysis. Furthermore, an edge detection algorithm is applied to highlight fine anomalies on the can surface.

[0249] Step 3:

[0250] The server inputs the processed images into an artificial intelligence model to identify the product's condition. The AI ​​model has been pre-trained and operates a comparison algorithm that distinguishes between normal products and defective products (e.g., dents, scratches, foreign objects).

[0251] Step 4:

[0252] The server aggregates the results of the AI ​​analysis, and if a product is identified as defective, it extracts detailed information about it. If a product is determined to be defective, it identifies which part is faulty and how.

[0253] Step 5:

[0254] The server sends the judgment result to the terminal. Based on the received information, the terminal notifies the user in real time. When a defective product is detected, a warning is displayed on the terminal's screen, and if necessary, an audio alert is given to alert the user.

[0255] Step 6:

[0256] The server records all judgment results in a database, accumulating data that can be used for future quality control and statistical analysis. This data is then used to analyze long-term production trends and optimize manufacturing processes.

[0257] (Example 1)

[0258] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0259] Product quality inspection on manufacturing lines is a time-consuming and inefficient process that requires significant manpower. In particular, it is difficult to quickly and accurately identify minute defects and flaws in the products being inspected, leading to increased defect rates and problems in quality assurance. Furthermore, recording and analyzing quality data is time-consuming, making continuous improvement of the manufacturing process difficult.

[0260] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0261] In this invention, the server includes means for collecting information from a device that acquires visual information of an object, image processing means for removing noise and improving the quality of the information, and analysis means using a machine learning model that identifies the characteristics of the object using the processed information. This makes it possible to automatically inspect the quality of products on a manufacturing line in real time and with high accuracy.

[0262] "Target object" refers to the product that is subject to quality inspection on the manufacturing line.

[0263] A "device for acquiring visual information" is a device used to collect image and video data of objects on a manufacturing line.

[0264] "Noise reduction" is the process of removing unwanted background noise from acquired image or video data.

[0265] "Quality improvement" refers to the process of adjusting the visual characteristics of images and video data to clearly identify defects in the object being inspected.

[0266] "Image processing means" refers to technical means for applying noise reduction and quality improvement to visual information.

[0267] A "machine learning model" is an algorithm that uses training data to make predictions and judgments in order to identify the characteristics of an object.

[0268] "Analysis means" refers to technical means for evaluating the state of an object based on processed visual information and identifying its features and defects.

[0269] "Display and warning means" refers to a system function that displays the identification results obtained by the analysis means and, if necessary, alerts the user.

[0270] "Data storage means" refers to technical means for recording analysis results so that they can be referenced later.

[0271] This invention is an automated product inspection system for a manufacturing line, providing a method for efficiently evaluating the quality of the target product. The system includes a device for acquiring visual information of the target object, a server for image processing and analysis, and a terminal for displaying and warning the results.

[0272] The server first collects high-resolution image data from visual information acquisition devices installed on the manufacturing line. These devices accurately capture the details of fast-moving objects and transmit the data to the server in real time.

[0273] Next, the server performs image processing on the acquired visual information to remove noise and improve quality. Specifically, the server uses dedicated software to adjust the brightness and saturation of the image and applies an edge detection algorithm to clearly highlight minute defects in the object.

[0274] Subsequently, the processed image data is analyzed using a generative AI model. The server utilizes a deep learning-based machine learning model to identify patterns between normal and defective products. This allows for highly accurate determination of the object's condition. For example, it can quickly detect minute dents on the surface or abnormal color changes.

[0275] The analysis results are sent from the server to the terminal for user review. The terminal immediately displays the inspection results and issues visual and auditory warnings if defective products are detected. This allows the user to address the problem quickly.

[0276] Furthermore, the server records all inspection results in a data storage system and manages them as a history. This data can be used to continuously improve quality control and optimize the manufacturing process.

[0277] Specific example

[0278] The user can monitor the production line of aluminum can manufacturing and promptly adjust the line based on the analysis results provided by the server. The discovery of defective products is immediately notified on the terminal, which helps improve manufacturing efficiency and maintain high product quality.

[0279] Example of prompt sentence

[0280] "Please explain the real-time quality inspection system in the manufacturing process of aluminum cans. Please tell me how AI is used in the factory's production line, along with specific examples."

[0281] The flow of the specific process in Example 1 will be described using FIG. 11.

[0282] Step 1:

[0283] The server collects the image data of aluminum cans as input from a device that acquires visual information installed on the manufacturing line. This device is equipped with a high-resolution camera, which continuously acquires images according to the movement of the product and transmits them to the server. The server temporarily stores the received image data in storage to prepare for the next process.

[0284] Step 2:

[0285] The server performs image processing for noise removal and quality improvement using the collected image data as input. Specifically, as data processing, a filter is used to remove noise from the image, and the brightness and saturation are adjusted to improve visibility. Also, by applying an edge detection algorithm, fine scratches and dents on the surface of the aluminum can are emphasized. As a result, the processed image data is output and passed to the next process.

[0286] Step 3:

[0287] The server feeds the processed image data into the AI ​​model. The AI ​​model uses a deep learning-based machine learning algorithm to analyze the product's health based on past learning results. As part of the data calculation, the model extracts features from the image and determines whether it is a normal or defective product. The analysis results are output, and the process moves to the next step.

[0288] Step 4:

[0289] The server sends the analysis results of the AI ​​model to the terminal. The terminal displays the received identification results as input on its screen, and if a defective product is detected, it warns the user with sound and visual indicators. Specifically, the terminal displays a message saying "Defective product detected" and explains the details of the anomaly (e.g., the degree and location of the dent). The user can also perform additional verification tasks through the terminal's interface.

[0290] Step 5:

[0291] The server records all generated analysis results as input to the data storage system. The data is systematically stored for later reference and includes information such as the date and time of inspection, location, and type of defects detected. This recorded data can then be used as output to generate quality control reports and improve the manufacturing process.

[0292] (Application Example 1)

[0293] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0294] In modern manufacturing lines, automation of quality inspection is required, but conventional systems require a great deal of manpower and time to perform accurate inspections. Furthermore, if defective products are overlooked, there is a possibility of large-scale product recalls after shipment, which significantly impacts production efficiency. In particular, there is a need for a system that can rapidly control the production line in real time based on inspection results.

[0295] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0296] In this invention, the server includes means for collecting images of an object from an image acquisition device, image processing means for performing noise reduction and quality improvement on the images, analysis means using an artificial intelligence algorithm to identify the state of the object using the processed images, and production control means for issuing an instruction to the autonomous machine to stop the production line when the analysis means detects a defective product. This enables automation of product inspection on the manufacturing line, as well as high-precision and real-time control of the production line.

[0297] An "image acquisition device" is a device used to collect visual information of a target object.

[0298] "Noise reduction" is a process that reduces unwanted random fluctuations and errors in order to improve the quality of image data.

[0299] "Quality improvement" refers to a series of processes performed to enhance the visibility and analytical accuracy of image data.

[0300] "Image processing means" refers to a method for optimizing data by applying a specific algorithm to an acquired image.

[0301] An "artificial intelligence algorithm" is a type of computer program used to learn and identify the characteristics of an object.

[0302] The "analysis means" is a means for identifying and evaluating specific features and states based on the acquired data.

[0303] The "display and warning means" is a device or program that performs display and warning used to notify the user of the result of identification.

[0304] The "information recording means" is a means for storing the identified results and historical data and managing them for future reference.

[0305] The "autonomous machine" is a mechanical device that can perform specific operations based on its own judgment.

[0306] The "production control means" is a means for managing the progress of the production process and making adjustments as necessary.

[0307] In this invention, the server uses image acquisition devices installed on the production line to collect product images in real time. The server performs noise removal and quality improvement processing on the images and prepares to check whether there are fine scratches or dents on the surface of the aluminum cans. In this process, image processing software such as OpenCV is used.

[0308] The processed images are input into the artificial intelligence algorithm in the server. This algorithm analyzes the characteristics of good and defective products using a generative AI model. By using deep learning frameworks such as TensorFlow and Keras here, the state of the product can be identified with high accuracy.

[0309] The analysis results are immediately transmitted from the server to the terminal, and the terminal displays the analysis results to the user. The terminal functions as a display and warning means and issues a warning when a defective product is detected. Thereafter, the autonomous machine can stop the production line based on the instructions of the server. Through this cooperation, the shipment of defective products can be efficiently prevented and the product quality can be maintained.

[0310] As a concrete example, in one factory, the system is in operation, and users can monitor the status of the production line in real time. One day, the generative AI model detects a minor defect, the system immediately issues an alert, and an instruction is sent to the autonomous machine to stop the line. As a result, the user can immediately address the problem and adjust the production process. The generative AI system can be improved based on a prompt message such as, "What algorithm would be most effective in exploring new ways to streamline product inspection?"

[0311] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0312] Step 1:

[0313] The server collects images of products from image acquisition equipment installed on the manufacturing line. During this process, the camera continuously photographs moving aluminum cans on the line and transmits the resulting image data to the server. The server receives this data as input.

[0314] Step 2:

[0315] The server performs noise reduction and quality enhancement on the received image data. For noise reduction, it uses OpenCV's Gaussian blur function to smooth the image, and for quality enhancement, it adjusts the brightness and contrast of the image to improve its clarity. The processed image data is then output.

[0316] Step 3:

[0317] The server inputs the processed image data into an artificial intelligence algorithm. Using a generative AI model, the AI ​​analyzes the features in the image and identifies whether the product is good or defective. Based on pre-trained data, the AI ​​detects minute defects on the product. The analysis results are output as identification information.

[0318] Step 4:

[0319] The server sends the identified results to the terminal. The terminal displays the results, allowing the user to check the product quality status in real time. If a defective product is detected, the terminal issues a warning and displays an alert on the screen. This notification is intended to allow the user to take quick action.

[0320] Step 5:

[0321] If a defective product is detected, the server instructs the autonomous machine to stop the production line. This instruction is transmitted to the autonomous machine via communication, and upon receiving it, the machine temporarily suspends the line's operation. This prevents defective products from being shipped.

