system

Abstract

We provide the system. [Solution] The present invention relates to a system that, in the development of new products such as communication equipment and services, comprises a design proposal generation unit, a quality inspection unit, and a control unit, and utilizes a generation AI as an essential element to automatically generate a variety of design proposals based on design requirements, automatically performs a multifaceted evaluation of each design proposal including market needs, technical feasibility, cost performance, compliance with laws and regulations, environmental impact, maintainability, and supply chain risk, and further, the quality inspection unit automatically inspects the parameters of each design proposal to detect abnormalities and non-conformities in real time, and the control unit feeds these results back to continuously improve the AI's learning and design proposal generation policy, thereby simultaneously achieving efficiency and quality improvement throughout the entire development process.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method executed by at least one processor, the method comprising the steps of: receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of a chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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] The problem that this invention aims to solve is that, in the development of new products such as communication equipment and services, the consideration of design proposals and quality inspections have traditionally relied heavily on manual processes. As a result, each process, including the generation and evaluation of design proposals, quality inspections, and anomaly detection, requires a great deal of time and effort, and it has been difficult to quickly and efficiently optimize design proposals and maintain quality. In particular, in today's rapidly changing market needs and technological trends, delays in development speed and inadequate quality control can lead to a decline in competitiveness and the loss of market opportunities. Furthermore, because a mechanism for comprehensively evaluating various parameters of design proposals and detecting and correcting anomalies and nonconformities in real time has not been sufficiently established, variations in design quality, inefficiencies in inspection processes, and the occurrence of human errors are unavoidable, resulting in the difficulty of achieving both efficiency and quality in the overall product development process. Therefore, the technical problem that this invention aims to solve is the strong need to simultaneously achieve efficiency and quality improvement in the entire development process by utilizing generative AI to perform automatic generation, optimization, quality inspection, anomaly detection, and feedback of design proposals in parallel and automatically. [Means for solving the problem]

[0005] The means for solving the problems of the present invention is to configure a system comprising a design proposal generation unit, a quality inspection unit, and a control unit. The design proposal generation unit receives multiple design parameters necessary for the development of communication equipment and services as input information, automatically generates various design proposals based on combinations of these design parameters using a generation AI, and further calculates an optimality score for each design proposal, taking into account market needs, technical feasibility, cost performance, and other evaluation indicators. The quality inspection unit determines whether each parameter value of each design proposal generated by the design proposal generation unit is within a preset normal range, identifies the nature of the abnormality if an abnormality is detected, and outputs the abnormality determination result in real time. The control unit comprehensively controls the operation of the design proposal generation unit and the quality inspection unit, and by executing design proposal generation, quality inspection, abnormality detection, and feedback in parallel and automatically, it integrates automatic generation and optimization of design proposals, automation of quality inspection, abnormality detection, and rapid feedback, thereby simultaneously achieving efficiency improvements and quality improvements across the entire product development process. [Brief explanation of the drawing]

[0006] [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]

[0007] 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.

[0008] First, let's explain the terminology used in the following explanation.

[0009] 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), and APU (Accelerated Processing Unit).

[0010] 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.

[0011] In the following embodiments, the storage with a reference sign is one or a plurality of non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include a flash memory (SSD (Solid State Drive)), a magnetic disk (for example, a hard disk), a magnetic tape, and the like.

[0012] In the following embodiments, the communication I / F (Interface) with a reference sign is an interface including a communication processor, an antenna, and the like. The communication I / F governs communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), and the like.

[0013] 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, may be only B, or may be a combination of A and B. Further, in the present specification, even when three or more matters are expressed by being connected with "and / or", the same concept as that for "A and / or B" is applied.

[0014] [First Embodiment]

[0015] FIG. 1 illustrates an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] As shown in FIG. 1, the data processing system 10 includes a data processing apparatus 12 and a smart device 14. An example of the data processing apparatus 12 is a server.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of the "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network), and the like.

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, the camera 42, and the communication I / F 44 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A receives user input via contact of an indicator by detecting the contact of the indicator (for example, a pen, a finger, or the like). The microphone 38B receives voice-based user input by detecting the user's voice. A control unit 46A in the processor 46 transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, a specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] 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.

[0022] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output 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. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0026] 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.

[0027] (Example 1)

[0028] The flow of a specific process in Example 1 will now be described. Each part of the system described below is implemented by a data processing device 12 and a smart device 14. The data processing device 12 will be referred to as a "server," and the smart device 14 will be referred to as a "terminal."

[0029] (Embodiments for carrying out the present invention)

[0030] Embodiments for carrying out the present invention will be described in more specific and detail. The system of the present invention consists of a server and a terminal, and includes a design proposal generation unit, a quality inspection unit, and a control unit. The main processing of the design proposal generation unit, the quality inspection unit, and the control unit is implemented on the server side, while the terminal side is mainly responsible for the user interface and input / output processing. The terminal is a personal computer, tablet terminal, smartphone, wearable device, or dedicated terminal operated by development personnel or quality control personnel, and the server is a cloud server with high-performance computing resources, an on-premise computing system, a distributed server group, etc.

[0031] The design proposal generation unit processes design requirements input from the terminal, such as communication speed (e.g., maximum 1Gbps, 10Gbps, 100Gbps), power consumption (e.g., 5W, 10W, 20W), cost (e.g., 10,000 yen, 50,000 yen, 100,000 yen per unit), chassis size (e.g., 100mm width x 50mm height x 200mm depth), environmental resistance (e.g., operating temperature range -20°C to 60°C, dustproof and waterproof rating IP67), expandability (e.g., module addition possible, interface type), security requirements (e.g., encryption method, authentication method), and communication protocol (e.g., wireless LAN, Bluetooth, The system accepts multiple design parameters, including LPWA, 5G, supported frequency bands (e.g., 2.4GHz, 5GHz, 28GHz), battery life (e.g., 24 hours, 72 hours), usability (e.g., number of operation buttons, presence or absence of display), manufacturing costs (e.g., material costs, assembly labor costs), material selection (e.g., resin, aluminum, stainless steel), mass production capability (e.g., feasibility of producing 10,000 units per month), maintainability (e.g., ease of parts replacement), software compatibility (e.g., compatibility with existing operating systems), compliance with regulations (e.g., Radio Law, RoHS Directive), and environmental impact reduction requirements (e.g., recycling rate, CO2 emissions). These parameters are sent from the terminal to the server and processed by the design proposal generation unit on the server.

[0032] The design proposal generation unit uses generative AI as an essential element. Generative AI consists of an AI engine that combines multiple AI technologies, such as large-scale language models, generative neural networks, evolutionary algorithms, Bayesian optimization, reinforcement learning, GANs, and transformer models. For example, the design proposal generation unit automatically generates multiple design proposals based on input design parameters, while referring to past design databases (e.g., product design information, failure cases, success cases from the past 10 years), market trend data (e.g., market research reports, competitor product specifications, user surveys), technology trend data (e.g., latest papers, patent information, standardization trends), user needs information (e.g., social media reviews, customer support history), legal and regulatory data (e.g., technical standards and environmental regulations in various countries), and supply chain information (e.g., parts procurement lead time, price fluctuations). For example, it is possible to generate a large number of diverse design proposals in a short time, depending on the application and target market, such as a design proposal that maximizes communication speed while minimizing power consumption, a design proposal that maximizes environmental resistance while minimizing costs, a design proposal that prioritizes security requirements, and a design proposal that balances multiple elements.

[0033] The generative AI scores each design proposal using a multifaceted evaluation index, including market needs conformity (e.g., degree of agreement with market research data), technical feasibility (e.g., feasibility with existing technologies), cost performance (e.g., performance-to-cost ratio), manufacturability (e.g., number of parts, number of assembly steps), scalability (e.g., ease of adding future functions), future potential (e.g., alignment with technological trends), differentiation from competing products (e.g., presence or absence of unique functions), regulatory compliance (e.g., conformity to regulations in various countries), environmental impact (e.g., life cycle CO2 emissions), usability (e.g., evaluation of operability), maintainability (e.g., maintenance frequency), safety (e.g., risk assessment in case of failure), reliability (e.g., MTBF value), and supply chain risk (e.g., stability of parts procurement). For example, the generative AI automatically calculates scores for each design proposal, such as "Market needs conformity 80 points, cost performance 70 points, technical feasibility 90 points, environmental impact 60 points, regulatory compliance 100 points," and presents them to the user on the terminal. Furthermore, generative AI learns from past design failures and market defect information, enabling it to automatically eliminate high-risk design proposals and suggest risk reduction measures (e.g., component redundancy, design change proposals).

