System

Abstract

An object of the present embodiment is to efficiently generate a design document and a code from a system configuration graph. A system according to an embodiment includes a reception unit, an analysis unit, and a generation unit. The receiving unit inputs a system configuration diagram. The analysis unit analyzes the demand on the basis of the system configuration graph input by the reception unit. The generation unit generates a design document and a code on the basis of the demand analyzed by the analysis unit.

Description

Technical Field

[0001] The technology disclosed herein relates to a system. Background Technology

[0002] Patent Document 1 discloses a personalized chatbot control method executed by at least one processor, the method comprising: receiving user speech; adding the user speech to a prompt containing instructions related to a chatbot role; encoding the prompt; and inputting the encoded prompt into a language model to generate chatbot speech in response to the user speech.

[0003] Patent document 1: Japanese Patent Application Publication No. 2022-180282. Summary of the Invention

[0004] In existing technologies, the process of generating design documents and code from system configuration diagrams requires a lot of time and effort, resulting in low efficiency.

[0005] The purpose of the system involved in this technical solution is to efficiently generate design documents and code from system configuration diagrams.

[0006] The system involved in this technical solution includes a receiving department, a parsing department, and a generation department. The receiving department is used to input system configuration diagrams. The parsing department parses requirements based on the system configuration diagrams input by the receiving department. The generation department generates design documents and code based on the requirements parsed by the parsing department.

[0007] The system involved in this technical solution can efficiently generate design documents and code from system configuration diagrams. Attached Figure Description

[0008] Figure 1 This is a conceptual diagram illustrating an example of the configuration of a data processing system according to the first embodiment.

[0009] Figure 2 This is a conceptual diagram illustrating an example of the main functions of the data processing apparatus and smart device according to the first embodiment.

[0010] Figure 3 This is a conceptual diagram illustrating an example of the data processing system configuration in the second embodiment.

[0011] Figure 4 This is a conceptual diagram illustrating an example of the main functions of the data processing device and smart glasses according to the second embodiment.

[0012] Figure 5 This is a conceptual diagram illustrating an example of the data processing system configuration in the third embodiment.

[0013] Figure 6This is a conceptual diagram illustrating an example of the main functions of the data processing device and head-mounted terminal according to the third embodiment.

[0014] Figure 7 This is a conceptual diagram illustrating an example of the data processing system configuration in the fourth embodiment.

[0015] Figure 8 This is a conceptual diagram illustrating an example of the functions of the main parts of the data processing device and robot according to the fourth embodiment.

[0016] Figure 9 It represents an emotion graph that maps multiple emotions.

[0017] Figure 10 It represents an emotion graph that maps multiple emotions.

[0018] Explanation of reference numerals in the attached figures Data processing systems 10, 210, 310, and 410 12 Data processing devices 14 Smart devices 214 Smart Glasses 314 Head-mounted terminal 414 Robot. Detailed Implementation

[0019] Hereinafter, an example of an implementation of the system involved in this disclosure will be described with reference to the accompanying drawings.

[0020] First, let's explain the terms used in the following description.

[0021] In the following embodiments, the processor (hereinafter referred to as "processor"), as indicated by the reference numerals, can be a single computing device or a combination of multiple computing devices. Furthermore, a processor can be a single computing device or a combination of multiple computing devices. Examples of computing devices 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), etc.

[0022] In the following embodiments, RAM (Random Access Memory), as indicated in the figures, is a memory that temporarily stores information and is used by the processor as working memory.

[0023] In the following embodiments, the memory, as indicated by the reference numerals, is one or more non-volatile storage devices used to store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), disks (e.g., hard disks), or magnetic tape, etc.

[0024] In the following embodiments, the communication I / F (Interface) with reference numerals is an interface including a communication processor and an antenna, etc. The communication I / F is responsible for communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] In the following implementation, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it can be only A, only B, or a combination of A and B. Furthermore, in this specification, when "and / or" connects more than three items, the same approach as "A and / or B" applies.

[0026] [First Implementation] Figure 1 An example of the configuration of the data processing system 10 according to the first embodiment is shown.

[0027] like Figure 1 As shown, the data processing system 10 includes a data processing device 12 and an intelligent device 14. An example of the data processing device 12 is a server.

[0028] 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, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a receiver 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. In addition, the receiver 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The receiving device 38 includes a touchscreen 38A and a microphone 38B, etc., for receiving user input. The touchscreen 38A receives user input generated by contact with an indicator (e.g., a pen or finger). The microphone 38B receives user input generated by sound by detecting the user's voice. The control unit 46A sends data representing user input received via the touchscreen 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, a specific processing unit 290 (see...) Figure 2 Get the data that represents the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, etc., and presents data to the user by outputting data in a user-perceptible form (e.g., sound and / or text). The display 40A displays visual information such as text and images according to instructions from the processor 46. The speaker 40B outputs sound 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 imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for sending and receiving various information between processor 46 and processor 28 via network 54.

[0033] Figure 2 An example of the main functions of the data processing device 12 and the smart device 14 is shown.

[0034] like Figure 2 As shown, in the data processing apparatus 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the memory 32. The specific processing program 56 is an example of a "program" as understood in this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0035] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0036] In the smart device 14, specific processing is performed by the processor 46. A specific processing program 60 is stored in the memory 50. The specific processing program 60 is used in conjunction with the data processing system 10. The processor 46 reads the specific processing program 60 from the memory 50 and executes the read specific processing program 60 on the RAM 48. Specific processing is implemented by the processor 46 operating as a control unit 46A based on the specific processing program 60 executed on the RAM 48. Furthermore, the smart device 14 may also have the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and use these models to perform the same processing as the specific processing unit 290.

[0037] 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 the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. In addition, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of the processing performed by the data processing system 10 of the first embodiment will be described.

[0038] Implementation Method 1 The cloud infrastructure design and construction system described in this invention aims to reduce the time required for cloud infrastructure design and construction while improving quality. This system supports multimodal operation and utilizes image-based generative AI to solve the problems of high workload and unstable quality in traditional cloud infrastructure projects. First, a system configuration diagram is created and input as an image into the generative AI. Then, a dialogue is conducted with the AI ​​to obtain detailed information related to the requirements. Design document formats are prepared in advance. After the dialogue, various design documents and the code required for construction are generated based on the system configuration diagram and the dialogue content. This reduces the original workload of several person-months to approximately one person-day. Even with limited dialogue, more standardized design documents are generated. The output design documents can be revised and reused as input, allowing for flexible adjustments. Furthermore, the construction of the cloud infrastructure generates Terraform code. This reduces unit testing to zero, significantly decreasing workload. The system supports multi-cloud environments, reading the cloud platforms used from the system configuration diagram, selecting appropriate formats, and combining the dialogue content to write design documents, thus achieving further time reduction. Therefore, cloud infrastructure design and construction systems can significantly reduce the time required for cloud infrastructure design and construction while improving quality.

[0039] The cloud infrastructure design and construction system described in this embodiment includes a receiving unit, a parsing unit, and a generation unit. The receiving unit is used to input a system configuration diagram. The system configuration diagram may include, for example, hardware configuration diagrams, software configuration diagrams, network configuration diagrams, etc., but is not limited to these examples. The receiving unit may receive the system configuration diagram as an image file. In addition, the receiving unit may also receive system configuration diagrams in PDF format or other digital formats. The parsing unit parses requirements based on the system configuration diagram input by the receiving unit. Requirement parsing may include, for example, functional requirements, non-functional requirements, constraints, etc., but is not limited to these examples. The parsing unit can parse each element of the system configuration diagram and extract its respective requirements. The parsing unit can also identify particularly important elements in the system configuration diagram and analyze the requirements in detail accordingly. The generation unit generates design documents and code based on the requirements parsed by the parsing unit. The generation of design documents and code may include, for example, a design document format, a programming language for the code, etc., but is not limited to these examples. The generation unit can generate design documents based on design document templates. The generation unit can also generate code in a suitable programming language based on the parsed requirements. Therefore, the cloud infrastructure design and construction system can automate the entire process from inputting system configuration diagrams and requirements analysis to generating design documents and code, significantly reducing working hours. Some or all of the above processes in the generation department can be implemented using a generation AI, or they can be omitted. For example, the generation department can input the requirements analysis results into the generation AI, which will then execute the generation of design documents and code.

[0040] The receiving unit is used to input system configuration diagrams. System configuration diagrams may include, for example, hardware configuration diagrams, software configuration diagrams, network configuration diagrams, etc., but are not limited to these examples. The receiving unit can receive system configuration diagrams as image files. In addition, the receiving unit can also receive system configuration diagrams in PDF format or other digital formats. Specifically, the receiving unit has the function of automatically recognizing user-uploaded files and converting them to the appropriate format. For example, for image files, it uses OCR (Optical Character Recognition) technology to convert them into text data; for PDF files, it parses their internal structure and extracts the required information. Furthermore, the receiving unit provides a user-input interface, allowing users to manually input system configuration diagrams. Thus, the receiving unit can flexibly receive system configuration diagrams in various formats, enabling smooth data transfer to the next parsing unit. The receiving unit also has the function of checking the received system configuration diagrams. Figure 1 This system provides functions to ensure data consistency and notify users of missing or inconsistent information. As a result, the receiving department can ensure data quality in the initial stages, smoothly facilitating subsequent processing by the parsing and generation departments.

[0041] The Analysis Department analyzes requirements based on the system architecture diagram input by the Receiving Department. Requirement analysis may include, but is not limited to, functional requirements, non-functional requirements, and constraints. The Analysis Department can analyze each element of the system architecture diagram and extract its respective requirements. Specifically, the Analysis Department can analyze the role and interrelationships of each component in the system architecture diagram to determine the required functions and performance. For example, analyzing server deployment and network topology extracts requirements related to overall system performance and reliability. The Analysis Department can also identify particularly important elements in the system architecture diagram and analyze requirements in detail accordingly. For example, analyzing database deployment and redundancy methods clarifies requirements related to data consistency and availability. Furthermore, the Analysis Department can utilize AI for requirement analysis. Specifically, it uses natural language processing technology to analyze the description of the system architecture diagram and automatically extracts requirements. It can also use machine learning algorithms to learn from past project data and automatically identify similar requirements. Thus, the Analysis Department can efficiently and accurately analyze requirements and provide data to the next generation department.

[0042] The generation department generates design documents and code based on the requirements analyzed by the parsing department. The generation of design documents and code may include, but is not limited to, examples such as design document format and programming language. The generation department can generate design documents based on design document templates. Specifically, the generation department applies the requirements provided by the parsing department to the template to automatically generate a design document for the entire system. The design document includes a system overview, detailed information on each component, their interrelationships, data flow, etc. The generation department can also generate code in appropriate programming languages ​​based on the parsed requirements. For example, for web applications, it can automatically generate HTML, CSS, JavaScript (registered trademark), etc., while server-side logic can generate Python or Java (registered trademark), etc. Furthermore, the generation department can utilize AI-generated design documents and code. Specifically, the requirements analysis results are input into the AI-generated design document, which then generates the design documents and code. The AI-generated design document learns from past project data and best practices, enabling it to generate optimal design documents and code. For example, the AI-generated design document can propose optimal architecture suggestions based on the requirements and generate the design document accordingly. The AI-generated design document can also consider code quality and performance to generate optimal code. As a result, the generation department can generate design documents and code efficiently and with high quality, significantly reducing the overall system time.

[0043] A dialogue department can be set up to facilitate conversations about the details of requirements. This dialogue department can, for example, engage in dialogue with users via a chatbot. For instance, it can automatically generate answers to user questions. The dialogue department can also utilize speech recognition technology to convert user speech into text for dialogue. For example, it can analyze user voice input in real time and generate appropriate responses. Furthermore, the dialogue department can dynamically adjust the dialogue process based on user input. For example, it can change the next question to be prompted based on user input. Thus, the dialogue department can obtain detailed requirements through dialogue with users, improving the accuracy of design documents and code. Some or all of the above processing in the dialogue department can be implemented using AI, or it can be done without AI. For example, the dialogue department can input user input into AI, which will then execute the dialogue process.

