system

Abstract

The system according to this embodiment aims to streamline the creation of test procedure manuals and improve their quality. [Solution] The system according to the embodiment comprises a document analysis unit, a code analysis unit, a procedure manual generation unit, and a continuous learning unit. The document analysis unit analyzes the design document and extracts important test items. The code analysis unit analyzes the program code and identifies the test target. The procedure manual generation unit generates a test procedure manual based on the information extracted by the document analysis unit and the code analysis unit. The continuous learning unit learns from the results of the tests performed and improves the accuracy of the procedure manual generation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there are problems that it takes time to create a test procedure manual, the quality deteriorates due to human errors, and it is laborious to confirm the consistency between the design document and the program.

[0005] The system according to the embodiment aims to improve the efficiency of creating a test procedure manual and improve the quality.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a document analysis unit, a code analysis unit, a procedure manual generation unit, and a continuous learning unit. The document analysis unit analyzes the design document and extracts important test items. The code analysis unit analyzes the program code and identifies the test target. The procedure manual generation unit generates a test procedure manual based on the information extracted by the document analysis unit and the code analysis unit. The continuous learning unit learns from the results of the tests performed and improves the accuracy of the procedure manual generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can streamline the creation of test procedure manuals and improve their quality. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The test document AI agent according to an embodiment of the present invention is a system that reads design documents and programs, and automatically generates detailed test procedures in cooperation with procedure creation tools such as Excel and Word. The test document AI agent analyzes the design documents using natural language processing and extracts important test items. For example, it automatically identifies functions and conditions that should be tested from within the design documents. Next, the test document AI agent automatically analyzes the program code to identify the test targets. For example, it scans and extracts the parts of the code that require testing. Furthermore, based on the extracted information, the test document AI agent automatically generates detailed and structured test procedures. For example, it creates procedures in a consistent format in Excel or Word format. Finally, the test document AI agent continuously learns from the results of the tests performed and improves its accuracy. For example, it analyzes past test results to improve the accuracy of the next test procedures. This mechanism enables improved development speed, improved test quality, and optimization of human resources. Specifically, it saves time by reducing manual work and improves the efficiency and quality of software development by generating high-quality test procedures with fewer errors. Furthermore, as the AI ​​continuously learns, it always applies the latest testing methodologies and flexibly adapts to project changes. This allows the test document AI agent to improve the efficiency and quality of software development.

[0029] The test document AI agent according to this embodiment comprises a document analysis unit, a code analysis unit, a procedure manual generation unit, and a continuous learning unit. The document analysis unit analyzes the design document and extracts important test items. For example, the document analysis unit analyzes the design document using natural language processing technology and automatically identifies functions and conditions to be tested. For example, the document analysis unit can divide the sentences of the design document using morphological analysis and extract important keywords. The document analysis unit can also analyze the structure of sentences using grammatical analysis and identify test items. Furthermore, the document analysis unit can understand the meaning of sentences using semantic analysis and extract test items. The code analysis unit analyzes the program code to identify the test target. For example, the code analysis unit analyzes the program code using static analysis technology and identifies parts that need to be tested. For example, the code analysis unit can analyze the structure of the code and identify changes. Furthermore, the code analysis unit can analyze the program's operation during execution using dynamic analysis technology and identify the test target. Furthermore, the code analysis unit can analyze the scope of impact and identify parts that need to be tested. The procedure manual generation unit generates test procedures based on information extracted by the document analysis unit and the code analysis unit. For example, the procedure manual generation unit automatically generates detailed and structured test procedures based on extracted test items and test targets. The procedure manual generation unit can create procedures in a consistent format, for example, in Excel format. It can also create procedures in Word format. Furthermore, the procedure manual generation unit can organize the contents of the procedures into a hierarchical structure to improve readability. The continuous learning unit improves the accuracy of the procedure manual generation unit by learning from the results of the tests that have been performed. For example, the continuous learning unit analyzes past test results to improve the accuracy of the next test procedures. For example, the continuous learning unit can collect test result data and improve accuracy using a learning algorithm. Furthermore, the continuous learning unit can adjust the frequency of updating the learning data to always apply the latest testing methods. Furthermore, the continuous learning unit can select the type of learning algorithm and apply the optimal learning method.As a result, the test document AI agent according to this embodiment analyzes design documents and program code and automatically generates test procedures, thereby improving development speed and test quality.

