system

Abstract

The system according to this embodiment aims to estimate the reasons for a judgment and the cause of a defect, and to propose solutions during the visual inspection of a product. [Solution] The system according to the embodiment comprises a scanning unit, a modeling unit, a transmission unit, a determination unit, and a proposal unit. The scanning unit acquires an image file of the product. The modeling unit performs 3D modeling based on the image file acquired by the scanning unit. The transmission unit transmits the data generated by the modeling unit to a digital twin platform. The determination unit makes a pass / fail determination by referring to the data transmitted by the transmission unit. The proposal unit estimates the cause of the defect and proposes a solution based on the determination result obtained by the determination unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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 the prior art, in appearance inspection by machine learning using image data, there is a problem that defective products can only be judged within the learning range, and the judgment logic is a black box.

[0005] The system according to the embodiment aims to estimate the reasons for judgment and defective causes, and propose solutions in the appearance inspection of products.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a scanning unit, a modeling unit, a transmission unit, a determination unit, and a proposal unit. The scanning unit acquires an image file of the product. The modeling unit performs 3D modeling based on the image file acquired by the scanning unit. The transmission unit transmits the data generated by the modeling unit to a digital twin platform. The determination unit makes a pass / fail determination by referring to the data transmitted by the transmission unit. The proposal unit estimates the cause of the defect and proposes a solution based on the determination result obtained by the determination unit. [Effects of the Invention]

[0007] The system according to this embodiment can estimate the reason for a judgment, the cause of a defect, and propose solutions during the visual inspection of a product. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

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

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The product inspection system according to an embodiment of the present invention proposes a "super inspection dome" to solve the problems of conventional machine learning-based visual inspection in the product inspection process of a factory. In the product inspection system, a 3D scanning device acquires an image file of the product as it passes through the "super inspection dome." This image file is transmitted to an edge server via a private 5G network. At the edge server, 3D modeling is performed, and this data is sent to a digital twin platform on a distributed computing infrastructure. Next, a generating AI refers to the digital twin data to determine whether the product is good or bad, estimate the cause of defects, and propose solutions. This mechanism eliminates the black box problem of the judgment logic that plagued conventional machine learning-based visual inspection, enabling the estimation of judgment reasons and defect causes, as well as the proposal of solutions. This significantly reduces manpower and contributes to improving factory productivity. For example, as a product passes through the "super inspection dome," a 3D scanning device acquires an image file of the product. At this time, the product's appearance is scanned in detail and acquired as 3D data. For example, minute scratches and defects on the surface of the product can be detected. This image file is transmitted to the edge server via a private 5G network. Next, the edge server performs 3D modeling based on the acquired image files. This 3D modeling generates detailed digital twin data of the product. This data is sent to the digital twin platform on the distributed computing infrastructure. The generating AI refers to the digital twin data and determines whether the product is good or bad. For example, if there is a minute scratch on the product's appearance, it analyzes the size and location of the scratch and determines that it is a defective product. The generating AI also estimates the cause of the defect. For example, it can identify potential problems that occurred during the product's manufacturing process and estimate their causes. Furthermore, the generating AI also proposes solutions. For example, it can suggest what measures should be taken to address problems that occurred during the product's manufacturing process. This leads to improved product quality and increased factory productivity.This system eliminates the problem of the judgment logic being a black box in conventional machine learning-based visual inspection, enabling estimation of the reason for judgment and the cause of defects, as well as the suggestion of solutions. This results in significant labor savings and contributes to improved factory productivity. The product inspection system acquires image files of products, performs 3D modeling, transmits them to a digital twin platform, and performs pass / fail judgment, estimation of the cause of defects, and suggestion of solutions.

[0029] The product inspection system according to the embodiment comprises a scanning unit, a modeling unit, a transmission unit, a determination unit, and a proposal unit. The scanning unit acquires an image file of the product. The image file of the product includes, but is not limited to, formats such as JPEG, PNG, and TIFF. The scanning unit can, for example, scan the appearance of the product in detail and acquire it as 3D data. For example, the scanning unit can detect minute scratches and defects on the surface of the product. The scanning unit can also apply different scanning algorithms depending on the shape and material of the product. For example, for metal products, a scanning algorithm that takes reflection into account is applied. For plastic products, a scanning algorithm that takes transparency into account is applied. For products with complex shapes, a scanning algorithm appropriate to the shape can be applied. The modeling unit performs 3D modeling based on the image file acquired by the scanning unit. The 3D modeling is performed based on, for example, the software used and the accuracy of the modeling, but is not limited to such examples. For example, the modeling unit can generate detailed digital twin data based on the acquired image file. The digital twin data includes, for example, the accuracy of the data and the format of the data, but is not limited to such examples. The transmission unit transmits the digital twin data generated by the modeling unit to a digital twin platform on a distributed computing infrastructure. The distributed computing infrastructure is configured based on, for example, the servers used and the method of data distribution, but is not limited to such examples. For example, the transmission unit can transmit the generated digital twin data to a digital twin platform on a distributed computing infrastructure in order to efficiently manage it. The judgment unit refers to the digital twin data and determines whether the product is good or bad. The judgment is made based on, for example, judgment criteria and the algorithm used, but is not limited to such examples. For example, if there is a minute scratch on the appearance of the product based on the digital twin data, the judgment unit can analyze the size and location of the scratch and determine that it is a defective product. The proposal unit estimates the cause of the defect and proposes a solution based on the judgment result obtained by the judgment unit.The estimation of the cause of defects and the proposal of solutions are performed based on, for example, the data used, estimation methods, and proposal criteria. For example, the proposal unit can identify problems that occurred during the product manufacturing process, estimate their causes, and propose what countermeasures should be taken. As a result, the product inspection system according to the embodiment can acquire image files of the product, perform 3D modeling, transmit them to a digital twin platform, and perform pass / fail judgment, estimation of the cause of defects, and proposal of solutions.

[0030] The scanning unit acquires image files of the product. These image files include, but are not limited to, formats such as JPEG, PNG, and TIFF. The scanning unit can, for example, scan the product's appearance in detail and acquire it as 3D data. Specifically, the scanning unit uses a high-resolution camera or laser scanner to capture detailed images of the product's surface and detect minute scratches and defects. This makes it possible to evaluate the product's quality with high accuracy. The scanning unit can also apply different scanning algorithms depending on the shape and material of the product. For example, for metal products, a scanning algorithm that takes reflection into account is applied, and for plastic products, a scanning algorithm that takes transparency into account is applied. Furthermore, for products with complex shapes, a scanning algorithm tailored to the shape can be applied. This allows the scanning unit to flexibly handle a variety of products and acquire accurate data. The scanning unit processes the acquired data in real time and transmits it to a central database. This allows the scanning unit to collect data efficiently and quickly, improving the overall system performance. In addition, the scanning unit can flexibly respond to specific situations and conditions by adjusting the data collection frequency and accuracy. This allows the scanning unit to collect data efficiently and effectively, improving the overall performance of the system.

[0031] The modeling unit performs 3D modeling based on image files acquired by the scanning unit. 3D modeling is performed based on, for example, the software used and the accuracy of the modeling, but is not limited to these examples. Specifically, the modeling unit uses advanced 3D modeling software to generate detailed digital twin data based on the acquired image files. This digital twin data includes, for example, the product's shape, dimensions, material, and surface condition. This allows the modeling unit to create a digital model with nearly the same accuracy as the actual product. Furthermore, the modeling unit can simulate the product's performance and durability based on the generated digital twin data. For example, it can simulate how the product deforms under specific environmental conditions and how much load it can withstand, thereby evaluating the product's quality. This allows the modeling unit to evaluate product quality with high accuracy and identify areas for improvement. Additionally, the modeling unit can share the generated digital twin data with other departments and systems. This allows the modeling unit to evaluate product quality with high accuracy and identify areas for improvement.

[0032] The transmission unit transmits the digital twin data generated by the modeling unit to the digital twin platform on a distributed computing infrastructure. The distributed computing infrastructure is configured based on, for example, the servers used and the method of data distribution, but is not limited to such examples. Specifically, the transmission unit efficiently transmits the generated digital twin data using a high-speed and stable communication protocol. This allows the transmission unit to quickly and reliably transmit the digital twin data to the digital twin platform on the distributed computing infrastructure. Furthermore, the transmission unit can compress and encrypt the transmitted digital twin data in order to efficiently manage it. This allows the transmission unit to efficiently transmit data while ensuring the security of the digital twin data. In addition, the transmission unit can share the transmitted digital twin data with other systems and departments. This allows the transmission unit to efficiently manage the digital twin data and improve the overall system performance.

[0033] The judgment unit refers to digital twin data to determine whether a product is good or bad. This judgment is based on criteria and algorithms, but is not limited to these. Specifically, the judgment unit can use AI to analyze digital twin data and, if a product has minor scratches on its surface, analyze the size and location of the scratches to determine if it is defective. The AI ​​uses image recognition technology to analyze digital twin data and identify minor scratches and defects on the product's surface. The judgment unit also checks whether the product's dimensions and shape match the design drawings and determines it is defective if they do not. Furthermore, the judgment unit analyzes the product's material and surface condition and determines it is defective if the material or surface condition does not meet specified standards. This allows the judgment unit to evaluate product quality with high accuracy and quickly identify defective products. In addition, the judgment unit can utilize historical data and statistical information to perform long-term quality evaluations and trend analyses. For example, based on past defective product data, it can predict quality fluctuations in specific products or manufacturing processes and formulate future countermeasures. This allows the judgment unit to handle not only real-time quality evaluation but also long-term quality control, improving the reliability and safety of the entire system.

