system

Abstract

The system according to this embodiment aims to automate the circuit design process and reduce design errors. [Solution] The system according to the embodiment comprises a requirements understanding unit, a design generation unit, an optimization unit, an error prediction unit, and a document generation unit. The requirements understanding unit understands the user's requirements. The design generation unit automatically generates a circuit design based on the requirements understood by the requirements understanding unit. The optimization unit optimizes the circuit design generated by the design generation unit. The error prediction unit predicts errors based on the circuit design optimized by the optimization unit. The document generation unit generates a technical document based on the errors predicted by the error prediction unit.

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] , , ,

[0003] , , , , ,

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance. <00​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​The system according to this embodiment comprises a requirements understanding unit, a design generation unit, an optimization unit, an error prediction unit, and a document generation unit. The requirements understanding unit understands the user's requirements. The design generation unit automatically generates a circuit design based on the requirements understood by the requirements understanding unit. The optimization unit optimizes the circuit design generated by the design generation unit. The error prediction unit predicts errors based on the circuit design optimized by the optimization unit. The document generation unit generates technical documentation based on the errors predicted by the error prediction unit. [Effects of the Invention]

[0007] The system according to this embodiment can automate the circuit design process and reduce design errors. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

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

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

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

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

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages 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), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

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

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0028] (Example of form 1) The circuit design automation system according to an embodiment of the present invention is a system that automatically generates an optimal circuit design based on user requirements. The circuit design automation system solves the problems of complexity and frequent errors in manually performed circuit design. By automatically generating an optimal circuit design based on user requirements, it reduces the risk of design errors and shortens the design process. Furthermore, it learns from past design data and proposes high-quality circuit designs in real time. This improves the speed and accuracy of the design process and reduces the burden on engineers by automating complex tasks. For example, the circuit design automation system understands the circuit design requirements entered by the user (e.g., current capacity, circuit purpose, etc.) in natural language and generates an optimal circuit design proposal. The language model proposes circuit diagram concepts and design proposals based on the input requirements. Next, the circuit design automation system uses a generative model that has learned from past design data and specifications to automatically generate a circuit diagram according to the user's requirements. This allows designers to compare multiple design proposals in a short time and select the best one. In addition, the circuit design automation system uses a reinforcement learning model to automatically detect problems that occur during the design process and proposes an optimal circuit design by adjusting the design parameters. This reduces design errors and improves quality. Furthermore, the circuit design automation system uses AI to learn past design error patterns and predict errors in new design proposals. By identifying areas where errors are likely to occur and suggesting corrections, it enhances design reliability. Finally, the circuit design automation system generates the technical documents and manuals required during the circuit design process. The generating AI automatically creates design documents and reports, reducing the burden on designers. In this way, the circuit design automation system transforms the way engineers work and innovates the design process. AI-powered automation reduces design errors and shortens development time, enabling users to deliver products that meet market needs more quickly. Additionally, the efficient design process reduces resources spent on prototyping and modifications, thus reducing environmental impact. Moreover, automated design tools make it easier for young engineers and students to acquire more advanced design skills, supporting the development of the next generation of engineers.This allows the circuit design automation system to understand user requirements and improve the efficiency and accuracy of the design process by automatically generating, optimizing, predicting errors in, and documenting circuit designs.

[0029] The circuit design automation system according to the embodiment comprises a requirements understanding unit, a design generation unit, an optimization unit, an error prediction unit, and a document generation unit. The requirements understanding unit understands the user's requirements. For example, the requirements understanding unit understands the circuit design requirements input by the user in natural language. The requirements understanding unit can analyze the user's requirements using natural language processing technology and extract the information necessary for design. For example, the requirements understanding unit decomposes the user's input using morphological analysis, performs grammatical analysis, and understands the requirements through semantic analysis. The design generation unit automatically generates a circuit design based on the requirements understood by the requirements understanding unit. For example, the design generation unit learns past design data and specifications and automatically generates a circuit diagram according to the user's requirements. The design generation unit can propose the optimal circuit design for the user's requirements using a generation AI. For example, the design generation unit inputs past design data into the generation AI and generates a new circuit diagram based on the user's requirements. The optimization unit optimizes the circuit design generated by the design generation unit. For example, the optimization unit automatically detects problems that occur during the design process using a reinforcement learning model and adjusts the design parameters. The optimization unit can optimize design parameters to improve design quality. For example, the optimization unit inputs design parameters into a reinforcement learning model and outputs optimal design parameters. The error prediction unit predicts errors based on the circuit design optimized by the optimization unit. For example, the error prediction unit uses AI to learn patterns of past design errors and predicts errors for new design proposals. The error prediction unit can identify areas where errors are likely to occur and suggest corrective actions. For example, the error prediction unit inputs past design error data into AI and predicts errors for new design proposals. The document generation unit generates technical documents based on the errors predicted by the error prediction unit. For example, the document generation unit generates technical documents and manuals necessary during the circuit design process. The document generation unit can automatically create design documents and reports using a generation AI. For example, the document generation unit inputs design data into a generation AI and generates technical documents.As a result, the circuit design automation system according to the embodiment can improve the efficiency and accuracy of the design process by understanding user requirements and automatically generating, optimizing, predicting errors in, and generating documentation for circuit designs.

[0030] The requirements understanding unit understands the user's requirements. For example, the requirements understanding unit understands the circuit design requirements entered by the user in natural language. The requirements understanding unit can analyze the user's requirements using natural language processing technology and extract the information necessary for design. Specifically, the requirements understanding unit decomposes the user's input using morphological analysis, performs grammatical analysis, and understands the requirements through semantic analysis. Morphological analysis decomposes the sentence entered by the user into individual words and identifies the part of speech of each word. Next, grammatical analysis analyzes the relationships between the decomposed words and grasps the overall structure of the sentence. Finally, semantic analysis understands the user's intent and requirements based on the results of grammatical analysis. For example, if the requirement "I want to design a highly efficient power supply circuit" is entered, the requirements understanding unit extracts the keywords "high efficiency," "power supply circuit," and "design," and organizes the information necessary for design based on these keywords. Furthermore, even if the user's requirements are ambiguous or incomplete, the requirements understanding unit can collect additional information through an interactive interface and supplement the requirements. For example, if a user simply inputs "high-efficiency power supply circuit," the requirements understanding unit will ask questions such as "What is the specific efficiency target percentage?" or "What is the voltage range to be used?" to confirm the detailed requirements. This allows the requirements understanding unit to accurately and thoroughly understand the user's requirements and provide the necessary information to the design generation unit.

[0031] The design generation unit automatically generates circuit designs based on the requirements understood by the requirements understanding unit. For example, the design generation unit learns from past design data and specifications to automatically generate circuit diagrams that meet user requirements. Using a generation AI, the design generation unit can propose the optimal circuit design for the user's requirements. Specifically, the design generation unit inputs past design data into the generation AI and generates a new circuit diagram based on the user's requirements. The generation AI uses deep learning technology to learn from past design data and understand design patterns and optimal configurations. For example, in power supply circuit design, it learns past highly efficient design patterns and proposes the optimal circuit configuration according to the user's requirements. Furthermore, the design generation unit can perform simulations on the generated circuit diagrams to verify the design's validity. Based on the simulation results, it modifies the design as needed to generate the optimal circuit diagram. For example, if the generated circuit diagram does not perform as expected under specific operating conditions, the design generation unit readjusts the circuit configuration and performs the simulation again. This allows the design generation unit to quickly and accurately generate the optimal circuit design for the user's requirements.

[0032] The optimization unit optimizes the circuit design generated by the design generation unit. For example, the optimization unit automatically detects problems that occur during the design process using a reinforcement learning model and adjusts the design parameters. Specifically, the optimization unit inputs design parameters into the reinforcement learning model and outputs the optimal design parameters. The reinforcement learning model can optimize the design parameters to improve the quality of the design. For example, the optimization unit adjusts the placement and connection methods of components to maximize the efficiency and stability of the circuit. Furthermore, the optimization unit can also optimize while considering the cost and ease of manufacturing of the design. For example, if a particular component is expensive, the optimization unit suggests an alternative component to reduce costs. Also, for designs that require complex procedures in the manufacturing process, the optimization unit simplifies the design and improves manufacturing efficiency. In this way, the optimization unit can provide the optimal circuit design by comprehensively considering design quality, cost, and ease of manufacturing.