[0322] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0323] This invention provides a system for streamlining product inspection on a manufacturing line and improving the user experience. It includes an image acquisition device, image processing means, analysis means using an artificial intelligence model, display and notification means, and database recording means, as well as an emotion engine that recognizes user emotions. This system enables a highly automated inspection process, maintains product quality, and provides an interface that considers the user's emotional state.

[0324] Detailed description of the embodiment

[0325] The server uses image acquisition equipment within the factory to capture images of aluminum cans moving along rollers. These images are transmitted to the server in real time, and the server performs quality improvement processing on the received images using noise reduction and edge detection algorithms. The processed image data is input into an artificial intelligence model using deep learning to analyze the presence of defects and the condition of the products. The results of this AI analysis are immediately sent from the server to the terminal.

[0326] The terminal provides real-time notifications to the user based on analysis results received from the server. The display and notification system displays a warning when a defective product is identified and provides an audio alert as needed. This information allows the user to take appropriate action immediately.

[0327] Furthermore, this system integrates an emotion engine, which analyzes data obtained from the user's facial expressions and voice to determine the user's emotional state. For example, if the user shows signs of dissatisfaction or confusion, the system dynamically adjusts the interface display and notification process, and adds supportive information to make it easier for the user to understand.

[0328] The database recording system records inspection results and user interaction history to help improve quality and optimize the user experience in the future. All data is securely stored and contributes to subsequent trend analysis and improvements to the manufacturing process.

[0329] Specific example

[0330] On a production line one day, while a user is monitoring the system, the server acquires images of newly arrived aluminum cans and performs AI-powered defect inspection. The terminal notifies the user of the detected defects, while an emotion engine analyzes the user's facial expressions to detect signs of attention or dissatisfaction. The terminal automatically selects the most appropriate way to display the information for the user, adding detailed instructions and support information to help the user respond quickly.

[0331] In this way, this system contributes to maintaining product quality and improving work efficiency by streamlining the manufacturing process and providing a flexible operating environment that takes user emotions into consideration.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] The server continuously acquires images of aluminum cans from image acquisition devices located on the production line. Acquisition is performed in real time, and the image data is immediately sent to the server to prepare it for processing.

[0335] Step 2:

[0336] The server performs image processing on the received image, removing noise and adjusting brightness and contrast. This process improves image visibility, and by applying an edge detection algorithm, it makes it easier to identify fine defects on the can surface.

[0337] Step 3:

[0338] The processed images are input into an artificial intelligence model on the server. The AI ​​model analyzes the images based on pre-trained data and determines whether the product is normal or defective. It can identify abnormalities such as dents and scratches with high accuracy.

[0339] Step 4:

[0340] The server evaluates the analysis results of the artificial intelligence model and records the details if a defective product is identified. The evaluation results immediately lead to the next step.

[0341] Step 5:

[0342] The server sends the analysis results to the terminal. Based on the data received by the terminal, it notifies the user in real time of the detection of defective products.

[0343] Step 6:

[0344] Devices equipped with an emotion engine analyze the user's facial expressions and voice to determine the user's emotional state. If there are signs that the user is dissatisfied or has questions, the content of the conversation and the interface are adjusted accordingly.

[0345] Step 7:

[0346] The device adjusts the displayed content according to the user's emotional state. It presents information in a format that is easy for the user to understand, and adds supplementary explanations and support information as needed to facilitate smooth communication.

[0347] Step 8:

[0348] The server records all test results and user feedback data in a database. This enables analysis aimed at improving the efficiency of the manufacturing line and enhancing the user experience.

[0349] (Example 2)

[0350] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0351] Modern manufacturing lines demand improved inspection accuracy and process efficiency in product inspection. However, conventional technologies lack high-precision defect inspection systems that integrate image processing and artificial intelligence, resulting in insufficient automation and cost reduction in quality control. Furthermore, there are insufficient means to reduce the burden on users and improve the user experience. Therefore, there is a need to provide a system that solves these problems and enhances the efficiency of the entire manufacturing process.

[0352] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0353] In this invention, the server includes means for collecting images of an object from an image acquisition device, image processing means for applying noise reduction and edge detection algorithms to the images, and analysis means for using a generative AI model to identify the state of the object using the processed images. This enables high-precision and efficient product inspection, as well as dynamic adjustment of the interface according to the user's emotional state.

[0354] An "image acquisition device" is a device used to collect images of an object, and specifically refers to a device capable of acquiring images of products moving along a manufacturing line in real time.

[0355] "Noise reduction" is the process of removing unwanted information from a digital image in order to improve image quality.

[0356] An "edge detection algorithm" is a processing technique used to detect the contours of objects in an image, and is used to clarify the shape and boundaries of objects.

[0357] A "generative AI model" is a pre-trained model designed to analyze the features of images and data using artificial intelligence technology and to identify the state of an object.

[0358] "Analysis means" refers to methods and processes for determining whether an object is defective or identifying its condition based on processed image data.

[0359] "Display and notification means" refers to a system for visually or audibly communicating the results of the analysis to the user, thereby encouraging the user to take prompt action.

[0360] A "database recording system" is a data management system that securely stores data such as analysis results and user operation history, and uses it for future quality control and system improvement.

[0361] "Dynamic interface adjustment" is the process of appropriately changing the displayed content and notification methods according to the user's emotional state and operating environment.

[0362] This invention is a system for highly automating product inspection on a manufacturing line and improving efficiency. The following describes the embodiments for implementing this system.

[0363] The server collects images of the target object, aluminum cans, through an image acquisition device. This image acquisition device is a camera installed on the manufacturing line that captures images of products moving in real time. The server then applies noise reduction and edge detection algorithms to the collected images using Python and OpenCV to improve image quality. A Gaussian filter is used for noise reduction, and the Canny method is used for edge detection.

[0364] Next, the server inputs the improved image quality into an AI model, specifically a deep learning model using TensorFlow. This model uses a convolutional neural network (CNN) to extract features from the image data and identify whether or not there are defective products and to determine the product's condition.

[0365] The identification results are sent from the server to the terminal. Based on these results, the terminal notifies the user in real time. Specifically, it displays a warning of defective product detection on the display and issues an audio alert if necessary, enabling the user to respond quickly.

[0366] Furthermore, the device has an integrated emotion engine that determines the user's emotional state based on data acquired from the camera and microphone. For example, it uses the Emotion API to analyze facial expressions and voice tone, and if the user is showing signs of dissatisfaction or confusion, it dynamically adjusts the interface display and adds personalized support information.

[0367] Inspection results and user interaction history are recorded in a database. This data is securely stored using an SQL database and used for trend analysis to improve quality and enhance manufacturing processes.

[0368] As a concrete example, a server acquires an image of an aluminum can, performs a defect inspection using an AI model, and sends the results to a terminal. The terminal receives the defect information and notifies the user. If the user shows signs of dissatisfaction, the terminal adjusts its interface and displays detailed instructions on how to resolve the issue.

[0369] An example of a prompt is: "Design a system that uses image processing and an AI model to inspect products on a manufacturing line and notifies the user of the results in real time. The system should recognize the user's emotional state and dynamically adjust the interface." By using an AI model generated based on such prompts, it is possible to achieve efficient product inspection and improve the user's work environment.

[0370] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0371] Step 1:

[0372] The server controls the image acquisition device to capture images of aluminum cans, which are the target objects on the manufacturing line. The image acquisition device uses a high-resolution camera and continuously captures multiple images in real time. The input is the manufacturing line through which the aluminum cans move, and the output is the acquired raw image data. This makes it possible to accurately record the current state of the target objects.

[0373] Step 2:

[0374] The server receives the acquired image data, and denoising is performed using Python and OpenCV. Specifically, a Gaussian filter is applied to reduce unwanted noise in the image. The input is the raw image data acquired in step 1, and the output is the denoised image data. This process lays the foundation for more accurate subsequent analysis.

[0375] Step 3:

[0376] The server performs edge detection on the denoised image. The Canny method of OpenCV is used to clarify the image contours. The input is the denoised image data, and the output is image data with enhanced contours. This process clarifies the shape of objects, enabling highly accurate analysis by AI models.

[0377] Step 4:

[0378] The server inputs edge-detected image data into an AI model, specifically a deep learning model using TensorFlow. A convolutional neural network (CNN) is used to extract features from the image data. The input is edge-enhanced image data, and the output is information about the presence or absence of defects and the condition of the product as an inspection result. During this process, the visual features of the image are analyzed to determine whether it is normal or defective.

[0379] Step 5:

[0380] The server sends the obtained inspection results to the terminal. The terminal notifies the user of these analysis results. Specifically, it displays a warning message for defective products on the display and plays an audio alert if necessary. The input is the inspection results from the AI ​​model, and the output is the visual and auditory information provided to the user. This step allows the user to immediately understand the situation on the production line.

[0381] Step 6:

[0382] The device uses an emotion engine to recognize the user's emotional state. It analyzes the user's facial expressions and voice tone captured by the camera and microphone. The input is the user's facial expression data and voice data, and the output is an evaluation of the user's emotional state. Using the Emotion API, it can determine if the user is showing dissatisfaction or confusion and dynamically change the notification content based on that.

[0383] Step 7:

[0384] The server stores all inspection results and user interaction history in a database. An SQL database is used to securely record the information and utilize it for future analysis and process improvement. Inputs are inspection result data and user interaction logs, and output is a database containing this organized information. This database contributes to the continuous optimization of product quality and user experience.

[0385] (Application Example 2)

[0386] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0387] There is a need to automate and streamline quality inspection on manufacturing lines while simultaneously improving the user experience. Conventional systems require human resources for inspecting defective products and struggle to respond to users' emotional states. To address this challenge, it is necessary to automatically identify the product's condition with high accuracy, while simultaneously analyzing user emotions and reactions in real time to dynamically adjust the interface.