[0034] The proposal department estimates the cause of defects and proposes solutions based on the judgment results obtained by the judgment department. The estimation of the cause of defects and the proposal of solutions are based on, for example, the data used, estimation methods, and proposal criteria, but are not limited to such examples. Specifically, the proposal department uses AI to analyze the judgment results and identify problems that occurred in the product manufacturing process. Based on past data and statistical information, the AI ​​detects abnormal patterns and trends in the manufacturing process and estimates the cause of defects. The proposal department also proposes what countermeasures should be taken based on the estimated cause of defects. For example, it can identify problems that occurred in a specific step of the manufacturing process and propose specific countermeasures to improve that step. Furthermore, the proposal department can simulate the effects of the proposed countermeasures and select the optimal countermeasure. In this way, the proposal department can provide specific countermeasures to improve product quality and support the efficiency and quality improvement of the manufacturing process. Furthermore, the proposal department can monitor the implementation status of the proposed countermeasures and modify them as necessary. In this way, the proposal department can support the continuous improvement of product quality and improve the reliability and safety of the entire system.

[0035] The scanning unit can scan the product's appearance in detail and acquire it as 3D data. For example, the scanning unit can detect minute scratches and defects on the product's surface. The scanning unit can also apply different scanning algorithms depending on the product's shape and material. For example, for metal products, a scanning algorithm that considers reflection is applied. For plastic products, a scanning algorithm that considers transparency is applied. For products with complex shapes, a scanning algorithm appropriate to the shape can be applied. This allows for more accurate inspection by scanning the product's appearance in detail and acquiring it as 3D data. Some or all of the above processing in the scanning unit may be performed using AI, for example, or without AI. For example, the scanning unit can input the data acquired by scanning the product's appearance into a generating AI, which can then analyze the data.

[0036] The modeling unit can perform 3D modeling based on acquired image files and generate detailed digital twin data. For example, the modeling unit can perform 3D modeling based on the software used and the accuracy of the modeling. The modeling unit can also apply different modeling algorithms depending on the shape and material of the product. For example, for metal products, a modeling algorithm that takes reflection into account is applied. For plastic products, a modeling algorithm that takes transparency into account is applied. For products with complex shapes, a modeling algorithm appropriate to the shape can be applied. This makes it possible to perform detailed inspection of products by performing 3D modeling based on acquired image files and generating detailed digital twin data. Some or all of the above processing in the modeling unit may be performed using AI, for example, or without AI. For example, the modeling unit can input acquired image files into a generation AI and perform 3D modeling using the generation AI.

[0037] The transmission unit can transmit the generated digital twin data to a digital twin platform on a distributed computing infrastructure. For example, the transmission unit can transmit data based on the servers used and the data distribution method. The transmission unit can also determine the transmission priority based on the importance of the data. For example, it can transmit important data first, general data with normal priority, and less important data later. This enables efficient data management by transmitting the generated digital twin data to a digital twin platform on a distributed computing infrastructure. Some or all of the above processing in the transmission unit may be performed using AI, for example, or without AI. For example, the transmission unit can input the generated digital twin data into a generating AI, and the generating AI can perform the data transmission.

[0038] The judgment unit can determine whether a product is good or bad by referring to digital twin data. For example, the judgment unit can determine whether a product is good or bad by referring to digital twin data. For example, if there are minute scratches on the appearance of a product, the judgment unit can analyze the size and location of the scratches based on the digital twin data and determine that the product is defective. The judgment unit can also improve the accuracy of the judgment by referring to data from the product's manufacturing process. For example, it can perform a detailed judgment based on the manufacturing process data. It can perform a judgment that takes into account the characteristics of the product based on the manufacturing process data. It can perform a judgment that takes into account product defects based on the manufacturing process data. As a result, accurate judgment becomes possible by referring to digital twin data to determine whether a product is good or bad. Some or all of the above processing in the judgment unit may be performed using, for example, a generating AI, or it may be performed without using a generating AI. For example, the judgment unit can input digital twin data into a generating AI and have the generating AI perform the good or bad judgment.

[0039] The proposal department can propose what measures should be taken to address problems that arise during the product manufacturing process. For example, the proposal department can identify problems that arise during the product manufacturing process, estimate their causes, and propose what measures should be taken. The proposal department can also optimize its proposals by considering the product's usage. For example, it can propose detailed solutions for frequently used products and standard solutions for less frequently used products. The proposals can be dynamically optimized according to usage. This improves product quality by proposing what measures should be taken to address problems that arise during the product manufacturing process. Some or all of the above-described processes in the proposal department may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal department can input data from the product's manufacturing process into a generative AI, and the generative AI can propose solutions.

[0040] The scanning unit can apply different scanning algorithms depending on the material and shape of the product during scanning. For example, for metal products, a scanning algorithm that takes reflection into account is applied. For plastic products, a scanning algorithm that takes transparency into account is applied. For products with complex shapes, a scanning algorithm appropriate to the shape can be applied. This improves scanning accuracy by applying different scanning algorithms depending on the material and shape of the product. Some or all of the above processing in the scanning unit may be performed using AI, for example, or without AI. For example, the scanning unit can input data on the material and shape of the product into a generating AI, and the generating AI can apply a scanning algorithm.

[0041] The scanning unit can improve scanning accuracy by taking into account environmental conditions such as the temperature and humidity of the product during scanning. For example, in a high-temperature environment, temperature correction can be performed to improve scanning accuracy. If the humidity is high, humidity correction can be performed to improve scanning accuracy. In a low-temperature environment, temperature correction can be performed to improve scanning accuracy. By improving scanning accuracy by taking into account environmental conditions such as the temperature and humidity of the product, more accurate scanning becomes possible. Some or all of the above processing in the scanning unit may be performed using AI, for example, or without AI. For example, the scanning unit can input temperature and humidity data of the product into a generating AI, and the generating AI can improve scanning accuracy.

[0042] The scanning unit can determine scanning priorities by referring to the product's manufacturing history during scanning. For example, the scanning unit can prioritize scanning important products based on their manufacturing history, prioritize scanning problematic products based on their manufacturing history, or prioritize scanning products that have gone through a specific manufacturing process based on their manufacturing history. This allows for priority scanning of important products by referring to the product's manufacturing history. Some or all of the above processing in the scanning unit may be performed using AI, for example, or without AI. For example, the scanning unit can input product manufacturing history data into a generating AI, and the generating AI can determine the scanning priorities.

[0043] The scanning unit can adjust the scanning frequency while taking into account the product's usage. For example, it can scan frequently used products more often, and scan less frequently used products more frequently. The scanning unit can dynamically adjust the scanning frequency according to the usage. This allows for scanning at an appropriate frequency by adjusting the scanning frequency while taking into account the product's usage. Some or all of the above processing in the scanning unit may be performed using AI, for example, or without AI. For example, the scanning unit can input product usage data into a generating AI, and the generating AI can adjust the scanning frequency.

[0044] The modeling unit can apply different modeling algorithms during modeling depending on the shape and material of the product. For example, in the case of metal products, a modeling algorithm that takes reflection into consideration is applied. In the case of plastic products, a modeling algorithm that takes transparency into consideration is applied. In the case of products with complex shapes, a modeling algorithm appropriate to the shape can be applied. This improves modeling accuracy by applying different modeling algorithms depending on the shape and material of the product. Some or all of the above processing in the modeling unit may be performed using AI, for example, or without AI. For example, the modeling unit can input data on the shape and material of the product into a generating AI, and the generating AI can apply a modeling algorithm.

[0045] The modeling unit can improve modeling accuracy by referencing data from the product's manufacturing process during modeling. For example, the modeling unit can improve modeling accuracy by referencing data from the product's manufacturing process during modeling. For example, it can perform detailed 3D modeling based on manufacturing process data. It can perform 3D modeling that takes product characteristics into account based on manufacturing process data. It can perform 3D modeling that takes product defects into account based on manufacturing process data. By improving modeling accuracy by referencing data from the product's manufacturing process, more accurate 3D modeling becomes possible. Some or all of the above processes in the modeling unit may be performed using AI, for example, or without AI. For example, the modeling unit can input data from the product's manufacturing process into a generating AI, and the generating AI can improve modeling accuracy.

[0046] The modeling unit can adjust the level of detail of the model by referring to the product's usage history during the modeling process. For example, the modeling unit can adjust the level of detail of the model by referring to the product's usage history during the modeling process. For example, it can model products that are used frequently in detail, and models products that are used infrequently in a standard manner. The level of detail of the model can be dynamically adjusted according to the usage history. This makes it possible to model with an appropriate level of detail by adjusting the level of detail of the model by referring to the product's usage history. Some or all of the above processing in the modeling unit may be performed using AI, for example, or without using AI. For example, the modeling unit can input product usage history data into a generating AI, and the generating AI can adjust the level of detail of the model.

[0047] The modeling unit can improve the accuracy of its modeling by referring to relevant product data during the modeling process. For example, it can perform detailed 3D modeling by referring to product design data, perform highly accurate 3D modeling by referring to product manufacturing data, or perform 3D modeling that reflects actual usage by referring to product usage data. By improving the accuracy of the modeling by referring to relevant product data, more accurate 3D modeling becomes possible. Some or all of the above processes in the modeling unit may be performed using AI, for example, or without AI. For example, the modeling unit can input relevant product data into a generating AI, and the generating AI can improve the accuracy of the modeling.