[0033] The error prediction unit predicts errors based on the circuit design optimized by the optimization unit. For example, the error prediction unit uses AI to learn past design error patterns and predicts errors for new design proposals. Specifically, the error prediction unit inputs past design error data into the AI ​​and makes error predictions for new design proposals. Based on past error patterns, the AI ​​can identify the location and cause of errors in the new design proposal. For example, if a particular circuit configuration has caused errors with a high probability in the past, the error prediction unit will detect that circuit configuration and warn of the possibility of errors. Furthermore, the error prediction unit can identify parts where errors are likely to occur and suggest corrective measures. For example, if the placement of a particular component is the cause of an error, the error prediction unit will suggest changing the placement of that component. In this way, the error prediction unit can improve the quality and reliability of the design by predicting potential errors at the early stages of design and providing corrective measures.

[0034] The document generation unit generates technical documents based on errors predicted by the error prediction unit. For example, the document generation unit generates technical documents and manuals necessary during the circuit design process. Specifically, the document generation unit can automatically create design documents and reports using generation AI. The generation AI automatically generates the content of technical documents based on design data and provides them to the user. For example, it can generate technical documents that include an overview of the circuit design, a list of components used, the design's objectives and requirements, details of the design process, error prediction results, and proposed corrections. Furthermore, the document generation unit can customize the generated technical documents according to user requirements. For example, it can generate documents that conform to a specific format or style, or highlight specific information. This allows the document generation unit to increase the transparency of the design process and provide users with detailed design information.

[0035] The requirements understanding unit can understand the circuit design requirements entered by the user in natural language. The requirements understanding unit can analyze the user's requirements using, for example, natural language processing technology and extract the information necessary for design. The requirements understanding unit can decompose the user's input using morphological analysis, perform grammatical analysis, and understand the requirements through semantic analysis. This improves the efficiency of requirements definition by understanding the requirements entered by the user in natural language. Some or all of the above processing in the requirements understanding unit may be performed using, for example, AI, or without AI. For example, the requirements understanding unit can input the user's input data into a generating AI and have the generating AI perform the requirements analysis.

[0036] The design generation unit can learn from past design data and specifications and automatically generate circuit diagrams according to user requirements. For example, the design generation unit can use a generation AI to propose the optimal circuit design for the user's requirements. The design generation unit can input past design data into the generation AI and generate new circuit diagrams based on user requirements. This allows for the efficient generation of high-quality circuit diagrams by utilizing past design data. Some or all of the above-described processes in the design generation unit may be performed using AI, for example, or without AI. For example, the design generation unit can input past design data into the generation AI and have the generation AI perform the circuit diagram generation.

[0037] The optimization unit can automatically detect problems that occur during the design process using a reinforcement learning model and adjust the design parameters. For example, the optimization unit inputs design parameters into a reinforcement learning model and outputs optimal design parameters. The optimization unit can optimize design parameters to improve the quality of the design. In this way, by using a reinforcement learning model, problems during the design process are automatically detected and optimal design parameters are provided. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input design parameters into a generating AI and have the generating AI perform the optimization.

[0038] The error prediction unit can use AI to learn past design error patterns and predict errors in new design proposals. For example, the error prediction unit inputs past design error data into the AI ​​and performs error predictions for the new design proposal. The error prediction unit can identify areas where errors are likely to occur and suggest corrective actions. By learning past error patterns, the accuracy of error predictions for new design proposals improves. Some or all of the above-described processes in the error prediction unit may be performed using AI, for example, or without AI. For example, the error prediction unit can input a design proposal into a generating AI and have the generating AI perform the error prediction.

[0039] The document generation unit can generate technical documents and manuals necessary in the circuit design process. For example, the document generation unit can automatically create design documents and reports using a generation AI. The document generation unit can input design data into the generation AI and generate technical documents. This reduces the burden on designers by automatically generating technical documents and manuals. Some or all of the above-described processes in the document generation unit may be performed using AI, or without AI. For example, the document generation unit can input design data into the generation AI and have the generation AI perform the document generation.

[0040] The requirements understanding unit can analyze the user's past requirements input history and select the optimal requirements understanding method. For example, the requirements understanding unit can automatically display requirements that the user has frequently entered in the past as candidates. The requirements understanding unit can prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. The requirements understanding unit can predict and suggest requirements to be used during specific time periods based on the user's past requirements input history. This enables efficient requirements understanding by analyzing past requirements input history. Some or all of the above processes in the requirements understanding unit may be performed using AI, for example, or without AI. For example, the requirements understanding unit can input past requirements input data into a generating AI and have the generating AI select the requirements understanding method.

[0041] The requirements understanding unit can filter requirements based on the user's current projects and areas of interest during the requirements understanding process. For example, the requirements understanding unit can prioritize understanding requirements related to the user's current ongoing projects. The requirements understanding unit can prioritize understanding highly relevant requirements based on the user's areas of interest. The requirements understanding unit can filter and understand necessary requirements according to the progress of the user's projects. This allows for the understanding of highly relevant requirements by filtering requirements based on the current projects and areas of interest. Some or all of the above processing in the requirements understanding unit may be performed using AI, for example, or without AI. For example, the requirements understanding unit can input project data into a generating AI and have the generating AI perform the filtering.

[0042] The requirements understanding unit can prioritize understanding highly relevant requirements by considering the user's geographical location information during requirements understanding. For example, if the user is in a specific region, the requirements understanding unit will prioritize understanding requirements related to that region. If the user is on the move, the requirements understanding unit can understand highly relevant requirements based on the user's current location. If the user is in a specific location, the requirements understanding unit can prioritize understanding requirements related to that location. This makes it possible to understand highly relevant requirements by considering geographical location information. Some or all of the above processing in the requirements understanding unit may be performed using AI, for example, or without AI. For example, the requirements understanding unit can input location information data into a generating AI and have the generating AI perform the requirements understanding.

[0043] The requirements understanding unit can analyze the user's social media activity and understand the relevant requirements during requirements understanding. For example, the requirements understanding unit can grasp the user's current interests from the user's social media posts and understand the relevant requirements. The requirements understanding unit can analyze the activity of the user's social media followers and friends and understand the relevant requirements. The requirements understanding unit can analyze the user's social media trends and understand the relevant requirements. This makes it possible to understand requirements based on the user's interests by analyzing social media activity. Some or all of the above processing in the requirements understanding unit may be performed using AI, for example, or without AI. For example, the requirements understanding unit can input social media data into a generating AI and have the generating AI perform the requirements understanding.

[0044] The design generation unit can adjust the level of detail of a design based on the importance of past design data during design generation. For example, the design generation unit can extract important elements from past design data and generate a detailed design. The design generation unit can generate a concise design based on the importance of past design data. The design generation unit can generate a balanced design based on the importance of past design data. This enables efficient design generation by adjusting the level of detail of the design based on the importance of past design data. Some or all of the above processes in the design generation unit may be performed using AI, for example, or without AI. For example, the design generation unit can input past design data into a generation AI and have the generation AI adjust the level of detail of the design.

[0045] The design generation unit can apply different design algorithms depending on the design category during design generation. For example, in the case of circuit design, the design generation unit can apply a specific circuit design algorithm. In the case of mechanical design, the design generation unit can apply a specific mechanical design algorithm. In the case of software design, the design generation unit can apply a specific software design algorithm. This makes it possible to generate more appropriate designs by applying algorithms according to the design category. Some or all of the above-described processes in the design generation unit may be performed using AI, for example, or without AI. For example, the design generation unit can input design category data into a generation AI and have the generation AI apply the design algorithm.

[0046] The design generation unit can determine the priority of designs based on their submission dates during the design generation process. For example, the design generation unit can prioritize the generation of designs with approaching deadlines. It can also postpone the generation of designs with later submission dates. Based on the submission dates, the design generation unit can generate well-balanced designs. This enables efficient design generation by determining priorities based on the submission dates. Some or all of the above-described processes in the design generation unit may be performed using AI, for example, or without AI. For example, the design generation unit can input submission date data into a generation AI and have the generation AI determine the design priorities.

[0047] The design generation unit can adjust the order of designs based on their relationships during the design generation process. For example, the design generation unit can prioritize the generation of highly related designs. The design generation unit can postpone the generation of less related designs. The design generation unit can generate balanced designs based on their relationships. This enables efficient design generation by adjusting the order based on the relationships of the designs. Some or all of the above-described processes in the design generation unit may be performed using AI, for example, or without AI. For example, the design generation unit can input design relationship data into a generation AI and have the generation AI adjust the design order.