[0034] The Quality Inspection Department operates on a server and automatically determines whether abnormal or non-compliant values ​​are included by comparing each parameter value of each design proposal generated by the Design Proposal Generation Department with pre-set normal range information and quality standard information. For example, it performs automated inspections based on a wide range of quality standards, such as whether the communication speed is below the specified value (e.g., minimum 500Mbps), whether the power consumption is within the acceptable range (e.g., maximum 15W), whether the cost is within the budget (e.g., within 20,000 yen per unit), whether the enclosure size is within design constraints (e.g., width 120mm or less), whether it violates legal regulations (e.g., compliance with technical standards for specific radio equipment), whether the materials meet environmental standards (e.g., RoHS directive compliance), and whether the battery life meets the minimum requirements (e.g., 48 hours or more). The Quality Inspection Department also utilizes generative AI, and in addition to simple threshold judgments, it uses an AI model that has learned past quality defect patterns and abnormality trends to detect complex abnormalities and potential risks with high accuracy. For example, the AI ​​can automatically detect correlation anomalies resulting from combinations of multiple parameters (e.g., heat generation risk due to combination of power consumption and enclosure size), the risk of recurrence of design patterns that have caused problems in the market in the past (e.g., increased failure rate of specific components), and the risk of supply chain instability (e.g., risk of supply disruption of specific components), and issue real-time warnings to the user on the device.

[0035] The control unit comprehensively controls the operation of the design proposal generation unit and the quality inspection unit on the server, executing a series of processes—design proposal generation, quality inspection, anomaly detection, and feedback—in parallel and automatically. For example, when the design proposal generation unit generates a new design proposal, the quality inspection unit immediately performs an automatic inspection. If an anomaly is detected, the details (e.g., abnormal power consumption, non-compliance with regulations, cost overruns) are fed back to the design proposal generation unit, and the generation system AI learns the anomaly trend and reflects it in subsequent design proposal generation. As a result, the AI ​​learns the quality inspection results each time a design proposal is generated, automatically improving the quality of design proposals and reducing the occurrence of anomalies. For example, if there have been many design proposals in the past that were judged as anomalies due to excessively high power consumption, the AI ​​strengthens its tendency to design in a way that suppresses power consumption and automatically adjusts subsequent design proposals so that power consumption is within the normal range. Furthermore, the control unit optimizes the parallel processing of the design proposal generation unit and the quality inspection unit, dramatically improving development speed by generating and inspecting multiple design proposals simultaneously.

[0036] On the terminal side, users can input design requirements and quality standards, and view and manipulate design proposals, quality inspection results, anomaly warnings, and scoring results sent from the server in real time. For example, users can compare the parameter values ​​and scores of each design proposal on the terminal screen, select the optimal design proposal, and check the details of anomalies and improvement suggestions. Furthermore, when users input modification instructions or additional requirements for a design proposal, that information is sent to the server, and the generative AI immediately reflects it in the generation of new design proposals and quality inspections. For example, if a user inputs requests such as "I want to reduce power consumption by another 5W," "I want the enclosure size to be 90mm or less," or "I want to support a new communication protocol," the generative AI immediately generates a new design proposal that takes those requirements into account, the quality inspection department automatically conducts the inspection, and the results are returned to the terminal.

[0037] Furthermore, the terminal side can also manage version control and history of design proposals. For example, it can display a list of previously generated design proposals and manage the parameter values, scores, quality inspection results, anomaly history, and user comments of each design proposal in chronological order. This contributes to improving the progress management and decision-making transparency of the entire development project.

[0038] Furthermore, the server-side generative AI continuously learns from the large amount of data obtained during the design proposal generation and quality inspection processes, automatically updating the AI ​​model itself. For example, it continuously incorporates the latest market trends, technological trends, changes in laws and regulations, changes in parts supply conditions, and user feedback to continuously improve the accuracy of design proposal generation and quality inspection. As a result, the system can always provide the latest and most optimal design proposals.

[0039] Thus, in this embodiment of the present invention, the main processing of the design proposal generation unit, quality inspection unit, and control unit is implemented on the server side, and by utilizing a generative AI as an essential element, the automatic generation, optimization, quality inspection, anomaly detection, feedback learning, version control, history management, and automatic updates of the AI ​​model are performed in parallel and automatically, and a system is realized on the terminal side in which the user can intuitively and efficiently operate and manage the design process. For example, it is applicable to the development of new products in all fields, such as the development of new models of communication equipment, the design of IoT devices, the launch of new network services, the design of industrial control devices, the development of medical devices, the design of embedded systems, the development of smart home devices, the design of in-vehicle communication equipment, the design of robot control devices, the design of energy management systems, the design of sensor networks, and the development of next-generation infrastructure equipment, and is an extremely practical and advanced embodiment that exhibits great effects such as improved design quality, shortened development period, cost reduction, reduction of human error, strengthened competitiveness, improved transparency of the development process, and accumulation and reuse of design knowledge.

[0040] (System Configuration)

[0041] The system according to this embodiment comprises a design proposal generation unit, a quality inspection unit, a control unit, a user interface unit, a database unit, a learning data collection unit, and a feedback unit. The design proposal generation unit receives design requirements and design parameters input from a terminal, such as communication speed, power consumption, cost, enclosure size, environmental resistance, expandability, security requirements, communication protocol, supported frequency band, battery life, usability, manufacturing cost, material selection, mass production feasibility, maintainability, software compatibility, compliance with legal regulations, and environmental load reduction requirements, and automatically generates a variety of design proposals using a generative AI. The design proposal generation unit provides the generation AI with specific prompts such as, "Generate 10 design proposals that maximize communication speed while keeping power consumption below 10W," "Present a design proposal that keeps costs under 20,000 yen and has a chassis size of 100mm or less in width," "Output multiple design proposals that prioritize environmental resistance and have an operating temperature range of -20°C to 60°C," and "Generate a design proposal that implements the latest encryption method as a security requirement." The AI ​​then creates design proposals by combining optimization algorithms, evolutionary algorithms, reinforcement learning, etc., while referring to past design data, market trend data, technology trend data, legal and regulatory data, user needs data, etc. Furthermore, the design proposal generation unit scores each generated design proposal using a multifaceted evaluation index including market needs suitability, technical feasibility, cost performance, manufacturability, scalability, future potential, differentiation from competing products, compliance with laws and regulations, environmental impact, usability, maintainability, safety, reliability, and supply chain risk. It automatically calculates scores such as "Market needs suitability 80 points, cost performance 70 points, technical feasibility 90 points, environmental impact 60 points, compliance with laws and regulations 100 points" and presents them to the user on the terminal via the user interface unit.

[0042] The Quality Inspection Department automatically determines whether any abnormal or non-conforming values ​​are included by comparing each parameter value of each design proposal generated by the Design Proposal Generation Department with pre-set normal range information and quality standard information. The Quality Inspection Department performs automated inspections based on a wide range of quality standards, such as "Is the communication speed below a minimum of 500Mbps?", "Is the power consumption below a maximum of 15W?", "Is the cost within 20,000 yen per unit?", "Is the enclosure size 120mm or less in width?", "Does it violate any legal regulations?", "Do the materials meet environmental standards?", and "Is the battery life 48 hours or more?". Furthermore, the Quality Inspection Department utilizes generative AI to detect complex anomalies and potential risks with high accuracy, not just simple threshold judgments, but also through AI models that have learned past quality defect patterns and anomaly trends. For example, the AI ​​automatically detects "heat generation risk due to combinations of power consumption and enclosure size", "increased failure rate of specific components", "supply chain disruption risk", and "recurrence risk of design patterns that have caused problems in the market in the past", and issues real-time warnings to users on the terminal side via the User Interface Department.