[0388] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0389] In this invention, the server includes a device for collecting target video from an image acquisition function, an image manipulation device for edge detection and improvement, an analysis device using an artificial intelligence model for identifying the state of the target, and an emotion engine for analyzing the user's emotional state and dynamically adjusting the interface. This enables the automation of quality inspection and improvement of the user experience.

[0390] An "image acquisition function" refers to a device or process for collecting video footage of a target into the system.

[0391] Edge detection is a processing technique that identifies boundaries in an image and uses them to improve image quality.

[0392] An "image manipulation device" is a device or software that applies various processing to an image to improve its quality.

[0393] An "artificial intelligence model" is an algorithm or structure that learns from data and automatically performs a specific task; in this context, it is used to identify the state of the target.

[0394] An "analytical device" is a device used to examine data or information in detail and output the results.

[0395] The "emotion engine" is a function that analyzes the user's emotional state and automatically adjusts the system interface accordingly.

[0396] "User experience" refers to the overall experience and feelings a user has when using a product or service.

[0397] In this invention, the server uses multiple devices and software to perform quality inspections on the manufacturing line and improve the user experience. Specifically, an image acquisition function, an image manipulation device, an artificial intelligence model, an analysis device, and an emotion engine work together.

[0398] The image acquisition function captures images of the product in real time and sends the data to a server. This image data is processed by an image manipulation device for noise reduction and edge detection. The OpenCV library is often used for this process. The processed images are then input into an artificial intelligence model using TensorFlow or PyTorch to determine the product's condition and identify defective products.

[0399] The analysis results are transmitted in real time to the user's device, providing the user with notifications of defective products and operating guides. The device also uses an emotion engine to analyze the user's facial expressions and voice, recognizing their emotional state. By utilizing services such as Microsoft Azure's Face API, the notification and information presentation methods can be dynamically adjusted in response to the user's reactions.

[0400] As a concrete example, in one factory, a server analyzes images of bottled beverages and notifies workers whenever a defective product is found. If the system determines that the worker is dissatisfied, detailed instructions are displayed on the terminal. In this way, the invented system enables quality control and rapid response to users.

[0401] An example of an input prompt for the generating AI model would be: "Analyze the following set of images to check for defective products. Also, check the user's facial expression image and select the appropriate notification method. If the user appears confused, provide additional guidance."

[0402] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0403] Step 1:

[0404] The server uses its image acquisition function to capture video of the product and receives the data in real time. This input data is raw video and is stored for subsequent processing.

[0405] Step 2:

[0406] The server performs noise reduction and edge detection on the video data received by the image manipulation device. The input is the video data from step 1, and by using the OpenCV library to remove unwanted noise and highlight important edges, it outputs highly accurate processed image data.

[0407] Step 3:

[0408] The server inputs the processed image data into an artificial intelligence model to identify the product's condition. Here, TensorFlow or PyTorch is used, employing deep learning techniques to identify defective products and outputting the results.

[0409] Step 4:

[0410] The server sends the analysis results to the terminal and notifies the user in real time whether there are any defective products. The output from step 3 becomes the input, and the terminal provides the information to the user visually or audibly.

[0411] Step 5:

[0412] The device analyzes facial expressions and voice data acquired from the user using an emotion engine to recognize the user's emotional state. This process utilizes Microsoft Azure's Face API, and the input data represents the user's current emotional state.

[0413] Step 6:

[0414] Based on the notification in step 4, the device dynamically adjusts the display and information delivery methods according to the user's emotional state. The input is the emotion analysis result from step 5, and the output is the adjusted display method for notifications and support information.

[0415] Step 7:

[0416] Users perform product quality control and corrections based on notifications and support information from the system. In this step, users operate the terminal and take appropriate action according to the displayed information.

[0417] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0418] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0419] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0420] [Third Embodiment]

[0421] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0422] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0423] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0424] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0425] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0426] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0427] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0428] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0429] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0430] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0431] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0432] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0433] This invention is a system for streamlining product inspection on a manufacturing line, and includes an image acquisition device, image processing means, analysis means, display and notification means, and database recording means. This allows for the automatic determination of the quality of the target product, specifically aluminum cans.

[0434] Detailed description of the embodiment

[0435] The server first collects real-time images of objects, such as aluminum cans, from image acquisition devices installed on the factory's production line. The image acquisition devices photograph the objects as they move along the rollers and transmit the image data to the server. This allows the server to obtain detailed visual data of the manufactured products in real time.

[0436] Next, the server uses image processing equipment to perform noise reduction and quality improvement on the received image data. Specifically, it adjusts the brightness and saturation of the image and performs edge detection to clearly display fine scratches and dents. This allows for the extraction of the maximum amount of information necessary for quality assessment.

[0437] The processed images are input into an artificial intelligence model on the server. Here, the analysis tool identifies the state of the object. The AI ​​model uses pre-trained characteristics of normal and defective products to perform real-time inspections. For example, it can identify dents or abnormal color differences in aluminum cans.

[0438] The judgment results are immediately sent from the server to the terminal, where they are displayed and notified for the terminal to check. If a defective product is detected, an alert is displayed on the terminal, and the user is notified with a warning sound and a displayed message. Detailed information is also displayed on the screen, such as "defective products detected on a specific shelf at a specific time."

[0439] Ultimately, the server records all inspection results in a database. This allows for data analysis during quality control at a later date, contributing to improvements in the manufacturing process and trend analysis.

[0440] Specific example

[0441] In a 24-hour aluminum can manufacturing line at a certain factory, a user monitors the production process via a monitor. A server continuously acquires images of aluminum cans moving along rollers, and after AI analysis, detects minute dents on the can's surface. This result is immediately transmitted to a terminal, and a notification is sent to the user if a defective product has been found. The user can then take immediate action on the production line, preventing the shipment of unnecessary defective products and maintaining the final product quality.

[0442] In this way, the system automatically performs highly accurate inspections, contributing to improved factory production efficiency and product quality.

[0443] The following describes the processing flow.

[0444] Step 1:

[0445] The server collects real-time images of aluminum cans moving on rollers from image acquisition devices within the factory. The camera captures a series of images of the cans at regular intervals and immediately transmits this data to the server.

[0446] Step 2:

[0447] The server performs basic image processing on the received image data, such as noise reduction and brightness / saturation correction. This prepares the image for easier analysis. Furthermore, an edge detection algorithm is applied to highlight fine anomalies on the can surface.

[0448] Step 3:

[0449] The server inputs the processed images into an artificial intelligence model to identify the product's condition. The AI ​​model has been pre-trained and operates a comparison algorithm that distinguishes between normal products and defective products (e.g., dents, scratches, foreign objects).

[0450] Step 4:

[0451] The server aggregates the results of the AI ​​analysis, and if a product is identified as defective, it extracts detailed information about it. If a product is determined to be defective, it identifies which part is faulty and how.

[0452] Step 5:

[0453] The server sends the judgment result to the terminal. Based on the received information, the terminal notifies the user in real time. When a defective product is detected, a warning is displayed on the terminal's screen, and if necessary, an audio alert is given to alert the user.

[0454] Step 6:

[0455] The server records all judgment results in a database, accumulating data that can be used for future quality control and statistical analysis. This data is then used to analyze long-term production trends and optimize manufacturing processes.

[0456] (Example 1)

[0457] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0458] Product quality inspection on manufacturing lines is a time-consuming and inefficient process that requires significant manpower. In particular, it is difficult to quickly and accurately identify minute defects and flaws in the products being inspected, leading to increased defect rates and problems in quality assurance. Furthermore, recording and analyzing quality data is time-consuming, making continuous improvement of the manufacturing process difficult.

[0459] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0460] In this invention, the server includes means for collecting information from a device that acquires visual information of an object, image processing means for removing noise and improving the quality of the information, and analysis means using a machine learning model that identifies the characteristics of the object using the processed information. This makes it possible to automatically inspect the quality of products on a manufacturing line in real time and with high accuracy.

[0461] "Target object" refers to the product that is subject to quality inspection on the manufacturing line.

[0462] A "device for acquiring visual information" is a device used to collect image and video data of objects on a manufacturing line.

[0463] "Noise reduction" is the process of removing unwanted background noise from acquired image or video data.

[0464] "Quality improvement" refers to the process of adjusting the visual characteristics of images and video data to clearly identify defects in the object being inspected.

[0465] "Image processing means" refers to technical means for applying noise reduction and quality improvement to visual information.

[0466] A "machine learning model" is an algorithm that uses training data to make predictions and judgments in order to identify the characteristics of an object.

[0467] "Analysis means" refers to technical means for evaluating the state of an object based on processed visual information and identifying its features and defects.

[0468] "Display and warning means" refers to a system function that displays the identification results obtained by the analysis means and, if necessary, alerts the user.

[0469] "Data storage means" refers to technical means for recording analysis results so that they can be referenced later.

[0470] This invention is an automated product inspection system for a manufacturing line, providing a method for efficiently evaluating the quality of the target product. The system includes a device for acquiring visual information of the target object, a server for image processing and analysis, and a terminal for displaying and warning the results.

[0471] The server first collects high-resolution image data from visual information acquisition devices installed on the manufacturing line. These devices accurately capture the details of fast-moving objects and transmit the data to the server in real time.

[0472] Next, the server performs image processing on the acquired visual information to remove noise and improve quality. Specifically, the server uses dedicated software to adjust the brightness and saturation of the image and applies an edge detection algorithm to clearly highlight minute defects in the object.

[0473] Subsequently, the processed image data is analyzed using a generative AI model. The server utilizes a deep learning-based machine learning model to identify patterns between normal and defective products. This allows for highly accurate determination of the object's condition. For example, it can quickly detect minute dents on the surface or abnormal color changes.

[0474] The analysis results are sent from the server to the terminal for user review. The terminal immediately displays the inspection results and issues visual and auditory warnings if defective products are detected. This allows the user to address the problem quickly.

[0475] Furthermore, the server records all inspection results in a data storage system and manages them as a history. This data can be used to continuously improve quality control and optimize the manufacturing process.

[0476] Specific example

[0477] Users can monitor the aluminum can manufacturing production line and quickly adjust the line based on analysis results provided by the server. Defective products are immediately notified via the terminal, helping to improve manufacturing efficiency and maintain high product quality.