[0048] The optimization unit can improve the accuracy of optimization by considering the interrelationships of the design during the optimization process. For example, the optimization unit analyzes the interrelationships of the design and proposes the optimal design. The optimization unit can perform balanced optimization by considering the interrelationships of the design. The optimization unit can perform efficient optimization based on the interrelationships of the design. As a result, the accuracy of optimization is improved by considering the interrelationships of the design. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input design interrelationship data into a generating AI and have the generating AI perform the optimization.

[0049] The optimization unit can perform optimization while considering the attribute information of the design submitter. For example, the optimization unit can perform optimal optimization based on the design submitter's experience. The optimization unit can perform efficient optimization based on the design submitter's expertise. The optimization unit can perform balanced optimization by considering the attribute information of the design submitter. This makes it possible to perform more appropriate optimization by considering the attribute information of the design submitter. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without using AI. For example, the optimization unit can input submitter attribute data into a generating AI and have the generating AI perform the optimization.

[0050] The optimization unit can perform optimization while considering the geographical distribution of the design. For example, the optimization unit can analyze the geographical distribution of the design and propose the optimal design. The optimization unit can perform balanced optimization while considering the geographical distribution of the design. The optimization unit can perform efficient optimization based on the geographical distribution of the design. As a result, more appropriate optimization becomes possible by considering the geographical distribution of the design. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input geographical distribution data into a generating AI and have the generating AI perform the optimization.

[0051] The optimization unit can improve the accuracy of optimization by referring to relevant design literature during the optimization process. For example, the optimization unit can refer to relevant design literature and propose an optimal design. The optimization unit can perform efficient optimization based on the relevant design literature. The optimization unit can perform balanced optimization by considering the relevant design literature. As a result, the accuracy of optimization is improved by referring to relevant literature. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input relevant literature data into a generating AI and have the generating AI perform the optimization.

[0052] The error prediction unit can predict the current error by referring to past error data during error prediction. For example, the error prediction unit predicts similar errors based on past error data. The error prediction unit can predict the current error by analyzing patterns in past error data. The error prediction unit can predict the probability of error occurrence by referring to past error data. This improves the accuracy of the current error prediction by referring to past error data. Some or all of the above processing in the error prediction unit may be performed using AI, for example, or without using AI. For example, the error prediction unit can input past error data into a generating AI and have the generating AI perform the error prediction.

[0053] The error prediction unit can apply different error prediction methods to each design category during error prediction. For example, in the case of circuit design, the error prediction unit can apply a specific error prediction method. In the case of mechanical design, the error prediction unit can apply a specific error prediction method. In the case of software design, the error prediction unit can apply a specific error prediction method. This allows for more accurate error prediction by applying an error prediction method appropriate to the design category. Some or all of the above-described processes in the error prediction unit may be performed using AI, for example, or without AI. For example, the error prediction unit can input design category data into a generating AI and have the generating AI apply the error prediction method.

[0054] The error prediction unit can analyze how errors change based on the design submission date when predicting errors. For example, the error prediction unit can prioritize predicting errors in designs with upcoming submission dates. The error prediction unit can postpone predicting errors in designs with later submission dates. The error prediction unit can analyze how errors change based on the submission date. This allows for more accurate error prediction by analyzing how errors change based on the design submission date. Some or all of the above processing in the error prediction unit may be performed using AI, for example, or without AI. For example, the error prediction unit can input submission date data into a generating AI and have the generating AI perform the error change analysis.

[0055] The error prediction unit can analyze errors by referring to relevant market data for the design when predicting errors. For example, the error prediction unit can predict the probability of an error occurring based on market data. The error prediction unit can analyze the impact of errors by referring to market data. The error prediction unit can propose methods for correcting errors based on market data. This improves the accuracy of error prediction by referring to relevant market data. Some or all of the above processing in the error prediction unit may be performed using AI, for example, or without AI. For example, the error prediction unit can input market data into a generating AI and have the generating AI perform the error analysis.

[0056] The document generation unit can adjust the level of detail in a document based on the importance of the design during document generation. For example, the document generation unit can generate a detailed document for important designs. For less important designs, the document generation unit can generate a concise document. The document generation unit can generate a balanced document based on importance. As a result, by adjusting the level of detail in a document based on the importance of the design, a more appropriate document is generated. Some or all of the above processing in the document generation unit may be performed using AI, for example, or without AI. For example, the document generation unit can input design importance data into a generation AI and have the generation AI adjust the level of detail in the document.

[0057] The document generation unit can apply different document generation algorithms depending on the design category during document generation. For example, the document generation unit can apply a specific document generation algorithm in the case of circuit design. For mechanical design, it can apply a specific document generation algorithm. For software design, it can apply a specific document generation algorithm. By applying a document generation algorithm appropriate to the design category, more appropriate documents are generated. Some or all of the above-described processes in the document generation unit may be performed using AI, for example, or without AI. For example, the document generation unit can input design category data into a generation AI and have the generation AI apply the document generation algorithm.

[0058] The document generation unit can determine the priority of documents based on the submission deadlines of the designs during document generation. For example, the document generation unit can prioritize the generation of documents for designs with approaching deadlines. The document generation unit can postpone the generation of documents for designs with later submission deadlines. The document generation unit can generate a balanced set of documents based on the submission deadlines. This enables efficient document generation by determining the priority of documents based on the submission deadlines of the designs. Some or all of the above processing in the document generation unit may be performed using AI, for example, or without AI. For example, the document generation unit can input submission deadline data into a generation AI and have the generation AI determine the document priority.

[0059] The document generation unit can adjust the order of documents based on the relevance of the designs during document generation. For example, the document generation unit can prioritize the generation of documents for highly relevant designs. The document generation unit can postpone the generation of documents for less relevant designs. The document generation unit can generate balanced documents based on relevance. This enables efficient document generation by adjusting the order of documents based on the relevance of the designs. Some or all of the above processing in the document generation unit may be performed using AI, for example, or without AI. For example, the document generation unit can input design relevance data into a generation AI and have the generation AI adjust the document order.

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

[0061] The requirements understanding unit can analyze the user's past requirements input history and select the optimal requirements understanding method. For example, it can automatically display requirements that the user has frequently entered in the past as candidates. It can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Based on the user's past requirements input history, it can predict and suggest requirements that will be used during specific time periods. This enables efficient requirements understanding by analyzing past requirements input history. Some or all of the above processing in the requirements understanding unit may be performed using AI, for example, or without AI. For example, the requirements understanding unit can input past requirements input data into a generating AI and have the generating AI select the requirements understanding method.

[0062] The requirements understanding unit can prioritize understanding highly relevant requirements by considering the user's geographical location information during requirements understanding. For example, if the user is in a specific region, it will prioritize understanding requirements related to that region. If the user is on the move, it can prioritize understanding highly relevant requirements based on their current location. If the user is in a specific location, it can prioritize understanding requirements related to that location. This makes it possible to understand highly relevant requirements by considering geographical location information. Some or all of the above processing in the requirements understanding unit may be performed using AI, for example, or without AI. For example, the requirements understanding unit can input location data into a generating AI and have the generating AI perform the requirements understanding.

[0063] The design generation unit can apply different design algorithms depending on the design category during design generation. For example, in the case of circuit design, a specific circuit design algorithm can be applied. In the case of mechanical design, a specific mechanical design algorithm can be applied. In the case of software design, a specific software design algorithm can be applied. This makes it possible to generate more appropriate designs by applying algorithms appropriate to the design category. Some or all of the above-described processes in the design generation unit may be performed using AI, for example, or without AI. For example, the design generation unit can input design category data into a generation AI and have the generation AI apply the design algorithm.

[0064] The optimization unit can improve the accuracy of optimization by considering the interrelationships of the design during the optimization process. For example, it can analyze the interrelationships of the design and propose the optimal design. It can perform balanced optimization by considering the interrelationships of the design. It can perform efficient optimization based on the interrelationships of the design. As a result, the accuracy of optimization is improved by considering the interrelationships of the design. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input design interrelationship data into a generating AI and have the generating AI perform the optimization.

[0065] The error prediction unit can apply different error prediction methods to each design category during error prediction. For example, a specific error prediction method can be applied to circuit design, mechanical design, and software design. By applying an error prediction method appropriate to the design category, more accurate error prediction becomes possible. Some or all of the above-described processes in the error prediction unit may be performed using AI, for example, or without AI. For example, the error prediction unit can input design category data into a generating AI and have the generating AI apply the error prediction method.