[0043] The control unit comprehensively controls the operation of the design proposal generation unit and the quality inspection unit, executing a series of processes—design proposal generation, quality inspection, anomaly detection, and feedback—in parallel and automatically. For example, when the design proposal generation unit generates a new design proposal, the control unit immediately has the quality inspection unit perform an automatic inspection. If an anomaly is detected, the control unit feeds the details back to the design proposal generation unit, and the generation system AI learns the anomaly trend and reflects it in subsequent design proposal generation. Furthermore, the control unit optimizes the parallel processing of the design proposal generation unit and the quality inspection unit, dramatically improving development speed by generating and inspecting multiple design proposals simultaneously. For example, it performs controls such as "simultaneously generating 10 different design proposals and performing quality inspections in parallel for each," "automatically adjusting the parameter search range of the design proposal generation unit if anomaly detection occurs frequently," and "re-executing design proposal generation and inspection in response to new design requirement input from the user."

[0044] The user interface unit allows users on the terminal to input design requirements and quality standards, and to view and manipulate design proposals, quality inspection results, anomaly warnings, and scoring results sent from the server in real time. The user interface unit has functions such as "comparing and displaying each parameter value and score of the design proposal in graphs and tables," "notifying of anomaly details and improvement suggestions via pop-ups," "managing version control and history of design proposals," and "providing a form for users to input modification instructions and additional requirements for design proposals." Furthermore, if a user inputs requests such as "I want to reduce power consumption by another 5W," "I want to reduce the chassis size to 90mm or less," or "I want to support a new communication protocol," the user interface unit sends that information to the server, and the generative AI immediately reflects it in the generation of new design proposals and quality inspections.

[0045] The Database Department stores and manages various data referenced by the Design Proposal Generation Department and the Quality Inspection Department. The Database Department has databases such as "Past Design Proposal Database," "Market Trend Database," "Technology Trend Database," "Legal Regulation Database," "User Needs Database," "Quality Defect Case Database," and "Supply Chain Information Database," and provides the information necessary for design proposal generation and quality inspection quickly and efficiently. For example, it enables processes such as "extracting similar design proposals by referring to product design information from the past 10 years," "evaluating the degree of suitability to market needs based on the latest market research reports," and "automatically matching technical standards and environmental regulations in each country."

[0046] The learning data collection unit collects large amounts of data obtained during the design proposal generation and quality inspection processes and stores it as training data for the generative AI. The learning data collection unit has functions such as "recording quality inspection results and anomaly detection history for each design proposal," "collecting user feedback and correction instructions," "collecting product defect information after market launch," and "recording supply chain fluctuation information." As a result, the generative AI continuously learns the latest design trends, quality risks, user needs, and market trends, automatically improving the accuracy of design proposal generation and quality inspection.

[0047] The feedback unit feeds back anomalies detected by the quality inspection unit, correction instructions from users, and defect information after the product is launched to the design proposal generation unit and the generation AI, enabling automatic updates of the AI ​​model and optimization of the design proposal generation policy. For example, the feedback unit performs processes such as "strengthening the power consumption emphasis of the design proposal generation unit if power consumption anomalies occur frequently," "automatically generating a design proposal generation prompt that prioritizes the relevant regulations if non-compliance with legal regulations is detected," and "immediately reflecting new defect information that occurs in the market into the AI ​​model."

[0048] Specific examples of prompts to be fed into the AI ​​when implementing the present invention include: "Generate 10 design proposals for communication equipment that meets the following criteria: communication speed of 1Gbps or more, power consumption of 10W or less, cost of 20,000 yen or less, housing size of 100mm or less, environmental resistance IP67, implementation of the latest encryption method, compliance with legal regulations, and reduction of environmental impact"; "For IoT device design, present multiple design proposals that have a battery life of 48 hours or more, mass production capability of 10,000 units per month, material cost of 5,000 yen or less per unit, Bluetooth communication support, and a focus on usability"; "For medical devices, generate a design proposal that is disinfection resistant, has 3 or fewer operation buttons, maintains software compatibility, and prioritizes compliance with legal regulations"; and "For automotive communication equipment design, output a design proposal that considers vibration resistance, operating temperature range of -40°C to 85°C, CAN communication support, cost performance, and reduction of supply chain risk."

[0049] Thus, the system according to this embodiment includes a design proposal generation unit, a quality inspection unit, a control unit, a user interface unit, a database unit, a learning data collection unit, and a feedback unit. Each unit works in cooperation to perform automatic generation, optimization, quality inspection, anomaly detection, feedback learning, version control, history management, and automatic updates of the AI ​​model in parallel and automatically, resulting in an extremely practical and advanced system configuration that allows users to intuitively and efficiently operate and manage the design process.

[0050] (Implementation Steps)

[0051] Step 1: Design Requirements Input Step Users input design requirements for the communication equipment or service to be developed through the terminal's user interface. For example, they can specify a wide range of specific parameters in detail, such as communication speed, power consumption, cost, enclosure size, environmental resistance, scalability, security requirements, communication protocol, supported frequency bands, battery life, usability, manufacturing cost, material selection, mass production feasibility, maintainability, software compatibility, regulatory compliance, and environmental impact reduction requirements. For instance, it is possible to input multiple conditions simultaneously, such as "communication speed of 1Gbps or more, power consumption of 10W or less, cost under 20,000 yen, enclosure size of 100mm or less, environmental resistance of IP67, implementation of the latest encryption method, compliance with regulations, and emphasis on reducing environmental impact."

[0052] Step 2: Automatic design proposal generation step The design proposal generation unit automatically generates a variety of design proposals using a generation AI on the server based on the design requirements received from the terminal. The generation AI is given specific prompts such as: "Generate 10 design proposals for communication equipment that meets the following criteria: communication speed of 1Gbps or more, power consumption of 10W or less, cost of 20,000 yen or less, enclosure size of 100mm or less, environmental resistance IP67, implementation of the latest encryption method, compliance with legal regulations, and reduction of environmental impact"; "For IoT device design, present multiple design proposals that have a battery life of 48 hours or more, mass production capability of 10,000 units per month, material cost of 5,000 yen or less per unit, Bluetooth communication support, and a focus on usability"; "For medical devices, generate a design proposal that is disinfection resistant, has 3 or fewer operation buttons, maintains software compatibility, and prioritizes compliance with legal regulations"; and "For automotive communication equipment design, output a design proposal that considers vibration resistance, operating temperature range of -40°C to 85°C, CAN communication support, cost performance, and reduction of supply chain risk." Generative AI references diverse databases, including past design data, market trends, technological trends, legal regulations, user needs, and supply chain information, and generates design proposals by combining optimization algorithms, evolutionary algorithms, and reinforcement learning.

[0053] Step 3: Design Proposal Scoring and Evaluation Step The design proposal generation unit scores multiple design proposals output by the generation AI using a multifaceted evaluation index that includes market needs suitability, technical feasibility, cost performance, manufacturability, scalability, future potential, differentiation from competing products, compliance with regulations, environmental impact, usability, maintainability, safety, reliability, and supply chain risk. For example, it automatically calculates scores such as "Market needs suitability 80 points, cost performance 70 points, technical feasibility 90 points, environmental impact 60 points, compliance with regulations 100 points" and presents them to the user on the terminal via the user interface unit. The user can compare these scores and select the optimal design proposal.

[0054] Step 4: Automated Quality Inspection and Anomaly Detection Step The Quality Inspection Department automatically determines whether any abnormal or non-conforming values ​​are included by comparing each parameter value of each design proposal generated by the Design Proposal Generation Department with pre-set normal range information and quality standard information. The Quality Inspection Department utilizes generation AI to detect complex anomalies and potential risks with high accuracy, not just simple threshold judgments, but also through an AI model that has learned past quality defect patterns and anomaly trends. For example, the AI ​​automatically detects "heat generation risk due to combination of power consumption and enclosure size," "increased failure rate of specific components," "supply chain disruption risk," and "recurrence risk of design patterns that have caused problems in the market in the past," and issues real-time warnings to the user on the terminal via the User Interface Department.