[0044] The analysis department can analyze requirements based on the system architecture diagram input by the receiving department and the dialogue results from the dialogue department. The analysis department can analyze each element of the system architecture diagram and extract its respective requirements. For example, the analysis department can identify particularly important elements in the system architecture diagram and analyze the requirements in detail accordingly. The analysis department can also analyze user requirements in detail based on the dialogue results from the dialogue department. For example, the analysis department can compare the user requirements obtained from the dialogue department with the system architecture diagram to confirm the consistency of the requirements. The analysis department can also determine the priority of requirements by combining the system architecture diagram and the dialogue results. For example, the analysis department can dynamically adjust the priority of requirements based on the importance of the system architecture diagram and the content of the dialogue results. Thus, the analysis department can improve the accuracy of requirement analysis by combining the system architecture diagram and the dialogue results. Some or all of the above processing in the analysis department can be implemented using AI, or AI can be used without it. For example, the analysis department can input the system architecture diagram and dialogue results into the AI, which will then perform the requirement analysis.

[0045] The generation department can generate design documents and code using AI. The generation department can generate design documents based on design document templates. For example, the generation department can use AI to automatically generate design documents based on the parsed requirements. The generation department can also generate code in a suitable programming language based on the parsed requirements. For example, the generation department can use AI to automatically generate requirement-based code. The AI ​​can use natural language generation technology or machine learning algorithms to generate design documents and code. For example, the AI ​​can receive requirements as input and use natural language generation technology to generate design documents. The AI ​​can also use machine learning algorithms to generate code based on requirements. Therefore, by using AI, the generation department can improve the accuracy of design document and code generation. Some or all of the above processes in the generation department can be implemented using AI, or they can be omitted. For example, the generation department can input the requirements parsing results into the AI, which will then generate the design documents and code.

[0046] The generation department supports multi-cloud environments, reading cloud types from system architecture diagrams and selecting appropriate formats. It can parse system architecture diagrams to identify cloud types. For example, it can identify cloud types based on cloud service information contained in the system architecture diagram. The generation department can also select appropriate formats based on cloud types. For example, it can select formats supporting cloud services such as AWS, Azure, and Google Cloud. Appropriate formats may include, but are not limited to, JSON, YAML, and XML. The generation department can also adjust the generation methods for design documents and code based on cloud service types. For example, when generating design documents and code supporting AWS, the generation department generates them based on AWS resource definitions and provider settings. Thus, the generation department can support multi-cloud environments and adapt to various cloud environments. Some or all of the above processing in the generation department can be implemented through generation AI, or it can be done without using generation AI. For example, the generation department can input the system architecture diagram into the generation AI, which will then perform cloud type identification and format selection.

[0047] The generation department can generate Terraform code. It can generate code based on Terraform resource definitions. For example, the generation department can use generation AI to automatically generate Terraform code based on the parsed requirements. Terraform code may include, but is not limited to, resource definitions, provider settings, etc. The generation department can use generation AI to generate requirement-based Terraform resource definitions. The generation department can also generate Terraform code based on provider settings. For example, the generation department can generate Terraform code based on provider settings that support cloud services such as AWS, Azure, and Google Cloud. Thus, the generation department automates the construction of cloud infrastructure by generating Terraform code. Some or all of the above processes in the generation department can be implemented using generation AI, or they can be performed without it. For example, the generation department can input the requirement parsing results into generation AI, which will then execute the generation of Terraform code.

[0048] The receiving department can analyze a user's past project history when inputting the system structure diagram to select the optimal input method. The receiving department can retrieve and analyze the user's past project history from a database. For example, the receiving department can prioritize recommending input methods previously used by the user. The receiving department can also select the most efficient input method based on the user's past project history. For example, the receiving department can analyze the user's past project history to customize the input method. Past project history may include, but is not limited to, examples such as project type, duration, and deliverables. Therefore, by analyzing the user's past project history, the receiving department can provide the optimal input method. Some or all of the above processing in the receiving department can be implemented using AI, or it may not require AI. For example, the receiving department can input the user's past project history into AI, which will then select the optimal input method.

[0049] The receiving department can filter system architecture diagrams based on the user's current project status and areas of interest when inputting them. The receiving department can retrieve and analyze the user's current project status from a database. For example, the receiving department can prioritize inputting highly relevant system architecture diagrams based on the user's current project status. The receiving department can also recommend the optimal system architecture diagram based on the user's areas of interest. For example, the receiving department can customize the input content by combining the user's current project status and areas of interest. Current project status may include, for example, progress, resource status, priority, etc., but is not limited to these examples. Thus, the receiving department can provide highly relevant system architecture diagrams based on the user's current project status and areas of interest. Some or all of the above processing in the receiving department can be implemented using AI, or it may not require AI. For example, the receiving department can input the user's current project status and areas of interest into AI, which will then perform the filtering.

[0050] The receiving department can consider the user's geographic location information when inputting system configuration diagrams, prioritizing diagrams with high relevance. The receiving department can obtain and analyze the user's geographic location information from GPS data or IP address. For example, the receiving department can prioritize system configuration diagrams with high relevance based on the user's current location. The receiving department can also consider the user's geographic location information to recommend the optimal system configuration diagram. For example, the receiving department can customize the input content based on the user's geographic location information. Geographic location information may include, but is not limited to, examples such as GPS data, IP address, and location information services. Thus, by considering the user's geographic location information, the receiving department can provide highly relevant system configuration diagrams. Some or all of the above processing in the receiving department can be implemented using AI, or it may not require AI. For example, the receiving department can input the user's geographic location information into AI, which will then select highly relevant system configuration diagrams.

[0051] The receiving department can analyze a user's social media activity when inputting a system structure diagram, and input relevant diagrams accordingly. The receiving department can retrieve and analyze user social media activity from a database. For example, based on user social media activity, the receiving department can prioritize inputting highly relevant system structure diagrams. The receiving department can also analyze user social media activity to recommend the optimal system structure diagram. For example, the receiving department can customize input content based on user social media activity. Social media activity may include, but is not limited to, examples such as posted content, number of followers, and interaction volume. Thus, by analyzing user social media activity, the receiving department can provide highly relevant system structure diagrams. Some or all of the above processing in the receiving department can be implemented using AI, or it may not require AI. For example, the receiving department can input user social media activity into AI, which will then select relevant system structure diagrams.

[0052] The analysis department can adjust the level of detail in the requirements analysis based on the importance of the system architecture diagram. The analysis department can assess the importance of the system architecture diagram and adjust the level of detail accordingly. For example, the analysis department can perform detailed requirements analysis on system architecture diagrams with high importance. The analysis department can also perform brief requirements analysis on system architecture diagrams with low importance. The importance of the system architecture diagram can include, for example, business impact, technical risks, dependencies, etc., but is not limited to these examples. The analysis department can assess the business impact of the system architecture diagram and adjust the level of detail accordingly. The analysis department can also assess technical risks and adjust the level of detail accordingly. Therefore, the analysis department can adjust the level of detail in the requirements analysis based on the importance of the system architecture diagram, achieving efficient requirements analysis. Some or all of the above processing in the analysis department can be implemented using AI, or AI can be used without it. For example, the analysis department can input the importance of the system architecture diagram into AI, and AI can perform the adjustment of the level of detail in the analysis.

[0053] The parsing unit can apply different parsing algorithms based on the category of the system architecture diagram during requirements parsing. The parsing unit can identify the category of the system architecture diagram and apply the corresponding parsing algorithm. For example, the parsing unit can apply a dedicated parsing algorithm to network-related system architecture diagrams. It can also apply a dedicated parsing algorithm to database-related system architecture diagrams. The categories of system architecture diagrams may include, for example, application architecture diagrams, infrastructure architecture diagrams, security architecture diagrams, etc., but are not limited to these examples. The parsing unit can apply algorithms for parsing application requirements to application architecture diagrams. It can also apply algorithms for parsing infrastructure requirements to infrastructure architecture diagrams. Thus, the parsing unit can apply parsing algorithms based on the category of the system architecture diagram, improving parsing accuracy. Some or all of the above processing in the parsing unit can be implemented using AI, or AI can be used without it. For example, the parsing unit can input the category of the system architecture diagram into the AI, which will then execute the application of the parsing algorithm.

[0054] The analysis department can determine the analysis priority based on the submission timing of the system architecture diagram during requirements analysis. The analysis department can evaluate the submission timing of the system architecture diagram and determine the analysis priority accordingly. For example, the analysis department can prioritize analyzing system architecture diagrams with more recent submission times. The analysis department can also postpone processing system architecture diagrams with more distant submission times. Submission times can include, for example, submission deadlines, project phases, schedules, etc., but are not limited to these examples. The analysis department can evaluate the submission deadline of the system architecture diagram and determine the analysis priority accordingly. The analysis department can also evaluate the project phase and determine the analysis priority accordingly. Therefore, the analysis department can determine the analysis priority based on the submission timing of the system architecture diagram, achieving efficient requirements analysis. Some or all of the above processing in the analysis department can be implemented using AI, or AI can be used without it. For example, the analysis department can input the submission timing of the system architecture diagram into the AI, which will then determine the analysis priority.

[0055] The analysis department can adjust the analysis order based on the relevance of the system architecture diagram during requirements analysis. The analysis department can evaluate the relevance of the system architecture diagram and adjust the analysis order accordingly. For example, the analysis department can prioritize analyzing system architecture diagrams with high relevance. The analysis department can also postpone processing system architecture diagrams with low relevance. The relevance of the system architecture diagram can include, for example, functional relevance, technical relevance, and business relevance, but is not limited to these examples. The analysis department can evaluate the functional relevance of the system architecture diagram and adjust the analysis order accordingly. The analysis department can also evaluate the technical relevance and adjust the analysis order accordingly. Therefore, the analysis department can adjust the analysis order based on the relevance of the system architecture diagram, achieving efficient requirements analysis. Some or all of the above processing in the analysis department can be implemented using AI, or AI can be used without it. For example, the analysis department can input the relevance of the system architecture diagram into the AI, which will then adjust the analysis order.

[0056] The generation department can adjust the level of detail generated based on the importance of requirements when generating design documents and code. The generation department can assess the importance of requirements and adjust the level of detail accordingly. For example, the generation department can generate detailed design documents and code for requirements with high importance. It can also generate concise design documents and code for requirements with low importance. The importance of requirements can include, but is not limited to, business impact, technical risks, dependencies, etc. The generation department can assess the business impact of requirements and adjust the level of detail accordingly. It can also assess technical risks and adjust the level of detail accordingly. Thus, the generation department can adjust the level of detail based on the importance of requirements, achieving efficient generation of design documents and code. Some or all of the above processing in the generation department can be achieved through generation AI, or it can be done without using generation AI. For example, the generation department can input the importance of requirements into the generation AI, which will then adjust the level of detail.

[0057] The generation department can apply different generation algorithms based on the category of requirements when generating design documents and code. The generation department can identify the category of requirements and apply the corresponding generation algorithm. For example, the generation department can apply a dedicated generation algorithm for network-related requirements. It can also apply a dedicated generation algorithm for database-related requirements. Requirement categories may include, for example, application-related, infrastructure-related, security-related, etc., but are not limited to these examples. The generation department can apply algorithms for generating application design documents and code to application-related requirements. It can also apply algorithms for generating infrastructure design documents and code to infrastructure-related requirements. Thus, the generation department can apply generation algorithms based on the category of requirements, improving generation accuracy. Some or all of the above processing in the generation department can be implemented through generation AI, or it may not be necessary to use generation AI. For example, the generation department can input the category of requirements into the generation AI, which will then execute the application of the generation algorithm.

[0058] The generation department can prioritize the generation of design documents and code based on the timing of requirement submissions. The generation department can assess the submission timing of requirements and determine the generation priority accordingly. For example, the generation department can prioritize generating requirements with more recent submission times. The generation department can also postpone processing requirements with more distant submission times. Submission times can include, for example, submission deadlines, project phases, schedules, etc., but are not limited to these examples. The generation department can assess the submission deadlines of requirements and determine the generation priority accordingly. The generation department can also assess the project phases and determine the generation priority accordingly. Thus, the generation department can prioritize the generation based on the submission timing of requirements, achieving efficient design document and code generation. Some or all of the above processing in the generation department can be implemented through a generation AI, or it can be done without using a generation AI. For example, the generation department can input the submission timing of requirements into the generation AI, which will then determine the generation priority.