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

[0067] Step 1: The requirements understanding unit understands the user's requirements. For example, it understands the circuit design requirements entered by the user in natural language, analyzes them using natural language processing technology, and extracts the information necessary for design. It understands the requirements through morphological analysis, grammatical analysis, and semantic analysis. Step 2: The design generation unit automatically generates circuit designs based on the requirements understood by the requirements understanding unit. For example, it learns from past design data and specifications and uses the generation AI to propose the optimal circuit design for the user's requirements. Step 3: The optimization unit optimizes the circuit design generated by the design generation unit. For example, it automatically detects problems that occur during the design process using a reinforcement learning model and adjusts the design parameters. Step 4: The error prediction unit predicts errors based on the circuit design optimized by the optimization unit. For example, it uses AI to learn past design error patterns and predicts errors for new design proposals. Step 5: The document generation unit generates technical documents based on the errors predicted by the error prediction unit. For example, it automatically creates design documents and reports using generation AI.

[0068] (Example of form 2) The circuit design automation system according to an embodiment of the present invention is a system that automatically generates an optimal circuit design based on user requirements. The circuit design automation system solves the problems of complexity and frequent errors in manually performed circuit design. By automatically generating an optimal circuit design based on user requirements, it reduces the risk of design errors and shortens the design process. Furthermore, it learns from past design data and proposes high-quality circuit designs in real time. This improves the speed and accuracy of the design process and reduces the burden on engineers by automating complex tasks. For example, the circuit design automation system understands the circuit design requirements entered by the user (e.g., current capacity, circuit purpose, etc.) in natural language and generates an optimal circuit design proposal. The language model proposes circuit diagram concepts and design proposals based on the input requirements. Next, the circuit design automation system uses a generative model that has learned from past design data and specifications to automatically generate a circuit diagram according to the user's requirements. This allows designers to compare multiple design proposals in a short time and select the best one. In addition, the circuit design automation system uses a reinforcement learning model to automatically detect problems that occur during the design process and proposes an optimal circuit design by adjusting the design parameters. This reduces design errors and improves quality. Furthermore, the circuit design automation system uses AI to learn past design error patterns and predict errors in new design proposals. By identifying areas where errors are likely to occur and suggesting corrections, it enhances design reliability. Finally, the circuit design automation system generates the technical documents and manuals required during the circuit design process. The generating AI automatically creates design documents and reports, reducing the burden on designers. In this way, the circuit design automation system transforms the way engineers work and innovates the design process. AI-powered automation reduces design errors and shortens development time, enabling users to deliver products that meet market needs more quickly. Additionally, the efficient design process reduces resources spent on prototyping and modifications, thus reducing environmental impact. Moreover, automated design tools make it easier for young engineers and students to acquire more advanced design skills, supporting the development of the next generation of engineers.This allows the circuit design automation system to understand user requirements and improve the efficiency and accuracy of the design process by automatically generating, optimizing, predicting errors in, and documenting circuit designs.

[0069] The circuit design automation system according to the embodiment comprises a requirements understanding unit, a design generation unit, an optimization unit, an error prediction unit, and a document generation unit. The requirements understanding unit understands the user's requirements. For example, the requirements understanding unit understands the circuit design requirements input by the user in natural language. The requirements understanding unit can analyze the user's requirements using natural language processing technology and extract the information necessary for design. For example, the requirements understanding unit decomposes the user's input using morphological analysis, performs grammatical analysis, and understands the requirements through semantic analysis. The design generation unit automatically generates a circuit design based on the requirements understood by the requirements understanding unit. For example, the design generation unit learns past design data and specifications and automatically generates a circuit diagram according to the user's requirements. The design generation unit can propose the optimal circuit design for the user's requirements using a generation AI. For example, the design generation unit inputs past design data into the generation AI and generates a new circuit diagram based on the user's requirements. The optimization unit optimizes the circuit design generated by the design generation unit. For example, the optimization unit automatically detects problems that occur during the design process using a reinforcement learning model and adjusts the design parameters. The optimization unit can optimize design parameters to improve design quality. For example, the optimization unit inputs design parameters into a reinforcement learning model and outputs optimal design parameters. The error prediction unit predicts errors based on the circuit design optimized by the optimization unit. For example, the error prediction unit uses AI to learn patterns of past design errors and predicts errors for new design proposals. The error prediction unit can identify areas where errors are likely to occur and suggest corrective actions. For example, the error prediction unit inputs past design error data into AI and predicts errors for new design proposals. The document generation unit generates technical documents based on the errors predicted by the error prediction unit. For example, the document generation unit generates technical documents and manuals necessary during the circuit design process. The document generation unit can automatically create design documents and reports using a generation AI. For example, the document generation unit inputs design data into a generation AI and generates technical documents.As a result, the circuit design automation system according to the embodiment can improve the efficiency and accuracy of the design process by understanding user requirements and automatically generating, optimizing, predicting errors in, and generating documentation for circuit designs.

[0070] The requirements understanding unit understands the user's requirements. For example, the requirements understanding unit understands the circuit design requirements entered by the user in natural language. The requirements understanding unit can analyze the user's requirements using natural language processing technology and extract the information necessary for design. Specifically, the requirements understanding unit decomposes the user's input using morphological analysis, performs grammatical analysis, and understands the requirements through semantic analysis. Morphological analysis decomposes the sentence entered by the user into individual words and identifies the part of speech of each word. Next, grammatical analysis analyzes the relationships between the decomposed words and grasps the overall structure of the sentence. Finally, semantic analysis understands the user's intent and requirements based on the results of grammatical analysis. For example, if the requirement "I want to design a highly efficient power supply circuit" is entered, the requirements understanding unit extracts the keywords "high efficiency," "power supply circuit," and "design," and organizes the information necessary for design based on these keywords. Furthermore, even if the user's requirements are ambiguous or incomplete, the requirements understanding unit can collect additional information through an interactive interface and supplement the requirements. For example, if a user simply inputs "high-efficiency power supply circuit," the requirements understanding unit will ask questions such as "What is the specific efficiency target percentage?" or "What is the voltage range to be used?" to confirm the detailed requirements. This allows the requirements understanding unit to accurately and thoroughly understand the user's requirements and provide the necessary information to the design generation unit.

[0071] The design generation unit automatically generates circuit designs based on the requirements understood by the requirements understanding unit. For example, the design generation unit learns from past design data and specifications to automatically generate circuit diagrams that meet user requirements. Using a generation AI, the design generation unit can propose the optimal circuit design for the user's requirements. Specifically, the design generation unit inputs past design data into the generation AI and generates a new circuit diagram based on the user's requirements. The generation AI uses deep learning technology to learn from past design data and understand design patterns and optimal configurations. For example, in power supply circuit design, it learns past highly efficient design patterns and proposes the optimal circuit configuration according to the user's requirements. Furthermore, the design generation unit can perform simulations on the generated circuit diagrams to verify the design's validity. Based on the simulation results, it modifies the design as needed to generate the optimal circuit diagram. For example, if the generated circuit diagram does not perform as expected under specific operating conditions, the design generation unit readjusts the circuit configuration and performs the simulation again. This allows the design generation unit to quickly and accurately generate the optimal circuit design for the user's requirements.

[0072] The optimization unit optimizes the circuit design generated by the design generation unit. For example, the optimization unit automatically detects problems that occur during the design process using a reinforcement learning model and adjusts the design parameters. Specifically, the optimization unit inputs design parameters into the reinforcement learning model and outputs the optimal design parameters. The reinforcement learning model can optimize the design parameters to improve the quality of the design. For example, the optimization unit adjusts the placement and connection methods of components to maximize the efficiency and stability of the circuit. Furthermore, the optimization unit can also optimize while considering the cost and ease of manufacturing of the design. For example, if a particular component is expensive, the optimization unit suggests an alternative component to reduce costs. Also, for designs that require complex procedures in the manufacturing process, the optimization unit simplifies the design and improves manufacturing efficiency. In this way, the optimization unit can provide the optimal circuit design by comprehensively considering design quality, cost, and ease of manufacturing.