[0055] Step 5: Feedback and Learning Steps The feedback unit feeds back anomalies detected by the quality inspection unit, correction instructions from users, and defect information after product launch to the design proposal generation unit and the generation AI, enabling automatic updates of the AI ​​model and optimization of the design proposal generation policy. For example, it performs processes such as "strengthening the power consumption emphasis of the design proposal generation unit if power consumption anomalies occur frequently," "automatically generating a design proposal generation prompt that prioritizes the relevant regulations if non-compliance with legal regulations is detected," and "immediately reflecting new defect information that occurs in the market into the AI ​​model," thereby continuously improving the accuracy and optimization of the entire system.

[0056] Step 6: User Interaction and Decision-Making Steps Through the user interface of the terminal, users can compare and display the parameter values ​​and scores of each design proposal in graphs and tables, and select the optimal design proposal while checking for anomalies and improvement suggestions. Furthermore, version control and history management of design proposals are performed, allowing for chronological management of parameter values, scores, quality inspection results, anomaly history, and user comments of past design proposals. When a user inputs modification instructions or additional requirements for a design proposal, that information is sent to the server, and the generation AI immediately reflects it in the generation of new design proposals and quality inspections.

[0057] (Specific use cases)

[0058] For example, when using the system of the present invention in a new product development project for communication equipment, the development team members first input detailed design requirements for the product via the user interface of the terminal. The input design requirements include a wide range of parameters, such as a communication speed of 1 Gbps or more, power consumption of 10 W or less, manufacturing cost of 20,000 yen or less, enclosure size width of 100 mm or less, environmental resistance IP67, battery life of 48 hours or more, implementation of the latest encryption method, compliance with laws and regulations, reduction of environmental impact, ensuring mass production, ensuring expandability, emphasis on usability, improvement of maintainability, support for specific communication protocols, and reduction of supply chain risk. These design requirements are sent from the terminal to the server and processed by the design proposal generation unit.

[0059] The design proposal generation unit provides the generating AI with a prompt message such as, "Generate 10 design proposals for communication equipment that simultaneously meet the following criteria: communication speed of 1Gbps or more, power consumption of 10W or less, manufacturing cost of 20,000 yen or less, enclosure width of 100mm or less, environmental resistance of IP67, battery life of 48 hours or more, implementation of the latest encryption method, compliance with legal regulations, reduction of environmental impact, assurance of mass production, assurance of expandability, emphasis on usability, improvement of maintainability, support for a specific communication protocol, and reduction of supply chain risk." The generating AI then automatically generates multiple design proposals by referencing past design databases, market trend data, technology trend data, legal and regulatory data, user needs data, supply chain information, etc., and by combining optimization algorithms, evolutionary algorithms, reinforcement learning, and other methods. The generated design proposal includes specific parameters that meet each requirement, such as a communication speed of 1.2Gbps, power consumption of 8.5W, manufacturing cost of 18,000 yen, chassis size of 95mm width, IP67 environmental resistance, battery life of 52 hours, implementation of AES256 encryption method, compliance with major domestic and international laws and regulations, 30 percent recycled material usage, monthly production capacity of 20,000 units, module expansion capability, touch panel, easily replaceable maintenance parts, support for LPWA communication protocols, and securing multiple suppliers for key components.

[0060] The design proposal generation unit scores each design proposal output by the generating AI using a multifaceted evaluation index, including market needs suitability, technical feasibility, cost performance, manufacturability, scalability, future potential, differentiation from competing products, legal and regulatory compliance, environmental impact, usability, maintainability, safety, reliability, and supply chain risk. For example, a certain design proposal may be automatically scored as follows: market needs suitability 85 points, cost performance 75 points, technical feasibility 92 points, environmental impact 65 points, legal and regulatory compliance 100 points, maintainability 80 points, and supply chain risk reduction 90 points. These scores are presented to the user on the terminal via the user interface unit, allowing the user to compare and consider multiple design proposals.

[0061] The Quality Inspection Department automatically determines whether any abnormal or non-conforming values ​​are included by comparing each parameter value of each design proposal generated by the Design Proposal Generation Department with pre-set normal range information and quality standard information. Utilizing the generation AI, the Quality Inspection Department not only performs simple threshold checks but also accurately detects complex anomalies and potential risks using an AI model that has learned from past quality defect patterns and anomaly trends. For example, the AI ​​automatically detects heat generation risks due to power consumption and enclosure size combinations, increased failure rates of specific components, supply chain disruption risks, and the risk of recurrence of design patterns that have caused problems in the market in the past, and issues real-time warnings to the user on the terminal via the User Interface Department.

[0062] Furthermore, the feedback unit feeds back anomalies detected by the quality inspection unit, correction instructions from users, and defect information after the product is launched to the design proposal generation unit and the generation AI, enabling automatic updates of the AI ​​model and optimization of the design proposal generation policy. For example, if power consumption anomalies occur frequently, the design proposal generation unit strengthens its emphasis on power consumption; if non-compliance with legal regulations is detected, it automatically generates a design proposal generation prompt that prioritizes the relevant regulations; and it immediately reflects new defect information that occurs in the market into the AI ​​model.

[0063] In such use cases, the system of the present invention performs automatic generation, optimization, quality inspection, anomaly detection, feedback learning, version control, history management, and automatic updates of the AI ​​model in parallel and automatically, allowing users to intuitively and efficiently operate and manage the design process. Specific examples of prompt statements to be fed into the generating AI include: "Generate 10 design proposals for communication equipment that simultaneously meet the following criteria: communication speed of 1Gbps or more, power consumption of 10W or less, manufacturing cost of 20,000 yen or less, enclosure width of 100mm or less, environmental resistance of IP67, battery life of 48 hours or more, implementation of the latest encryption method, compliance with legal regulations, reduction of environmental impact, assurance of mass production, assurance of scalability, emphasis on usability, improvement of maintainability, support for a specific communication protocol, and reduction of supply chain risk."

[0064] (Application Example 1) The flow of a specific process in Application Example 1 will be explained below. Each part of the system described below is implemented by a data processing device 12 and a smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0065] (Embodiments for carrying out the present invention)

[0066] Embodiments for carrying out the present invention will be described in more detail. The system of the present invention aims to optimize the operation and stabilize the quality of factory robots and comprises an operation plan generation unit, a quality inspection unit, a control unit, a user interface unit, a database unit, a learning data collection unit, and a feedback unit. Each unit is mainly implemented on a server, and the user interface unit is implemented on a terminal at the site, a terminal for administrators, a tablet, a smartphone, etc.

[0067] The motion plan generation unit accepts as input information multiple parameters related to the operation of the factory robot, such as speed, acceleration, gripping force, work sequence, power consumption, coordinated operation timing, safety distance, path, maintenance interval, stopping position accuracy, work cycle time, transport weight, material of the object to be gripped, size of the work area, timing of coordination with peripheral equipment, working environment temperature, humidity, vibration resistance, electrostatic discharge resistance, and conditions for coordinated operation with the operator. These parameters are specified in detail from a terminal according to the on-site production plan, product specifications, work content, equipment constraints, operator safety requirements, maintenance plan, energy costs, and supply chain status. For example, the speed can be set in four stages: 0.5 m / s, 0.7 m / s, 1.0 m / s, and 1.2 m / s; the acceleration in four stages: 0.2 m / s², 0.5 m / s², 0.8 m / s², and 1.0 m / s²; the gripping force in four stages: 10 N, 20 N, 30 N, and 40 N; the work sequence can be set as an integer from 1 to 4; and the power consumption can be set as 100 W, 120 W, 140 W, or 160 W, etc., values ​​that are appropriate to the actual conditions on site.