[0059] The generation department can adjust the generation order of design documents and code based on the relevance of requirements. The generation department can assess the relevance of requirements and adjust the generation order accordingly. For example, the generation department can prioritize generating requirements with high relevance. The generation department can also postpone processing requirements with low relevance. Requirement relevance can include, for example, functional relevance, technical relevance, business relevance, etc., but is not limited to these examples. The generation department can assess the functional relevance of requirements and adjust the generation order accordingly. The generation department can also assess the technical relevance and adjust the generation order accordingly. Thus, the generation department can adjust the generation order based on the relevance of requirements, achieving efficient design document and code generation. Some or all of the above processing in the generation department can be implemented through generation AI, or it can be done without using generation AI. For example, the generation department can input the relevance of requirements into the generation AI, which will then adjust the generation order.

[0060] The dialogue department can select the optimal dialogue approach by referring to the user's past dialogue history. The dialogue department can retrieve and analyze the user's past dialogue history from a database. For example, the dialogue department can select preferred dialogue styles from the user's past dialogue history. The dialogue department can also prioritize the use of terms and phrases previously used by the user. Past dialogue history may include, for example, dialogue logs, past Q&As, dialogue results, etc., but is not limited to such examples. The dialogue department can analyze the user's past dialogue history to customize the optimal dialogue approach. Thus, by referring to the user's past dialogue history, the dialogue department can provide the optimal dialogue approach. Some or all of the above processing in the dialogue department can be implemented by AI, or it may not require AI. For example, the dialogue department can input the user's past dialogue history into AI, and let AI perform the selection of the optimal dialogue approach.

[0061] The dialogue department can customize dialogue content based on the user's current project status during conversations. The dialogue department can retrieve and analyze the user's current project status from a database. For example, it can provide highly relevant dialogue content based on the user's current project status. The dialogue department can also consider the user's current project status and recommend the optimal dialogue approach. Current project status may include, but is not limited to, examples such as progress, resource status, and priority. The dialogue department can customize dialogue content based on the user's current project status, thus providing highly relevant dialogue content. Some or all of the above processing in the dialogue department can be implemented using AI, or it may not require AI. For example, the dialogue department can input the user's current project status into AI, which will then customize the dialogue content.

[0062] The dialogue unit can consider the user's geographic location information during a conversation to select the optimal dialogue method. The dialogue unit can obtain and analyze the user's geographic location information from GPS data or IP address. For example, the dialogue unit can provide highly relevant dialogue content based on the user's current location. The dialogue unit can also consider the user's geographic location information to recommend the optimal dialogue method. For example, the dialogue unit can customize dialogue content based on the user's geographic location information. Geographic location information may include, but is not limited to, examples such as GPS data, IP address, and location information services. Thus, by considering the user's geographic location information, the dialogue unit can provide highly relevant dialogue content. Some or all of the above processing in the dialogue unit can be implemented using AI, or it may not require AI. For example, the dialogue unit can input the user's geographic location information into AI, which will then select the optimal dialogue method.

[0063] The dialogue department can analyze users' social media activity during conversations and adjust the dialogue content accordingly. The dialogue department can retrieve and analyze users' social media activity from a database. For example, it can provide highly relevant dialogue content based on users' social media activity. The dialogue department can also analyze users' social media activity to recommend the optimal dialogue approach. Social media activity can include, but is not limited to, examples such as content posted, number of followers, and interaction volume. The dialogue department can customize dialogue content based on users' social media activity. Thus, by analyzing users' social media activity, the dialogue department can provide highly relevant dialogue content. Some or all of the above processing in the dialogue department can be implemented using AI, or it can be done without AI. For example, the dialogue department can input users' social media activity into AI, which will then adjust the dialogue content.

[0064] The system involved in this embodiment is not limited to the above examples. For example, various modifications can be made as described below.

[0065] The processing department can analyze a user's past project history to select the optimal input method. For example, the processing department can retrieve and analyze a user's past project history from a database. It can prioritize and recommend input methods that the user has used in the past. The processing department can also select the most efficient input method based on the user's past project history. Past project history may include project type, duration, deliverables, etc., but is not limited to these examples. Thus, by analyzing the user's past project history, the processing department can provide the optimal input method. Some or all of the above processing in the processing department can be implemented using AI, or it may not require AI. For example, the processing department can input the user's past project history into AI, which will then select the optimal input method.

[0066] The analysis department can adjust the level of detail in the requirements analysis based on the importance of the system architecture diagram. For example, the analysis department can assess the importance of the system architecture diagram and adjust the level of detail accordingly. For system architecture diagrams with high importance, a detailed requirements analysis can be performed. For system architecture diagrams with low importance, a concise requirements analysis can be performed. The importance of the system architecture diagram can include business impact, technical risks, dependencies, etc., but is not limited to these examples. The analysis department can assess the business impact of the system architecture diagram and adjust the level of detail accordingly. The analysis department can also assess technical risks and adjust the level of detail accordingly. Thus, the analysis department can adjust the level of detail in the requirements analysis based on the importance of the system architecture diagram, achieving efficient requirements analysis. Some or all of the above processing in the analysis department can be implemented using AI, or AI can be used without it. For example, the analysis department can input the importance of the system architecture diagram into AI, which will then adjust the level of detail in the analysis.

[0067] The generation department can adjust the level of detail generated based on the importance of requirements when generating design documents and code. For example, the generation department can assess the importance of requirements and adjust the level of detail accordingly. For requirements with high importance, detailed design documents and code can be generated. For requirements with low importance, concise design documents and code can be generated. The importance of requirements can include business impact, technical risks, dependencies, etc., but is not limited to these examples. The generation department can assess the business impact of requirements and adjust the level of detail accordingly. The generation department can also assess technical risks and adjust the level of detail accordingly. Thus, the generation department can adjust the level of detail based on the importance of requirements, achieving efficient generation of design documents and code. Some or all of the above processing in the generation department can be achieved through generation AI, or it can be done without using generation AI. For example, the generation department can input the importance of requirements into the generation AI, which will then adjust the level of detail.

[0068] The dialogue department can refer to a user's past dialogue history to select the optimal dialogue approach during a conversation. For example, the dialogue department can retrieve and analyze a user's past dialogue history from a database. It can select preferred dialogue styles from this history. The dialogue department can also prioritize the use of terms and phrases previously used by the user. Past dialogue history can include dialogue logs, past Q&As, dialogue results, etc., but is not limited to these examples. The dialogue department can analyze a user's past dialogue history to customize the optimal dialogue approach. Thus, by referring to a user's past dialogue history, the dialogue department can provide the optimal dialogue approach. Some or all of the above processing in the dialogue department can be implemented using AI, or it can be done without AI. For example, the dialogue department can input the user's past dialogue history into AI, which can then select the optimal dialogue approach.

[0069] The receiving department can consider the user's geographic location information when inputting system configuration diagrams, prioritizing diagrams with high relevance. For example, the receiving department can obtain and analyze the user's geographic location information from GPS data or IP address. Based on the user's current location, highly relevant system configuration diagrams can be prioritized. The receiving department can also consider the user's geographic location information to recommend the optimal system configuration diagram. For example, the receiving department can customize the input content based on the user's geographic location information. Geographic location information may include GPS data, IP address, location information services, etc., but is not limited to these examples. Thus, by considering the user's geographic location information, the receiving department can provide highly relevant system configuration diagrams. Some or all of the above processing in the receiving department can be implemented using AI, or AI may not be used. For example, the receiving department can input the user's geographic location information into AI, which will then select highly relevant system configuration diagrams.

[0070] The dialogue department can analyze users' social media activity during conversations and adjust the content accordingly. For example, it can retrieve and analyze users' social media activity from a database. Based on this activity, it can provide highly relevant dialogue content. The department can also analyze this activity to recommend optimal conversational approaches. Social media activity can include, but is not limited to, content posts, number of followers, and engagement. The department can customize dialogue content based on users' social media activity. Thus, by analyzing users' social media activity, the department can provide highly relevant dialogue content. Some or all of the above processing in the dialogue department can be implemented using AI, or it can be done without AI. For example, the department can input users' social media activity into AI, which can then adjust the dialogue content.

[0071] The following is a brief description of the processing flow of Implementation Method 1.

[0072] Step 1: The receiving department inputs the system configuration diagram. The system configuration diagram includes hardware configuration diagram, software configuration diagram, network configuration diagram, etc. The receiving department can accept system configuration diagrams in image file, PDF format, and other digital formats.

[0073] Step 2: The Analysis Department analyzes the requirements based on the system architecture diagram input by the Receiving Department. Requirements analysis includes functional requirements, non-functional requirements, and constraints. The Analysis Department analyzes each element of the system architecture diagram and extracts its respective requirements. It can also identify particularly important elements in the system architecture diagram and analyze the requirements in detail accordingly.

[0074] Step 3: The generation department generates design documents and code based on the requirements analyzed by the analysis department. The design documents are generated using a design document format or template. A suitable programming language is selected for code generation. The generation department can also input the requirements analysis results into the generation AI, which will then execute the generation of the design documents and code.

[0075] Implementation Method 2 The cloud infrastructure design and construction system described in this invention aims to reduce the time required for cloud infrastructure design and construction while improving quality. This system supports multimodal operation and utilizes image-based generative AI to solve the problems of high workload and unstable quality in traditional cloud infrastructure projects. First, a system configuration diagram is created and input as an image into the generative AI. Then, a dialogue is conducted with the AI ​​to obtain detailed information related to the requirements. Design document formats are prepared in advance. After the dialogue, various design documents and the code required for construction are generated based on the system configuration diagram and the dialogue content. This reduces the original workload of several person-months to approximately one person-day. Even with limited dialogue, more standardized design documents are generated. The output design documents can be revised and reused as input, allowing for flexible adjustments. Furthermore, the construction of the cloud infrastructure generates Terraform code. This reduces unit testing to zero, significantly decreasing workload. The system supports multi-cloud environments, reading the cloud platforms used from the system configuration diagram, selecting appropriate formats, and combining the dialogue content to write design documents, thus achieving further time reduction. Therefore, cloud infrastructure design and construction systems can significantly reduce the time required for cloud infrastructure design and construction while improving quality.

[0076] The cloud infrastructure design and construction system described in this embodiment includes a receiving unit, a parsing unit, and a generation unit. The receiving unit is used to input a system configuration diagram. The system configuration diagram may include, for example, hardware configuration diagrams, software configuration diagrams, network configuration diagrams, etc., but is not limited to these examples. The receiving unit may receive the system configuration diagram as an image file. In addition, the receiving unit may also receive system configuration diagrams in PDF format or other digital formats. The parsing unit parses requirements based on the system configuration diagram input by the receiving unit. Requirement parsing may include, for example, functional requirements, non-functional requirements, constraints, etc., but is not limited to these examples. The parsing unit can parse each element of the system configuration diagram and extract its respective requirements. The parsing unit can also identify particularly important elements in the system configuration diagram and analyze the requirements in detail accordingly. The generation unit generates design documents and code based on the requirements parsed by the parsing unit. The generation of design documents and code may include, for example, a design document format, a programming language for the code, etc., but is not limited to these examples. The generation unit can generate design documents based on design document templates. The generation unit can also generate code in a suitable programming language based on the parsed requirements. Therefore, the cloud infrastructure design and construction system can automate the entire process from inputting system configuration diagrams and requirements analysis to generating design documents and code, significantly reducing working hours. Some or all of the above processes in the generation department can be implemented using a generation AI, or they can be omitted. For example, the generation department can input the requirements analysis results into the generation AI, which will then execute the generation of design documents and code.

[0077] The receiving unit is used to input system configuration diagrams. System configuration diagrams may include, for example, hardware configuration diagrams, software configuration diagrams, network configuration diagrams, etc., but are not limited to these examples. The receiving unit can receive system configuration diagrams as image files. In addition, the receiving unit can also receive system configuration diagrams in PDF format or other digital formats. Specifically, the receiving unit has the function of automatically recognizing user-uploaded files and converting them to the appropriate format. For example, for image files, it uses OCR (Optical Character Recognition) technology to convert them into text data; for PDF files, it parses their internal structure and extracts the required information. Furthermore, the receiving unit provides a user-input interface, allowing users to manually input system configuration diagrams. Thus, the receiving unit can flexibly receive system configuration diagrams in various formats, enabling smooth data transfer to the next parsing unit. The receiving unit also has the function of checking the received system configuration diagrams. Figure 1 This system provides functions to ensure data consistency and notify users of missing or inconsistent information. As a result, the receiving department can ensure data quality in the initial stages, smoothly facilitating subsequent processing by the parsing and generation departments.