[0048] The transmission unit can determine the transmission priority based on the importance of the data at the time of transmission. For example, the transmission unit can determine the transmission priority based on the importance of the data at the time of transmission. For example, it can transmit important data first. It can transmit general data with normal priority. It can transmit less important data later. In this way, by determining the transmission priority based on the importance of the data, important data can be transmitted first. Some or all of the above processing in the transmission unit may be performed using AI, for example, or without AI. For example, the transmission unit can input the importance of the data into a generating AI, and the generating AI can determine the transmission priority.

[0049] The transmitting unit can optimize the transmission method when transmitting data, taking into account the network status. For example, if the network is congested, it changes the transmission method and transmits the data. If the network is stable, it transmits the data using the normal transmission method. If the network is unstable, it can optimize the transmission method and transmit the data. This enables efficient data transmission by optimizing the transmission method while considering the network status. Some or all of the above processing in the transmitting unit may be performed using AI, for example, or without AI. For example, the transmitting unit can input network status data into a generating AI, and the generating AI can optimize the transmission method.

[0050] The transmitting unit can adjust the transmission order based on the relevance of the data during transmission. For example, the transmitting unit can adjust the transmission order based on the relevance of the data during transmission. For example, it can prioritize the transmission of highly relevant data and postpone the transmission of less relevant data. The transmission order can be dynamically adjusted according to the relevance of the data. This enables efficient data transmission by adjusting the transmission order based on the relevance of the data. Some or all of the above processing in the transmitting unit may be performed using AI, for example, or without AI. For example, the transmitting unit can input the relevance of the data into a generating AI, and the generating AI can adjust the transmission order.

[0051] The transmission unit can change the transmission method depending on the size and format of the data during transmission. For example, it can split large data into smaller portions for transmission, or send small data in batches. It can also select the optimal transmission method depending on the data format. This allows for efficient data transmission by changing the transmission method according to the size and format of the data. Some or all of the above-described processes in the transmission unit may be performed using AI, for example, or without AI. For example, the transmission unit can input the size and format of the data into a generating AI, and the generating AI can change the transmission method.

[0052] The judgment unit can improve its judgment accuracy by referring to data from the product's manufacturing process during the judgment process. For example, the judgment unit can improve its judgment accuracy by referring to data from the product's manufacturing process during the judgment process. For example, it can perform a detailed judgment based on the manufacturing process data. It can perform a judgment that takes into account the characteristics of the product based on the manufacturing process data. It can perform a judgment that takes into account product defects based on the manufacturing process data. In this way, by improving the judgment accuracy by referring to data from the product's manufacturing process, more accurate judgments become possible. Some or all of the above processing in the judgment unit may be performed using, for example, a generating AI, or it may be performed without using a generating AI. For example, the judgment unit can input data from the product's manufacturing process into a generating AI, and the judgment accuracy can be improved by the generating AI.

[0053] The judgment unit can optimize the judgment criteria when making a judgment, taking into account the product's usage. For example, the judgment unit can optimize the judgment criteria when making a judgment, taking into account the product's usage. For example, it can apply stricter judgment criteria to products that are used frequently, and standard judgment criteria to products that are used infrequently. The judgment criteria can be dynamically optimized according to the usage. This makes it possible to make more appropriate judgments by optimizing the judgment criteria while taking into account the product's usage. Some or all of the above processing in the judgment unit may be performed using, for example, a generative AI, or without a generative AI. For example, the judgment unit can input product usage data into a generative AI, and the generative AI can optimize the judgment criteria.

[0054] The judgment unit can determine the priority of judgment by referring to relevant product data during the judgment process. For example, the judgment unit can determine the priority of judgment by referring to relevant product data during the judgment process. For example, it can prioritize judging important products based on the relevant data. For example, it can prioritize judging problematic products based on the relevant data. For example, it can prioritize judging products that have gone through a specific manufacturing process based on the relevant data. In this way, by determining the priority of judgment by referring to relevant product data, important products can be judged preferentially. Some or all of the above processing in the judgment unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the judgment unit can input relevant product data into a generating AI, and the generating AI can determine the priority of judgment.

[0055] The judgment unit can change the judgment criteria by referring to the product's usage history during the judgment process. For example, the judgment unit can change the judgment criteria by referring to the product's usage history during the judgment process. For example, it can apply stricter judgment criteria to products that are used frequently, and standard judgment criteria to products that are used infrequently. The judgment criteria can be dynamically changed according to the usage history. This makes it possible to make more appropriate judgments by changing the judgment criteria by referring to the product's usage history. Some or all of the above-described processes in the judgment unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the judgment unit can input product usage history data into a generating AI, and the generating AI can change the judgment criteria.

[0056] The proposal unit can improve the accuracy of its proposals by referring to data from the product's manufacturing process. For example, it can propose detailed solutions based on the manufacturing process data, propose solutions that take into account the product's characteristics, and propose solutions that take into account product defects. By improving the accuracy of proposals by referring to data from the product's manufacturing process, more accurate proposals become possible. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input data from the product's manufacturing process into a generative AI, and the generative AI can improve the accuracy of the proposals.

[0057] The proposal unit can optimize its proposals by considering the product's usage. For example, it can propose detailed solutions for frequently used products and standard solutions for less frequently used products. The proposal unit can dynamically optimize its proposals according to the usage. This allows for more appropriate proposals by optimizing the proposals by considering the product's usage. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input product usage data into a generative AI and use the generative AI to optimize the proposals.

[0058] The proposal unit can modify its proposal content by referring to relevant product data when making a proposal. For example, it can modify its proposal content by referring to relevant product data when making a proposal. For example, it can propose a detailed solution based on the relevant data. It can propose a solution that takes into account the characteristics of the product based on the relevant data. It can propose a solution that takes into account product defects based on the relevant data. This makes it possible to make more appropriate proposals by modifying the proposal content by referring to relevant product data. Some or all of the above processing in the proposal unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the proposal unit can input relevant product data into a generation AI and modify the proposal content using the generation AI.

[0059] The proposal unit can adjust the level of detail of its proposals by referring to the product's usage history. For example, it can propose detailed solutions for frequently used products and standard solutions for less frequently used products. The level of detail of the proposals can be dynamically adjusted according to the usage history. This allows for more appropriate proposals by adjusting the level of detail of the proposals by referring to the product's usage history. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input product usage history data into a generative AI, and the generative AI can adjust the level of detail of the proposals.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The product inspection system may also include a real-time feedback unit. The real-time feedback unit provides immediate feedback as the product is scanned. For example, if the scanning unit scans the appearance of a product and detects a minor scratch or defect, the real-time feedback unit can immediately notify the operator of this information. The real-time feedback unit can also suggest adjustments to the product's production line based on the scan results. For example, it can suggest adjusting the production line speed or reviewing a specific process based on the scan results. This enables real-time monitoring of product quality and rapid response. Some or all of the above processing in the real-time feedback unit may be performed using AI, for example, or without AI. For example, the real-time feedback unit can input scan data into a generating AI, which can then provide feedback.

[0062] The product inspection system may also include a predictive maintenance unit. This unit analyzes product scan data and manufacturing process data to predict the risk of future defects. For example, based on data acquired by the scanning unit, it can analyze product degradation trends and predict the likelihood of specific parts failing. The predictive maintenance unit can also suggest maintenance timing, taking into account product usage and environmental conditions. For instance, it can suggest early maintenance for frequently used products and a standard maintenance schedule for less frequently used products. This enables preventative maintenance and improves product reliability. Some or all of the above-described processes in the predictive maintenance unit may be performed using AI, or without AI. For example, the predictive maintenance unit can input scan data and manufacturing process data into a generating AI, which can then suggest maintenance timing.

[0063] The product inspection system may also include a user feedback unit. The user feedback unit collects feedback from product users and uses it to improve product quality. For example, if a product user reports a defect, this information can be collected and compared with the product's manufacturing process and scan data. The user feedback unit can also suggest improvements to the product based on the collected feedback. For instance, based on user feedback, it can suggest changing the material of a specific part or reviewing the manufacturing process. This allows for product improvements that reflect user opinions, leading to increased customer satisfaction. Some or all of the above-described processes in the user feedback unit may be performed using AI, or not. For example, the user feedback unit can input feedback data into a generating AI, which can then suggest improvements.

[0064] The product inspection system may also include an environmental monitoring unit. The environmental monitoring unit monitors the product's manufacturing and storage environments and evaluates the impact of environmental conditions on product quality. For example, it can monitor the temperature and humidity of the manufacturing environment and analyze how these conditions affect product quality. The environmental monitoring unit can also monitor the product's storage environment and suggest appropriate storage conditions. For example, since high temperature and humidity accelerate product deterioration, it can suggest an appropriate range of temperature and humidity. This enables environmental management to maintain product quality. Some or all of the above-described processes in the environmental monitoring unit may be performed using AI, for example, or without AI. For example, the environmental monitoring unit can input environmental data into a generating AI, which can then evaluate the impact of environmental conditions.