[0068] The motion plan generation unit uses generative AI as an essential element. The generative AI consists of an AI engine that combines large-scale language models, generative neural networks, evolutionary algorithms, reinforcement learning, Bayesian optimization, GANs, transformer models, etc. For example, based on the input motion parameters, it automatically generates multiple motion plans by combining optimization algorithms, evolutionary algorithms, and reinforcement learning, while referring to past operational databases (robot operation logs for the past several years, anomaly occurrence history, maintenance history), on-site requirements data (production plan, work content, worker schedule), equipment specification data (robot model, payload capacity, range of motion, control method), quality standard data (tolerance for each product, visual inspection standards), maintenance history data (parts replacement history, failure history), sensor data (motor current, temperature, vibration, torque, position accuracy, abnormal noise, current consumption, external shock), work environment information (temperature, humidity, dust, illuminance), and supply chain information (parts procurement lead time, price fluctuations, supply stability). For example, it can quickly generate a large number of diverse operation plans to meet the diverse requirements of the site, such as operation plans that maximize transport speed while minimizing power consumption, operation plans that optimize gripping force while shortening work cycle time, operation plans that optimize coordinated operation timing to avoid interference between multiple robots, operation plans that prioritize maintainability and extend maintenance intervals, and operation plans that are robust against fluctuations in the working environment temperature.

[0069] Furthermore, the motion plan generation unit scores each generated motion plan using a multifaceted evaluation index, including productivity (throughput, operating rate), safety (distance from the worker, safety stop responsiveness), efficiency (energy consumption, working time), energy consumption (power consumption, peak power), maintainability (parts lifespan, ease of maintenance), cooperation (coordination efficiency of multiple robots), downtime reduction (frequency of abnormal occurrences, recovery time), and quality stability (product variability, work accuracy). For example, it automatically calculates scores such as "productivity 85 points, safety 90 points, efficiency 80 points, energy consumption 75 points, maintainability 88 points, cooperation 92 points, downtime reduction 95 points, quality stability 93 points" and presents them to on-site personnel and managers via the user interface unit.

[0070] The Quality Inspection Department automatically determines whether there are any abnormal or non-conforming values ​​by comparing the parameter values ​​of each motion plan generated by the Motion Plan Generation Department and the real-time sensor data acquired from the robot with pre-set normal ranges and quality standards. For example, thresholds are set based on on-site safety and quality standards, such as speed being in the range of 0.6 m / s to 1.1 m / s, acceleration being in the range of 0.3 m / s² to 0.9 m / s², gripping force being in the range of 15 N to 35 N, power consumption being in the range of 110 W to 150 W, motor current being in the range of 0.8 A to 1.2 A, temperature being a normalized value of 0.8 to 1.2, vibration being a normalized value of 0.8 to 1.2, torque being within the specified range, positional accuracy being within ±0.1 mm, no abnormal noise being detected, and external impact being below the specified value. The Quality Inspection Department utilizes generative AI to not only make simple threshold judgments, but also to detect complex abnormalities and potential risks with high accuracy using an AI model that has learned past quality defect patterns and abnormal trends. For example, the AI ​​automatically detects complex on-site risks such as the risk of overheating due to the combination of power consumption and gripping force, the risk of parts wear due to the combination of acceleration and work sequence, the possibility of failure due to simultaneous abnormalities in motor current and vibration, the correlation between fluctuations in working environment temperature and a decrease in operational accuracy, and the risk of interference during the coordinated operation of multiple robots, and issues real-time warnings to on-site personnel via the user interface.

[0071] The control unit comprehensively controls the operation of the motion plan generation unit and the quality inspection unit, and performs motion plan generation, quality inspection, anomaly detection, feedback learning, parameter optimization, and automatic AI model updates in parallel and automatically. For example, as soon as the motion plan generation unit generates a new motion plan, the quality inspection unit immediately performs an automatic inspection, and if an anomaly is detected, it feeds back the details (e.g., power consumption anomaly, acceleration anomaly, gripping force anomaly, sensor anomaly, coordinated motion anomaly, etc.) to the motion plan generation unit, and the generation system AI learns the anomaly trend and reflects it in subsequent motion plan generation. In this way, the AI ​​learns the quality inspection results each time a motion plan is generated, automatically improving the quality of motion plans and reducing the occurrence of anomalies. Furthermore, the control unit optimizes the parallel processing of the motion plan generation unit and the quality inspection unit, and dramatically improves on-site productivity by generating and inspecting multiple motion plans simultaneously.

[0072] The user interface allows field personnel and managers to view and operate operation plans, quality inspection results, anomaly warnings, and scoring results in real time. For example, it has functions such as displaying the parameter values ​​and scores of operation plans in graphs and tables for comparison, notifying users of anomalies and improvement suggestions via pop-ups, managing version and history of operation plans, and providing forms for users to input modification instructions and additional requirements for operation plans. When a user inputs requests such as "I want to reduce power consumption by another 10W," "I want to change the gripping force from 20N to 25N," "I want to optimize the coordinated operation timing," or "I want to change the work order," that information is sent to the server, and the generation AI immediately reflects it in the generation of new operation plans and quality inspections.

[0073] The database unit stores and manages various data referenced by the operation plan generation unit and the quality inspection unit. For example, it has databases for past operation plans, operation logs, quality defect cases, maintenance history, sensors, work environment, and supply chain information, providing the information necessary for operation plan generation and quality inspection quickly and efficiently.

[0074] The learning data collection unit collects large amounts of data obtained during the process of generating action plans and quality inspections, and stores it as training data for generative AI. For example, it records quality inspection results and anomaly detection history for each action plan, user feedback and correction instructions, product defect information after market launch, and supply chain fluctuation information, contributing to the continuous improvement of the accuracy of the AI ​​model.

[0075] The feedback unit feeds back anomalies detected by the quality inspection unit, correction instructions from users, and defect information that occurs on-site to the operation plan generation unit and the generation AI, enabling automatic updates of the AI ​​model and optimization of the operation plan generation policy. For example, if power consumption anomalies occur frequently, the operation plan generation unit strengthens its emphasis on power consumption; if a cooperative operation anomaly is detected, it automatically generates a prompt to prioritize cooperative timing optimization; and it immediately reflects new defect information that occurs on-site into the AI ​​model.

[0076] Thus, the embodiments of the present invention integrate and automatically realize factory robot motion plan generation, quality inspection, anomaly detection, feedback learning, parameter optimization, automatic AI model updates, operation and management via a user interface, information storage and utilization via a database, AI accuracy improvement through learning data collection, and enhanced on-site adaptability through feedback. These embodiments are extremely practical and advanced, resulting in significant benefits such as improved on-site productivity, quality stabilization, reduced downtime, reduced maintenance costs, improved on-site safety, optimized operations, and knowledge accumulation and reuse.

[0077] For example, optimizing the operation of a transport robot involves simultaneously optimizing transport speed, acceleration, stopping position accuracy, path selection, gripping force, power consumption, coordinated operation timing, work area size, and timing of coordination with peripheral equipment to optimize line balance and improve safety in cooperation with operators. For example, optimizing the operation of an assembly robot involves considering parts supply timing, fastening torque, assembly sequence, work cycle time, vibration resistance, electrostatic discharge resistance, working environment temperature, and humidity to achieve both quality stability and productivity. For example, optimizing the operation of an inspection robot involves optimizing camera imaging timing, lighting control, inspection path, inspection speed, anomaly detection algorithm, and data transfer timing to maximize inspection accuracy and throughput. For example, optimizing the operation of a palletizing robot involves optimizing loading sequence, gripping force, loading height, transport path, coordinated operation timing, work area size, power consumption, and maintenance intervals to achieve both work efficiency and safety.

[0078] Furthermore, AI-based anomaly detection can, for example, detect signs of bearing wear from simultaneous abnormalities in motor current and vibration, enabling preventative maintenance. For example, it can estimate grease depletion or component wear from abnormal increases in power consumption and work cycle time, and automatically adjust maintenance plans. For example, it can provide early warnings of robot interference and safety risks by detecting disruptions in coordinated operation timing or external impacts. For example, the AI ​​can learn the correlation between sudden changes in working environment temperature and humidity and a decrease in operation accuracy, and automatically generate operation plans that are resilient to environmental changes.

[0079] In this manner, this embodiment integrates and automatically implements AI-powered operation plan generation, quality inspection, anomaly detection, and feedback learning to address diverse on-site challenges and operational requirements, resulting in extremely broad and practical effects such as optimization of factory robot operations, quality stabilization, improved on-site safety, reduced maintenance costs, knowledge accumulation and reuse, and company-wide deployment of on-site knowledge.