[0478] Example of a prompt

[0479] "Please describe a real-time quality inspection system used in the aluminum can manufacturing process. Please explain, with specific examples, how AI is being used on the factory production line."

[0480] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0481] Step 1:

[0482] The server collects image data of aluminum cans as input from a visual information acquisition device installed on the production line. This device is equipped with a high-resolution camera and continuously acquires images as the product moves, transmitting them to the server. The server temporarily stores the received image data in storage in preparation for the next processing step.

[0483] Step 2:

[0484] The server takes the collected image data as input and performs image processing to remove noise and improve quality. Specifically, it uses filters to remove noise from the image as part of data processing, and adjusts brightness and saturation to improve visibility. It also applies an edge detection algorithm to highlight minute scratches and dents on the surface of the aluminum can. As a result, the processed image data is passed to the next process as output.

[0485] Step 3:

[0486] The server feeds the processed image data into the AI ​​model. The AI ​​model uses a deep learning-based machine learning algorithm to analyze the product's health based on past learning results. As part of the data calculation, the model extracts features from the image and determines whether it is a normal or defective product. The analysis results are output, and the process moves to the next step.

[0487] Step 4:

[0488] The server sends the analysis results of the AI ​​model to the terminal. The terminal displays the received identification results as input on its screen, and if a defective product is detected, it warns the user with sound and visual indicators. Specifically, the terminal displays a message saying "Defective product detected" and explains the details of the anomaly (e.g., the degree and location of the dent). The user can also perform additional verification tasks through the terminal's interface.

[0489] Step 5:

[0490] The server records all generated analysis results as input to the data storage system. The data is systematically stored for later reference and includes information such as the date and time of inspection, location, and type of defects detected. This recorded data can then be used as output to generate quality control reports and improve the manufacturing process.

[0491] (Application Example 1)

[0492] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0493] In modern manufacturing lines, automation of quality inspection is required, but conventional systems require a great deal of manpower and time to perform accurate inspections. Furthermore, if defective products are overlooked, there is a possibility of large-scale product recalls after shipment, which significantly impacts production efficiency. In particular, there is a need for a system that can rapidly control the production line in real time based on inspection results.

[0494] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0495] In this invention, the server includes means for collecting images of an object from an image acquisition device, image processing means for performing noise reduction and quality improvement on the images, analysis means using an artificial intelligence algorithm to identify the state of the object using the processed images, and production control means for issuing an instruction to the autonomous machine to stop the production line when the analysis means detects a defective product. This enables automation of product inspection on the manufacturing line, as well as high-precision and real-time control of the production line.

[0496] An "image acquisition device" is a device used to collect visual information of a target object.

[0497] "Noise reduction" is a process that reduces unwanted random fluctuations and errors in order to improve the quality of image data.

[0498] "Quality improvement" refers to a series of processes performed to enhance the visibility and analytical accuracy of image data.

[0499] "Image processing means" refers to a method for optimizing data by applying a specific algorithm to an acquired image.

[0500] An "artificial intelligence algorithm" is a type of computer program used to learn and identify the characteristics of an object.

[0501] "Analysis means" are methods for identifying and evaluating specific characteristics or states based on acquired data.

[0502] "Display and warning means" refers to devices or programs that provide displays and warnings to inform the user of the results of the identification.

[0503] "Information recording means" refers to means for storing identified results and historical data and managing them so that they can be referenced at a later date.

[0504] An "autonomous machine" is a mechanical device that can perform specific actions based on its own judgment.

[0505] "Production control means" are means for managing the progress of the production process and making adjustments as needed.

[0506] In this invention, the server collects images of the product in real time using image acquisition equipment installed on the manufacturing line. The server then performs noise reduction and quality improvement processing on these images to prepare them for checking for minor scratches or dents on the surface of the aluminum cans. Image processing software such as OpenCV is used for this process.

[0507] The processed images are input into an artificial intelligence algorithm on the server. This algorithm uses a generative AI model to analyze the characteristics of good and defective products. By using deep learning frameworks such as TensorFlow and Keras, the condition of the products can be identified with high accuracy.

[0508] Analysis results are immediately transmitted from the server to the terminal, which displays the results to the user. The terminal functions as a display and warning system, issuing a warning if a defective product is detected. Subsequently, the autonomous machine can stop the production line based on instructions from the server. This collaboration efficiently prevents the shipment of defective products and maintains product quality.

[0509] As a concrete example, in one factory, the system is in operation, and users can monitor the status of the production line in real time. One day, the generative AI model detects a minor defect, the system immediately issues an alert, and an instruction is sent to the autonomous machine to stop the line. As a result, the user can immediately address the problem and adjust the production process. The generative AI system can be improved based on a prompt message such as, "What algorithm would be most effective in exploring new ways to streamline product inspection?"

[0510] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0511] Step 1:

[0512] The server collects images of products from image acquisition equipment installed on the manufacturing line. During this process, the camera continuously photographs moving aluminum cans on the line and transmits the resulting image data to the server. The server receives this data as input.

[0513] Step 2:

[0514] The server performs noise reduction and quality enhancement on the received image data. For noise reduction, it uses OpenCV's Gaussian blur function to smooth the image, and for quality enhancement, it adjusts the brightness and contrast of the image to improve its clarity. The processed image data is then output.

[0515] Step 3:

[0516] The server inputs the processed image data into an artificial intelligence algorithm. Using a generative AI model, the AI ​​analyzes the features in the image and identifies whether the product is good or defective. Based on pre-trained data, the AI ​​detects minute defects on the product. The analysis results are output as identification information.

[0517] Step 4:

[0518] The server sends the identified results to the terminal. The terminal displays the results, allowing the user to check the product quality status in real time. If a defective product is detected, the terminal issues a warning and displays an alert on the screen. This notification is intended to allow the user to take quick action.

[0519] Step 5:

[0520] If a defective product is detected, the server instructs the autonomous machine to stop the production line. This instruction is transmitted to the autonomous machine via communication, and upon receiving it, the machine temporarily suspends the line's operation. This prevents defective products from being shipped.

[0521] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0522] This invention provides a system for streamlining product inspection on a manufacturing line and improving the user experience. It includes an image acquisition device, image processing means, analysis means using an artificial intelligence model, display and notification means, and database recording means, as well as an emotion engine that recognizes user emotions. This system enables a highly automated inspection process, maintains product quality, and provides an interface that considers the user's emotional state.

[0523] Detailed description of the embodiment

[0524] The server uses image acquisition equipment within the factory to capture images of aluminum cans moving along rollers. These images are transmitted to the server in real time, and the server performs quality improvement processing on the received images using noise reduction and edge detection algorithms. The processed image data is input into an artificial intelligence model using deep learning to analyze the presence of defects and the condition of the products. The results of this AI analysis are immediately sent from the server to the terminal.

[0525] The terminal provides real-time notifications to the user based on analysis results received from the server. The display and notification system displays a warning when a defective product is identified and provides an audio alert as needed. This information allows the user to take appropriate action immediately.

[0526] Furthermore, this system integrates an emotion engine, which analyzes data obtained from the user's facial expressions and voice to determine the user's emotional state. For example, if the user shows signs of dissatisfaction or confusion, the system dynamically adjusts the interface display and notification process, and adds supportive information to make it easier for the user to understand.

[0527] The database recording system records inspection results and user interaction history to help improve quality and optimize the user experience in the future. All data is securely stored and contributes to subsequent trend analysis and improvements to the manufacturing process.

[0528] Specific example

[0529] On a production line one day, while a user is monitoring the system, the server acquires images of newly arrived aluminum cans and performs AI-powered defect inspection. The terminal notifies the user of the detected defects, while an emotion engine analyzes the user's facial expressions to detect signs of attention or dissatisfaction. The terminal automatically selects the most appropriate way to display the information for the user, adding detailed instructions and support information to help the user respond quickly.

[0530] In this way, this system contributes to maintaining product quality and improving work efficiency by streamlining the manufacturing process and providing a flexible operating environment that takes user emotions into consideration.

[0531] The following describes the processing flow.

[0532] Step 1:

[0533] The server continuously acquires images of aluminum cans from image acquisition devices located on the production line. Acquisition is performed in real time, and the image data is immediately sent to the server to prepare it for processing.

[0534] Step 2:

[0535] The server performs image processing on the received image, removing noise and adjusting brightness and contrast. This process improves image visibility, and by applying an edge detection algorithm, it makes it easier to identify fine defects on the can surface.

[0536] Step 3:

[0537] The processed images are input into an artificial intelligence model on the server. The AI ​​model analyzes the images based on pre-trained data and determines whether the product is normal or defective. It can identify abnormalities such as dents and scratches with high accuracy.

[0538] Step 4:

[0539] The server evaluates the analysis results of the artificial intelligence model and records the details if a defective product is identified. The evaluation results immediately lead to the next step.

[0540] Step 5:

[0541] The server sends the analysis results to the terminal. Based on the data received by the terminal, it notifies the user in real time of the detection of defective products.

[0542] Step 6:

[0543] Devices equipped with an emotion engine analyze the user's facial expressions and voice to determine the user's emotional state. If there are signs that the user is dissatisfied or has questions, the content of the conversation and the interface are adjusted accordingly.

[0544] Step 7:

[0545] The device adjusts the displayed content according to the user's emotional state. It presents information in a format that is easy for the user to understand, and adds supplementary explanations and support information as needed to facilitate smooth communication.

[0546] Step 8:

[0547] The server records all test results and user feedback data in a database. This enables analysis aimed at improving the efficiency of the manufacturing line and enhancing the user experience.

[0548] (Example 2)

[0549] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0550] Modern manufacturing lines demand improved inspection accuracy and process efficiency in product inspection. However, conventional technologies lack high-precision defect inspection systems that integrate image processing and artificial intelligence, resulting in insufficient automation and cost reduction in quality control. Furthermore, there are insufficient means to reduce the burden on users and improve the user experience. Therefore, there is a need to provide a system that solves these problems and enhances the efficiency of the entire manufacturing process.