[0065] The product inspection system may also include a traceability unit. The traceability unit tracks the manufacturing and distribution history of a product and uses this information for product quality control. For example, it can record data for each stage of the product's manufacturing process and identify which stage a defect occurred at. The traceability unit can also track the product's distribution history and identify which distribution route a problem occurred at. For example, if product damage is frequent at a particular distribution route, it can suggest a review of that route. This strengthens product quality control and enables early detection and countermeasures for problems. Some or all of the above processes in the traceability unit may be performed using AI, for example, or not. For example, the traceability unit can input manufacturing and distribution history data into a generating AI, which can then identify problems and suggest countermeasures.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The scanning unit acquires an image file of the product. The image file of the product may be in formats such as JPEG, PNG, or TIFF. The scanning unit can scan the product's appearance in detail and acquire it as 3D data. For example, it can detect minute scratches or defects on the surface of the product. It can also apply different scanning algorithms depending on the shape and material of the product. For example, for metal products, a scanning algorithm that takes reflection into account is applied, and for plastic products, a scanning algorithm that takes transparency into account is applied. For products with complex shapes, a scanning algorithm appropriate to the shape can be applied. Step 2: The modeling unit performs 3D modeling based on the image files acquired by the scanning unit. 3D modeling is performed based on the software used and the accuracy of the modeling. For example, detailed digital twin data can be generated based on the acquired image files. Digital twin data includes data accuracy and data format. Step 3: The transmission unit sends the digital twin data generated by the modeling unit to the digital twin platform on the distributed computing infrastructure. The distributed computing infrastructure is configured based on the servers used and the method of data distribution. For example, the generated digital twin data can be sent to the digital twin platform on the distributed computing infrastructure in order to efficiently manage it. Step 4: The judgment unit refers to the digital twin data and determines whether the product is good or bad. The judgment is made based on the judgment criteria and the algorithm used. For example, if there are minute scratches on the product's appearance based on the digital twin data, the size and location of the scratches can be analyzed and the product can be determined to be defective. Step 5: The proposal unit estimates the cause of the defect and proposes solutions based on the judgment results obtained by the judgment unit. The estimation of the cause of the defect and the proposal of solutions are based on the data used, estimation methods, and proposal criteria. For example, it can identify problems that occurred during the product manufacturing process, estimate their causes, and propose what countermeasures should be taken.

[0068] (Example of form 2) The product inspection system according to an embodiment of the present invention proposes a "super inspection dome" to solve the problems of conventional machine learning-based visual inspection in the product inspection process of a factory. In the product inspection system, a 3D scanning device acquires an image file of the product as it passes through the "super inspection dome." This image file is transmitted to an edge server via a private 5G network. At the edge server, 3D modeling is performed, and this data is sent to a digital twin platform on a distributed computing infrastructure. Next, a generating AI refers to the digital twin data to determine whether the product is good or bad, estimate the cause of defects, and propose solutions. This mechanism eliminates the black box problem of the judgment logic that plagued conventional machine learning-based visual inspection, enabling the estimation of judgment reasons and defect causes, as well as the proposal of solutions. This significantly reduces manpower and contributes to improving factory productivity. For example, as a product passes through the "super inspection dome," a 3D scanning device acquires an image file of the product. At this time, the product's appearance is scanned in detail and acquired as 3D data. For example, minute scratches and defects on the surface of the product can be detected. This image file is transmitted to the edge server via a private 5G network. Next, the edge server performs 3D modeling based on the acquired image files. This 3D modeling generates detailed digital twin data of the product. This data is sent to the digital twin platform on the distributed computing infrastructure. The generating AI refers to the digital twin data and determines whether the product is good or bad. For example, if there is a minute scratch on the product's appearance, it analyzes the size and location of the scratch and determines that it is a defective product. The generating AI also estimates the cause of the defect. For example, it can identify potential problems that occurred during the product's manufacturing process and estimate their causes. Furthermore, the generating AI also proposes solutions. For example, it can suggest what measures should be taken to address problems that occurred during the product's manufacturing process. This leads to improved product quality and increased factory productivity.This system eliminates the problem of the judgment logic being a black box in conventional machine learning-based visual inspection, enabling estimation of the reason for judgment and the cause of defects, as well as the suggestion of solutions. This results in significant labor savings and contributes to improved factory productivity. The product inspection system acquires image files of products, performs 3D modeling, transmits them to a digital twin platform, and performs pass / fail judgment, estimation of the cause of defects, and suggestion of solutions.

[0069] The product inspection system according to the embodiment comprises a scanning unit, a modeling unit, a transmission unit, a determination unit, and a proposal unit. The scanning unit acquires an image file of the product. The image file of the product includes, but is not limited to, formats such as JPEG, PNG, and TIFF. The scanning unit can, for example, scan the appearance of the product in detail and acquire it as 3D data. For example, the scanning unit can detect minute scratches and defects on the surface of the product. The scanning unit can also apply different scanning algorithms depending on the shape and material of the product. For example, for metal products, a scanning algorithm that takes reflection into account is applied. For plastic products, a scanning algorithm that takes transparency into account is applied. For products with complex shapes, a scanning algorithm appropriate to the shape can be applied. The modeling unit performs 3D modeling based on the image file acquired by the scanning unit. The 3D modeling is performed based on, for example, the software used and the accuracy of the modeling, but is not limited to such examples. For example, the modeling unit can generate detailed digital twin data based on the acquired image file. The digital twin data includes, for example, the accuracy of the data and the format of the data, but is not limited to such examples. The transmission unit transmits the digital twin data generated by the modeling unit to a digital twin platform on a distributed computing infrastructure. The distributed computing infrastructure is configured based on, for example, the servers used and the method of data distribution, but is not limited to such examples. For example, the transmission unit can transmit the generated digital twin data to a digital twin platform on a distributed computing infrastructure in order to efficiently manage it. The judgment unit refers to the digital twin data and determines whether the product is good or bad. The judgment is made based on, for example, judgment criteria and the algorithm used, but is not limited to such examples. For example, if there is a minute scratch on the appearance of the product based on the digital twin data, the judgment unit can analyze the size and location of the scratch and determine that it is a defective product. The proposal unit estimates the cause of the defect and proposes a solution based on the judgment result obtained by the judgment unit.The estimation of the cause of defects and the proposal of solutions are performed based on, for example, the data used, estimation methods, and proposal criteria. For example, the proposal unit can identify problems that occurred during the product manufacturing process, estimate their causes, and propose what countermeasures should be taken. As a result, the product inspection system according to the embodiment can acquire image files of the product, perform 3D modeling, transmit them to a digital twin platform, and perform pass / fail judgment, estimation of the cause of defects, and proposal of solutions.

[0070] The scanning unit acquires image files of the product. These image files include, but are not limited to, formats such as JPEG, PNG, and TIFF. The scanning unit can, for example, scan the product's appearance in detail and acquire it as 3D data. Specifically, the scanning unit uses a high-resolution camera or laser scanner to capture detailed images of the product's surface and detect minute scratches and defects. This makes it possible to evaluate the product's quality with high accuracy. The scanning unit can also apply different scanning algorithms depending on the shape and material of the product. For example, for metal products, a scanning algorithm that takes reflection into account is applied, and for plastic products, a scanning algorithm that takes transparency into account is applied. Furthermore, for products with complex shapes, a scanning algorithm tailored to the shape can be applied. This allows the scanning unit to flexibly handle a variety of products and acquire accurate data. The scanning unit processes the acquired data in real time and transmits it to a central database. This allows the scanning unit to collect data efficiently and quickly, improving the overall system performance. In addition, the scanning unit can flexibly respond to specific situations and conditions by adjusting the data collection frequency and accuracy. This allows the scanning unit to collect data efficiently and effectively, improving the overall performance of the system.

[0071] The modeling unit performs 3D modeling based on image files acquired by the scanning unit. 3D modeling is performed based on, for example, the software used and the accuracy of the modeling, but is not limited to these examples. Specifically, the modeling unit uses advanced 3D modeling software to generate detailed digital twin data based on the acquired image files. This digital twin data includes, for example, the product's shape, dimensions, material, and surface condition. This allows the modeling unit to create a digital model with nearly the same accuracy as the actual product. Furthermore, the modeling unit can simulate the product's performance and durability based on the generated digital twin data. For example, it can simulate how the product deforms under specific environmental conditions and how much load it can withstand, thereby evaluating the product's quality. This allows the modeling unit to evaluate product quality with high accuracy and identify areas for improvement. Additionally, the modeling unit can share the generated digital twin data with other departments and systems. This allows the modeling unit to evaluate product quality with high accuracy and identify areas for improvement.

[0072] The transmission unit transmits the digital twin data generated by the modeling unit to the digital twin platform on a distributed computing infrastructure. The distributed computing infrastructure is configured based on, for example, the servers used and the method of data distribution, but is not limited to such examples. Specifically, the transmission unit efficiently transmits the generated digital twin data using a high-speed and stable communication protocol. This allows the transmission unit to quickly and reliably transmit the digital twin data to the digital twin platform on the distributed computing infrastructure. Furthermore, the transmission unit can compress and encrypt the transmitted digital twin data in order to efficiently manage it. This allows the transmission unit to efficiently transmit data while ensuring the security of the digital twin data. In addition, the transmission unit can share the transmitted digital twin data with other systems and departments. This allows the transmission unit to efficiently manage the digital twin data and improve the overall system performance.