[0080] (System Configuration)

[0081] The system according to this embodiment includes an action plan generation unit, a quality inspection unit, a control unit, a user interface unit, a database unit, a learning data collection unit, and a feedback unit. The motion plan generation unit accepts various parameters related to the operation of factory robots as input information, such as speed, acceleration, gripping force, work sequence, power consumption, coordinated operation timing, safety distance, path, maintenance interval, stopping position accuracy, work cycle time, transport weight, material of the object to be gripped, size of the work area, timing of coordination with peripheral equipment, working environment temperature, humidity, vibration resistance, electrostatic discharge resistance, and cooperative operation conditions with the operator. Using a generation AI, it provides prompt statements to the generation AI, such as "Generate 10 motion plans that maximize transport speed while minimizing power consumption," "Generate multiple motion plans that optimize gripping force while shortening the work cycle time," "Output a motion plan that optimizes coordinated operation timing to avoid interference between multiple robots," "Present a motion plan that prioritizes maintainability and extends the maintenance interval," and "Generate a motion plan that is robust against fluctuations in the working environment temperature." The AI ​​then automatically generates multiple motion plans by combining optimization algorithms, evolutionary algorithms, and reinforcement learning, while referring to past operation databases, on-site requirements data, equipment specifications data, quality standards data, maintenance history data, sensor data, working environment information, and supply chain information. The operation plan generation unit scores each generated operation plan using a multifaceted evaluation index, including productivity, operating rate, safety, distance from the worker, safety stop responsiveness, efficiency, energy consumption, working time, peak power, maintainability, parts lifespan, ease of maintenance, cooperativeness, efficiency of coordination between multiple robots, downtime reduction, frequency of abnormal occurrences, recovery time, quality stability, product variability, and work accuracy. It automatically calculates scores such as "productivity 85 points, safety 90 points, efficiency 80 points, energy consumption 75 points, maintainability 88 points, cooperativeness 92 points, downtime reduction 95 points, quality stability 93 points" and presents them to on-site personnel and managers via the user interface unit.

[0082] The Quality Inspection Department automatically determines whether there are any abnormal or non-conforming values ​​by comparing the parameter values ​​of each motion plan generated by the Motion Plan Generation Department and the real-time sensor data acquired from the robot with pre-set normal ranges and quality standards. For example, the Quality Inspection Department sets thresholds based on on-site safety and quality standards, such as speed being in the range of 0.6 m / s to 1.1 m / s, acceleration being in the range of 0.3 m / s² to 0.9 m / s², gripping force being in the range of 15 N to 35 N, power consumption being in the range of 110 W to 150 W, motor current being in the range of 0.8 A to 1.2 A, temperature being a normalized value of 0.8 to 1.2, vibration being a normalized value of 0.8 to 1.2, torque being within the specified range, positional accuracy being within ±0.1 mm, no abnormal noise being detected, and external impact being below the specified value, and makes automatic judgments based on these. Furthermore, the Quality Inspection Department utilizes generative AI to not only perform simple threshold judgments, but also uses AI models that have learned past quality defect patterns and abnormal trends to automatically detect complex on-site risks, such as the risk of overheating due to the combination of power consumption and gripping force, the risk of parts wear due to the combination of acceleration and work sequence, the signs of failure due to simultaneous abnormalities in motor current and vibration, the correlation between fluctuations in working environment temperature and a decrease in operational accuracy, and the risk of interference during the coordinated operation of multiple robots. The AI ​​then issues real-time warnings to on-site personnel via the user interface.

[0083] The control unit comprehensively controls the operation of the motion plan generation unit and the quality inspection unit, and performs motion plan generation, quality inspection, anomaly detection, feedback learning, parameter optimization, and automatic AI model updates in parallel and automatically. For example, as soon as the motion plan generation unit generates a new motion plan, the quality inspection unit immediately performs an automatic inspection, and if an anomaly is detected, it feeds back the details (e.g., power consumption anomaly, acceleration anomaly, gripping force anomaly, sensor anomaly, coordinated operation anomaly, etc.) to the motion plan generation unit, and the generation system AI learns the anomaly trend and reflects it in subsequent motion plan generation. The control unit optimizes the parallel processing of the motion plan generation unit and the quality inspection unit, and dramatically improves on-site productivity by generating and inspecting multiple motion plans simultaneously. Furthermore, the control unit responds immediately to new design requirements from the user and changes in on-site conditions, and automatically updates the operation parameters and AI model of the entire system.

[0084] The user interface unit allows field personnel and managers to view and operate operation plans, quality inspection results, anomaly warnings, and scoring results in real time. The user interface unit has functions such as comparing and displaying each parameter value and score of operation plans in graphs and tables, notifying of anomalies and improvement suggestions via pop-ups, version control and history management of operation plans, providing forms for users to input modification instructions and additional requirements for operation plans, allowing field workers to directly select and modify operation plans from tablet devices, enabling managers to make decisions by referring to past anomaly and improvement history, and instantly regenerating operation plans in response to changes in field work status and production plans. When a user inputs requests such as "I want to reduce power consumption by another 10W," "I want to change the gripping force from 20N to 25N," "I want to optimize the coordinated operation timing," or "I want to change the work order," that information is sent to the server, and the generation AI immediately reflects it in the generation of new operation plans and quality inspections.

[0085] The database unit stores and manages various data referenced by the operation plan generation unit and the quality inspection unit. The database unit has databases such as a past operation plan database, an operation log database, a quality defect case database, a maintenance history database, a sensor database, a work environment database, and a supply chain information database, providing the information necessary for operation plan generation and quality inspection quickly and efficiently. For example, it can be used in a variety of ways, such as AI learning failure predictions based on past anomaly occurrence patterns and maintenance history, optimizing component selection for operation plans based on supply chain component supply information, generating operation plans that are robust against temperature and humidity fluctuations based on work environment data, and optimizing the site based on past production plans and work history.

[0086] The learning data collection unit collects large amounts of data obtained during the process of generating action plans and quality inspections, and stores it as learning data for the generative AI. The learning data collection unit records, for example, quality inspection results and anomaly judgment history for each action plan, user feedback and correction instructions, product defect information after market launch, supply chain fluctuation information, field worker operation history, maintenance work execution history, and response history when anomalies occur, contributing to the continuous improvement of the accuracy of the AI ​​model. For example, the AI ​​can learn the characteristics of action plans with a high frequency of anomalies and strengthen risk avoidance when generating subsequent action plans, learn the trends of action plans that are frequently used in the field to improve field adaptability, and learn the correlation between maintenance history and anomaly occurrences to strengthen preventive maintenance.

[0087] The feedback unit feeds back anomalies detected by the quality inspection unit, correction instructions from users, and defect information that occurs on-site to the operation plan generation unit and the generation AI, enabling automatic updates of the AI ​​model and optimization of the operation plan generation policy. The feedback unit has functions such as strengthening the operation plan generation unit's emphasis on power consumption if power consumption anomalies occur frequently, automatically generating a prompt to prioritize coordinated timing optimization if coordinated operation anomalies are detected, immediately reflecting new defect information that occurs on-site in the AI ​​model, incorporating improvement suggestions from on-site workers into the AI ​​learning data, and strengthening maintenance interval optimization based on actual maintenance work performance.

[0088] Specific examples of prompt statements to be input to the generating AI when implementing the present invention include: "Generate 10 operation plans that simultaneously satisfy the following conditions: transport speed of 1.0 m / s or more, power consumption of 120 W or less, gripping force of 20 N to 30 N, work cycle time of 15 seconds or less, optimized cooperative operation timing, work area width of 2 m, enhanced temperature fluctuation resistance, and minimized frequency of abnormal occurrences"; "Present multiple operation plans for an assembly robot that optimize parts supply timing, fastening torque of 2 Nm to 3 Nm, automatic optimization of work sequence, enhanced vibration resistance, and emphasis on maintainability"; and "Generate operation plans for an inspection robot that simultaneously consider camera imaging timing optimization, inspection path shortening, inspection speed maximization, improved abnormality detection accuracy, and optimized data transfer timing."