[0078] The Analysis Department analyzes requirements based on the system architecture diagram input by the Receiving Department. Requirement analysis may include, but is not limited to, functional requirements, non-functional requirements, and constraints. The Analysis Department can analyze each element of the system architecture diagram and extract its respective requirements. Specifically, the Analysis Department can analyze the role and interrelationships of each component in the system architecture diagram to determine the required functions and performance. For example, analyzing server deployment and network topology extracts requirements related to overall system performance and reliability. The Analysis Department can also identify particularly important elements in the system architecture diagram and analyze requirements in detail accordingly. For example, analyzing database deployment and redundancy methods clarifies requirements related to data consistency and availability. Furthermore, the Analysis Department can utilize AI for requirement analysis. Specifically, it uses natural language processing technology to analyze the description of the system architecture diagram and automatically extracts requirements. It can also use machine learning algorithms to learn from past project data and automatically identify similar requirements. Thus, the Analysis Department can efficiently and accurately analyze requirements and provide data to the next generation department.

[0079] The generation department generates design documents and code based on the requirements analyzed by the parsing department. The generation of design documents and code may include, but is not limited to, examples such as design document format and programming language. The generation department can generate design documents based on design document templates. Specifically, the generation department applies the requirements provided by the parsing department to a template to automatically generate a comprehensive system design document. The design document includes a system overview, detailed information on each component, their interrelationships, and data flow. The generation department can also generate code in appropriate programming languages ​​based on the parsed requirements. For example, for web applications, it can automatically generate HTML, CSS, and JavaScript code; server-side logic can generate Python or Java code. Furthermore, the generation department can utilize AI-generated design documents and code. Specifically, the requirements analysis results are input into the AI-generated design document, which then generates the design documents and code. The AI-generated design document learns from past project data and best practices, enabling it to generate optimal design documents and code. For example, it can propose optimal architecture suggestions based on the requirements and generate design documents accordingly. The AI-generated design document can also consider code quality and performance to generate optimal code. Therefore, the generation department can generate design documents and code efficiently and with high quality, significantly reducing overall system workload.

[0080] A dialogue department can be set up to facilitate conversations about the details of requirements. This dialogue department can, for example, engage in dialogue with users via a chatbot. For instance, it can automatically generate answers to user questions. The dialogue department can also utilize speech recognition technology to convert user speech into text for dialogue. For example, it can analyze user voice input in real time and generate appropriate responses. Furthermore, the dialogue department can dynamically adjust the dialogue process based on user input. For example, it can change the next question to be prompted based on user input. Thus, the dialogue department can obtain detailed requirements through dialogue with users, improving the accuracy of design documents and code. Some or all of the above processing in the dialogue department can be implemented using AI, or it can be done without AI. For example, the dialogue department can input user input into AI, which will then execute the dialogue process.

[0081] The analysis department can analyze requirements based on the system architecture diagram input by the receiving department and the dialogue results from the dialogue department. The analysis department can analyze each element of the system architecture diagram and extract its respective requirements. For example, the analysis department can identify particularly important elements in the system architecture diagram and analyze the requirements in detail accordingly. The analysis department can also analyze user requirements in detail based on the dialogue results from the dialogue department. For example, the analysis department can compare the user requirements obtained from the dialogue department with the system architecture diagram to confirm the consistency of the requirements. The analysis department can also determine the priority of requirements by combining the system architecture diagram and the dialogue results. For example, the analysis department can dynamically adjust the priority of requirements based on the importance of the system architecture diagram and the content of the dialogue results. Thus, the analysis department can improve the accuracy of requirement analysis by combining the system architecture diagram and the dialogue results. Some or all of the above processing in the analysis department can be implemented using AI, or AI can be used without it. For example, the analysis department can input the system architecture diagram and dialogue results into the AI, which will then perform the requirement analysis.

[0082] The generation department can generate design documents and code using AI. The generation department can generate design documents based on design document templates. For example, the generation department can use AI to automatically generate design documents based on the parsed requirements. The generation department can also generate code in a suitable programming language based on the parsed requirements. For example, the generation department can use AI to automatically generate requirement-based code. The AI ​​can use natural language generation technology or machine learning algorithms to generate design documents and code. For example, the AI ​​can receive requirements as input and use natural language generation technology to generate design documents. The AI ​​can also use machine learning algorithms to generate code based on requirements. Therefore, by using AI, the generation department can improve the accuracy of design document and code generation. Some or all of the above processes in the generation department can be implemented using AI, or they can be omitted. For example, the generation department can input the requirements parsing results into the AI, which will then generate the design documents and code.

[0083] The generation department supports multi-cloud environments, reading cloud types from system architecture diagrams and selecting appropriate formats. It can parse system architecture diagrams to identify cloud types. For example, it can identify cloud types based on cloud service information contained in the system architecture diagram. The generation department can also select appropriate formats based on cloud types. For example, it can select formats supporting cloud services such as AWS, Azure, and Google Cloud. Appropriate formats may include, but are not limited to, JSON, YAML, and XML. The generation department can also adjust the generation methods for design documents and code based on cloud service types. For example, when generating design documents and code supporting AWS, the generation department generates them based on AWS resource definitions and provider settings. Thus, the generation department can support multi-cloud environments and adapt to various cloud environments. Some or all of the above processing in the generation department can be implemented through generation AI, or it can be done without using generation AI. For example, the generation department can input the system architecture diagram into the generation AI, which will then perform cloud type identification and format selection.

[0084] The generation department can generate Terraform code. It can generate code based on Terraform resource definitions. For example, the generation department can use generation AI to automatically generate Terraform code based on the parsed requirements. Terraform code may include, but is not limited to, resource definitions, provider settings, etc. The generation department can use generation AI to generate requirement-based Terraform resource definitions. The generation department can also generate Terraform code based on provider settings. For example, the generation department can generate Terraform code based on provider settings that support cloud services such as AWS, Azure, and Google Cloud. Thus, the generation department automates the construction of cloud infrastructure by generating Terraform code. Some or all of the above processes in the generation department can be implemented using generation AI, or they can be performed without it. For example, the generation department can input the requirement parsing results into generation AI, which will then execute the generation of Terraform code.

[0085] The receiving unit can infer the user's emotions and adjust the input timing of the system's composition graph based on the inferred user emotions. For example, the receiving unit can capture the user's facial expressions using a camera and use emotion inference algorithms to infer emotions. For instance, the receiving unit can calculate an emotion score based on facial expression changes and adjust the input timing. The receiving unit can also record the user's voice and use speech analysis technology to infer emotions. For instance, the receiving unit can analyze the tone and speed of the voice, calculate an emotion score, and adjust the input timing. The receiving unit can also collect the user's biometric data (heart rate or skin conductance) using sensors and use emotion inference algorithms to infer emotions. For instance, the receiving unit can calculate an emotion score based on heart rate changes and adjust the input timing. Thus, the receiving unit can adjust the input timing based on the user's emotions, reducing user stress. Emotion inference can be achieved through emotion engines or generative AI, etc. Generative AI can be text-based AI (such as LLM) or multimodal AI, but is not limited to these examples. Some or all of the above processing in the receiving unit can be implemented using AI, or AI can be omitted. For example, the receiving unit can input user image data captured by a camera into generative AI, which will then perform the inference of the user's emotions.

[0086] The receiving department can analyze a user's past project history when inputting the system structure diagram to select the optimal input method. The receiving department can retrieve and analyze the user's past project history from a database. For example, the receiving department can prioritize recommending input methods previously used by the user. The receiving department can also select the most efficient input method based on the user's past project history. For example, the receiving department can analyze the user's past project history to customize the input method. Past project history may include, but is not limited to, examples such as project type, duration, and deliverables. Therefore, by analyzing the user's past project history, the receiving department can provide the optimal input method. Some or all of the above processing in the receiving department can be implemented using AI, or it may not require AI. For example, the receiving department can input the user's past project history into AI, which will then select the optimal input method.

[0087] The receiving department can filter system architecture diagrams based on the user's current project status and areas of interest when inputting them. The receiving department can retrieve and analyze the user's current project status from a database. For example, the receiving department can prioritize inputting highly relevant system architecture diagrams based on the user's current project status. The receiving department can also recommend the optimal system architecture diagram based on the user's areas of interest. For example, the receiving department can customize the input content by combining the user's current project status and areas of interest. Current project status may include, for example, progress, resource status, priority, etc., but is not limited to these examples. Thus, the receiving department can provide highly relevant system architecture diagrams based on the user's current project status and areas of interest. Some or all of the above processing in the receiving department can be implemented using AI, or it may not require AI. For example, the receiving department can input the user's current project status and areas of interest into AI, which will then perform the filtering.

[0088] The receiving department can infer the user's emotions and determine the priority of the input system composition diagram based on the inferred emotions. For example, the receiving department can capture the user's facial expressions using a camera and use emotion inference algorithms to infer emotions. For instance, the receiving department can calculate an emotion score based on facial expression changes to determine the priority of the system composition diagram. The receiving department can also record the user's voice and use speech analysis technology to infer emotions. For instance, the receiving department can analyze the tone and speed of the voice, calculate an emotion score, and determine the priority of the system composition diagram. The receiving department can also collect the user's biometric data (heart rate or skin conductance) through sensors and use emotion inference algorithms to infer emotions. For instance, the receiving department can calculate an emotion score based on heart rate changes to determine the priority of the system composition diagram. Thus, the receiving department can determine the priority of the system composition diagram based on the user's emotions, thereby responding to user needs. Emotion inference can be achieved through emotion engines or generative AI, etc. Generative AI can be text-based AI (such as LLM) or multimodal AI, but is not limited to these examples. Some or all of the above processing in the receiving department can be implemented using AI, or AI may not be used. For example, the receiving department can input user image data captured by the camera into the AI ​​generator, which will then perform inferences about the user's emotions.

[0089] The receiving department can consider the user's geographic location information when inputting system configuration diagrams, prioritizing diagrams with high relevance. The receiving department can obtain and analyze the user's geographic location information from GPS data or IP address. For example, the receiving department can prioritize system configuration diagrams with high relevance based on the user's current location. The receiving department can also consider the user's geographic location information to recommend the optimal system configuration diagram. For example, the receiving department can customize the input content based on the user's geographic location information. Geographic location information may include, but is not limited to, examples such as GPS data, IP address, and location information services. Thus, by considering the user's geographic location information, the receiving department can provide highly relevant system configuration diagrams. Some or all of the above processing in the receiving department can be implemented using AI, or it may not require AI. For example, the receiving department can input the user's geographic location information into AI, which will then select highly relevant system configuration diagrams.

[0090] The receiving department can analyze a user's social media activity when inputting a system structure diagram, and input relevant diagrams accordingly. The receiving department can retrieve and analyze user social media activity from a database. For example, based on user social media activity, the receiving department can prioritize inputting highly relevant system structure diagrams. The receiving department can also analyze user social media activity to recommend the optimal system structure diagram. For example, the receiving department can customize input content based on user social media activity. Social media activity may include, but is not limited to, examples such as posted content, number of followers, and interaction volume. Thus, by analyzing user social media activity, the receiving department can provide highly relevant system structure diagrams. Some or all of the above processing in the receiving department can be implemented using AI, or it may not require AI. For example, the receiving department can input user social media activity into AI, which will then select relevant system structure diagrams.

[0091] The analysis unit can infer a user's emotions and adjust the demand analysis method based on the inferred emotions. For example, the analysis unit can capture a user's facial expressions using a camera and use emotion inference algorithms to infer emotions. For instance, the analysis unit can calculate an emotion score based on facial expression changes and adjust the demand analysis method accordingly. The analysis unit can also record the user's voice and use voice analysis technology to infer emotions. For instance, the analysis unit can analyze the tone and speed of the voice, calculate an emotion score, and adjust the demand analysis method accordingly. The analysis unit can also collect user biometric data (heart rate or skin conductance) using sensors and use emotion inference algorithms to infer emotions. For instance, the analysis unit can calculate an emotion score based on heart rate changes and adjust the demand analysis method accordingly. Thus, the analysis unit can adjust the demand analysis method based on the user's emotions, providing the optimal analysis method for the user. Emotion inference can be achieved through emotion engines or generative AI, etc. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the analysis unit can be implemented using AI, or AI may not be used. For example, the analysis unit can input user image data captured by the camera into the AI ​​generator, which then performs inferences about the user's emotions.