[0073] The judgment unit refers to digital twin data to determine whether a product is good or bad. This judgment is based on criteria and algorithms, but is not limited to these. Specifically, the judgment unit can use AI to analyze digital twin data and, if a product has minor scratches on its surface, analyze the size and location of the scratches to determine if it is defective. The AI ​​uses image recognition technology to analyze digital twin data and identify minor scratches and defects on the product's surface. The judgment unit also checks whether the product's dimensions and shape match the design drawings and determines it is defective if they do not. Furthermore, the judgment unit analyzes the product's material and surface condition and determines it is defective if the material or surface condition does not meet specified standards. This allows the judgment unit to evaluate product quality with high accuracy and quickly identify defective products. In addition, the judgment unit can utilize historical data and statistical information to perform long-term quality evaluations and trend analyses. For example, based on past defective product data, it can predict quality fluctuations in specific products or manufacturing processes and formulate future countermeasures. This allows the judgment unit to handle not only real-time quality evaluation but also long-term quality control, improving the reliability and safety of the entire system.

[0074] The proposal department estimates the cause of defects and proposes solutions based on the judgment results obtained by the judgment department. The estimation of the cause of defects and the proposal of solutions are based on, for example, the data used, estimation methods, and proposal criteria, but are not limited to such examples. Specifically, the proposal department uses AI to analyze the judgment results and identify problems that occurred in the product manufacturing process. Based on past data and statistical information, the AI ​​detects abnormal patterns and trends in the manufacturing process and estimates the cause of defects. The proposal department also proposes what countermeasures should be taken based on the estimated cause of defects. For example, it can identify problems that occurred in a specific step of the manufacturing process and propose specific countermeasures to improve that step. Furthermore, the proposal department can simulate the effects of the proposed countermeasures and select the optimal countermeasure. In this way, the proposal department can provide specific countermeasures to improve product quality and support the efficiency and quality improvement of the manufacturing process. Furthermore, the proposal department can monitor the implementation status of the proposed countermeasures and modify them as necessary. In this way, the proposal department can support the continuous improvement of product quality and improve the reliability and safety of the entire system.

[0075] The scanning unit can scan the product's appearance in detail and acquire it as 3D data. For example, the scanning unit can detect minute scratches and defects on the product's surface. The scanning unit can also apply different scanning algorithms depending on the product's shape and material. For example, for metal products, a scanning algorithm that considers reflection is applied. For plastic products, a scanning algorithm that considers transparency is applied. For products with complex shapes, a scanning algorithm appropriate to the shape can be applied. This allows for more accurate inspection by scanning the product's appearance in detail and acquiring it as 3D data. Some or all of the above processing in the scanning unit may be performed using AI, for example, or without AI. For example, the scanning unit can input the data acquired by scanning the product's appearance into a generating AI, which can then analyze the data.

[0076] The modeling unit can perform 3D modeling based on acquired image files and generate detailed digital twin data. For example, the modeling unit can perform 3D modeling based on the software used and the accuracy of the modeling. The modeling unit can also apply different modeling algorithms depending on the shape and material of the product. For example, for metal products, a modeling algorithm that takes reflection into account is applied. For plastic products, a modeling algorithm that takes transparency into account is applied. For products with complex shapes, a modeling algorithm appropriate to the shape can be applied. This makes it possible to perform detailed inspection of products by performing 3D modeling based on acquired image files and generating detailed digital twin data. Some or all of the above processing in the modeling unit may be performed using AI, for example, or without AI. For example, the modeling unit can input acquired image files into a generation AI and perform 3D modeling using the generation AI.

[0077] The transmission unit can transmit the generated digital twin data to a digital twin platform on a distributed computing infrastructure. For example, the transmission unit can transmit data based on the servers used and the data distribution method. The transmission unit can also determine the transmission priority based on the importance of the data. For example, it can transmit important data first, general data with normal priority, and less important data later. This enables efficient data management by transmitting the generated digital twin data to a digital twin platform on a distributed computing infrastructure. Some or all of the above processing in the transmission unit may be performed using AI, for example, or without AI. For example, the transmission unit can input the generated digital twin data into a generating AI, and the generating AI can perform the data transmission.

[0078] The judgment unit can determine whether a product is good or bad by referring to digital twin data. For example, the judgment unit can determine whether a product is good or bad by referring to digital twin data. For example, if there are minute scratches on the appearance of a product, the judgment unit can analyze the size and location of the scratches based on the digital twin data and determine that the product is defective. The judgment unit can also improve the accuracy of the judgment by referring to data from the product's manufacturing process. For example, it can perform a detailed judgment based on the manufacturing process data. It can perform a judgment that takes into account the characteristics of the product based on the manufacturing process data. It can perform a judgment that takes into account product defects based on the manufacturing process data. As a result, accurate judgment becomes possible by referring to digital twin data to determine whether a product is good or bad. Some or all of the above processing in the judgment unit may be performed using, for example, a generating AI, or it may be performed without using a generating AI. For example, the judgment unit can input digital twin data into a generating AI and have the generating AI perform the good or bad judgment.

[0079] The proposal department can propose what measures should be taken to address problems that arise during the product manufacturing process. For example, the proposal department can identify problems that arise during the product manufacturing process, estimate their causes, and propose what measures should be taken. The proposal department can also optimize its proposals by considering the product's usage. For example, it can propose detailed solutions for frequently used products and standard solutions for less frequently used products. The proposals can be dynamically optimized according to usage. This improves product quality by proposing what measures should be taken to address problems that arise during the product manufacturing process. Some or all of the above-described processes in the proposal department may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal department can input data from the product's manufacturing process into a generative AI, and the generative AI can propose solutions.

[0080] The scanning unit can estimate the product's emotions and adjust the scan detail based on the estimated emotions. For example, if the product is stressed, a detailed scan is performed to detect minor defects. If the product is relaxed, a standard scan is performed to detect common defects. If the product is in a hurry, a simplified scan is performed to detect only major defects. This allows for a more appropriate scan by adjusting the scan detail based on the product's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the scanning unit may be performed using AI or not. For example, the scanning unit can input product emotion data into a generative AI, which can then adjust the scan detail.

[0081] The scanning unit can apply different scanning algorithms depending on the material and shape of the product during scanning. For example, for metal products, a scanning algorithm that takes reflection into account is applied. For plastic products, a scanning algorithm that takes transparency into account is applied. For products with complex shapes, a scanning algorithm appropriate to the shape can be applied. This improves scanning accuracy by applying different scanning algorithms depending on the material and shape of the product. Some or all of the above processing in the scanning unit may be performed using AI, for example, or without AI. For example, the scanning unit can input data on the material and shape of the product into a generating AI, and the generating AI can apply a scanning algorithm.

[0082] The scanning unit can improve scanning accuracy by taking into account environmental conditions such as the temperature and humidity of the product during scanning. For example, in a high-temperature environment, temperature correction can be performed to improve scanning accuracy. If the humidity is high, humidity correction can be performed to improve scanning accuracy. In a low-temperature environment, temperature correction can be performed to improve scanning accuracy. By improving scanning accuracy by taking into account environmental conditions such as the temperature and humidity of the product, more accurate scanning becomes possible. Some or all of the above processing in the scanning unit may be performed using AI, for example, or without AI. For example, the scanning unit can input temperature and humidity data of the product into a generating AI, and the generating AI can improve scanning accuracy.

[0083] The scanning unit can estimate the product's emotions and adjust the scanning timing based on the estimated emotions. For example, if the product is stressed, the scanning timing may be delayed. If the product is relaxed, the scanning timing may be kept normal. If the product is in a hurry, the scanning timing may be sped up. By adjusting the scanning timing based on the product's emotions, scanning can be performed at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the scanning unit may be performed using AI or not using AI. For example, the scanning unit can input product emotion data into a generative AI, which can then adjust the scanning timing.

[0084] The scanning unit can determine scanning priorities by referring to the product's manufacturing history during scanning. For example, the scanning unit can prioritize scanning important products based on their manufacturing history, prioritize scanning problematic products based on their manufacturing history, or prioritize scanning products that have gone through a specific manufacturing process based on their manufacturing history. This allows for priority scanning of important products by referring to the product's manufacturing history. Some or all of the above processing in the scanning unit may be performed using AI, for example, or without AI. For example, the scanning unit can input product manufacturing history data into a generating AI, and the generating AI can determine the scanning priorities.

[0085] The scanning unit can adjust the scanning frequency while taking into account the product's usage. For example, it can scan frequently used products more often, and scan less frequently used products more frequently. The scanning unit can dynamically adjust the scanning frequency according to the usage. This allows for scanning at an appropriate frequency by adjusting the scanning frequency while taking into account the product's usage. Some or all of the above processing in the scanning unit may be performed using AI, for example, or without AI. For example, the scanning unit can input product usage data into a generating AI, and the generating AI can adjust the scanning frequency.

[0086] The modeling unit can estimate the emotion of a product and adjust the level of detail of the 3D model based on the estimated emotion. For example, if the product is stressed, a detailed 3D model can be created. If the product is relaxed, a standard 3D model can be created. If the product is in a hurry, a simplified 3D model can be created. This allows for more appropriate 3D modeling by adjusting the level of detail of the 3D model based on the emotion of the product. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the modeling unit may be performed using AI or not using AI. For example, the modeling unit can input product emotion data into a generative AI, and the generative AI can adjust the level of detail of the 3D model.

[0087] The modeling unit can apply different modeling algorithms during modeling depending on the shape and material of the product. For example, in the case of metal products, a modeling algorithm that takes reflection into consideration is applied. In the case of plastic products, a modeling algorithm that takes transparency into consideration is applied. In the case of products with complex shapes, a modeling algorithm appropriate to the shape can be applied. This improves modeling accuracy by applying different modeling algorithms depending on the shape and material of the product. Some or all of the above processing in the modeling unit may be performed using AI, for example, or without AI. For example, the modeling unit can input data on the shape and material of the product into a generating AI, and the generating AI can apply a modeling algorithm.