[0089] As described above, the system according to this embodiment comprises a motion plan generation unit, a quality inspection unit, a control unit, a user interface unit, a database unit, a learning data collection unit, and a feedback unit. Each unit works in cooperation to perform automatic generation, optimization, quality inspection, anomaly detection, feedback learning, version control, history management, and automatic updates of AI models for factory robots in parallel and automatically. This results in an extremely practical and advanced system configuration that delivers significant benefits such as improved productivity on site, stable quality, reduced downtime, reduced maintenance costs, improved on-site safety, and knowledge accumulation and reuse.

[0090] (Implementation Steps)

[0091] Step 1: Inputting Operating Requirements Step On-site personnel or managers input detailed requirements for the operation of factory robots through the user interface. These requirements cover a wide range of aspects, such as transport speed, acceleration, gripping force, work sequence, power consumption, coordinated operation timing, safety distance, path, maintenance interval, stopping position accuracy, work cycle time, transport weight, material of the object being gripped, size of the work area, timing of coordination with peripheral equipment, working environment temperature, humidity, vibration resistance, electrostatic discharge resistance, and conditions for coordinated operation with operators. These requirements are specified in detail, reflecting on-site production plans, product specifications, work content, equipment constraints, operator safety requirements, maintenance plans, energy costs, and supply chain conditions.

[0092] Step 2: Automatic generation of action plan step The motion plan generation unit automatically generates a variety of motion plans using a generation AI based on the input requirements. The generation AI is given prompts such as, "Generate 10 motion plans that simultaneously satisfy the following: transport speed of 1.0 m / s or more, power consumption of 120 W or less, gripping force of 20 N to 30 N, work cycle time of 15 seconds or less, optimized cooperative operation timing, work area width of 2 m, enhanced temperature fluctuation resistance, and minimized frequency of abnormal occurrences," "Present multiple motion plans for an assembly robot that optimize parts supply timing, fastening torque of 2 Nm to 3 Nm, automatic optimization of work sequence, enhanced vibration resistance, and emphasis on maintainability," and "Generate motion plans for an inspection robot that simultaneously consider optimized camera imaging timing, shortened inspection path, maximized inspection speed, improved abnormality detection accuracy, and optimized data transfer timing." The generation AI refers to past operational data, site requirements, equipment specifications, quality standards, maintenance history, sensor data, work environment information, supply chain information, etc., and creates motion plans by combining optimization algorithms, evolutionary algorithms, and reinforcement learning.

[0093] Step 3: Action Plan Scoring and Evaluation Step The motion plan generation unit scores each motion plan output by the generating AI using a multifaceted evaluation index such as productivity, operating rate, safety, distance from the worker, safety stop responsiveness, efficiency, energy consumption, working time, peak power, maintainability, parts lifespan, ease of maintenance, cooperativeness, efficiency of coordination between multiple robots, downtime reduction, frequency of abnormal occurrences, recovery time, quality stability, product variability, and work accuracy. It automatically calculates scores such as "productivity 85 points, safety 90 points, efficiency 80 points, energy consumption 75 points, maintainability 88 points, cooperativeness 92 points, downtime reduction 95 points, quality stability 93 points" and presents them to on-site personnel and managers via the user interface unit.

[0094] Step 4: Automated Quality Inspection and Anomaly Detection Step The Quality Inspection Department automatically determines whether there are any abnormal or non-conforming values ​​by comparing the parameter values ​​of each motion plan generated by the Motion Plan Generation Department and the real-time sensor data acquired from the robot with pre-set normal ranges and quality standards. The Quality Inspection Department utilizes the generated AI not only for simple threshold judgments, but also uses an AI model that has learned past quality defect patterns and abnormal trends to automatically detect complex on-site risks, such as the risk of overheating due to the combination of power consumption and gripping force, the risk of parts wear due to the combination of acceleration and work sequence, signs of failure due to simultaneous abnormalities in motor current and vibration, the correlation between fluctuations in working environment temperature and the decrease in operation accuracy, and the risk of interference during coordinated operation of multiple robots. The AI ​​then issues real-time warnings to on-site personnel via the User Interface Department.

[0095] Step 5: Feedback and Learning Steps The feedback unit feeds back anomalies detected by the quality inspection unit, correction instructions from users, and defect information that occurs on-site to the operation plan generation unit and the generation AI, enabling automatic updates of the AI ​​model and optimization of the operation plan generation policy. For example, if power consumption anomalies occur frequently, the operation plan generation unit strengthens its emphasis on power consumption; if a cooperative operation anomaly is detected, it automatically generates a prompt that prioritizes cooperative timing optimization; and it immediately reflects new defect information that occurs on-site into the AI ​​model.

[0096] Step 6: User Interaction and Decision-Making Steps Through the user interface, users can compare and display the parameter values ​​and scores of each action plan in graphs and tables, and select the optimal action plan while reviewing the details of any anomalies and improvement suggestions. Furthermore, the system manages the version and history of action plans, allowing for chronological management of parameter values, scores, quality inspection results, anomaly history, and user comments for past action plans. When a user inputs correction instructions or additional requirements for an action plan, this information is sent to the server, and the generating AI immediately reflects this in the generation of new action plans and quality inspections.

[0097] (Specific use cases)

[0098] For example, when applying the system of the present invention to optimize the operation of a transport robot in a factory, the on-site personnel input detailed operation requirements through the user interface, such as a transport speed of 1.0 m / s or more, power consumption of 120 W or less, gripping force of 20 N to 30 N, work cycle time of 15 seconds or less, optimized cooperative operation timing, work area width of 2 m, enhanced temperature fluctuation resistance, minimization of abnormality occurrence frequency, improved maintainability, and reduced parts wear. These requirements are set reflecting the on-site production plan, product specifications, work content, equipment constraints, worker safety requirements, maintenance plan, energy costs, supply chain status, etc. Based on these requirements, the operation plan generation unit gives the generating AI a prompt message stating, "Generate 10 operation plans for a transport robot that simultaneously satisfy the following conditions: transport speed of 1.0 m / s or more, power consumption of 120 W or less, gripping force of 20 N to 30 N, work cycle time of 15 seconds or less, optimized cooperative operation timing, work area width of 2 m, enhanced temperature fluctuation resistance, minimization of abnormality occurrence frequency, improved maintainability, and reduced parts wear." The generating AI references past operational data, site requirements, equipment specifications, quality standards, maintenance history, sensor data, work environment information, and supply chain information, and combines optimization algorithms, evolutionary algorithms, and reinforcement learning to automatically generate multiple operation plans that meet various requirements, such as a transport speed of 1.1 m / s, power consumption of 115 W, gripping force of 25 N, work cycle time of 13 seconds, cooperative operation timing of 0.5 seconds, work area width of 2.1 m, enhanced temperature fluctuation resistance, abnormality occurrence frequency of 0.01 times / day, improved maintainability design, and a structure that reduces component wear.

[0099] The motion plan generation unit scores each motion plan output by the generating AI using a multifaceted evaluation index such as productivity, operating rate, safety, distance from the worker, safety stop responsiveness, efficiency, energy consumption, working time, peak power, maintainability, parts lifespan, ease of maintenance, cooperativeness, efficiency of coordination between multiple robots, downtime reduction, frequency of abnormal occurrences, recovery time, quality stability, product variability, and work accuracy. It automatically calculates scores such as "productivity 88 points, safety 92 points, efficiency 85 points, energy consumption 78 points, maintainability 90 points, cooperativeness 95 points, downtime reduction 97 points, quality stability 94 points" and presents them to on-site personnel and managers via the user interface unit. The Quality Inspection Department sets thresholds based on on-site safety and quality standards for each parameter value of each motion plan generated by the Motion Plan Generation Department and real-time sensor data acquired from the robot. These thresholds include, for example, a speed range of 0.6 m / s to 1.1 m / s, acceleration range of 0.3 m / s² to 0.9 m / s², gripping force range of 15 N to 35 N, power consumption range of 110 W to 150 W, motor current range of 0.8 A to 1.2 A, normalized temperature of 0.8 to 1.2, normalized vibration of 0.8 to 1.2, torque within the specified range, positional accuracy within ±0.1 mm, no abnormal noise detected, and external impact below the specified value. Based on these thresholds, the department automatically makes a judgment. Furthermore, the Quality Inspection Department utilizes generative AI to automatically detect complex on-site risks, such as the risk of overheating due to a combination of power consumption and gripping force, the risk of parts wear due to a combination of acceleration and work sequence, the possibility of failure due to simultaneous abnormalities in motor current and vibration, the correlation between fluctuations in working environment temperature and a decrease in operational accuracy, and the risk of interference during the coordinated operation of multiple robots. The AI ​​then issues real-time warnings to on-site personnel via the user interface.