[0092] The analysis department can adjust the level of detail in the requirements analysis based on the importance of the system architecture diagram. The analysis department can assess the importance of the system architecture diagram and adjust the level of detail accordingly. For example, the analysis department can perform detailed requirements analysis on system architecture diagrams with high importance. The analysis department can also perform brief requirements analysis on system architecture diagrams with low importance. The importance of the system architecture diagram can include, for example, business impact, technical risks, dependencies, etc., but is not limited to these examples. The analysis department can assess the business impact of the system architecture diagram and adjust the level of detail accordingly. The analysis department can also assess technical risks and adjust the level of detail accordingly. Therefore, the analysis department can adjust the level of detail in the requirements analysis based on the importance of the system architecture diagram, achieving efficient requirements analysis. Some or all of the above processing in the analysis department can be implemented using AI, or AI can be used without it. For example, the analysis department can input the importance of the system architecture diagram into AI, and AI can perform the adjustment of the level of detail in the analysis.

[0093] The parsing unit can apply different parsing algorithms based on the category of the system architecture diagram during requirements parsing. The parsing unit can identify the category of the system architecture diagram and apply the corresponding parsing algorithm. For example, the parsing unit can apply a dedicated parsing algorithm to network-related system architecture diagrams. It can also apply a dedicated parsing algorithm to database-related system architecture diagrams. The categories of system architecture diagrams may include, for example, application architecture diagrams, infrastructure architecture diagrams, security architecture diagrams, etc., but are not limited to these examples. The parsing unit can apply algorithms for parsing application requirements to application architecture diagrams. It can also apply algorithms for parsing infrastructure requirements to infrastructure architecture diagrams. Thus, the parsing unit can apply parsing algorithms based on the category of the system architecture diagram, improving parsing accuracy. Some or all of the above processing in the parsing unit can be implemented using AI, or AI can be used without it. For example, the parsing unit can input the category of the system architecture diagram into the AI, which will then execute the application of the parsing algorithm.

[0094] The analysis unit can infer a user's emotions and determine the priority of request analysis based on these inferred emotions. For example, the analysis unit can capture a user's facial expressions using a camera and use emotion inference algorithms to infer emotions. For instance, the analysis unit can calculate an emotion score based on facial expression changes to determine the priority of request analysis. The analysis unit can also record a user's voice and use voice analysis technology to infer emotions. For instance, the analysis unit can analyze the tone and speed of the voice, calculate an emotion score, and determine the priority of request analysis. The analysis unit can also collect user biometric data (heart rate or skin conductance) using sensors and use emotion inference algorithms to infer emotions. For instance, the analysis unit can calculate an emotion score based on heart rate changes to determine the priority of request analysis. Thus, the analysis unit can determine the priority of request analysis based on the user's emotions, thereby responding to user requests. Emotion inference can be achieved through emotion engines or generative AI, etc. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the analysis unit can be implemented using AI, or AI may not be used. For example, the analysis unit can input user image data captured by the camera into the AI ​​generator, which then performs inferences about the user's emotions.

[0095] The analysis department can determine the analysis priority based on the submission timing of the system architecture diagram during requirements analysis. The analysis department can evaluate the submission timing of the system architecture diagram and determine the analysis priority accordingly. For example, the analysis department can prioritize analyzing system architecture diagrams with more recent submission times. The analysis department can also postpone processing system architecture diagrams with more distant submission times. Submission times can include, for example, submission deadlines, project phases, schedules, etc., but are not limited to these examples. The analysis department can evaluate the submission deadline of the system architecture diagram and determine the analysis priority accordingly. The analysis department can also evaluate the project phase and determine the analysis priority accordingly. Therefore, the analysis department can determine the analysis priority based on the submission timing of the system architecture diagram, achieving efficient requirements analysis. Some or all of the above processing in the analysis department can be implemented using AI, or AI can be used without it. For example, the analysis department can input the submission timing of the system architecture diagram into the AI, which will then determine the analysis priority.

[0096] The analysis department can adjust the analysis order based on the relevance of the system architecture diagram during requirements analysis. The analysis department can evaluate the relevance of the system architecture diagram and adjust the analysis order accordingly. For example, the analysis department can prioritize analyzing system architecture diagrams with high relevance. The analysis department can also postpone processing system architecture diagrams with low relevance. The relevance of the system architecture diagram can include, for example, functional relevance, technical relevance, and business relevance, but is not limited to these examples. The analysis department can evaluate the functional relevance of the system architecture diagram and adjust the analysis order accordingly. The analysis department can also evaluate the technical relevance and adjust the analysis order accordingly. Therefore, the analysis department can adjust the analysis order based on the relevance of the system architecture diagram, achieving efficient requirements analysis. Some or all of the above processing in the analysis department can be implemented using AI, or AI can be used without it. For example, the analysis department can input the relevance of the system architecture diagram into the AI, which will then adjust the analysis order.

[0097] The generation department can infer the user's emotions and adjust the generation methods of design documents and code based on the inferred user emotions. For example, the generation department can capture the user's facial expressions using a camera and use emotion inference algorithms to infer emotions. For instance, the generation department can calculate an emotion score based on facial expression changes and adjust the generation methods of design documents and code. The generation department can also record the user's voice and use speech analysis technology to infer emotions. For instance, the generation department can analyze the tone and speed of the voice, calculate an emotion score, and adjust the generation methods of design documents and code. The generation department can also collect the user's biological data (heart rate or skin conductance) through sensors and use emotion inference algorithms to infer emotions. For instance, the generation department can calculate an emotion score based on heart rate changes and adjust the generation methods of design documents and code. Thus, the generation department can adjust the generation methods of design documents and code based on the user's emotions, providing the optimal generation method for the user. Emotion inference can be achieved through emotion inference functions such as emotion engines or generative AI. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation department can be implemented using AI, or AI may not be used. For example, the generation unit can input user image data captured by the camera into the generation AI, which will then perform the inference of the user's emotions.

[0098] The generation department can adjust the level of detail generated based on the importance of requirements when generating design documents and code. The generation department can assess the importance of requirements and adjust the level of detail accordingly. For example, the generation department can generate detailed design documents and code for requirements with high importance. It can also generate concise design documents and code for requirements with low importance. The importance of requirements can include, but is not limited to, business impact, technical risks, dependencies, etc. The generation department can assess the business impact of requirements and adjust the level of detail accordingly. It can also assess technical risks and adjust the level of detail accordingly. Thus, the generation department can adjust the level of detail based on the importance of requirements, achieving efficient generation of design documents and code. Some or all of the above processing in the generation department can be achieved through generation AI, or it can be done without using generation AI. For example, the generation department can input the importance of requirements into the generation AI, which will then adjust the level of detail.

[0099] The generation department can apply different generation algorithms based on the category of requirements when generating design documents and code. The generation department can identify the category of requirements and apply the corresponding generation algorithm. For example, the generation department can apply a dedicated generation algorithm for network-related requirements. It can also apply a dedicated generation algorithm for database-related requirements. Requirement categories may include, for example, application-related, infrastructure-related, security-related, etc., but are not limited to these examples. The generation department can apply algorithms for generating application design documents and code to application-related requirements. It can also apply algorithms for generating infrastructure design documents and code to infrastructure-related requirements. Thus, the generation department can apply generation algorithms based on the category of requirements, improving generation accuracy. Some or all of the above processing in the generation department can be implemented through generation AI, or it may not be necessary to use generation AI. For example, the generation department can input the category of requirements into the generation AI, which will then execute the application of the generation algorithm.

[0100] The generation department can infer the user's emotions and adjust the generation order of design documents and code based on the inferred emotions. For example, the generation department can capture the user's facial expressions using a camera and use emotion inference algorithms to infer emotions. For instance, the generation department can calculate an emotion score based on facial expression changes and adjust the generation order of design documents and code. The generation department can also record the user's voice and use speech analysis technology to infer emotions. For instance, the generation department can analyze the tone and speed of the voice, calculate an emotion score, and adjust the generation order of design documents and code. The generation department can also collect the user's biometric data (heart rate or skin conductance) using sensors and use emotion inference algorithms to infer emotions. For instance, the generation department can calculate an emotion score based on heart rate changes and adjust the generation order of design documents and code. Thus, the generation department can adjust the generation order of design documents and code based on the user's emotions to respond to user needs. Emotion inference can be achieved through emotion engines or generative AI, etc. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation department can be achieved through generative AI, or AI can be omitted. For example, the generation unit can input user image data captured by the camera into the generation AI, which will then perform the inference of the user's emotions.

[0101] The generation department can prioritize the generation of design documents and code based on the timing of requirement submissions. The generation department can assess the submission timing of requirements and determine the generation priority accordingly. For example, the generation department can prioritize generating requirements with more recent submission times. The generation department can also postpone processing requirements with more distant submission times. Submission times can include, for example, submission deadlines, project phases, schedules, etc., but are not limited to these examples. The generation department can assess the submission deadlines of requirements and determine the generation priority accordingly. The generation department can also assess the project phases and determine the generation priority accordingly. Thus, the generation department can prioritize the generation based on the submission timing of requirements, achieving efficient design document and code generation. Some or all of the above processing in the generation department can be implemented through a generation AI, or it can be done without using a generation AI. For example, the generation department can input the submission timing of requirements into the generation AI, which will then determine the generation priority.

[0102] The generation department can adjust the generation order of design documents and code based on the relevance of requirements. The generation department can assess the relevance of requirements and adjust the generation order accordingly. For example, the generation department can prioritize generating requirements with high relevance. The generation department can also postpone processing requirements with low relevance. Requirement relevance can include, for example, functional relevance, technical relevance, business relevance, etc., but is not limited to these examples. The generation department can assess the functional relevance of requirements and adjust the generation order accordingly. The generation department can also assess the technical relevance and adjust the generation order accordingly. Thus, the generation department can adjust the generation order based on the relevance of requirements, achieving efficient design document and code generation. Some or all of the above processing in the generation department can be implemented through generation AI, or it can be done without using generation AI. For example, the generation department can input the relevance of requirements into the generation AI, which will then adjust the generation order.

[0103] The dialogue unit can infer the user's emotions and adjust the dialogue based on these inferred emotions. For example, the dialogue unit can capture the user's facial expressions using a camera and use emotion inference algorithms to infer emotions. For instance, the dialogue unit can calculate an emotion score based on facial expression changes and adjust the dialogue accordingly. The dialogue unit can also record the user's voice and use speech analysis technology to infer emotions. For instance, the dialogue unit can analyze the tone and speed of the voice, calculate an emotion score, and adjust the dialogue accordingly. The dialogue unit can also collect the user's biometric data (heart rate or skin conductance) using sensors and use emotion inference algorithms to infer emotions. For instance, the dialogue unit can calculate an emotion score based on heart rate changes and adjust the dialogue accordingly. Thus, the dialogue unit can adjust the dialogue based on the user's emotions, providing the optimal dialogue for the user. Emotion inference can be achieved through emotion engines or generative AI, etc. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the dialogue unit can be implemented using AI, or AI may not be used. For example, the dialogue unit can input user image data captured by the camera into the AI ​​generator, which will then perform inferences about the user's emotions.

[0104] The dialogue department can select the optimal dialogue approach by referring to the user's past dialogue history. The dialogue department can retrieve and analyze the user's past dialogue history from a database. For example, the dialogue department can select preferred dialogue styles from the user's past dialogue history. The dialogue department can also prioritize the use of terms and phrases previously used by the user. Past dialogue history may include, for example, dialogue logs, past Q&As, dialogue results, etc., but is not limited to such examples. The dialogue department can analyze the user's past dialogue history to customize the optimal dialogue approach. Thus, by referring to the user's past dialogue history, the dialogue department can provide the optimal dialogue approach. Some or all of the above processing in the dialogue department can be implemented by AI, or it may not require AI. For example, the dialogue department can input the user's past dialogue history into AI, and let AI perform the selection of the optimal dialogue approach.