[0551] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0552] In this invention, the server includes means for collecting images of an object from an image acquisition device, image processing means for applying noise reduction and edge detection algorithms to the images, and analysis means for using a generative AI model to identify the state of the object using the processed images. This enables high-precision and efficient product inspection, as well as dynamic adjustment of the interface according to the user's emotional state.

[0553] An "image acquisition device" is a device used to collect images of an object, and specifically refers to a device capable of acquiring images of products moving along a manufacturing line in real time.

[0554] "Noise reduction" is the process of removing unwanted information from a digital image in order to improve image quality.

[0555] An "edge detection algorithm" is a processing technique used to detect the contours of objects in an image, and is used to clarify the shape and boundaries of objects.

[0556] A "generative AI model" is a pre-trained model designed to analyze the features of images and data using artificial intelligence technology and to identify the state of an object.

[0557] "Analysis means" refers to methods and processes for determining whether an object is defective or identifying its condition based on processed image data.

[0558] "Display and notification means" refers to a system for visually or audibly communicating the results of the analysis to the user, thereby encouraging the user to take prompt action.

[0559] A "database recording system" is a data management system that securely stores data such as analysis results and user operation history, and uses it for future quality control and system improvement.

[0560] "Dynamic interface adjustment" is the process of appropriately changing the displayed content and notification methods according to the user's emotional state and operating environment.

[0561] This invention is a system for highly automating product inspection on a manufacturing line and improving efficiency. The following describes the embodiments for implementing this system.

[0562] The server collects images of the target object, aluminum cans, through an image acquisition device. This image acquisition device is a camera installed on the manufacturing line that captures images of products moving in real time. The server then applies noise reduction and edge detection algorithms to the collected images using Python and OpenCV to improve image quality. A Gaussian filter is used for noise reduction, and the Canny method is used for edge detection.

[0563] Next, the server inputs the improved image quality into an AI model, specifically a deep learning model using TensorFlow. This model uses a convolutional neural network (CNN) to extract features from the image data and identify whether or not there are defective products and to determine the product's condition.

[0564] The identification results are sent from the server to the terminal. Based on these results, the terminal notifies the user in real time. Specifically, it displays a warning of defective product detection on the display and issues an audio alert if necessary, enabling the user to respond quickly.

[0565] Furthermore, the device has an integrated emotion engine that determines the user's emotional state based on data acquired from the camera and microphone. For example, it uses the Emotion API to analyze facial expressions and voice tone, and if the user is showing signs of dissatisfaction or confusion, it dynamically adjusts the interface display and adds personalized support information.

[0566] Inspection results and user interaction history are recorded in a database. This data is securely stored using an SQL database and used for trend analysis to improve quality and enhance manufacturing processes.

[0567] As a concrete example, a server acquires an image of an aluminum can, performs a defect inspection using an AI model, and sends the results to a terminal. The terminal receives the defect information and notifies the user. If the user shows signs of dissatisfaction, the terminal adjusts its interface and displays detailed instructions on how to resolve the issue.

[0568] An example of a prompt is: "Design a system that uses image processing and an AI model to inspect products on a manufacturing line and notifies the user of the results in real time. The system should recognize the user's emotional state and dynamically adjust the interface." By using an AI model generated based on such prompts, it is possible to achieve efficient product inspection and improve the user's work environment.

[0569] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0570] Step 1:

[0571] The server controls the image acquisition device to capture images of aluminum cans, which are the target objects on the manufacturing line. The image acquisition device uses a high-resolution camera and continuously captures multiple images in real time. The input is the manufacturing line through which the aluminum cans move, and the output is the acquired raw image data. This makes it possible to accurately record the current state of the target objects.

[0572] Step 2:

[0573] The server receives the acquired image data, and denoising is performed using Python and OpenCV. Specifically, a Gaussian filter is applied to reduce unwanted noise in the image. The input is the raw image data acquired in step 1, and the output is the denoised image data. This process lays the foundation for more accurate subsequent analysis.

[0574] Step 3:

[0575] The server performs edge detection on the denoised image. The Canny method of OpenCV is used to clarify the image contours. The input is the denoised image data, and the output is image data with enhanced contours. This process clarifies the shape of objects, enabling highly accurate analysis by AI models.

[0576] Step 4:

[0577] The server inputs edge-detected image data into an AI model, specifically a deep learning model using TensorFlow. A convolutional neural network (CNN) is used to extract features from the image data. The input is edge-enhanced image data, and the output is information about the presence or absence of defects and the condition of the product as an inspection result. During this process, the visual features of the image are analyzed to determine whether it is normal or defective.

[0578] Step 5:

[0579] The server sends the obtained inspection results to the terminal. The terminal notifies the user of these analysis results. Specifically, it displays a warning message for defective products on the display and plays an audio alert if necessary. The input is the inspection results from the AI ​​model, and the output is the visual and auditory information provided to the user. This step allows the user to immediately understand the situation on the production line.

[0580] Step 6:

[0581] The device uses an emotion engine to recognize the user's emotional state. It analyzes the user's facial expressions and voice tone captured by the camera and microphone. The input is the user's facial expression data and voice data, and the output is an evaluation of the user's emotional state. Using the Emotion API, it can determine if the user is showing dissatisfaction or confusion and dynamically change the notification content based on that.

[0582] Step 7:

[0583] The server stores all inspection results and user interaction history in a database. An SQL database is used to securely record the information and utilize it for future analysis and process improvement. Inputs are inspection result data and user interaction logs, and output is a database containing this organized information. This database contributes to the continuous optimization of product quality and user experience.

[0584] (Application Example 2)

[0585] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0586] There is a need to automate and streamline quality inspection on manufacturing lines while simultaneously improving the user experience. Conventional systems require human resources for inspecting defective products and struggle to respond to users' emotional states. To address this challenge, it is necessary to automatically identify the product's condition with high accuracy, while simultaneously analyzing user emotions and reactions in real time to dynamically adjust the interface.

[0587] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0588] In this invention, the server includes a device for collecting target video from an image acquisition function, an image manipulation device for edge detection and improvement, an analysis device using an artificial intelligence model for identifying the state of the target, and an emotion engine for analyzing the user's emotional state and dynamically adjusting the interface. This enables the automation of quality inspection and improvement of the user experience.

[0589] An "image acquisition function" refers to a device or process for collecting video footage of a target into the system.

[0590] Edge detection is a processing technique that identifies boundaries in an image and uses them to improve image quality.

[0591] An "image manipulation device" is a device or software that applies various processing to an image to improve its quality.

[0592] An "artificial intelligence model" is an algorithm or structure that learns from data and automatically performs a specific task; in this context, it is used to identify the state of the target.

[0593] An "analytical device" is a device used to examine data or information in detail and output the results.

[0594] The "emotion engine" is a function that analyzes the user's emotional state and automatically adjusts the system interface accordingly.

[0595] "User experience" refers to the overall experience and feelings a user has when using a product or service.

[0596] In this invention, the server uses multiple devices and software to perform quality inspections on the manufacturing line and improve the user experience. Specifically, an image acquisition function, an image manipulation device, an artificial intelligence model, an analysis device, and an emotion engine work together.

[0597] The image acquisition function captures images of the product in real time and sends the data to a server. This image data is processed by an image manipulation device for noise reduction and edge detection. The OpenCV library is often used for this process. The processed images are then input into an artificial intelligence model using TensorFlow or PyTorch to determine the product's condition and identify defective products.

[0598] The analysis results are transmitted in real time to the user's device, providing the user with notifications of defective products and operating guides. The device also uses an emotion engine to analyze the user's facial expressions and voice, recognizing their emotional state. By utilizing services such as Microsoft Azure's Face API, the notification and information presentation methods can be dynamically adjusted in response to the user's reactions.

[0599] As a concrete example, in one factory, a server analyzes images of bottled beverages and notifies workers whenever a defective product is found. If the system determines that the worker is dissatisfied, detailed instructions are displayed on the terminal. In this way, the invented system enables quality control and rapid response to users.

[0600] An example of an input prompt for the generating AI model would be: "Analyze the following set of images to check for defective products. Also, check the user's facial expression image and select the appropriate notification method. If the user appears confused, provide additional guidance."

[0601] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0602] Step 1:

[0603] The server uses its image acquisition function to capture video of the product and receives the data in real time. This input data is raw video and is stored for subsequent processing.

[0604] Step 2:

[0605] The server performs noise reduction and edge detection on the video data received by the image manipulation device. The input is the video data from step 1, and by using the OpenCV library to remove unwanted noise and highlight important edges, it outputs highly accurate processed image data.

[0606] Step 3:

[0607] The server inputs the processed image data into an artificial intelligence model to identify the product's condition. Here, TensorFlow or PyTorch is used, employing deep learning techniques to identify defective products and outputting the results.

[0608] Step 4:

[0609] The server sends the analysis results to the terminal and notifies the user in real time whether there are any defective products. The output from step 3 becomes the input, and the terminal provides the information to the user visually or audibly.

[0610] Step 5:

[0611] The device analyzes facial expressions and voice data acquired from the user using an emotion engine to recognize the user's emotional state. This process utilizes Microsoft Azure's Face API, and the input data represents the user's current emotional state.

[0612] Step 6:

[0613] Based on the notification in step 4, the device dynamically adjusts the display and information delivery methods according to the user's emotional state. The input is the emotion analysis result from step 5, and the output is the adjusted display method for notifications and support information.

[0614] Step 7:

[0615] Users perform product quality control and corrections based on notifications and support information from the system. In this step, users operate the terminal and take appropriate action according to the displayed information.

[0616] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0617] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0618] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0619] [Fourth Embodiment]

[0620] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0621] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0622] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0623] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0624] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0625] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0626] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0627] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0628] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0629] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0630] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0631] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0632] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0633] This invention is a system for streamlining product inspection on a manufacturing line, and includes an image acquisition device, image processing means, analysis means, display and notification means, and database recording means. This allows for the automatic determination of the quality of the target product, specifically aluminum cans.