[0100] The feedback unit feeds back anomalies detected by the quality inspection unit, correction instructions from users, and defect information that occurs on-site to the operation plan generation unit and the generation AI, enabling automatic updates of the AI ​​model and optimization of the operation plan generation policy. For example, if power consumption anomalies occur frequently, the operation plan generation unit strengthens its emphasis on power consumption; if a cooperative operation anomaly is detected, it automatically generates a prompt that prioritizes cooperative timing optimization; and it immediately reflects new defect information that occurs on-site into the AI ​​model. Through the user interface unit, users can compare and display the parameter values ​​and scores of each operation plan in graphs and tables, and select the optimal operation plan while checking the anomaly details and improvement suggestions. Furthermore, it manages the version and history of operation plans, allowing for chronological management of parameter values, scores, quality inspection results, anomaly history, and user comments of past operation plans. When a user inputs correction instructions or additional requirements for an operation plan, that information is sent to the server, and the generation AI immediately reflects it in the generation of new operation plans and quality inspections.

[0101] Specific examples of prompt statements to be input to the generating AI when implementing the present invention include: "Generate 10 operation plans for a transport robot that simultaneously satisfy the following conditions: transport speed of 1.0 m / s or more, power consumption of 120 W or less, gripping force of 20 N to 30 N, work cycle time of 15 seconds or less, optimized cooperative operation timing, work area width of 2 m, enhanced temperature fluctuation resistance, minimized frequency of abnormal occurrences, improved maintainability, and reduced parts wear"; "Present multiple operation plans for an assembly robot that optimize parts supply timing, fastening torque of 2 Nm to 3 Nm, automatic optimization of work sequence, enhanced vibration resistance, and emphasis on maintainability"; and "Generate an operation plan for an inspection robot that simultaneously considers optimized camera imaging timing, shortened inspection path, maximized inspection speed, improved abnormality detection accuracy, and optimized data transfer timing."

[0102] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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.

[0103] 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.

[0104] 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.

[0105] For example, the data collection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the smart device 14 and processes it with the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be modified in various ways.

[0106] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0107] [Second Embodiment]

[0108] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0109] 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.

[0110] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0111] 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, camera 42, and communication interface 44 are also connected to the bus 52.

[0112] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0113] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0114] 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.

[0115] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0116] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0117] 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.

[0118] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. The smart glasses 214 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 identification processing unit 290 using these models.

[0119] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is realized by the data processing device 12 and the smart glasses 214. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0120] (Example 1)

[0121] Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0122] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0123] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] Furthermore, the processing by the data processing system 10 described above 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.

[0125] For example, the data collection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the smart glasses 214 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0126] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0127] [Third Embodiment]

[0128] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0129] 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.

[0130] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0131] 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, display 343, and communication interface 44 are also connected to the bus 52.

[0132] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0134] 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.

[0135] 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.

[0136] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0137] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0138] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0139] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the headset terminal 314. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0140] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0141] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0142] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0143] 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 headset terminal 314, 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 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.

[0144] For example, the data collection unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the headset terminal 314 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the speaker 240 and display 343 of the headset terminal 314 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0145] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0146] [Fourth Embodiment]

[0147] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] 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.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0150] 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, controlled object 443, and communication interface 44 are also connected to the bus 52.

[0151] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0153] 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.

[0154] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0155] 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.

[0156] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0157] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0158] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0159] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the robot 414. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0160] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0161] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0162] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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.

[0163] 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 robot 414, 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 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 external devices, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or external devices.

[0164] For example, the data collection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the robot 414 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using a generation AI. For example, the serving unit is implemented by the speaker 240 and controlled object 443 of the robot 414 and the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0165] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0166] 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.

[0167] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0168] 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.

[0169] 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.

[0170] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0171] 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."

[0172] 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.

[0173] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0174] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0183] 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.

[0184] Furthermore, the following additional information is disclosed regarding the above explanation.

[0185] (Claim 1)

[0186] A factory robot motion optimization system comprising a motion plan generation unit, a quality inspection unit, and a control unit, wherein the motion plan generation unit accepts multiple parameters related to the operation of the factory robot, such as speed, acceleration, gripping force, work sequence, power consumption, coordinated operation timing, safety distance, path, and maintenance interval as input information, and uses a generative AI to automatically generate multiple motion plans by combining optimization algorithms, evolutionary algorithms, reinforcement learning, etc., while referring to past operational data, site requirements, equipment specifications, work content, quality standards, maintenance history, sensor data, work environment information, supply chain information, etc., and evaluates each motion plan using multifaceted evaluation indicators such as productivity, safety, efficiency, energy consumption, maintainability, coordination, downtime reduction, and quality stability. The system is characterized by performing scoring, the quality inspection unit comparing each parameter value of each operation plan generated by the operation plan generation unit and real-time sensor data acquired from the robot, such as motor current, temperature, vibration, torque, position accuracy, abnormal noise, current consumption, and external shock, with preset normal ranges and quality standards to determine whether abnormal or non-conforming values ​​are included, and further detecting complex anomalies and potential risks with high accuracy using an AI model that has learned past anomaly patterns and quality defect trends using a generation AI, and the control unit comprehensively controlling the operation of the operation plan generation unit and the quality inspection unit, and executing operation plan generation, quality inspection, anomaly detection, feedback learning, parameter optimization, and automatic AI model updates in parallel and automatically. (Claim 2)

[0187] The system according to claim 1, wherein the motion plan generation unit uses a generative AI to randomly or optimally select combinations of candidate values ​​for multiple motion parameters such as speed, acceleration, gripping force, work sequence, power consumption, coordinated operation timing, safety distance, path, and maintenance interval of a factory robot, generates motion plans for each combination, and further scores each motion plan based on multiple evaluation indicators such as productivity, safety, efficiency, energy consumption, maintainability, coordination, downtime reduction, and quality stability. (Claim 3)

[0188] The system according to claim 1, wherein the quality inspection department compares the parameter values ​​of each operation plan and real-time sensor data acquired from the robot with pre-set normal ranges and quality standard information, determines that an abnormality exists if it is outside the range, identifies the nature of the abnormality, outputs the abnormality determination result in real time, and the control unit further feeds the abnormality determination result back to the operation plan generation unit, thereby allowing the generation system AI to learn the tendency for abnormalities to occur when generating operation plans and reflect it in subsequent operation plan generation. [Explanation of Symbols]

[0189] 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 system comprising a design proposal generation unit, a quality inspection unit, and a control unit, wherein the design proposal generation unit receives multiple design parameters in the development of communication equipment or services as input information, automatically generates multiple design proposals based on combinations of said design parameters using a generation AI, calculates an optimality score for each design proposal considering market needs, technical feasibility, cost performance, and other evaluation indicators, the quality inspection unit determines whether each parameter value of each design proposal generated by the design proposal generation unit is within a preset normal range, identifies the nature of the abnormality if an abnormality is detected, outputs the abnormality determination result in real time, and the control unit comprehensively controls the operation of the design proposal generation unit and the quality inspection unit, and performs design proposal generation, quality inspection, abnormality detection, and feedback in parallel and automatically.

2. The system according to claim 1, wherein the design proposal generation unit uses a generation AI to randomly or optimally select combinations of candidate values ​​for multiple parameters, including communication speed, power consumption, cost, and other design parameters, generates a design proposal for each combination, and further performs scoring for each design proposal based on multiple evaluation indicators.

3. The system according to claim 1, wherein the quality inspection department compares each parameter value of each design proposal with pre-set normal range information, determines that it is abnormal if it is outside the range, identifies the nature of the abnormality, outputs the abnormality determination result in real time, and the control unit further feeds the abnormality determination result back to the design proposal generation unit, thereby allowing the generation system AI to learn the tendency of abnormality occurrences when generating design proposals and reflect it in subsequent design proposal generation.

Images