[0105] The dialogue department can customize dialogue content based on the user's current project status during conversations. The dialogue department can retrieve and analyze the user's current project status from a database. For example, it can provide highly relevant dialogue content based on the user's current project status. The dialogue department can also consider the user's current project status and recommend the optimal dialogue approach. Current project status may include, but is not limited to, examples such as progress, resource status, and priority. The dialogue department can customize dialogue content based on the user's current project status, thus providing highly relevant dialogue content. Some or all of the above processing in the dialogue department can be implemented using AI, or it may not require AI. For example, the dialogue department can input the user's current project status into AI, which will then customize the dialogue content.

[0106] The dialogue unit can infer a user's emotions and determine the priority of the conversation based on the inferred emotions. For example, the dialogue unit can capture the user's facial expressions through a camera and use emotion inference algorithms to infer emotions. For instance, the dialogue unit can calculate an emotion score based on facial expression changes to determine the conversation priority. The dialogue unit can also record the user's voice and use speech analysis technology to infer emotions. For instance, the dialogue unit can analyze the tone and speed of the voice to calculate an emotion score and determine the conversation priority. The dialogue unit can also collect the user's biometric data (heart rate or skin conductance) through sensors and use emotion inference algorithms to infer emotions. For instance, the dialogue unit can calculate an emotion score based on heart rate changes to determine the conversation priority. Thus, the dialogue unit can determine the priority of the conversation based on the user's emotions, thereby responding to the user's needs. Emotion inference can be achieved through emotion engines or generative AI, etc. Generative AI can be text-based AI (such as LLM) or multimodal AI, but is not limited to these examples. Some or all of the above processing in the dialogue unit can be implemented using AI, or AI can be omitted. For example, the dialogue unit can input user image data captured by a camera into the generative AI, which will then perform the inference of the user's emotions.

[0107] The dialogue unit can consider the user's geographic location information during a conversation to select the optimal dialogue method. The dialogue unit can obtain and analyze the user's geographic location information from GPS data or IP address. For example, the dialogue unit can provide highly relevant dialogue content based on the user's current location. The dialogue unit can also consider the user's geographic location information to recommend the optimal dialogue method. For example, the dialogue unit can customize dialogue content based on the user's geographic location information. Geographic location information may include, but is not limited to, examples such as GPS data, IP address, and location information services. Thus, by considering the user's geographic location information, the dialogue unit can provide highly relevant dialogue content. Some or all of the above processing in the dialogue unit can be implemented using AI, or it may not require AI. For example, the dialogue unit can input the user's geographic location information into AI, which will then select the optimal dialogue method.

[0108] The dialogue department can analyze users' social media activity during conversations and adjust the dialogue content accordingly. The dialogue department can retrieve and analyze users' social media activity from a database. For example, it can provide highly relevant dialogue content based on users' social media activity. The dialogue department can also analyze users' social media activity to recommend the optimal dialogue approach. Social media activity can include, but is not limited to, examples such as content posted, number of followers, and interaction volume. The dialogue department can customize dialogue content based on users' social media activity. Thus, by analyzing users' social media activity, the dialogue department can provide highly relevant dialogue content. Some or all of the above processing in the dialogue department can be implemented using AI, or it can be done without AI. For example, the dialogue department can input users' social media activity into AI, which will then adjust the dialogue content.

[0109] The system involved in this embodiment is not limited to the above examples. For example, various modifications can be made as described below.

[0110] The processing department can analyze a user's past project history to select the optimal input method. For example, the processing department can retrieve and analyze a user's past project history from a database. It can prioritize and recommend input methods that the user has used in the past. The processing department can also select the most efficient input method based on the user's past project history. Past project history may include project type, duration, deliverables, etc., but is not limited to these examples. Thus, by analyzing the user's past project history, the processing department can provide the optimal input method. Some or all of the above processing in the processing department can be implemented using AI, or it may not require AI. For example, the processing department can input the user's past project history into AI, which will then select the optimal input method.

[0111] The analysis department can adjust the level of detail in the requirements analysis based on the importance of the system architecture diagram. For example, the analysis department can assess the importance of the system architecture diagram and adjust the level of detail accordingly. For system architecture diagrams with high importance, a detailed requirements analysis can be performed. For system architecture diagrams with low importance, a concise requirements analysis can be performed. The importance of the system architecture diagram can include business impact, technical risks, dependencies, etc., but is not limited to these examples. The analysis department can assess the business impact of the system architecture diagram and adjust the level of detail accordingly. The analysis department can also assess technical risks and adjust the level of detail accordingly. Thus, the analysis department can adjust the level of detail in the requirements analysis based on the importance of the system architecture diagram, achieving efficient requirements analysis. Some or all of the above processing in the analysis department can be implemented using AI, or AI can be used without it. For example, the analysis department can input the importance of the system architecture diagram into AI, which will then adjust the level of detail in the analysis.

[0112] The generation department can adjust the level of detail generated based on the importance of requirements when generating design documents and code. For example, the generation department can assess the importance of requirements and adjust the level of detail accordingly. For requirements with high importance, detailed design documents and code can be generated. For requirements with low importance, concise design documents and code can be generated. The importance of requirements can include business impact, technical risks, dependencies, etc., but is not limited to these examples. The generation department can assess the business impact of requirements and adjust the level of detail accordingly. The generation department can also assess technical risks and adjust the level of detail accordingly. Thus, the generation department can adjust the level of detail based on the importance of requirements, achieving efficient generation of design documents and code. Some or all of the above processing in the generation department can be achieved through generation AI, or it can be done without using generation AI. For example, the generation department can input the importance of requirements into the generation AI, which will then adjust the level of detail.

[0113] The dialogue department can refer to a user's past dialogue history to select the optimal dialogue approach during a conversation. For example, the dialogue department can retrieve and analyze a user's past dialogue history from a database. It can select preferred dialogue styles from this history. The dialogue department can also prioritize the use of terms and phrases previously used by the user. Past dialogue history can include dialogue logs, past Q&As, dialogue results, etc., but is not limited to these examples. The dialogue department can analyze a user's past dialogue history to customize the optimal dialogue approach. Thus, by referring to a user's past dialogue history, the dialogue department can provide the optimal dialogue approach. Some or all of the above processing in the dialogue department can be implemented using AI, or it can be done without AI. For example, the dialogue department can input the user's past dialogue history into AI, which can then select the optimal dialogue approach.

[0114] The receiving department can infer a user's emotions and adjust the input timing of the system's structure graph based on the inferred user emotions. For example, the receiving department can capture the user's facial expressions through a camera and use an emotion inference algorithm to infer emotions. An emotion score can be calculated based on changes in facial expressions, and the input timing can be adjusted accordingly. The receiving department can also record the user's voice and use speech analysis technology to infer emotions. The tone and speed of the voice can be analyzed to calculate an emotion score and adjust the input timing. The receiving department can also collect the user's biometric data (heart rate or skin conductance) through sensors and use an emotion inference algorithm to infer emotions. An emotion score can be calculated based on changes in heart rate, and the input timing can be adjusted accordingly. Thus, the receiving department can adjust the input timing based on the user's emotions, reducing user stress. Emotion inference is achieved through emotion inference functions such as emotion engines or generative AI. Generative AI can be text-based AI (such as LLM) or multimodal AI, but is not limited to these examples. Some or all of the above processing in the receiving department can be implemented using AI, or AI can be omitted. For example, the receiving department can input user image data captured by a camera into the generative AI, which will then perform the inference of the user's emotions.

[0115] The analysis unit can infer a user's emotions and adjust the demand analysis method based on the inferred emotions. For example, the analysis unit can capture a user's facial expressions through a camera and use an emotion inference algorithm to infer emotions. An emotion score can be calculated based on facial expression changes, and the demand analysis method can be adjusted accordingly. The analysis unit can also record a user's voice and use voice analysis technology to infer emotions. The tone and speed of the voice can be analyzed, an emotion score can be calculated, and the demand analysis method can be adjusted accordingly. The analysis unit can also collect user biometric data (heart rate or skin conductance) through sensors and use an emotion inference algorithm to infer emotions. An emotion score can be calculated based on heart rate changes, and the demand analysis method can be adjusted accordingly. Thus, the analysis unit can adjust the demand analysis method based on the user's emotions, providing the optimal analysis method for the user. Emotion inference is achieved through emotion inference functions such as emotion engines or generative AI. Generative AI can be text-based AI (such as LLM) or multimodal AI, but is not limited to these examples. Some or all of the above processing in the analysis unit can be implemented using AI, or AI can be omitted. For example, the analysis unit can input user image data captured by a camera into the generative AI, which will then perform the inference of user emotions.

[0116] The generation department can infer users' emotions and adjust the generation methods of design documents and code based on the inferred emotions. For example, the generation department can capture users' facial expressions through a camera and use emotion inference algorithms to infer emotions. Emotion scores can be calculated based on facial expression changes, and the generation methods of design documents and code can be adjusted accordingly. The generation department can also record users' voices and use speech analysis technology to infer emotions. The tone and speed of the voice can be analyzed to calculate emotion scores, and the generation methods of design documents and code can be adjusted accordingly. The generation department can also collect users' biometric data (heart rate or skin conductance) through sensors and use emotion inference algorithms to infer emotions. Emotion scores can be calculated based on heart rate changes, and the generation methods of design documents and code can be adjusted accordingly. Thus, the generation department can adjust the generation methods of design documents and code based on users' emotions, providing the optimal generation method for users. Emotion inference is achieved through emotion inference functions such as emotion engines or generative AI. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation department can be implemented using AI, or AI may not be used. For example, the generation unit can input user image data captured by the camera into the generation AI, which will then perform the inference of the user's emotions.

[0117] The dialogue unit can infer a user's emotions and adjust the dialogue based on these inferred emotions. For example, the dialogue unit can capture a user's facial expressions using a camera and use an emotion inference algorithm to infer emotions. An emotion score can be calculated based on facial expression changes, and the dialogue can be adjusted accordingly. The dialogue unit can also record a user's voice and use speech analysis technology to infer emotions. The tone and speed of the voice can be analyzed to calculate an emotion score and adjust the dialogue accordingly. The dialogue unit can also collect user biometric data (heart rate or skin conductance) using sensors and use an emotion inference algorithm to infer emotions. An emotion score can be calculated based on heart rate changes, and the dialogue can be adjusted accordingly. Thus, the dialogue unit can adjust the dialogue based on the user's emotions, providing the optimal dialogue for the user. Emotion inference is achieved through emotion engines or generative AI, etc. Generative AI can be text-based AI (such as LLM) or multimodal AI, but is not limited to these examples. Some or all of the above processing in the dialogue unit can be implemented using AI, or AI can be omitted. For example, the dialogue unit can input user image data captured by a camera into the generative AI, which will then perform the inference of user emotions.

[0118] The receiving department can consider the user's geographic location information when inputting system configuration diagrams, prioritizing diagrams with high relevance. For example, the receiving department can obtain and analyze the user's geographic location information from GPS data or IP address. Based on the user's current location, highly relevant system configuration diagrams can be prioritized. The receiving department can also consider the user's geographic location information to recommend the optimal system configuration diagram. For example, the receiving department can customize the input content based on the user's geographic location information. Geographic location information may include GPS data, IP address, location information services, etc., but is not limited to these examples. Thus, by considering the user's geographic location information, the receiving department can provide highly relevant system configuration diagrams. Some or all of the above processing in the receiving department can be implemented using AI, or AI may not be used. For example, the receiving department can input the user's geographic location information into AI, which will then select highly relevant system configuration diagrams.

[0119] The dialogue department can analyze users' social media activity during conversations and adjust the content accordingly. For example, it can retrieve and analyze users' social media activity from a database. Based on this activity, it can provide highly relevant dialogue content. The department can also analyze this activity to recommend optimal conversational approaches. Social media activity can include, but is not limited to, content posts, number of followers, and engagement. The department can customize dialogue content based on users' social media activity. Thus, by analyzing users' social media activity, the department can provide highly relevant dialogue content. Some or all of the above processing in the dialogue department can be implemented using AI, or it can be done without AI. For example, the department can input users' social media activity into AI, which can then adjust the dialogue content.