[0073] The error prediction unit predicts errors based on the circuit design optimized by the optimization unit. For example, the error prediction unit uses AI to learn past design error patterns and predicts errors for new design proposals. Specifically, the error prediction unit inputs past design error data into the AI ​​and makes error predictions for new design proposals. Based on past error patterns, the AI ​​can identify the location and cause of errors in the new design proposal. For example, if a particular circuit configuration has caused errors with a high probability in the past, the error prediction unit will detect that circuit configuration and warn of the possibility of errors. Furthermore, the error prediction unit can identify parts where errors are likely to occur and suggest corrective measures. For example, if the placement of a particular component is the cause of an error, the error prediction unit will suggest changing the placement of that component. In this way, the error prediction unit can improve the quality and reliability of the design by predicting potential errors at the early stages of design and providing corrective measures.

[0074] The document generation unit generates technical documents based on errors predicted by the error prediction unit. For example, the document generation unit generates technical documents and manuals necessary during the circuit design process. Specifically, the document generation unit can automatically create design documents and reports using generation AI. The generation AI automatically generates the content of technical documents based on design data and provides them to the user. For example, it can generate technical documents that include an overview of the circuit design, a list of components used, the design's objectives and requirements, details of the design process, error prediction results, and proposed corrections. Furthermore, the document generation unit can customize the generated technical documents according to user requirements. For example, it can generate documents that conform to a specific format or style, or highlight specific information. This allows the document generation unit to increase the transparency of the design process and provide users with detailed design information.

[0075] The requirements understanding unit can understand the circuit design requirements entered by the user in natural language. The requirements understanding unit can analyze the user's requirements using, for example, natural language processing technology and extract the information necessary for design. The requirements understanding unit can decompose the user's input using morphological analysis, perform grammatical analysis, and understand the requirements through semantic analysis. This improves the efficiency of requirements definition by understanding the requirements entered by the user in natural language. Some or all of the above processing in the requirements understanding unit may be performed using, for example, AI, or without AI. For example, the requirements understanding unit can input the user's input data into a generating AI and have the generating AI perform the requirements analysis.

[0076] The design generation unit can learn from past design data and specifications and automatically generate circuit diagrams according to user requirements. For example, the design generation unit can use a generation AI to propose the optimal circuit design for the user's requirements. The design generation unit can input past design data into the generation AI and generate new circuit diagrams based on user requirements. This allows for the efficient generation of high-quality circuit diagrams by utilizing past design data. Some or all of the above-described processes in the design generation unit may be performed using AI, for example, or without AI. For example, the design generation unit can input past design data into the generation AI and have the generation AI perform the circuit diagram generation.

[0077] The optimization unit can automatically detect problems that occur during the design process using a reinforcement learning model and adjust the design parameters. For example, the optimization unit inputs design parameters into a reinforcement learning model and outputs optimal design parameters. The optimization unit can optimize design parameters to improve the quality of the design. In this way, by using a reinforcement learning model, problems during the design process are automatically detected and optimal design parameters are provided. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input design parameters into a generating AI and have the generating AI perform the optimization.

[0078] The error prediction unit can use AI to learn past design error patterns and predict errors in new design proposals. For example, the error prediction unit inputs past design error data into the AI ​​and performs error predictions for the new design proposal. The error prediction unit can identify areas where errors are likely to occur and suggest corrective actions. By learning past error patterns, the accuracy of error predictions for new design proposals improves. Some or all of the above-described processes in the error prediction unit may be performed using AI, for example, or without AI. For example, the error prediction unit can input a design proposal into a generating AI and have the generating AI perform the error prediction.

[0079] The document generation unit can generate technical documents and manuals necessary in the circuit design process. For example, the document generation unit can automatically create design documents and reports using a generation AI. The document generation unit can input design data into the generation AI and generate technical documents. This reduces the burden on designers by automatically generating technical documents and manuals. Some or all of the above-described processes in the document generation unit may be performed using AI, or without AI. For example, the document generation unit can input design data into the generation AI and have the generation AI perform the document generation.

[0080] The requirements understanding unit can estimate the user's emotions and adjust the priority of requirements based on the estimated user emotions. For example, if the user is stressed, the requirements understanding unit can prioritize understanding important requirements and respond quickly. If the user is relaxed, the requirements understanding unit can carefully understand detailed requirements and consider the overall balance. If the user is in a hurry, the requirements understanding unit can quickly understand the most important requirements and postpone other requirements. This allows for a more appropriate understanding of requirements by adjusting the priority of requirements based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the requirements understanding unit may be performed using AI or not. For example, the requirements understanding unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0081] The requirements understanding unit can analyze the user's past requirements input history and select the optimal requirements understanding method. For example, the requirements understanding unit can automatically display requirements that the user has frequently entered in the past as candidates. The requirements understanding unit can prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. The requirements understanding unit can predict and suggest requirements to be used during specific time periods based on the user's past requirements input history. This enables efficient requirements understanding by analyzing past requirements input history. Some or all of the above processes in the requirements understanding unit may be performed using AI, for example, or without AI. For example, the requirements understanding unit can input past requirements input data into a generating AI and have the generating AI select the requirements understanding method.

[0082] The requirements understanding unit can filter requirements based on the user's current projects and areas of interest during the requirements understanding process. For example, the requirements understanding unit can prioritize understanding requirements related to the user's current ongoing projects. The requirements understanding unit can prioritize understanding highly relevant requirements based on the user's areas of interest. The requirements understanding unit can filter and understand necessary requirements according to the progress of the user's projects. This allows for the understanding of highly relevant requirements by filtering requirements based on the current projects and areas of interest. Some or all of the above processing in the requirements understanding unit may be performed using AI, for example, or without AI. For example, the requirements understanding unit can input project data into a generating AI and have the generating AI perform the filtering.

[0083] The requirements understanding unit can estimate the user's emotions and adjust the timing of requirement acquisition based on the estimated user emotions. For example, if the user is stressed, the requirements understanding unit can postpone requirement acquisition until the user is relaxed. If the user is relaxed, the requirements understanding unit can adjust the timing of acquiring detailed requirements. If the user is in a hurry, the requirements understanding unit can quickly acquire requirements and postpone other requirements. This allows requirements to be acquired at a more appropriate time by adjusting the timing of requirement acquisition based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the requirements understanding unit may be performed using AI or not using AI. For example, the requirements understanding unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0084] The requirements understanding unit can prioritize understanding highly relevant requirements by considering the user's geographical location information during requirements understanding. For example, if the user is in a specific region, the requirements understanding unit will prioritize understanding requirements related to that region. If the user is on the move, the requirements understanding unit can understand highly relevant requirements based on the user's current location. If the user is in a specific location, the requirements understanding unit can prioritize understanding requirements related to that location. This makes it possible to understand highly relevant requirements by considering geographical location information. Some or all of the above processing in the requirements understanding unit may be performed using AI, for example, or without AI. For example, the requirements understanding unit can input location information data into a generating AI and have the generating AI perform the requirements understanding.

[0085] The requirements understanding unit can analyze the user's social media activity and understand the relevant requirements during requirements understanding. For example, the requirements understanding unit can grasp the user's current interests from the user's social media posts and understand the relevant requirements. The requirements understanding unit can analyze the activity of the user's social media followers and friends and understand the relevant requirements. The requirements understanding unit can analyze the user's social media trends and understand the relevant requirements. This makes it possible to understand requirements based on the user's interests by analyzing social media activity. Some or all of the above processing in the requirements understanding unit may be performed using AI, for example, or without AI. For example, the requirements understanding unit can input social media data into a generating AI and have the generating AI perform the requirements understanding.

[0086] The design generation unit can estimate the user's emotions and adjust the design's presentation based on those emotions. For example, if the user is relaxed, the design generation unit can generate a visually appealing design. If the user is in a hurry, the design generation unit can generate a concise and to-the-point design. If the user is excited, the design generation unit can generate a design with visually stimulating effects. By adjusting the design's presentation based on the user's emotions, a more appropriate design is generated. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the design generation unit may be performed using AI, or not using AI. For example, the design generation unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0087] The design generation unit can adjust the level of detail of a design based on the importance of past design data during design generation. For example, the design generation unit can extract important elements from past design data and generate a detailed design. The design generation unit can generate a concise design based on the importance of past design data. The design generation unit can generate a balanced design based on the importance of past design data. This enables efficient design generation by adjusting the level of detail of the design based on the importance of past design data. Some or all of the above processes in the design generation unit may be performed using AI, for example, or without AI. For example, the design generation unit can input past design data into a generation AI and have the generation AI adjust the level of detail of the design.