[0634] Detailed description of the embodiment

[0635] The server first collects real-time images of objects, such as aluminum cans, from image acquisition devices installed on the factory's production line. The image acquisition devices photograph the objects as they move along the rollers and transmit the image data to the server. This allows the server to obtain detailed visual data of the manufactured products in real time.

[0636] Next, the server uses image processing equipment to perform noise reduction and quality improvement on the received image data. Specifically, it adjusts the brightness and saturation of the image and performs edge detection to clearly display fine scratches and dents. This allows for the extraction of the maximum amount of information necessary for quality assessment.

[0637] The processed images are input into an artificial intelligence model on the server. Here, the analysis tool identifies the state of the object. The AI ​​model uses pre-trained characteristics of normal and defective products to perform real-time inspections. For example, it can identify dents or abnormal color differences in aluminum cans.

[0638] The judgment results are immediately sent from the server to the terminal, where they are displayed and notified for the terminal to check. If a defective product is detected, an alert is displayed on the terminal, and the user is notified with a warning sound and a displayed message. Detailed information is also displayed on the screen, such as "defective products detected on a specific shelf at a specific time."

[0639] Ultimately, the server records all inspection results in a database. This allows for data analysis during quality control at a later date, contributing to improvements in the manufacturing process and trend analysis.

[0640] Specific example

[0641] In a 24-hour aluminum can manufacturing line at a certain factory, a user monitors the production process via a monitor. A server continuously acquires images of aluminum cans moving along rollers, and after AI analysis, detects minute dents on the can's surface. This result is immediately transmitted to a terminal, and a notification is sent to the user if a defective product has been found. The user can then take immediate action on the production line, preventing the shipment of unnecessary defective products and maintaining the final product quality.

[0642] In this way, the system automatically performs highly accurate inspections, contributing to improved factory production efficiency and product quality.

[0643] The following describes the processing flow.

[0644] Step 1:

[0645] The server collects real-time images of aluminum cans moving on rollers from image acquisition devices within the factory. The camera captures a series of images of the cans at regular intervals and immediately transmits this data to the server.

[0646] Step 2:

[0647] The server performs basic image processing on the received image data, such as noise reduction and brightness / saturation correction. This prepares the image for easier analysis. Furthermore, an edge detection algorithm is applied to highlight fine anomalies on the can surface.

[0648] Step 3:

[0649] The server inputs the processed images into an artificial intelligence model to identify the product's condition. The AI ​​model has been pre-trained and operates a comparison algorithm that distinguishes between normal products and defective products (e.g., dents, scratches, foreign objects).

[0650] Step 4:

[0651] The server aggregates the results of the AI ​​analysis, and if a product is identified as defective, it extracts detailed information about it. If a product is determined to be defective, it identifies which part is faulty and how.

[0652] Step 5:

[0653] The server sends the judgment result to the terminal. Based on the received information, the terminal notifies the user in real time. When a defective product is detected, a warning is displayed on the terminal's screen, and if necessary, an audio alert is given to alert the user.

[0654] Step 6:

[0655] The server records all judgment results in a database, accumulating data that can be used for future quality control and statistical analysis. This data is then used to analyze long-term production trends and optimize manufacturing processes.

[0656] (Example 1)

[0657] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0658] Product quality inspection on manufacturing lines is a time-consuming and inefficient process that requires significant manpower. In particular, it is difficult to quickly and accurately identify minute defects and flaws in the products being inspected, leading to increased defect rates and problems in quality assurance. Furthermore, recording and analyzing quality data is time-consuming, making continuous improvement of the manufacturing process difficult.

[0659] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0660] In this invention, the server includes means for collecting information from a device that acquires visual information of an object, image processing means for removing noise and improving the quality of the information, and analysis means using a machine learning model that identifies the characteristics of the object using the processed information. This makes it possible to automatically inspect the quality of products on a manufacturing line in real time and with high accuracy.

[0661] "Target object" refers to the product that is subject to quality inspection on the manufacturing line.

[0662] A "device for acquiring visual information" is a device used to collect image and video data of objects on a manufacturing line.

[0663] "Noise reduction" is the process of removing unwanted background noise from acquired image or video data.

[0664] "Quality improvement" refers to the process of adjusting the visual characteristics of images and video data to clearly identify defects in the object being inspected.

[0665] "Image processing means" refers to technical means for applying noise reduction and quality improvement to visual information.

[0666] A "machine learning model" is an algorithm that uses training data to make predictions and judgments in order to identify the characteristics of an object.

[0667] "Analysis means" refers to technical means for evaluating the state of an object based on processed visual information and identifying its features and defects.

[0668] "Display and warning means" refers to a system function that displays the identification results obtained by the analysis means and, if necessary, alerts the user.

[0669] "Data storage means" refers to technical means for recording analysis results so that they can be referenced later.

[0670] This invention is an automated product inspection system for a manufacturing line, providing a method for efficiently evaluating the quality of the target product. The system includes a device for acquiring visual information of the target object, a server for image processing and analysis, and a terminal for displaying and warning the results.

[0671] The server first collects high-resolution image data from visual information acquisition devices installed on the manufacturing line. These devices accurately capture the details of fast-moving objects and transmit the data to the server in real time.

[0672] Next, the server performs image processing on the acquired visual information to remove noise and improve quality. Specifically, the server uses dedicated software to adjust the brightness and saturation of the image and applies an edge detection algorithm to clearly highlight minute defects in the object.

[0673] Subsequently, the processed image data is analyzed using a generative AI model. The server utilizes a deep learning-based machine learning model to identify patterns between normal and defective products. This allows for highly accurate determination of the object's condition. For example, it can quickly detect minute dents on the surface or abnormal color changes.

[0674] The analysis results are sent from the server to the terminal for user review. The terminal immediately displays the inspection results and issues visual and auditory warnings if defective products are detected. This allows the user to address the problem quickly.

[0675] Furthermore, the server records all inspection results in a data storage system and manages them as a history. This data can be used to continuously improve quality control and optimize the manufacturing process.

[0676] Specific example

[0677] Users can monitor the aluminum can manufacturing production line and quickly adjust the line based on analysis results provided by the server. Defective products are immediately notified via the terminal, helping to improve manufacturing efficiency and maintain high product quality.

[0678] Example of a prompt

[0679] "Please describe a real-time quality inspection system used in the aluminum can manufacturing process. Please explain, with specific examples, how AI is being used on the factory production line."

[0680] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0681] Step 1:

[0682] The server collects image data of aluminum cans as input from a visual information acquisition device installed on the production line. This device is equipped with a high-resolution camera and continuously acquires images as the product moves, transmitting them to the server. The server temporarily stores the received image data in storage in preparation for the next processing step.

[0683] Step 2:

[0684] The server takes the collected image data as input and performs image processing to remove noise and improve quality. Specifically, it uses filters to remove noise from the image as part of data processing, and adjusts brightness and saturation to improve visibility. It also applies an edge detection algorithm to highlight minute scratches and dents on the surface of the aluminum can. As a result, the processed image data is passed to the next process as output.

[0685] Step 3:

[0686] The server feeds the processed image data into the AI ​​model. The AI ​​model uses a deep learning-based machine learning algorithm to analyze the product's health based on past learning results. As part of the data calculation, the model extracts features from the image and determines whether it is a normal or defective product. The analysis results are output, and the process moves to the next step.

[0687] Step 4:

[0688] The server sends the analysis results of the AI ​​model to the terminal. The terminal displays the received identification results as input on its screen, and if a defective product is detected, it warns the user with sound and visual indicators. Specifically, the terminal displays a message saying "Defective product detected" and explains the details of the anomaly (e.g., the degree and location of the dent). The user can also perform additional verification tasks through the terminal's interface.

[0689] Step 5:

[0690] The server records all generated analysis results as input to the data storage system. The data is systematically stored for later reference and includes information such as the date and time of inspection, location, and type of defects detected. This recorded data can then be used as output to generate quality control reports and improve the manufacturing process.

[0691] (Application Example 1)

[0692] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0693] In modern manufacturing lines, automation of quality inspection is required, but conventional systems require a great deal of manpower and time to perform accurate inspections. Furthermore, if defective products are overlooked, there is a possibility of large-scale product recalls after shipment, which significantly impacts production efficiency. In particular, there is a need for a system that can rapidly control the production line in real time based on inspection results.

[0694] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0695] In this invention, the server includes means for collecting images of an object from an image acquisition device, image processing means for performing noise reduction and quality improvement on the images, analysis means using an artificial intelligence algorithm to identify the state of the object using the processed images, and production control means for issuing an instruction to the autonomous machine to stop the production line when the analysis means detects a defective product. This enables automation of product inspection on the manufacturing line, as well as high-precision and real-time control of the production line.

[0696] An "image acquisition device" is a device used to collect visual information of a target object.

[0697] "Noise reduction" is a process that reduces unwanted random fluctuations and errors in order to improve the quality of image data.

[0698] "Quality improvement" refers to a series of processes performed to enhance the visibility and analytical accuracy of image data.

[0699] "Image processing means" refers to a method for optimizing data by applying a specific algorithm to an acquired image.

[0700] An "artificial intelligence algorithm" is a type of computer program used to learn and identify the characteristics of an object.

[0701] "Analysis means" are methods for identifying and evaluating specific characteristics or states based on acquired data.

[0702] "Display and warning means" refers to devices or programs that provide displays and warnings to inform the user of the results of the identification.

[0703] "Information recording means" refers to means for storing identified results and historical data and managing them so that they can be referenced at a later date.

[0704] An "autonomous machine" is a mechanical device that can perform specific actions based on its own judgment.

[0705] "Production control means" are means for managing the progress of the production process and making adjustments as needed.

[0706] In this invention, the server collects images of the product in real time using image acquisition equipment installed on the manufacturing line. The server then performs noise reduction and quality improvement processing on these images to prepare them for checking for minor scratches or dents on the surface of the aluminum cans. Image processing software such as OpenCV is used for this process.