[0088] The modeling unit can improve modeling accuracy by referencing data from the product's manufacturing process during modeling. For example, the modeling unit can improve modeling accuracy by referencing data from the product's manufacturing process during modeling. For example, it can perform detailed 3D modeling based on manufacturing process data. It can perform 3D modeling that takes product characteristics into account based on manufacturing process data. It can perform 3D modeling that takes product defects into account based on manufacturing process data. By improving modeling accuracy by referencing data from the product's manufacturing process, more accurate 3D modeling becomes possible. Some or all of the above processes in the modeling unit may be performed using AI, for example, or without AI. For example, the modeling unit can input data from the product's manufacturing process into a generating AI, and the generating AI can improve modeling accuracy.

[0089] The modeling unit can estimate the emotions of products and determine modeling priorities based on the estimated emotions. For example, if a product is stressed, it is modeled preferentially. If a product is relaxed, it is modeled with normal priority. If a product is in a hurry, it can be modeled later. This allows important products to be modeled preferentially by determining modeling priorities based on the emotions of the products. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the modeling unit may be performed using AI or not using AI. For example, the modeling unit can input product emotion data into a generative AI, and the generative AI can determine the modeling priorities.

[0090] The modeling unit can adjust the level of detail of the model by referring to the product's usage history during the modeling process. For example, the modeling unit can adjust the level of detail of the model by referring to the product's usage history during the modeling process. For example, it can model products that are used frequently in detail, and models products that are used infrequently in a standard manner. The level of detail of the model can be dynamically adjusted according to the usage history. This makes it possible to model with an appropriate level of detail by adjusting the level of detail of the model by referring to the product's usage history. Some or all of the above processing in the modeling unit may be performed using AI, for example, or without using AI. For example, the modeling unit can input product usage history data into a generating AI, and the generating AI can adjust the level of detail of the model.

[0091] The modeling unit can improve the accuracy of its modeling by referring to relevant product data during the modeling process. For example, it can perform detailed 3D modeling by referring to product design data, perform highly accurate 3D modeling by referring to product manufacturing data, or perform 3D modeling that reflects actual usage by referring to product usage data. By improving the accuracy of the modeling by referring to relevant product data, more accurate 3D modeling becomes possible. Some or all of the above processes in the modeling unit may be performed using AI, for example, or without AI. For example, the modeling unit can input relevant product data into a generating AI, and the generating AI can improve the accuracy of the modeling.

[0092] The transmitting unit can estimate the product's emotions and adjust the timing of data transmission based on the estimated emotions. For example, if the product is stressed, the timing of data transmission may be delayed. If the product is relaxed, the timing of data transmission may be normal. If the product is in a hurry, the timing of data transmission may be sped up. By adjusting the timing of data transmission based on the product's emotions, it becomes possible to transmit data at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the transmitting unit may be performed using AI or not using AI. For example, the transmitting unit can input product emotion data into a generative AI, and the generative AI can adjust the timing of data transmission.

[0093] The transmission unit can determine the transmission priority based on the importance of the data at the time of transmission. For example, the transmission unit can determine the transmission priority based on the importance of the data at the time of transmission. For example, it can transmit important data first. It can transmit general data with normal priority. It can transmit less important data later. In this way, by determining the transmission priority based on the importance of the data, important data can be transmitted first. Some or all of the above processing in the transmission unit may be performed using AI, for example, or without AI. For example, the transmission unit can input the importance of the data into a generating AI, and the generating AI can determine the transmission priority.

[0094] The transmitting unit can optimize the transmission method when transmitting data, taking into account the network status. For example, if the network is congested, it changes the transmission method and transmits the data. If the network is stable, it transmits the data using the normal transmission method. If the network is unstable, it can optimize the transmission method and transmit the data. This enables efficient data transmission by optimizing the transmission method while considering the network status. Some or all of the above processing in the transmitting unit may be performed using AI, for example, or without AI. For example, the transmitting unit can input network status data into a generating AI, and the generating AI can optimize the transmission method.

[0095] The transmission unit can estimate the product's emotions and determine the priority of transmitted data based on the estimated emotions. For example, if the product is stressed, important data is sent first. If the product is relaxed, data is sent with normal priority. If the product is in a hurry, less important data can be sent later. This ensures that important data is sent first by prioritizing the transmitted data based on the product's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the transmission unit may be performed using AI or not using AI. For example, the transmission unit can input product emotion data into a generative AI, which can then determine the priority of the transmitted data.

[0096] The transmitting unit can adjust the transmission order based on the relevance of the data during transmission. For example, the transmitting unit can adjust the transmission order based on the relevance of the data during transmission. For example, it can prioritize the transmission of highly relevant data and postpone the transmission of less relevant data. The transmission order can be dynamically adjusted according to the relevance of the data. This enables efficient data transmission by adjusting the transmission order based on the relevance of the data. Some or all of the above processing in the transmitting unit may be performed using AI, for example, or without AI. For example, the transmitting unit can input the relevance of the data into a generating AI, and the generating AI can adjust the transmission order.

[0097] The transmission unit can change the transmission method depending on the size and format of the data during transmission. For example, it can split large data into smaller portions for transmission, or send small data in batches. It can also select the optimal transmission method depending on the data format. This allows for efficient data transmission by changing the transmission method according to the size and format of the data. Some or all of the above-described processes in the transmission unit may be performed using AI, for example, or without AI. For example, the transmission unit can input the size and format of the data into a generating AI, and the generating AI can change the transmission method.

[0098] The judgment unit can estimate the product's emotions and adjust the judgment criteria based on the estimated emotions of the product. For example, if the product is stressed, a strict judgment criterion may be applied. If the product is relaxed, a standard judgment criterion may be applied. If the product is in a hurry, a lenient judgment criterion may be applied. This allows for more appropriate judgments by adjusting the judgment criteria based on the product's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the judgment unit may be performed using a generative AI, or not using a generative AI. For example, the judgment unit can input product emotion data into a generative AI and have the generative AI adjust the judgment criteria.

[0099] The judgment unit can improve its judgment accuracy by referring to data from the product's manufacturing process during the judgment process. For example, the judgment unit can improve its judgment accuracy by referring to data from the product's manufacturing process during the judgment process. For example, it can perform a detailed judgment based on the manufacturing process data. It can perform a judgment that takes into account the characteristics of the product based on the manufacturing process data. It can perform a judgment that takes into account product defects based on the manufacturing process data. In this way, by improving the judgment accuracy by referring to data from the product's manufacturing process, more accurate judgments become possible. Some or all of the above processing in the judgment unit may be performed using, for example, a generating AI, or it may be performed without using a generating AI. For example, the judgment unit can input data from the product's manufacturing process into a generating AI, and the judgment accuracy can be improved by the generating AI.

[0100] The judgment unit can optimize the judgment criteria when making a judgment, taking into account the product's usage. For example, the judgment unit can optimize the judgment criteria when making a judgment, taking into account the product's usage. For example, it can apply stricter judgment criteria to products that are used frequently, and standard judgment criteria to products that are used infrequently. The judgment criteria can be dynamically optimized according to the usage. This makes it possible to make more appropriate judgments by optimizing the judgment criteria while taking into account the product's usage. Some or all of the above processing in the judgment unit may be performed using, for example, a generative AI, or without a generative AI. For example, the judgment unit can input product usage data into a generative AI, and the generative AI can optimize the judgment criteria.

[0101] The judgment unit can estimate the product's emotions and adjust the display method of the judgment result based on the estimated emotions of the product. For example, if the product is stressed, a detailed judgment result can be displayed. If the product is relaxed, a standard judgment result can be displayed. If the product is in a hurry, a simplified judgment result can be displayed. This allows for a more appropriate display by adjusting the display method of the judgment result based on the product's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the judgment unit may be performed using a generative AI, or not using a generative AI. For example, the judgment unit can input product emotion data into a generative AI, and the generative AI can adjust the display method of the judgment result.

[0102] The judgment unit can determine the priority of judgment by referring to relevant product data during the judgment process. For example, the judgment unit can determine the priority of judgment by referring to relevant product data during the judgment process. For example, it can prioritize judging important products based on the relevant data. For example, it can prioritize judging problematic products based on the relevant data. For example, it can prioritize judging products that have gone through a specific manufacturing process based on the relevant data. In this way, by determining the priority of judgment by referring to relevant product data, important products can be judged preferentially. Some or all of the above processing in the judgment unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the judgment unit can input relevant product data into a generating AI, and the generating AI can determine the priority of judgment.

[0103] The judgment unit can change the judgment criteria by referring to the product's usage history during the judgment process. For example, the judgment unit can change the judgment criteria by referring to the product's usage history during the judgment process. For example, it can apply stricter judgment criteria to products that are used frequently, and standard judgment criteria to products that are used infrequently. The judgment criteria can be dynamically changed according to the usage history. This makes it possible to make more appropriate judgments by changing the judgment criteria by referring to the product's usage history. Some or all of the above-described processes in the judgment unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the judgment unit can input product usage history data into a generating AI, and the generating AI can change the judgment criteria.