[0088] The design generation unit can apply different design algorithms depending on the design category during design generation. For example, in the case of circuit design, the design generation unit can apply a specific circuit design algorithm. In the case of mechanical design, the design generation unit can apply a specific mechanical design algorithm. In the case of software design, the design generation unit can apply a specific software design algorithm. This makes it possible to generate more appropriate designs by applying algorithms according to the design category. Some or all of the above-described processes in the design generation unit may be performed using AI, for example, or without AI. For example, the design generation unit can input design category data into a generation AI and have the generation AI apply the design algorithm.

[0089] The design generation unit can estimate the user's emotions and adjust the length of the design based on the estimated emotions. For example, if the user is in a hurry, the design generation unit can generate a short, concise design. If the user is relaxed, the design generation unit can generate a longer design that includes detailed explanations. If the user is excited, the design generation unit can generate a design with visually stimulating effects. By adjusting the length of the design based on the user's emotions, a more appropriate design is generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the design generation unit may be performed using AI, for example, or not using AI. For example, the design generation unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0090] The design generation unit can determine the priority of designs based on their submission dates during the design generation process. For example, the design generation unit can prioritize the generation of designs with approaching deadlines. It can also postpone the generation of designs with later submission dates. Based on the submission dates, the design generation unit can generate well-balanced designs. This enables efficient design generation by determining priorities based on the submission dates. Some or all of the above-described processes in the design generation unit may be performed using AI, for example, or without AI. For example, the design generation unit can input submission date data into a generation AI and have the generation AI determine the design priorities.

[0091] The design generation unit can adjust the order of designs based on their relationships during the design generation process. For example, the design generation unit can prioritize the generation of highly related designs. The design generation unit can postpone the generation of less related designs. The design generation unit can generate balanced designs based on their relationships. This enables efficient design generation by adjusting the order based on the relationships of the designs. Some or all of the above-described processes in the design generation unit may be performed using AI, for example, or without AI. For example, the design generation unit can input design relationship data into a generation AI and have the generation AI adjust the design order.

[0092] The optimization unit can estimate the user's emotions and adjust the optimization criteria based on the estimated emotions. For example, if the user is relaxed, the optimization unit can apply detailed optimization criteria. If the user is in a hurry, the optimization unit can apply concise optimization criteria. If the user is excited, the optimization unit can apply optimization criteria with visually stimulating effects. This allows for more appropriate optimization by adjusting the optimization criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the optimization unit may be performed using AI, for example, or not using AI. For example, the optimization unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0093] The optimization unit can improve the accuracy of optimization by considering the interrelationships of the design during the optimization process. For example, the optimization unit analyzes the interrelationships of the design and proposes the optimal design. The optimization unit can perform balanced optimization by considering the interrelationships of the design. The optimization unit can perform efficient optimization based on the interrelationships of the design. As a result, the accuracy of optimization is improved by considering the interrelationships of the design. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input design interrelationship data into a generating AI and have the generating AI perform the optimization.

[0094] The optimization unit can perform optimization while considering the attribute information of the design submitter. For example, the optimization unit can perform optimal optimization based on the design submitter's experience. The optimization unit can perform efficient optimization based on the design submitter's expertise. The optimization unit can perform balanced optimization by considering the attribute information of the design submitter. This makes it possible to perform more appropriate optimization by considering the attribute information of the design submitter. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without using AI. For example, the optimization unit can input submitter attribute data into a generating AI and have the generating AI perform the optimization.

[0095] The optimization unit can estimate the user's emotions and adjust the order in which the optimization results are displayed based on the estimated emotions. For example, if the user is relaxed, the optimization unit can display detailed optimization results. If the user is in a hurry, the optimization unit can display concise optimization results. If the user is excited, the optimization unit can display optimization results with visually stimulating effects. This allows for more appropriate result display by adjusting the order in which the optimization results are displayed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the optimization unit may be performed using AI or not using AI. For example, the optimization unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0096] The optimization unit can perform optimization while considering the geographical distribution of the design. For example, the optimization unit can analyze the geographical distribution of the design and propose the optimal design. The optimization unit can perform balanced optimization while considering the geographical distribution of the design. The optimization unit can perform efficient optimization based on the geographical distribution of the design. As a result, more appropriate optimization becomes possible by considering the geographical distribution of the design. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input geographical distribution data into a generating AI and have the generating AI perform the optimization.

[0097] The optimization unit can improve the accuracy of optimization by referring to relevant design literature during the optimization process. For example, the optimization unit can refer to relevant design literature and propose an optimal design. The optimization unit can perform efficient optimization based on the relevant design literature. The optimization unit can perform balanced optimization by considering the relevant design literature. As a result, the accuracy of optimization is improved by referring to relevant literature. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input relevant literature data into a generating AI and have the generating AI perform the optimization.

[0098] The error prediction unit can estimate the user's emotions and adjust the display method of the error prediction based on the estimated user emotions. For example, if the user is nervous, the error prediction unit can provide a simple and highly visible display method. If the user is relaxed, the error prediction unit can provide a display method that includes detailed information. If the user is in a hurry, the error prediction unit can provide a display method that gets straight to the point. By adjusting the display method of the error prediction based on the user's emotions, more appropriate error predictions can be made. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the error prediction unit may be performed using AI, for example, or not using AI. For example, the error prediction unit can input user emotion data into the generative AI and have the generative AI perform emotion estimation.

[0099] The error prediction unit can predict the current error by referring to past error data during error prediction. For example, the error prediction unit predicts similar errors based on past error data. The error prediction unit can predict the current error by analyzing patterns in past error data. The error prediction unit can predict the probability of error occurrence by referring to past error data. This improves the accuracy of the current error prediction by referring to past error data. Some or all of the above processing in the error prediction unit may be performed using AI, for example, or without using AI. For example, the error prediction unit can input past error data into a generating AI and have the generating AI perform the error prediction.

[0100] The error prediction unit can apply different error prediction methods to each design category during error prediction. For example, in the case of circuit design, the error prediction unit can apply a specific error prediction method. In the case of mechanical design, the error prediction unit can apply a specific error prediction method. In the case of software design, the error prediction unit can apply a specific error prediction method. This allows for more accurate error prediction by applying an error prediction method appropriate to the design category. Some or all of the above-described processes in the error prediction unit may be performed using AI, for example, or without AI. For example, the error prediction unit can input design category data into a generating AI and have the generating AI apply the error prediction method.

[0101] The error prediction unit can estimate the user's emotions and adjust the importance of error predictions based on the estimated emotions. For example, if the user is stressed, the error prediction unit will prioritize displaying important errors. If the user is relaxed, the error prediction unit can display detailed error information. If the user is in a hurry, the error prediction unit can display concise error information. By adjusting the importance of error predictions based on the user's emotions, more appropriate error predictions can be made. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the error prediction unit may be performed using AI or not using AI. For example, the error prediction unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0102] The error prediction unit can analyze how errors change based on the design submission date when predicting errors. For example, the error prediction unit can prioritize predicting errors in designs with upcoming submission dates. The error prediction unit can postpone predicting errors in designs with later submission dates. The error prediction unit can analyze how errors change based on the submission date. This allows for more accurate error prediction by analyzing how errors change based on the design submission date. Some or all of the above processing in the error prediction unit may be performed using AI, for example, or without AI. For example, the error prediction unit can input submission date data into a generating AI and have the generating AI perform the error change analysis.

[0103] The error prediction unit can analyze errors by referring to relevant market data for the design when predicting errors. For example, the error prediction unit can predict the probability of an error occurring based on market data. The error prediction unit can analyze the impact of errors by referring to market data. The error prediction unit can propose methods for correcting errors based on market data. This improves the accuracy of error prediction by referring to relevant market data. Some or all of the above processing in the error prediction unit may be performed using AI, for example, or without AI. For example, the error prediction unit can input market data into a generating AI and have the generating AI perform the error analysis.