[0707] The processed images are input into an artificial intelligence algorithm on the server. This algorithm uses a generative AI model to analyze the characteristics of good and defective products. By using deep learning frameworks such as TensorFlow and Keras, the condition of the products can be identified with high accuracy.

[0708] Analysis results are immediately transmitted from the server to the terminal, which displays the results to the user. The terminal functions as a display and warning system, issuing a warning if a defective product is detected. Subsequently, the autonomous machine can stop the production line based on instructions from the server. This collaboration efficiently prevents the shipment of defective products and maintains product quality.

[0709] As a concrete example, in one factory, the system is in operation, and users can monitor the status of the production line in real time. One day, the generative AI model detects a minor defect, the system immediately issues an alert, and an instruction is sent to the autonomous machine to stop the line. As a result, the user can immediately address the problem and adjust the production process. The generative AI system can be improved based on a prompt message such as, "What algorithm would be most effective in exploring new ways to streamline product inspection?"

[0710] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0711] Step 1:

[0712] The server collects images of products from image acquisition equipment installed on the manufacturing line. During this process, the camera continuously photographs moving aluminum cans on the line and transmits the resulting image data to the server. The server receives this data as input.

[0713] Step 2:

[0714] The server performs noise reduction and quality enhancement on the received image data. For noise reduction, it uses OpenCV's Gaussian blur function to smooth the image, and for quality enhancement, it adjusts the brightness and contrast of the image to improve its clarity. The processed image data is then output.

[0715] Step 3:

[0716] The server inputs the processed image data into an artificial intelligence algorithm. Using a generative AI model, the AI ​​analyzes the features in the image and identifies whether the product is good or defective. Based on pre-trained data, the AI ​​detects minute defects on the product. The analysis results are output as identification information.

[0717] Step 4:

[0718] The server sends the identified results to the terminal. The terminal displays the results, allowing the user to check the product quality status in real time. If a defective product is detected, the terminal issues a warning and displays an alert on the screen. This notification is intended to allow the user to take quick action.

[0719] Step 5:

[0720] If a defective product is detected, the server instructs the autonomous machine to stop the production line. This instruction is transmitted to the autonomous machine via communication, and upon receiving it, the machine temporarily suspends the line's operation. This prevents defective products from being shipped.

[0721] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0722] This invention provides a system for streamlining product inspection on a manufacturing line and improving the user experience. It includes an image acquisition device, image processing means, analysis means using an artificial intelligence model, display and notification means, and database recording means, as well as an emotion engine that recognizes user emotions. This system enables a highly automated inspection process, maintains product quality, and provides an interface that considers the user's emotional state.

[0723] Detailed description of the embodiment

[0724] The server uses image acquisition equipment within the factory to capture images of aluminum cans moving along rollers. These images are transmitted to the server in real time, and the server performs quality improvement processing on the received images using noise reduction and edge detection algorithms. The processed image data is input into an artificial intelligence model using deep learning to analyze the presence of defects and the condition of the products. The results of this AI analysis are immediately sent from the server to the terminal.

[0725] The terminal provides real-time notifications to the user based on analysis results received from the server. The display and notification system displays a warning when a defective product is identified and provides an audio alert as needed. This information allows the user to take appropriate action immediately.

[0726] Furthermore, this system integrates an emotion engine, which analyzes data obtained from the user's facial expressions and voice to determine the user's emotional state. For example, if the user shows signs of dissatisfaction or confusion, the system dynamically adjusts the interface display and notification process, and adds supportive information to make it easier for the user to understand.

[0727] The database recording system records inspection results and user interaction history to help improve quality and optimize the user experience in the future. All data is securely stored and contributes to subsequent trend analysis and improvements to the manufacturing process.

[0728] Specific example

[0729] On a production line one day, while a user is monitoring the system, the server acquires images of newly arrived aluminum cans and performs AI-powered defect inspection. The terminal notifies the user of the detected defects, while an emotion engine analyzes the user's facial expressions to detect signs of attention or dissatisfaction. The terminal automatically selects the most appropriate way to display the information for the user, adding detailed instructions and support information to help the user respond quickly.

[0730] In this way, this system contributes to maintaining product quality and improving work efficiency by streamlining the manufacturing process and providing a flexible operating environment that takes user emotions into consideration.

[0731] The following describes the processing flow.

[0732] Step 1:

[0733] The server continuously acquires images of aluminum cans from image acquisition devices located on the production line. Acquisition is performed in real time, and the image data is immediately sent to the server to prepare it for processing.

[0734] Step 2:

[0735] The server performs image processing on the received image, removing noise and adjusting brightness and contrast. This process improves image visibility, and by applying an edge detection algorithm, it makes it easier to identify fine defects on the can surface.

[0736] Step 3:

[0737] The processed images are input into an artificial intelligence model on the server. The AI ​​model analyzes the images based on pre-trained data and determines whether the product is normal or defective. It can identify abnormalities such as dents and scratches with high accuracy.

[0738] Step 4:

[0739] The server evaluates the analysis results of the artificial intelligence model and records the details if a defective product is identified. The evaluation results immediately lead to the next step.

[0740] Step 5:

[0741] The server sends the analysis results to the terminal. Based on the data received by the terminal, it notifies the user in real time of the detection of defective products.

[0742] Step 6:

[0743] Devices equipped with an emotion engine analyze the user's facial expressions and voice to determine the user's emotional state. If there are signs that the user is dissatisfied or has questions, the content of the conversation and the interface are adjusted accordingly.

[0744] Step 7:

[0745] The device adjusts the displayed content according to the user's emotional state. It presents information in a format that is easy for the user to understand, and adds supplementary explanations and support information as needed to facilitate smooth communication.

[0746] Step 8:

[0747] The server records all test results and user feedback data in a database. This enables analysis aimed at improving the efficiency of the manufacturing line and enhancing the user experience.

[0748] (Example 2)

[0749] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0750] Modern manufacturing lines demand improved inspection accuracy and process efficiency in product inspection. However, conventional technologies lack high-precision defect inspection systems that integrate image processing and artificial intelligence, resulting in insufficient automation and cost reduction in quality control. Furthermore, there are insufficient means to reduce the burden on users and improve the user experience. Therefore, there is a need to provide a system that solves these problems and enhances the efficiency of the entire manufacturing process.

[0751] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0752] In this invention, the server includes means for collecting images of an object from an image acquisition device, image processing means for applying noise reduction and edge detection algorithms to the images, and analysis means for using a generative AI model to identify the state of the object using the processed images. This enables high-precision and efficient product inspection, as well as dynamic adjustment of the interface according to the user's emotional state.

[0753] An "image acquisition device" is a device used to collect images of an object, and specifically refers to a device capable of acquiring images of products moving along a manufacturing line in real time.

[0754] "Noise reduction" is the process of removing unwanted information from a digital image in order to improve image quality.

[0755] An "edge detection algorithm" is a processing technique used to detect the contours of objects in an image, and is used to clarify the shape and boundaries of objects.

[0756] A "generative AI model" is a pre-trained model designed to analyze the features of images and data using artificial intelligence technology and to identify the state of an object.

[0757] "Analysis means" refers to methods and processes for determining whether an object is defective or identifying its condition based on processed image data.

[0758] "Display and notification means" refers to a system for visually or audibly communicating the results of the analysis to the user, thereby encouraging the user to take prompt action.

[0759] A "database recording system" is a data management system that securely stores data such as analysis results and user operation history, and uses it for future quality control and system improvement.

[0760] "Dynamic interface adjustment" is the process of appropriately changing the displayed content and notification methods according to the user's emotional state and operating environment.

[0761] This invention is a system for highly automating product inspection on a manufacturing line and improving efficiency. The following describes the embodiments for implementing this system.

[0762] The server collects images of the target object, aluminum cans, through an image acquisition device. This image acquisition device is a camera installed on the manufacturing line that captures images of products moving in real time. The server then applies noise reduction and edge detection algorithms to the collected images using Python and OpenCV to improve image quality. A Gaussian filter is used for noise reduction, and the Canny method is used for edge detection.

[0763] Next, the server inputs the improved image quality into an AI model, specifically a deep learning model using TensorFlow. This model uses a convolutional neural network (CNN) to extract features from the image data and identify whether or not there are defective products and to determine the product's condition.

[0764] The identification results are sent from the server to the terminal. Based on these results, the terminal notifies the user in real time. Specifically, it displays a warning of defective product detection on the display and issues an audio alert if necessary, enabling the user to respond quickly.

[0765] Furthermore, the device has an integrated emotion engine that determines the user's emotional state based on data acquired from the camera and microphone. For example, it uses the Emotion API to analyze facial expressions and voice tone, and if the user is showing signs of dissatisfaction or confusion, it dynamically adjusts the interface display and adds personalized support information.

[0766] Inspection results and user interaction history are recorded in a database. This data is securely stored using an SQL database and used for trend analysis to improve quality and enhance manufacturing processes.

[0767] As a concrete example, a server acquires an image of an aluminum can, performs a defect inspection using an AI model, and sends the results to a terminal. The terminal receives the defect information and notifies the user. If the user shows signs of dissatisfaction, the terminal adjusts its interface and displays detailed instructions on how to resolve the issue.

[0768] An example of a prompt is: "Design a system that uses image processing and an AI model to inspect products on a manufacturing line and notifies the user of the results in real time. The system should recognize the user's emotional state and dynamically adjust the interface." By using an AI model generated based on such prompts, it is possible to achieve efficient product inspection and improve the user's work environment.

[0769] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0770] Step 1:

[0771] The server controls the image acquisition device to capture images of aluminum cans, which are the target objects on the manufacturing line. The image acquisition device uses a high-resolution camera and continuously captures multiple images in real time. The input is the manufacturing line through which the aluminum cans move, and the output is the acquired raw image data. This makes it possible to accurately record the current state of the target objects.

[0772] Step 2:

[0773] The server receives the acquired image data, and denoising is performed using Python and OpenCV. Specifically, a Gaussian filter is applied to reduce unwanted noise in the image. The input is the raw image data acquired in step 1, and the output is the denoised image data. This process lays the foundation for more accurate subsequent analysis.