[0104] The suggestion unit can estimate the product's emotions and adjust the suggestions based on the estimated emotions. For example, if the product is stressed, it can suggest a detailed solution. If the product is relaxed, it can suggest a standard solution. If the product is in a hurry, it can suggest a simple solution. By adjusting the suggestions based on the product's emotions, more appropriate suggestions can be made. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using a generative AI, or not. For example, the suggestion unit can input product emotion data into a generative AI, and the generative AI can adjust the suggestions.

[0105] The proposal unit can improve the accuracy of its proposals by referring to data from the product's manufacturing process. For example, it can propose detailed solutions based on the manufacturing process data, propose solutions that take into account the product's characteristics, and propose solutions that take into account product defects. By improving the accuracy of proposals by referring to data from the product's manufacturing process, more accurate proposals become possible. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input data from the product's manufacturing process into a generative AI, and the generative AI can improve the accuracy of the proposals.

[0106] The proposal unit can optimize its proposals by considering the product's usage. For example, it can propose detailed solutions for frequently used products and standard solutions for less frequently used products. The proposal unit can dynamically optimize its proposals according to the usage. This allows for more appropriate proposals by optimizing the proposals by considering the product's usage. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input product usage data into a generative AI and use the generative AI to optimize the proposals.

[0107] The suggestion unit can estimate the product's emotions and determine the priority of suggestions based on the estimated emotions. For example, if the product is stressed, important suggestions will be prioritized. If the product is relaxed, suggestions will be given the normal priority. If the product is in a hurry, less important suggestions can be postponed. This allows important suggestions to be prioritized by determining the priority of suggestions based on the product's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using a generative AI, or not. For example, the suggestion unit can input product emotion data into a generative AI, and the generative AI can determine the priority of suggestions.

[0108] The proposal unit can modify its proposal content by referring to relevant product data when making a proposal. For example, it can modify its proposal content by referring to relevant product data when making a proposal. For example, it can propose a detailed solution based on the relevant data. It can propose a solution that takes into account the characteristics of the product based on the relevant data. It can propose a solution that takes into account product defects based on the relevant data. This makes it possible to make more appropriate proposals by modifying the proposal content by referring to relevant product data. Some or all of the above processing in the proposal unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the proposal unit can input relevant product data into a generation AI and modify the proposal content using the generation AI.

[0109] The proposal unit can adjust the level of detail of its proposals by referring to the product's usage history. For example, it can propose detailed solutions for frequently used products and standard solutions for less frequently used products. The level of detail of the proposals can be dynamically adjusted according to the usage history. This allows for more appropriate proposals by adjusting the level of detail of the proposals by referring to the product's usage history. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input product usage history data into a generative AI, and the generative AI can adjust the level of detail of the proposals.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The product inspection system may also include a real-time feedback unit. The real-time feedback unit provides immediate feedback as the product is scanned. For example, if the scanning unit scans the appearance of a product and detects a minor scratch or defect, the real-time feedback unit can immediately notify the operator of this information. The real-time feedback unit can also suggest adjustments to the product's production line based on the scan results. For example, it can suggest adjusting the production line speed or reviewing a specific process based on the scan results. This enables real-time monitoring of product quality and rapid response. Some or all of the above processing in the real-time feedback unit may be performed using AI, for example, or without AI. For example, the real-time feedback unit can input scan data into a generating AI, which can then provide feedback.

[0112] The product inspection system may also include a predictive maintenance unit. This unit analyzes product scan data and manufacturing process data to predict the risk of future defects. For example, based on data acquired by the scanning unit, it can analyze product degradation trends and predict the likelihood of specific parts failing. The predictive maintenance unit can also suggest maintenance timing, taking into account product usage and environmental conditions. For instance, it can suggest early maintenance for frequently used products and a standard maintenance schedule for less frequently used products. This enables preventative maintenance and improves product reliability. Some or all of the above-described processes in the predictive maintenance unit may be performed using AI, or without AI. For example, the predictive maintenance unit can input scan data and manufacturing process data into a generating AI, which can then suggest maintenance timing.

[0113] The product inspection system may also include a user feedback unit. The user feedback unit collects feedback from product users and uses it to improve product quality. For example, if a product user reports a defect, this information can be collected and compared with the product's manufacturing process and scan data. The user feedback unit can also suggest improvements to the product based on the collected feedback. For instance, based on user feedback, it can suggest changing the material of a specific part or reviewing the manufacturing process. This allows for product improvements that reflect user opinions, leading to increased customer satisfaction. Some or all of the above-described processes in the user feedback unit may be performed using AI, or not. For example, the user feedback unit can input feedback data into a generating AI, which can then suggest improvements.

[0114] The product inspection system may also include an environmental monitoring unit. The environmental monitoring unit monitors the product's manufacturing and storage environments and evaluates the impact of environmental conditions on product quality. For example, it can monitor the temperature and humidity of the manufacturing environment and analyze how these conditions affect product quality. The environmental monitoring unit can also monitor the product's storage environment and suggest appropriate storage conditions. For example, since high temperature and humidity accelerate product deterioration, it can suggest an appropriate range of temperature and humidity. This enables environmental management to maintain product quality. Some or all of the above-described processes in the environmental monitoring unit may be performed using AI, for example, or without AI. For example, the environmental monitoring unit can input environmental data into a generating AI, which can then evaluate the impact of environmental conditions.

[0115] The product inspection system may also include a traceability unit. The traceability unit tracks the manufacturing and distribution history of a product and uses this information for product quality control. For example, it can record data for each stage of the product's manufacturing process and identify which stage a defect occurred at. The traceability unit can also track the product's distribution history and identify which distribution route a problem occurred at. For example, if product damage is frequent at a particular distribution route, it can suggest a review of that route. This strengthens product quality control and enables early detection and countermeasures for problems. Some or all of the above processes in the traceability unit may be performed using AI, for example, or not. For example, the traceability unit can input manufacturing and distribution history data into a generating AI, which can then identify problems and suggest countermeasures.

[0116] The product inspection system may further include an emotion estimation unit. The emotion estimation unit estimates the emotions of the product user and evaluates the product quality based on those emotions. For example, it can analyze the user's facial expressions and voice while using the product to estimate the user's satisfaction or dissatisfaction. The emotion estimation unit can also suggest improvements to the product based on the estimated emotions. For example, if the user is dissatisfied, it can identify the cause and suggest improvements. This makes it possible to improve the product to reflect the user's emotions, thereby improving customer satisfaction. Some or all of the above processing in the emotion estimation unit may be performed using AI, for example, or without AI. For example, the emotion estimation unit can input the user's emotion data into a generating AI, which can then suggest improvements.

[0117] The product inspection system may further include an emotional feedback unit. The emotional feedback unit provides real-time feedback on the user's emotions, improving the product user experience. For example, while a user is using the product, the emotional feedback unit can analyze the user's facial expressions and voice, and if the user is experiencing stress, it can immediately provide that information as feedback. The emotional feedback unit can also suggest ways to use the product based on the user's emotions. For example, if the user is experiencing stress, it can suggest ways to use the product to relax. This enables feedback that reflects the user's emotions in real time, improving the product user experience. Some or all of the above processing in the emotional feedback unit may be performed using AI, for example, or without AI. For example, the emotional feedback unit can input the user's emotional data into a generating AI, which can then provide feedback.

[0118] The product inspection system may also include an emotion analysis unit. The emotion analysis unit analyzes the emotions of product users in detail and suggests improvements to the product based on the analysis results. For example, it can analyze the user's facial expressions and voice while using the product and analyze changes in the user's emotions in detail. The emotion analysis unit can also suggest improvements to the product based on the analysis results. For example, if a user is dissatisfied with a particular function, it can suggest improvements to that function. This makes it possible to analyze the user's emotions in detail and use that information to improve the product. Some or all of the above processing in the emotion analysis unit may be performed using AI, for example, or without AI. For example, the emotion analysis unit can input the user's emotion data into a generating AI, which can then suggest improvements.

[0119] The product inspection system may also include an emotion monitoring unit. The emotion monitoring unit continuously monitors the emotions of product users and accumulates the data. For example, it can continuously analyze the user's facial expressions and voice while they are using the product and monitor changes in the user's emotions. The emotion monitoring unit can also analyze long-term emotional trends based on the accumulated data. For example, it can analyze what kind of emotional changes a user experiences over a specific period and suggest improvements to the product based on the results. This makes it possible to continuously monitor the user's emotions and use this information to improve the product from a long-term perspective. Some or all of the above processing in the emotion monitoring unit may be performed using AI, for example, or without AI. For example, the emotion monitoring unit can input the user's emotional data into a generating AI, which can then suggest improvements.