[0120] The following is a brief description of the processing flow of Implementation Method 2.

[0121] Step 1: The receiving department inputs the system configuration diagram. The system configuration diagram includes hardware configuration diagram, software configuration diagram, network configuration diagram, etc. The receiving department can accept system configuration diagrams in image file, PDF format, and other digital formats.

[0122] Step 2: The Analysis Department analyzes the requirements based on the system architecture diagram input by the Receiving Department. Requirements analysis includes functional requirements, non-functional requirements, and constraints. The Analysis Department analyzes each element of the system architecture diagram and extracts its respective requirements. It can also identify particularly important elements in the system architecture diagram and analyze the requirements in detail accordingly.

[0123] Step 3: The generation department generates design documents and code based on the requirements analyzed by the analysis department. The design documents are generated using a design document format or template. A suitable programming language is selected for code generation. The generation department can also input the requirements analysis results into the generation AI, which will then execute the generation of the design documents and code.

[0124] The specific processing unit 290 sends 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 voice representing the user's input to the result of the specific processing. The control unit 46A sends the voice data representing the user's input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0125] Data generation model 58 is what is known as generative AI (Artificial Intelligence). An example of data generation model 58 includes ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Generative AI, such as data generation model 58, is obtained by deep learning through a neural network. The data generation model 58 is input with a prompt containing instructions, and with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data of still images or data of moving images). The data generation model 58 infers the inference data based on the instructions shown in the prompt and outputs the inference result in one or more data forms such as speech 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 above-described specific processing while using the data generation model 58. The data generation model 58 can also be a fine-tuned model to output inference results from prompts without instructions; in this case, the data generation model 58 can output inference results from prompts without instructions. The data processing device 12, etc., includes multiple data generation models 58, including AI other than generative AI. AI other than generative AI includes, but is not limited to, 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. Furthermore, AI can also act as an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to this example. Moreover, processing performed by AI, including generative AI, can be replaced by rule-based processing, and vice versa.

[0126] Furthermore, the processing performed by the aforementioned data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or external devices, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or external devices.

[0127] For example, the receiving unit can input the system configuration diagram through the receiving device 38 of the smart device 14 or the communication I / F 26 of the data processing device 12. For example, the parsing unit is implemented by the specific processing unit 290 of the data processing device 12 to parse the requirements of the system configuration diagram. For example, the generation unit can generate design documents and code by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above examples and can be modified in various ways.

[0128] [Second Implementation] Figure 3 An example of the configuration of the data processing system 210 according to the second embodiment is shown.

[0129] like Figure 3 As shown, the data processing system 210 includes a data processing device 12 and smart glasses 214. One example of the data processing device 12 is a server.

[0130] 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, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN and / or LAN, etc.

[0131] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0132] Microphone 238 receives user commands by receiving the user's voice. Microphone 238 captures the user's voice, converts the captured sound into speech data, and outputs it to processor 46. Speaker 240 outputs sound according to commands from processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, used to capture the user's surroundings (e.g., the shooting range defined by an angle of view equivalent to the field of vision of an average healthy person).

[0134] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F 44 and 26 is performed in a secure state.

[0135] Figure 4 An example of the main functions of the data processing device 12 and the smart glasses 214 is shown. Figure 4 As shown, in the data processing device 12, specific processing is performed by the processor 28. The memory 32 stores a specific processing program 56.

[0136] The processor 28 reads a specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0137] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0138] In the smart glasses 214, specific processing is performed by the processor 46. A specific processing program 60 is stored in the memory 50. The processor 46 reads the specific processing program 60 from the memory 50 and executes the read specific processing program 60 on the RAM 48. Specific processing is implemented by the processor 46 operating as a control unit 46A based on the specific processing program 60 executed on the RAM 48. Furthermore, the smart glasses 214 may also have the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and use these models to perform the same processing as the specific processing unit 290.

[0139] 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 the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. In addition, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.).

[0140] The specific processing unit 290 sends 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 voice input representing the user's input to the specific processing result. The control unit 46A sends the voice data representing the user's input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0141] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 includes generative AIs 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 a prompt containing instructions, and also with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data of still images or data of moving images). The data generation model 58 infers the inference data based on the instructions shown in the prompt and outputs the inference result in one or more data forms such as speech 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 aforementioned specific processing while using the data generation model 58. The data generation model 58 can also be a fine-tuned model to output inference results from prompts that do not contain instructions; in this case, the data generation model 58 is able to output inference results from prompts that do not contain instructions. The data processing device 12, etc., includes various data generation models 58, which include AI other than generative AI. These AIs include, 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 are capable of various processing methods, but are not limited to these examples. Furthermore, AI can also be an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to these examples. Moreover, processing performed by AI including generative AI can be replaced by rule-based processing, and vice versa.

[0142] The data processing system 210 of the second embodiment performs the same processing as the data processing system 10 of the first embodiment. The processing performed by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or external devices, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or external devices.

[0143] For example, the receiving unit can input the system configuration diagram via the microphone 238 of the smart glasses 214 or the communication I / F 26 of the data processing device 12. For example, the analysis unit, implemented by the specific processing unit 290 of the data processing device 12, analyzes the requirements of the system configuration diagram. For example, the generation unit can generate design documents and code by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above examples and can be modified in various ways.

[0144] [Third Implementation] Figure 5 An example of the configuration of the data processing system 310 according to the third embodiment is shown.

[0145] like Figure 5 As shown, the data processing system 310 includes a data processing device 12 and a head-mounted terminal 314. An example of the data processing device 12 is a server.

[0146] 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, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN and / or LAN, etc.

[0147] The head-mounted terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0148] Microphone 238 receives user commands by receiving the user's voice. Microphone 238 captures the user's voice, converts the captured sound into speech data, and outputs it to processor 46. Speaker 240 outputs sound according to commands from processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, used to capture the user's surroundings (e.g., the shooting range defined by an angle of view equivalent to the field of vision of an average healthy person).

[0150] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F 44 and 26 is performed in a secure state.

[0151] Figure 6 An example of the main functions of the data processing device 12 and the head-mounted terminal 314 is shown. Figure 6 As shown, in the data processing device 12, specific processing is performed by the processor 28. The memory 32 stores a specific processing program 56.

[0152] The processor 28 reads a specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0153] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0154] In the head-mounted terminal 314, specific processing is performed by the processor 46. A specific program 60 is stored in the memory 50. The processor 46 reads the specific program 60 from the memory 50 and executes the read specific program 60 on the RAM 48. Specific processing is implemented by the processor 46 operating as a control unit 46A based on the specific program 60 executed on the RAM 48. Furthermore, the head-mounted terminal 314 may also have the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and use these models to perform the same processing as the specific processing unit 290.

[0155] 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 the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. In addition, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.).

[0156] The specific processing unit 290 sends the result of the specific processing to the head-mounted terminal 314. In the head-mounted 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 voice representing the user's input to the specific processing result. The control unit 46A sends the voice data representing the user's input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0157] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 includes generative AIs 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 a prompt containing instructions, and also with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data of still images or data of moving images). The data generation model 58 infers the inference data based on the instructions shown in the prompt and outputs the inference result in one or more data forms such as speech 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 aforementioned specific processing while using the data generation model 58. The data generation model 58 can also be a fine-tuned model to output inference results from prompts that do not contain instructions; in this case, the data generation model 58 is able to output inference results from prompts that do not contain instructions. The data processing device 12, etc., includes various data generation models 58, which include AI other than generative AI. These AIs include, 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 are capable of various processing methods, but are not limited to these examples. Furthermore, AI can also be an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to these examples. Moreover, processing performed by AI including generative AI can be replaced by rule-based processing, and vice versa.

[0158] The data processing system 310 of the third embodiment performs the same processing as the data processing system 10 of the first embodiment. The processing performed by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the head-mounted terminal 314, but it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the head-mounted terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the head-mounted terminal 314 or external devices, and the head-mounted terminal 314 acquires or collects information required for processing from the data processing device 12 or external devices.

[0159] For example, the receiving unit can input the system configuration diagram via the microphone 238 of the head-mounted terminal 314 or the communication I / F 26 of the data processing device 12. For example, the analysis unit, implemented by the specific processing unit 290 of the data processing device 12, analyzes the requirements of the system configuration diagram. For example, the generation unit can generate design documents and code by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above examples and can be modified in various ways.

[0160] [Fourth Implementation] Figure 7 An example of the configuration of the data processing system 410 according to the fourth embodiment is shown.

[0161] like Figure 7 As shown, 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.

[0162] 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, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN and / or LAN, etc.

[0163] Robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control object 443. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, and control object 443 are also connected to the bus 52.

[0164] Microphone 238 receives user commands by receiving the user's voice. Microphone 238 captures the user's voice, converts the captured sound into speech data, and outputs it to processor 46. Speaker 240 outputs sound according to commands from processor 46.

[0165] The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, used to photograph the user's surroundings (e.g., the shooting range defined by an angle of view equivalent to the field of vision of an average healthy person).

[0166] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F 44 and 26 is performed in a secure state.

[0167] The controlled object 443 includes a display device, LEDs for the eyes, and motors for driving the arms, hands, and feet. The posture and movements of the robot 414 are controlled by controlling the motors for the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. In addition, facial expressions of the robot 414 can also be expressed by controlling the illumination state of the LEDs for the robot 414's eyes.

[0168] Figure 8 An example of the main functions of the data processing device 12 and the robot 414 is shown. For example... Figure 8 As shown, in the data processing device 12, specific processing is performed by the processor 28. The memory 32 stores a specific processing program 56.

[0169] The processor 28 reads a specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0170] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0171] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in memory 50. Processor 46 reads the specific program 60 from memory 50 and executes the read specific program 60 on RAM 48. Specific processing is achieved by processor 46 acting as control unit 46A based on the specific program 60 executed on RAM 48. Furthermore, robot 414 may also have the same data generation model and emotion-specific model as data generation model 58 and emotion-specific model 59, and use these models to perform the same processing as specific processing unit 290.

[0172] 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 the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. In addition, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.).

[0173] The specific processing unit 290 sends 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 voice representing the user's input regarding the result of the specific processing. The control unit 46A sends the voice data representing the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0174] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 includes generative AIs 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 a prompt containing instructions, and also with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data of still images or data of moving images). The data generation model 58 infers the inference data based on the instructions shown in the prompt and outputs the inference result in one or more data forms such as speech 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 aforementioned specific processing while using the data generation model 58. The data generation model 58 can also be a fine-tuned model to output inference results from prompts that do not contain instructions; in this case, the data generation model 58 is able to output inference results from prompts that do not contain instructions. The data processing device 12, etc., includes various data generation models 58, which include AI other than generative AI. These AIs include, 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 are capable of various processing methods, but are not limited to these examples. Furthermore, AI can also be an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to these examples. Moreover, processing performed by AI including generative AI can be replaced by rule-based processing, and vice versa.

[0175] The data processing system 410 of the fourth embodiment performs the same processing as the data processing system 10 of the first embodiment. The processing performed by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or external devices, and the robot 414 acquires or collects information required for processing from the data processing device 12 or external devices.

[0176] For example, the receiving unit can input the system configuration diagram via the microphone 238 of the robot 414 or the communication I / F 26 of the data processing device 12. For example, the analysis unit, implemented by the specific processing unit 290 of the data processing device 12, analyzes the requirements of the system configuration diagram. For example, the generation unit can generate design documents and code by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above examples and can be modified in various ways.

[0177] Furthermore, the emotion-specific model 59, serving as an emotion engine, can determine the user's emotion based on a specific mapping. Specifically, the emotion-specific model 59 can determine the user's emotion based on an emotion graph that serves as a specific mapping (see...). Figure 9 The system determines the user's emotions. In addition, the emotion-specific model 59 can also determine the robot's emotions in the same way, and the specific processing unit 290 can also perform specific processing using the robot's emotions.