[0104] The document generation unit can estimate the user's emotions and adjust the way the document is presented based on the estimated emotions. For example, if the user is relaxed, the document generation unit can generate a document with detailed explanations. If the user is in a hurry, the document generation unit can generate a concise and to-the-point document. If the user is excited, the document generation unit can generate a document with visually stimulating effects. By adjusting the way the document is presented based on the user's emotions, a more appropriate document is generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the document generation unit may be performed using AI, for example, or not using AI. For example, the document generation unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0105] The document generation unit can adjust the level of detail in a document based on the importance of the design during document generation. For example, the document generation unit can generate a detailed document for important designs. For less important designs, the document generation unit can generate a concise document. The document generation unit can generate a balanced document based on importance. As a result, by adjusting the level of detail in a document based on the importance of the design, a more appropriate document is generated. Some or all of the above processing in the document generation unit may be performed using AI, for example, or without AI. For example, the document generation unit can input design importance data into a generation AI and have the generation AI adjust the level of detail in the document.

[0106] The document generation unit can apply different document generation algorithms depending on the design category during document generation. For example, the document generation unit can apply a specific document generation algorithm in the case of circuit design. For mechanical design, it can apply a specific document generation algorithm. For software design, it can apply a specific document generation algorithm. By applying a document generation algorithm appropriate to the design category, more appropriate documents are generated. Some or all of the above-described processes in the document generation unit may be performed using AI, for example, or without AI. For example, the document generation unit can input design category data into a generation AI and have the generation AI apply the document generation algorithm.

[0107] The document generation unit can estimate the user's emotions and adjust the length of the document based on the estimated emotions. For example, if the user is in a hurry, the document generation unit can generate a short, concise document. If the user is relaxed, the document generation unit can generate a longer document with detailed explanations. If the user is excited, the document generation unit can generate a document with visually stimulating effects. By adjusting the length of the document based on the user's emotions, a more appropriate document is generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the document generation unit may be performed using AI, for example, or not using AI. For example, the document generation unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0108] The document generation unit can determine the priority of documents based on the submission deadlines of the designs during document generation. For example, the document generation unit can prioritize the generation of documents for designs with approaching deadlines. The document generation unit can postpone the generation of documents for designs with later submission deadlines. The document generation unit can generate a balanced set of documents based on the submission deadlines. This enables efficient document generation by determining the priority of documents based on the submission deadlines of the designs. Some or all of the above processing in the document generation unit may be performed using AI, for example, or without AI. For example, the document generation unit can input submission deadline data into a generation AI and have the generation AI determine the document priority.

[0109] The document generation unit can adjust the order of documents based on the relevance of the designs during document generation. For example, the document generation unit can prioritize the generation of documents for highly relevant designs. The document generation unit can postpone the generation of documents for less relevant designs. The document generation unit can generate balanced documents based on relevance. This enables efficient document generation by adjusting the order of documents based on the relevance of the designs. Some or all of the above processing in the document generation unit may be performed using AI, for example, or without AI. For example, the document generation unit can input design relevance data into a generation AI and have the generation AI adjust the document order.

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

[0111] The requirements understanding unit can estimate the user's emotions and adjust the priority of requirements based on the estimated user emotions. For example, if the user is stressed, it can prioritize understanding important requirements and respond quickly. If the user is relaxed, it can carefully understand detailed requirements and consider the overall balance. If the user is in a hurry, it can quickly understand the most important requirements and postpone other requirements. This allows for a more appropriate understanding of requirements by adjusting the priority of requirements based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the requirements understanding unit may be performed using AI or not. For example, the requirements understanding unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0112] The requirements understanding unit can analyze the user's past requirements input history and select the optimal requirements understanding method. For example, it can automatically display requirements that the user has frequently entered in the past as candidates. It can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Based on the user's past requirements input history, it can predict and suggest requirements that will be used during specific time periods. This enables efficient requirements understanding by analyzing past requirements input history. Some or all of the above processing in the requirements understanding unit may be performed using AI, for example, or without AI. For example, the requirements understanding unit can input past requirements input data into a generating AI and have the generating AI select the requirements understanding method.

[0113] The design generation unit can estimate the user's emotions and adjust the design's presentation based on those emotions. For example, if the user is relaxed, it can generate a visually appealing design. If the user is in a hurry, it can generate a concise and to-the-point design. If the user is excited, it can generate a design with visually stimulating effects. By adjusting the design's presentation based on the user's emotions, a more appropriate design is generated. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the design generation unit may be performed using AI, or not. For example, the design generation unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0114] The optimization unit can estimate the user's emotions and adjust the optimization criteria based on the estimated emotions. For example, if the user is relaxed, detailed optimization criteria can be applied. If the user is in a hurry, concise optimization criteria can be applied. If the user is excited, optimization criteria with visually stimulating effects can be applied. This allows for more appropriate optimization by adjusting the optimization criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the optimization unit may be performed using AI, or not using AI. For example, the optimization unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0115] The error prediction unit can estimate the user's emotions and adjust the display method of the error prediction based on the estimated user emotions. For example, if the user is nervous, a simple and highly visible display method can be provided. If the user is relaxed, a display method containing detailed information can be provided. If the user is in a hurry, a display method that gets straight to the point can be provided. By adjusting the display method of the error prediction based on the user's emotions, more appropriate error predictions can be made. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the error prediction unit may be performed using AI, for example, or without AI. For example, the error prediction unit can input user emotion data into the generative AI and have the generative AI perform emotion estimation.

[0116] The requirements understanding unit can prioritize understanding highly relevant requirements by considering the user's geographical location information during requirements understanding. For example, if the user is in a specific region, it will prioritize understanding requirements related to that region. If the user is on the move, it can prioritize understanding highly relevant requirements based on their current location. If the user is in a specific location, it can prioritize understanding requirements related to that location. This makes it possible to understand highly relevant requirements by considering geographical location information. Some or all of the above processing in the requirements understanding unit may be performed using AI, for example, or without AI. For example, the requirements understanding unit can input location data into a generating AI and have the generating AI perform the requirements understanding.

[0117] The design generation unit can apply different design algorithms depending on the design category during design generation. For example, in the case of circuit design, a specific circuit design algorithm can be applied. In the case of mechanical design, a specific mechanical design algorithm can be applied. In the case of software design, a specific software design algorithm can be applied. This makes it possible to generate more appropriate designs by applying algorithms appropriate to the design category. Some or all of the above-described processes in the design generation unit may be performed using AI, for example, or without AI. For example, the design generation unit can input design category data into a generation AI and have the generation AI apply the design algorithm.

[0118] The optimization unit can improve the accuracy of optimization by considering the interrelationships of the design during the optimization process. For example, it can analyze the interrelationships of the design and propose the optimal design. It can perform balanced optimization by considering the interrelationships of the design. It can perform efficient optimization based on the interrelationships of the design. As a result, the accuracy of optimization is improved by considering the interrelationships of the design. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input design interrelationship data into a generating AI and have the generating AI perform the optimization.

[0119] The error prediction unit can apply different error prediction methods to each design category during error prediction. For example, a specific error prediction method can be applied to circuit design, mechanical design, and software design. By applying an error prediction method appropriate to the design category, more accurate error prediction becomes possible. Some or all of the above-described processes in the error prediction unit may be performed using AI, for example, or without AI. For example, the error prediction unit can input design category data into a generating AI and have the generating AI apply the error prediction method.

[0120] The document generation unit can estimate the user's emotions and adjust the way the document is presented based on the estimated emotions. For example, if the user is relaxed, it can generate a document with detailed explanations. If the user is in a hurry, it can generate a concise and to-the-point document. If the user is excited, it can generate a document with visually stimulating effects. By adjusting the way the document is presented based on the user's emotions, a more appropriate document is generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the document generation unit may be performed using AI, for example, or not using AI. For example, the document generation unit can input user emotion data into the generative AI and have the generative AI perform emotion estimation.