[0120] The product inspection system may further include an emotion prediction unit. The emotion prediction unit predicts the emotions of the product user and suggests improvements to the product based on the prediction results. For example, it can analyze the user's facial expressions and voice while using the product and predict future changes in emotions. The emotion prediction unit can also suggest improvements to the product based on the prediction results. For example, if there is a high probability that the user will feel dissatisfied in the future, it can identify the cause and suggest improvements. This makes it possible to predict the user's emotions and make improvements to the product in advance. Some or all of the above processing in the emotion prediction unit may be performed using AI, for example, or without AI. For example, the emotion prediction unit can input the user's emotion data into a generating AI, and the generating AI can suggest improvements.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The scanning unit acquires an image file of the product. The image file of the product may be in formats such as JPEG, PNG, or TIFF. The scanning unit can scan the product's appearance in detail and acquire it as 3D data. For example, it can detect minute scratches or defects on the surface of the product. It can also apply different scanning algorithms depending on the shape and material of the product. For example, for metal products, a scanning algorithm that takes reflection into account is applied, and for plastic products, a scanning algorithm that takes transparency into account is applied. For products with complex shapes, a scanning algorithm appropriate to the shape can be applied. Step 2: The modeling unit performs 3D modeling based on the image files acquired by the scanning unit. 3D modeling is performed based on the software used and the accuracy of the modeling. For example, detailed digital twin data can be generated based on the acquired image files. Digital twin data includes data accuracy and data format. Step 3: The transmission unit sends the digital twin data generated by the modeling unit to the digital twin platform on the distributed computing infrastructure. The distributed computing infrastructure is configured based on the servers used and the method of data distribution. For example, the generated digital twin data can be sent to the digital twin platform on the distributed computing infrastructure in order to efficiently manage it. Step 4: The judgment unit refers to the digital twin data and determines whether the product is good or bad. The judgment is made based on the judgment criteria and the algorithm used. For example, if there are minute scratches on the product's appearance based on the digital twin data, the size and location of the scratches can be analyzed and the product can be determined to be defective. Step 5: The proposal unit estimates the cause of the defect and proposes solutions based on the judgment results obtained by the judgment unit. The estimation of the cause of the defect and the proposal of solutions are based on the data used, estimation methods, and proposal criteria. For example, it can identify problems that occurred during the product manufacturing process, estimate their causes, and propose what countermeasures should be taken.

[0123] 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.

[0124] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the scanning unit, modeling unit, transmission unit, determination unit, and proposal unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the scanning unit acquires an image file of the product using the camera 42 of the smart device 14. The modeling unit performs 3D modeling using the identification processing unit 290 of the data processing unit 12. The transmission unit transmits digital twin data via the communication I / F 44 of the smart device 14. The determination unit determines whether the product is good or bad using the identification processing unit 290 of the data processing unit 12. The proposal unit estimates the cause of the defect and proposes a solution using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] 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.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0130] 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.

[0131] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, 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.

[0132] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] 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.

[0134] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] 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.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the scanning unit, modeling unit, transmission unit, determination unit, and proposal unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the scanning unit acquires an image file of the product using the camera 42 of the smart glasses 214. The modeling unit performs 3D modeling using the identification processing unit 290 of the data processing unit 12. The transmission unit transmits digital twin data via the communication I / F 44 of the smart glasses 214. The determination unit determines whether the product is good or bad using the identification processing unit 290 of the data processing unit 12. The proposal unit estimates the cause of the defect and proposes a solution using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] 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.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0146] 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.

[0147] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, 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.

[0148] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] 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.

[0150] 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.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] 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.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the scanning unit, modeling unit, transmission unit, determination unit, and proposal unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the scanning unit acquires an image file of the product using the camera 42 of the headset terminal 314. The modeling unit performs 3D modeling using the identification processing unit 290 of the data processing unit 12. The transmission unit transmits digital twin data via the communication I / F 44 of the headset terminal 314. The determination unit determines whether the product is good or bad using the identification processing unit 290 of the data processing unit 12. The proposal unit estimates the cause of the defect and proposes a solution using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] 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.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0162] 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.

[0163] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, 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.

[0164] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] 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.

[0166] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] 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.

[0168] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] 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.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the scanning unit, modeling unit, transmission unit, determination unit, and proposal unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the scanning unit acquires an image file of the product using the camera 42 of the robot 414. The modeling unit performs 3D modeling using the identification processing unit 290 of the data processing unit 12. The transmission unit transmits digital twin data via the communication I / F 44 of the robot 414. The determination unit determines whether the product is good or bad using the identification processing unit 290 of the data processing unit 12. The proposal unit estimates the cause of the defect and proposes a solution using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0176] 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.

[0177] Figure 9 shows the 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.

[0178] 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.

[0179] 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.

[0180] 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, and motorcycles, 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 based, for example, 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.

[0181] 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."

[0182] 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.

[0183] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] 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 other things 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.

[0193] 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.

[0194] (Note 1) A scanning unit that acquires image files of the product, A modeling unit that performs 3D modeling based on the image file acquired by the scanning unit, A transmission unit that transmits the data generated by the modeling unit to a digital twin platform, A determination unit that performs a pass / fail determination by referring to the data transmitted by the transmission unit, The system includes a proposal unit that estimates the cause of the defect and proposes a solution based on the determination result obtained by the determination unit. A system characterized by the following features. (Note 2) The scanning unit is The product's exterior is scanned in detail and obtained as 3D data. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned modeling unit is Based on the acquired image files, 3D modeling is performed to generate detailed digital twin data. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned transmitting unit The generated digital twin data is sent to a digital twin platform on a distributed computing infrastructure. The system described in Appendix 1, characterized by the features described herein. (Note 5) The determination unit, The quality of the product is determined by referring to digital twin data. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned proposal section is, We propose what measures should be taken to address problems that occurred during the product manufacturing process. The system described in Appendix 1, characterized by the features described herein. (Note 7) The scanning unit is The system estimates the sentiment of the product and adjusts the level of detail of the scan based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The scanning unit is During scanning, different scanning algorithms are applied depending on the material and shape of the product. The system described in Appendix 1, characterized by the features described herein. (Note 9) The scanning unit is During scanning, the product's environmental conditions, such as temperature and humidity, are taken into consideration to improve scanning accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 10) The scanning unit is The system estimates the product's emotions and adjusts the timing of scans based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The scanning unit is During scanning, the product's manufacturing history is referenced to determine the scanning priority. The system described in Appendix 1, characterized by the features described herein. (Note 12) The scanning unit is During scanning, the scanning frequency is adjusted based on the product's usage. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned modeling unit is Estimate the sentiment of the product and adjust the level of detail of the 3D model based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned modeling unit is During modeling, different modeling algorithms are applied depending on the shape and material of the product. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned modeling unit is During modeling, we improve modeling accuracy by referencing data from the product's manufacturing process. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned modeling unit is Estimate the sentiment of the product and determine the modeling priorities based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned modeling unit is During modeling, refer to the product's usage history to adjust the level of detail in the model. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned modeling unit is During modeling, referencing relevant product data improves the accuracy of the model. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned transmitting unit We estimate the sentiment of the product and adjust the timing of data transmission based on the estimated sentiment of the product. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned transmitting unit When sending data, the system prioritizes transmission based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned transmitting unit When sending data, the transmission method is optimized considering the network status. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned transmitting unit The system estimates the sentiment of a product and prioritizes the data to be sent based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned transmitting unit When sending data, adjust the order of transmission based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned transmitting unit When sending data, the sending method is changed depending on the size and format of the data. The system described in Appendix 1, characterized by the features described herein. (Note 25) The determination unit, Estimate the sentiment of the product and adjust the judgment criteria based on the estimated sentiment of the product. The system described in Appendix 1, characterized by the features described herein. (Note 26) The determination unit, During the judgment process, data from the product's manufacturing process is referenced to improve the accuracy of the judgment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The determination unit, When making a decision, the evaluation criteria are optimized by taking into account the product's usage. The system described in Appendix 1, characterized by the features described herein. (Note 28) The determination unit, The system estimates the emotional state of a product and adjusts how the results are displayed based on the estimated emotional state. The system described in Appendix 1, characterized by the features described herein. (Note 29) The determination unit, When making a decision, the priority of the decision is determined by referring to relevant product data. The system described in Appendix 1, characterized by the features described herein. (Note 30) The determination unit, When making a decision, the evaluation criteria are changed by referring to the product's usage history. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned proposal section is, Estimate the sentiment of the product and adjust the suggestions based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned proposal section is, When making a proposal, we refer to data from the product's manufacturing process to improve the accuracy of the proposal. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned proposal section is, When making a proposal, optimize the proposal content by considering the product's usage. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned proposal section is, Estimate the sentiment of a product and prioritize suggestions based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned proposal section is, When making a proposal, refer to relevant product data to modify the proposal. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned proposal section is, When making a proposal, refer to the product usage history to adjust the level of detail in the proposal. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A scanning unit that acquires image files of the product, A modeling unit that performs 3D modeling based on the image file acquired by the scanning unit, A transmission unit that transmits the data generated by the modeling unit to a digital twin platform, A determination unit that performs a pass / fail determination by referring to the data transmitted by the transmission unit, The system includes a proposal unit that estimates the cause of the defect and proposes a solution based on the determination result obtained by the determination unit. A system characterized by the following features.

2. The scanning unit is The product's exterior is scanned in detail and obtained as 3D data. The system according to feature 1.

3. The aforementioned modeling unit is Based on the acquired image files, 3D modeling is performed to generate detailed digital twin data. The system according to feature 1.

4. The aforementioned transmitting unit The generated digital twin data is sent to a digital twin platform on a distributed computing infrastructure. The system according to feature 1.

5. The determination unit, The quality of the product is determined by referring to digital twin data. The system according to feature 1.

6. The aforementioned proposal section is, We propose what measures should be taken to address problems that occurred during the product manufacturing process. The system according to feature 1.

7. The scanning unit is The system estimates the sentiment of the product and adjusts the level of detail of the scan based on the estimated sentiment. The system according to feature 1.

8. The scanning unit is During scanning, different scanning algorithms are applied depending on the material and shape of the product. The system according to feature 1.

Images