[0178] Figure 9 This is a diagram representing an emotion map 400 that maps various emotions. In the emotion map 400, emotions are arranged radially from the center in concentric circles. The closer to the center of the concentric circles, the more primitive the emotion is. Further out on the concentric circles, emotions are arranged representing states or actions arising from mood. Emotion is a concept that includes both feelings and mental states. To the left of the concentric circles, emotions generated by reactions occurring in the brain are arranged roughly. To the right of the concentric circles, emotions guided by situational judgments are arranged roughly. Above and below the concentric circles, emotions generated by reactions occurring in the brain and guided by situational judgments are arranged roughly. Furthermore, the emotion of "pleasure" is arranged above the concentric circles, and the emotion of "unpleasantness" is arranged below. Thus, in the emotion map 400, various emotions are mapped according to the structure of emotion generation, while easily generated emotions are mapped nearby.

[0179] These emotions are distributed at the 3 o'clock position on the Emotion Chart 400, and usually fluctuate between peace and unease. In the right half of the Emotion Chart 400, because situational awareness is more dominant than internal feelings, it gives a sense of calm.

[0180] The inner side of the emotion diagram 400 represents the mind, and the outer side of the emotion diagram 400 represents actions. Therefore, the further you go to the outer side of the emotion diagram 400, the more the emotion can be seen (manifested in actions).

[0181] Here, human emotions are based on a balance of various factors such as posture and blood sugar levels. When these balances deviate from the ideal, it indicates unhappiness; when they approach the ideal, it indicates pleasure. In robots, cars, and motorcycles, emotions can also be created based on a balance of factors such as posture and remaining battery power. When these balances deviate from the ideal, it indicates unhappiness; when they approach the ideal, it indicates pleasure. Emotion maps can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Speech Emotion Recognition and Brain Physiological Signal Analysis Systems for Emotion, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). In the left half of the emotion map, emotions belonging to the "Reaction" domain, where sensation is dominant, are arranged. Furthermore, in the right half of the emotion map, emotions belonging to the "Situation" domain, where situational cognition is dominant, are arranged.

[0182] The emotion map defines two types of emotions that promote learning. One is a negative emotion located near the middle of "repentance" or "reflection" on the situation side. That is, when the robot experiences negative emotions such as "I never want to feel this way again" or "I never want to be scolded again." The other is a positive emotion located near "desire" on the response side. That is, when the robot experiences positive feelings such as "wanting more" or "wanting to know more."

[0183] The emotion-specific model 59 feeds user input into a pre-learned neural network to obtain emotion values ​​representing each emotion shown in the emotion graph 400, and determines the user's emotion. This neural network is pre-learned based on multiple learning data sets that combine user input with emotion values ​​representing each emotion shown in the emotion graph 400. Furthermore, this neural network is learned to... Figure 10 As shown in sentiment graph 900, sentiment values ​​in nearby configurations are similar to each other. Figure 10 Examples show that multiple emotions such as "peace of mind", "stability", and "reassurance" have similar emotional values.

[0184] In the above embodiments, a specific processing is described by a single computer 22, but the technology disclosed herein is not limited to this, and distributed processing by multiple computers, including computer 22, is also possible.

[0185] In the above embodiments, an example of storing a specific processing program 56 in memory 32 is illustrated, but the technology disclosed herein is not limited thereto. For example, the specific processing program 56 may also be stored in a portable computer-readable non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 performs specific processing according to the specific processing program 56.

[0186] Alternatively, the specific processing program 56 can be stored in a storage device such as a server connected to the data processing device 12 via a network 54, and the specific processing program 56 can be downloaded and installed into the computer 22 upon request from the data processing device 12.

[0187] Furthermore, it is not necessary to store the entire specific process 56 in a storage device such as a server connected to the data processing device 12 via the network 54, nor is it necessary to store the entire specific process 56 in the memory 32; a portion of the specific process 56 may also be stored.

[0188] As a hardware resource for performing specific processing, various processors can be used. For example, a CPU is a general-purpose processor that functions as a hardware resource for performing specific processing by executing software, i.e., programs. Additionally, a dedicated circuit can be listed as a processor; it is a processor with a circuit structure specifically designed for performing specific processing, such as a FPGA (Field-Programmable Gate Array), PLD (Programmable Logic Device), or ASIC (Application Specific Integrated Circuit). Every processor has built-in or connected memory, and every processor executes specific processing by using that memory.

[0189] The hardware resources for performing a specific process can consist of one of these various processors, or a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Furthermore, the hardware resources for performing a specific process can also be a single processor.

[0190] As an example of a single processor, the first type consists of a combination of one or more CPUs and software, which functions as a hardware resource to perform specific processing. The second type uses a processor, such as a System-on-a-chip (SoC), which implements the entire system functionality, including multiple hardware resources performing specific processing, using a single IC chip. In this case, the specific processing is implemented using one or more of the aforementioned processors that serve as hardware resources.

[0191] Furthermore, as the hardware architecture of these various processors, more specifically, circuits combining semiconductor elements and other circuit components can be used. Moreover, the specific process described above is merely an example. Therefore, it goes without saying that, without departing from the main point, unnecessary steps can be removed, new steps can be added, or the processing order can be changed.

[0192] Furthermore, although the above examples have been described in terms of first to fourth embodiments, some or all of these embodiments can be combined. Additionally, the smart device 14, smart glasses 214, head-mounted terminal 314, and robot 414 are just examples and can be combined separately, or other devices may be used. Furthermore, although the above examples have been described in terms of morphological example 1 and morphological example 2, these can also be combined.

[0193] The foregoing descriptions and illustrations are detailed explanations of the parts covered by this disclosure and are merely one example of this disclosure. For instance, the descriptions of the above-described structure, function, role, and effect are just one example of the structure, function, role, and effect of the parts covered by this disclosure. Therefore, it goes without saying that, without departing from the spirit of this disclosure, unnecessary parts can be deleted, new elements can be added, or replacements can be made to the foregoing descriptions and illustrations. Furthermore, to avoid confusion and facilitate understanding of the parts covered by this disclosure, explanations of technical common sense that does not require special explanation for implementing this disclosure have been omitted from the foregoing descriptions and illustrations.

[0194] All documents, patent applications and technical standards described in this specification are incorporated herein by reference as if they were specifically and individually described as incorporated by reference.

[0195] [Postscript 1] A system, characterized in that it includes: a receiving unit for inputting a system configuration diagram; The analysis unit is used to analyze the system configuration diagram input by the receiving unit. The generation department is used to generate design documents and code based on the requirements parsed by the parsing department.

[0196] [Postscript 2] The system as described in Appendix 1 is characterized in that, It includes a dialogue section for communicating the details of the stated requirements.

[0197] [Postscript 3] The system as described in Appendix 1 is characterized in that, The analysis unit analyzes the requirements based on the system configuration diagram input by the receiving unit and the dialogue results of the dialogue unit.

[0198] [Postscript 4] The system as described in Appendix 1 is characterized in that, The generation department generates design documents and code using AI.

[0199] [Postscript 5] The system as described in Appendix 1 is characterized in that, The generation unit supports multi-cloud environments, reads the cloud type from the system configuration diagram, and selects the appropriate format.

[0200] [Postscript 6] The system as described in Appendix 1 is characterized in that, The generation department generates Terraform code.

[0201] [Postscript 7] The system as described in Appendix 1 is characterized in that, The receiving department estimates the user's emotions and adjusts the input timing of the system configuration diagram based on the estimated user emotions.

[0202] [Postscript 8] The system as described in Appendix 1 is characterized in that, When inputting the system configuration diagram, the receiving department analyzes the user's past project history and selects the optimal input method.

[0203] [Postscript 9] The system as described in Appendix 1 is characterized in that, When the receiving department inputs the system configuration diagram, it filters based on the user's current project status and areas of interest.

[0204] [Postscript 10] The system as described in Appendix 1 is characterized in that, The receiving department estimates the user's emotions and determines the priority of the input system configuration diagram based on the estimated user emotions.

[0205] [Postscript 11] The system as described in Appendix 1 is characterized in that, When inputting system configuration diagrams, the receiving department considers the user's geographical location information and prioritizes inputting configuration diagrams with high relevance.

[0206] [Postscript 12] The system as described in Appendix 1 is characterized in that, When the receiving department inputs a system configuration diagram, it analyzes the user's social media activities and inputs a relevant configuration diagram.

[0207] [Postscript 13] The system as described in Appendix 1 is characterized in that, The parsing unit infers the user's emotions and adjusts the method of demand parsing based on the inferred user emotions.

[0208] [Postscript 14] The system as described in Appendix 1 is characterized in that, When performing requirements analysis, the analysis department adjusts the level of detail based on the importance of the system configuration diagram.

[0209] [Postscript 15] The system as described in Appendix 1 is characterized in that, During the requirement analysis, the analysis unit applies different analysis algorithms based on the category of the system configuration diagram.

[0210] [Postscript 16] The system as described in Appendix 1 is characterized in that, The parsing unit infers the user's emotions and determines the priority of demand parsing based on the inferred user emotions.

[0211] [Postscript 17] The system as described in Appendix 1 is characterized in that, When performing requirement analysis, the parsing department determines the priority of the analysis based on the timing of the submission of the system configuration diagram.

[0212] [Postscript 18] The system as described in Appendix 1 is characterized in that, During the requirement analysis, the analysis unit adjusts the analysis order based on the relevance of the system configuration diagram.

[0213] [Postscript 19] The system as described in Appendix 1 is characterized in that, The generation unit infers the user's emotions and adjusts the generation method of design documents and code based on the inferred user emotions.

[0214] [Postscript 20] The system as described in Appendix 1 is characterized in that, When generating design documents and code, the generation department adjusts the level of detail based on the importance of the requirements.

[0215] [Postscript 21] The system as described in Appendix 1 is characterized in that, When generating design documents and code, the generation department applies different generation algorithms according to the category of requirements.

[0216] [Postscript 22] The system as described in Appendix 1 is characterized in that, The generation unit infers the user's emotions and adjusts the generation order of design documents and code based on the inferred user emotions.

[0217] [Postscript 23] The system as described in Appendix 1 is characterized in that, When generating design documents and code, the generation department determines the priority of generation based on the timing of requirement submission.

[0218] [Postscript 24] The system as described in Appendix 1 is characterized in that, When generating design documents and code, the generation department adjusts the generation order based on the relevance of requirements.

[0219] [Postscript 25] The system as described in Appendix 2 is characterized in that, The dialogue unit presupposes the user's emotions and adjusts the dialogue process based on the presumed emotions.

[0220] [Postscript 26] The system as described in Appendix 2 is characterized in that, During a conversation, the dialogue unit refers to the user's past conversation history to select the optimal dialogue method.

[0221] [Postscript 27] The system as described in Appendix 2 is characterized in that, The dialogue department customizes the dialogue content based on the user's current project status during the dialogue.

[0222] [Postscript 28] The system as described in Appendix 2 is characterized in that, The dialogue unit presupposes the user's emotions and determines the priority of the dialogue based on the presumed user emotions.

[0223] [Postscript 29] The system as described in Appendix 2 is characterized in that, During a conversation, the dialogue unit considers the user's geographical location information and selects the optimal dialogue method.

[0224] [Postscript 30] The system as described in Appendix 2 is characterized in that, The dialogue department analyzes users' social media activity and adjusts the dialogue content accordingly during the conversation.

Claims

1. A system, characterized in that, include: The reception department is used to input system configuration diagrams; The analysis unit is used to analyze the system configuration diagram input by the receiving unit. The generation department is used to generate design documents and code based on the requirements parsed by the parsing department.

2. The system as described in claim 1, characterized in that, Also includes: The dialogue section is used for discussions regarding the details of the stated requirements.

3. The system as described in claim 2, characterized in that, The analysis unit analyzes the requirements based on the system configuration diagram input by the receiving unit and the dialogue results of the dialogue unit.

4. The system as described in claim 1, characterized in that, The generation department generates design documents and code using AI.

5. The system as described in claim 1, characterized in that, The generation unit supports multi-cloud environments, reads the cloud type from the system configuration diagram, and selects the appropriate format.

6. The system as described in claim 1, characterized in that, The generation department generates Terraform code.

7. The system as described in claim 1, characterized in that, The receiving department estimates the user's emotions and adjusts the input timing of the system configuration diagram based on the estimated user emotions.

8. The system as described in claim 1, characterized in that, When inputting the system configuration diagram, the receiving department analyzes the user's past project history and selects the optimal input method.

9. The system as described in claim 1, characterized in that, When the receiving department inputs the system configuration diagram, it filters based on the user's current project status and areas of interest.

Images