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

[0122] Step 1: The requirements understanding unit understands the user's requirements. For example, it understands the circuit design requirements entered by the user in natural language, analyzes them using natural language processing technology, and extracts the information necessary for design. It understands the requirements through morphological analysis, grammatical analysis, and semantic analysis. Step 2: The design generation unit automatically generates circuit designs based on the requirements understood by the requirements understanding unit. For example, it learns from past design data and specifications and uses the generation AI to propose the optimal circuit design for the user's requirements. Step 3: The optimization unit optimizes the circuit design generated by the design generation unit. For example, it automatically detects problems that occur during the design process using a reinforcement learning model and adjusts the design parameters. Step 4: The error prediction unit predicts errors based on the circuit design optimized by the optimization unit. For example, it uses AI to learn past design error patterns and predicts errors for new design proposals. Step 5: The document generation unit generates technical documents based on the errors predicted by the error prediction unit. For example, it automatically creates design documents and reports using generation AI.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

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

[0126] Each of the multiple elements described above, including the requirements understanding unit, design generation unit, optimization unit, error prediction unit, and document generation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the requirements understanding unit is implemented by the control unit 46A of the smart device 14 and understands the circuit design requirements entered by the user in natural language. The design generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past design data and specifications to automatically generate a circuit diagram according to the user's requirements. The optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and uses a reinforcement learning model to automatically detect problems that occur during the design process and adjust the design parameters. The error prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past design error patterns to predict errors for new design proposals. The document generation unit is implemented by the control unit 46A of the smart device 14 and generates technical documents and manuals necessary in the circuit design process. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

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

[0142] Each of the multiple elements described above, including the requirements understanding unit, design generation unit, optimization unit, error prediction unit, and document generation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the requirements understanding unit is implemented by the control unit 46A of the smart glasses 214 and understands the circuit design requirements entered by the user in natural language. The design generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past design data and specifications to automatically generate a circuit diagram according to the user's requirements. The optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and uses a reinforcement learning model to automatically detect problems that occur during the design process and adjust the design parameters. The error prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past design error patterns to predict errors for new design proposals. The document generation unit is implemented by the control unit 46A of the smart glasses 214 and generates technical documents and manuals necessary in the circuit design process. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

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

[0158] Each of the multiple elements described above, including the requirements understanding unit, design generation unit, optimization unit, error prediction unit, and document generation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the requirements understanding unit is implemented by the control unit 46A of the headset terminal 314 and understands the circuit design requirements entered by the user in natural language. The design generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past design data and specifications to automatically generate a circuit diagram according to the user's requirements. The optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and uses a reinforcement learning model to automatically detect problems that occur during the design process and adjust the design parameters. The error prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past design error patterns to predict errors for new design proposals. The document generation unit is implemented by the control unit 46A of the headset terminal 314 and generates technical documents and manuals necessary in the circuit design process. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

[0160] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0172] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

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

[0175] Each of the multiple elements described above, including the requirements understanding unit, design generation unit, optimization unit, error prediction unit, and document generation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the requirements understanding unit is implemented by the control unit 46A of the robot 414 and understands the circuit design requirements input by the user in natural language. The design generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past design data and specifications to automatically generate a circuit diagram according to the user's requirements. The optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and uses a reinforcement learning model to automatically detect problems that occur during the design process and adjust the design parameters. The error prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past design error patterns to predict errors for new design proposals. The document generation unit is implemented by the control unit 46A of the robot 414 and generates technical documents and manuals necessary in the circuit design process. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0186] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

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

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) A requirements understanding unit that understands user requirements, A design generation unit that automatically generates a circuit design based on the requirements understood by the requirements understanding unit, An optimization unit that optimizes the circuit design generated by the design generation unit, An error prediction unit that predicts errors based on the circuit design optimized by the optimization unit, The system includes a document generation unit that generates technical documents based on errors predicted by the error prediction unit. A system characterized by the following features. (Note 2) The requirements understanding unit, Understand the circuit design requirements entered by the user in natural language. The system described in Appendix 1, characterized by the features described herein. (Note 3) The design generation unit, It learns from past design data and specifications and automatically generates circuit diagrams that meet the user's requirements. The system described in Appendix 1, characterized by the features described herein. (Note 4) The optimization unit, Using reinforcement learning models, problems that occur during the design process are automatically detected, and design parameters are adjusted. The system described in Appendix 1, characterized by the features described herein. (Note 5) The error prediction unit, Using AI, we learn patterns of past design errors and predict errors in new design proposals. The system described in Appendix 1, characterized by the features described herein. (Note 6) The document generation unit, Generates technical documents and manuals required during the circuit design process. The system described in Appendix 1, characterized by the features described herein. (Note 7) The requirements understanding unit, Estimate user sentiment and adjust requirement priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The requirements understanding unit, Analyze the user's past requirements input history and select the optimal method for understanding those requirements. The system described in Appendix 1, characterized by the features described herein. (Note 9) The requirements understanding unit, When understanding requirements, filtering is performed based on the user's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The requirements understanding unit, It estimates the user's emotions and adjusts the timing of requirement acquisition based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The requirements understanding unit, When understanding requirements, prioritize understanding the most relevant requirements by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The requirements understanding unit, When understanding requirements, analyze users' social media activity and understand the relevant requirements. The system described in Appendix 1, characterized by the features described herein. (Note 13) The design generation unit, We estimate the user's emotions and adjust the design's presentation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The design generation unit, During design generation, the level of detail of the design is adjusted based on the importance of past design data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The design generation unit, When generating designs, different design algorithms are applied depending on the design category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The design generation unit, The system estimates the user's emotions and adjusts the design length based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The design generation unit, When generating designs, prioritize the designs based on when they were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The design generation unit, During design generation, the order of designs is adjusted based on their relationships. The system described in Appendix 1, characterized by the features described herein. (Note 19) The optimization unit, It estimates user sentiment and adjusts optimization criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The optimization unit, During optimization, consider the interrelationships of the design to improve the accuracy of the optimization. The system described in Appendix 1, characterized by the features described herein. (Note 21) The optimization unit, During optimization, the attribute information of the design submitter is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 22) The optimization unit, It estimates the user's emotions and adjusts the order in which the optimization results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The optimization unit, During optimization, the geographical distribution of the design is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 24) The optimization unit, During optimization, refer to relevant design literature to improve the accuracy of the optimization. The system described in Appendix 1, characterized by the features described herein. (Note 25) The error prediction unit, It estimates the user's emotions and adjusts how error predictions are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The error prediction unit, When predicting errors, past error data is referenced to predict the current error. The system described in Appendix 1, characterized by the features described herein. (Note 27) The error prediction unit, When predicting errors, different error prediction methods are applied for each design category. The system described in Appendix 1, characterized by the features described herein. (Note 28) The error prediction unit, It estimates the user's emotions and adjusts the importance of error predictions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The error prediction unit, When predicting errors, analyze how errors change based on the design submission date. The system described in Appendix 1, characterized by the features described herein. (Note 30) The error prediction unit, When predicting errors, we analyze errors by referring to relevant market data for the design. The system described in Appendix 1, characterized by the features described herein. (Note 31) The document generation unit, It estimates the user's emotions and adjusts the way the document is written based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The document generation unit, When generating documents, adjust the level of detail in the document based on the importance of the design. The system described in Appendix 1, characterized by the features described herein. (Note 33) The document generation unit, When generating documents, different document generation algorithms are applied depending on the design category. The system described in Appendix 1, characterized by the features described herein. (Note 34) The document generation unit, It estimates the user's emotions and adjusts the document length based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The document generation unit, When generating documents, prioritize them based on the design submission deadline. The system described in Appendix 1, characterized by the features described herein. (Note 36) The document generation unit, During document generation, the order of documents is adjusted based on the relevance of the design. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

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

Claims

1. A requirements understanding unit that understands user requirements, A design generation unit that automatically generates a circuit design based on the requirements understood by the requirements understanding unit, An optimization unit that optimizes the circuit design generated by the design generation unit, An error prediction unit that predicts errors based on the circuit design optimized by the optimization unit, The system includes a document generation unit that generates technical documents based on errors predicted by the error prediction unit. A system characterized by the following features.

2. The requirements understanding unit, Understand the circuit design requirements entered by the user in natural language. The system according to feature 1.

3. The design generation unit, It learns from past design data and specifications and automatically generates circuit diagrams that meet the user's requirements. The system according to feature 1.

4. The optimization unit, Using reinforcement learning models, problems that occur during the design process are automatically detected, and design parameters are adjusted. The system according to feature 1.

5. The error prediction unit, Using AI, we learn patterns of past design errors and predict errors in new design proposals. The system according to feature 1.

6. The document generation unit, Generates technical documents and manuals required during the circuit design process. The system according to feature 1.

7. The requirements understanding unit, Estimate user sentiment and adjust requirement priorities based on the estimated user sentiment. The system according to feature 1.

8. The requirements understanding unit, Analyze the user's past requirements input history and select the optimal method for understanding those requirements. The system according to feature 1.

9. The requirements understanding unit, When understanding requirements, filtering is performed based on the user's current projects and areas of interest. The system according to feature 1.

10. The requirements understanding unit, It estimates the user's emotions and adjusts the timing of requirement acquisition based on the estimated user emotions. The system according to feature 1.

Images