[0774] Step 3:

[0775] The server performs edge detection on the denoised image. The Canny method of OpenCV is used to clarify the image contours. The input is the denoised image data, and the output is image data with enhanced contours. This process clarifies the shape of objects, enabling highly accurate analysis by AI models.

[0776] Step 4:

[0777] The server inputs edge-detected image data into an AI model, specifically a deep learning model using TensorFlow. A convolutional neural network (CNN) is used to extract features from the image data. The input is edge-enhanced image data, and the output is information about the presence or absence of defects and the condition of the product as an inspection result. During this process, the visual features of the image are analyzed to determine whether it is normal or defective.

[0778] Step 5:

[0779] The server sends the obtained inspection results to the terminal. The terminal notifies the user of these analysis results. Specifically, it displays a warning message for defective products on the display and plays an audio alert if necessary. The input is the inspection results from the AI ​​model, and the output is the visual and auditory information provided to the user. This step allows the user to immediately understand the situation on the production line.

[0780] Step 6:

[0781] The device uses an emotion engine to recognize the user's emotional state. It analyzes the user's facial expressions and voice tone captured by the camera and microphone. The input is the user's facial expression data and voice data, and the output is an evaluation of the user's emotional state. Using the Emotion API, it can determine if the user is showing dissatisfaction or confusion and dynamically change the notification content based on that.

[0782] Step 7:

[0783] The server stores all inspection results and user interaction history in a database. An SQL database is used to securely record the information and utilize it for future analysis and process improvement. Inputs are inspection result data and user interaction logs, and output is a database containing this organized information. This database contributes to the continuous optimization of product quality and user experience.

[0784] (Application Example 2)

[0785] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0786] There is a need to automate and streamline quality inspection on manufacturing lines while simultaneously improving the user experience. Conventional systems require human resources for inspecting defective products and struggle to respond to users' emotional states. To address this challenge, it is necessary to automatically identify the product's condition with high accuracy, while simultaneously analyzing user emotions and reactions in real time to dynamically adjust the interface.

[0787] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0788] In this invention, the server includes a device for collecting target video from an image acquisition function, an image manipulation device for edge detection and improvement, an analysis device using an artificial intelligence model for identifying the state of the target, and an emotion engine for analyzing the user's emotional state and dynamically adjusting the interface. This enables the automation of quality inspection and improvement of the user experience.

[0789] An "image acquisition function" refers to a device or process for collecting video footage of a target into the system.

[0790] Edge detection is a processing technique that identifies boundaries in an image and uses them to improve image quality.

[0791] An "image manipulation device" is a device or software that applies various processing to an image to improve its quality.

[0792] An "artificial intelligence model" is an algorithm or structure that learns from data and automatically performs a specific task; in this context, it is used to identify the state of the target.

[0793] An "analytical device" is a device used to examine data or information in detail and output the results.

[0794] The "emotion engine" is a function that analyzes the user's emotional state and automatically adjusts the system interface accordingly.

[0795] "User experience" refers to the overall experience and feelings a user has when using a product or service.

[0796] In this invention, the server uses multiple devices and software to perform quality inspections on the manufacturing line and improve the user experience. Specifically, an image acquisition function, an image manipulation device, an artificial intelligence model, an analysis device, and an emotion engine work together.

[0797] The image acquisition function captures images of the product in real time and sends the data to a server. This image data is processed by an image manipulation device for noise reduction and edge detection. The OpenCV library is often used for this process. The processed images are then input into an artificial intelligence model using TensorFlow or PyTorch to determine the product's condition and identify defective products.

[0798] The analysis results are transmitted in real time to the user's device, providing the user with notifications of defective products and operating guides. The device also uses an emotion engine to analyze the user's facial expressions and voice, recognizing their emotional state. By utilizing services such as Microsoft Azure's Face API, the notification and information presentation methods can be dynamically adjusted in response to the user's reactions.

[0799] As a concrete example, in one factory, a server analyzes images of bottled beverages and notifies workers whenever a defective product is found. If the system determines that the worker is dissatisfied, detailed instructions are displayed on the terminal. In this way, the invented system enables quality control and rapid response to users.

[0800] An example of an input prompt for the generating AI model would be: "Analyze the following set of images to check for defective products. Also, check the user's facial expression image and select the appropriate notification method. If the user appears confused, provide additional guidance."

[0801] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0802] Step 1:

[0803] The server uses its image acquisition function to capture video of the product and receives the data in real time. This input data is raw video and is stored for subsequent processing.

[0804] Step 2:

[0805] The server performs noise reduction and edge detection on the video data received by the image manipulation device. The input is the video data from step 1, and by using the OpenCV library to remove unwanted noise and highlight important edges, it outputs highly accurate processed image data.

[0806] Step 3:

[0807] The server inputs the processed image data into an artificial intelligence model to identify the product's condition. Here, TensorFlow or PyTorch is used, employing deep learning techniques to identify defective products and outputting the results.

[0808] Step 4:

[0809] The server sends the analysis results to the terminal and notifies the user in real time whether there are any defective products. The output from step 3 becomes the input, and the terminal provides the information to the user visually or audibly.

[0810] Step 5:

[0811] The device analyzes facial expressions and voice data acquired from the user using an emotion engine to recognize the user's emotional state. This process utilizes Microsoft Azure's Face API, and the input data represents the user's current emotional state.

[0812] Step 6:

[0813] Based on the notification in step 4, the device dynamically adjusts the display and information delivery methods according to the user's emotional state. The input is the emotion analysis result from step 5, and the output is the adjusted display method for notifications and support information.

[0814] Step 7:

[0815] Users perform product quality control and corrections based on notifications and support information from the system. In this step, users operate the terminal and take appropriate action according to the displayed information.

[0816] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0817] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0818] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0819] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0820] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0821] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0822] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0823] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0824] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0825] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0826] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0827] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0828] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0829] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0830] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0831] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0832] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0833] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0834] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0835] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0836] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0837] The following is further disclosed regarding the embodiments described above.

[0838] (Claim 1)

[0839] A means for collecting images of an object from an image acquisition device,

[0840] Image processing means for performing noise reduction and quality improvement on the aforementioned image,

[0841] Analysis means using an artificial intelligence model that identifies the state of an object using the processed image,

[0842] A display and notification means for displaying the identification results obtained by the aforementioned analysis means and notifying of defective products,

[0843] A database recording means for recording the aforementioned identification results and managing their history,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, wherein the image processing means applies an edge detection algorithm.

[0847] (Claim 3)

[0848] The system according to claim 1, wherein the artificial intelligence model includes deep learning.

[0849] "Example 1"

[0850] (Claim 1)

[0851] A means of collecting information from a device that acquires visual information of an object,

[0852] Image processing means for performing noise reduction and quality improvement on the aforementioned information,

[0853] An analysis means using a machine learning model that identifies the characteristics of an object using the processed information,

[0854] A display and warning means for displaying the identification results obtained by the analysis means and notifying of defective products,

[0855] A data storage means for accumulating the aforementioned identification results and managing their history,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, wherein the image processing means applies a boundary detection method.

[0859] (Claim 3)

[0860] The system according to claim 1, wherein the machine learning model includes deep learning technology.

[0861] "Application Example 1"

[0862] (Claim 1)

[0863] A means for collecting images of an object from an image acquisition device,

[0864] Image processing means for performing noise reduction and quality improvement on the aforementioned image,

[0865] An analysis means using an artificial intelligence algorithm that identifies the state of an object using the processed image,

[0866] A display and warning means for displaying the identification results obtained by the aforementioned analysis means and notifying of defective products,

[0867] Information recording means for recording the aforementioned identification results and managing their history,

[0868] When the aforementioned analysis means detects a defective product, a production control means issues an instruction to the autonomous machine to stop the production line.

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, wherein the image processing means applies an edge detection algorithm.

[0872] (Claim 3)

[0873] The system according to claim 1, wherein the artificial intelligence algorithm includes deep learning.

[0874] "Example 2 of combining an emotion engine"

[0875] (Claim 1)

[0876] A means for collecting images of an object from an image acquisition device,

[0877] Image processing means that applies noise reduction and edge detection algorithms to the aforementioned image,

[0878] Analysis means using a generative AI model that identifies the state of an object using the processed image,

[0879] A display and notification means that displays the identification results obtained by the aforementioned analysis means, notifies the user of defective products, and adjusts the interface according to the user's emotional state,

[0880] A database recording means that records the aforementioned identification results and user interaction history, and performs history management to support future quality improvement and work efficiency improvements,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, wherein the image processing means performs noise reduction processing to improve the image quality of the object.

[0884] (Claim 3)

[0885] The system according to claim 1, wherein the generating AI model includes deep learning and automatically detects defective products from acquired images.

[0886] "Application example 2 when combining with an emotional engine"

[0887] (Claim 1)

[0888] A device that collects video footage of the target using an image acquisition function,

[0889] An image manipulation device that performs edge detection and improvement on the aforementioned video,

[0890] An analysis device using an artificial intelligence model that identifies the state of a target using the manipulated video,

[0891] A device that displays the identification results from the aforementioned analytical device and notifies of defective products,

[0892] A data storage device that stores the aforementioned identification results and manages their history,

[0893] A device including an emotion engine that analyzes the user's emotional state and dynamically adjusts the interface,

[0894] A system that includes this.

[0895] (Claim 2)

[0896] The system according to claim 1, wherein the image manipulation device applies an edge detection process.

[0897] (Claim 3)

[0898] The system according to claim 1, wherein the artificial intelligence model includes machine learning. [Explanation of symbols]

[0899] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting images of an object from an image acquisition device, Image processing means for performing noise reduction and quality improvement on the aforementioned image, Analysis means using an artificial intelligence model that identifies the state of an object using the processed image, A display and notification means for displaying the identification results obtained by the aforementioned analysis means and notifying of defective products, A database recording means for recording the aforementioned identification results and managing their history, A system that includes this.

2. The system according to claim 1, wherein the image processing means applies an edge detection algorithm.

3. The system according to claim 1, wherein the artificial intelligence model includes deep learning.

Images