[0030] The document analysis unit analyzes design documents and extracts important test items. For example, the document analysis unit analyzes design documents using natural language processing technology to automatically identify functions and conditions that should be tested. Specifically, the document analysis unit uses morphological analysis to divide sentences in the design document and extract important keywords. Morphological analysis is a technology that divides sentences into words and phrases and identifies the meaning and role of each. This allows for the efficient extraction of important information related to testing from the design document. The document analysis unit also uses grammatical analysis to analyze the structure of sentences and identify test items. Grammatical analysis is a technology that analyzes the structure of sentences and identifies sentence elements such as subjects, predicates, and objects. This allows for an understanding of the context of the design document and the accurate identification of functions and conditions that should be tested. Furthermore, the document analysis unit uses semantic analysis to understand the meaning of sentences and extract test items. Semantic analysis is a technology that understands the meaning of sentences and identifies appropriate test items based on the context. This allows for a deep understanding of the content of the design document and the accurate identification of functions and conditions that should be tested. The document analysis department can combine these technologies to analyze design documents and efficiently extract important test items. This significantly streamlines test preparation work and improves test quality.

[0031] The code analysis unit analyzes program code to identify test targets. For example, the code analysis unit analyzes program code using static analysis techniques to identify parts that need testing. Static analysis is a technique that analyzes program code without execution to evaluate the structure and quality of the code. This allows for the prior identification of potential bugs and problem areas in the code. Specifically, the code analysis unit analyzes the structure of the code and identifies the parts that have been changed. Structural code analysis is a technique that analyzes the dependencies between modules and functions in the code and evaluates the impact of changes on other parts. This allows for the efficient identification of test targets related to the changed parts. The code analysis unit also analyzes the program's behavior during execution using dynamic analysis techniques to identify test targets. Dynamic analysis is a technique that analyzes the program while it is running and evaluates its behavior and performance during execution. This allows for the identification of problems and bugs that occur during execution and the accurate identification of test targets. Furthermore, the code analysis unit analyzes the scope of impact to identify parts that need testing. Scope of impact analysis is a technique that evaluates the impact of code changes on other parts and identifies the scope that needs testing. This allows for the efficient identification of test targets and improves the quality of the tests. The code analysis unit can combine these technologies to analyze program code and efficiently identify test targets. This significantly streamlines test preparation work and improves test quality.

[0032] The procedure manual generation unit generates test procedures based on information extracted by the document analysis unit and the code analysis unit. For example, the procedure manual generation unit automatically generates detailed and structured test procedures based on extracted test items and test targets. Specifically, the procedure manual generation unit can create procedures in a consistent format using Excel. Excel-formatted procedures organize test items and procedures in a table format, improving readability. The procedure manual generation unit can also create procedures in Word format. Word-formatted procedures organize test items and procedures in a document format, allowing for the addition of detailed explanations and annotations. Furthermore, the procedure manual generation unit can organize the contents of the procedures in a hierarchical structure, improving readability. Hierarchical procedures organize test items and procedures hierarchically, making important information easier to see. By combining these technologies, the procedure manual generation unit can automatically generate test procedures, significantly streamlining test preparation work. This improves test quality.

[0033] The continuous learning unit improves the accuracy of the procedure manual generation unit by learning from the results of tests that have been conducted. For example, the continuous learning unit analyzes past test results to improve the accuracy of the next test manual. Specifically, the continuous learning unit can collect test result data and improve accuracy using a learning algorithm. A learning algorithm is a technology that learns patterns and trends based on past test results to improve the accuracy of the next test manual. This allows the continuous learning unit to always apply the latest testing methods and improve test quality. The continuous learning unit can also adjust the update frequency of the learning data to always apply the latest testing methods. By adjusting the update frequency of the learning data, it can quickly incorporate the latest testing methods and technologies and improve test quality. Furthermore, the continuous learning unit can select the type of learning algorithm and apply the optimal learning method. By selecting the type of learning algorithm, it can apply the optimal learning method to improve the accuracy of the test manual and improve test quality. By combining these technologies, the continuous learning unit can improve the accuracy of the test manual and improve test quality. As a result, the test document AI agent according to this embodiment analyzes design documents and program code and automatically generates test procedures, thereby improving development speed and test quality.

[0034] The document analysis unit can analyze design documents using natural language processing and extract important test items. For example, the document analysis unit can analyze design documents using morphological analysis techniques and extract important keywords. For example, the document analysis unit can use morphological analysis to segment sentences in design documents and identify functions and conditions to be tested. Furthermore, the document analysis unit can analyze sentence structure using grammatical analysis techniques and identify test items. The document analysis unit can also use grammatical analysis techniques to analyze sentence structure and identify functions and conditions to be tested. In addition, the document analysis unit can use semantic analysis techniques to understand the meaning of sentences and extract test items. This allows for the efficient extraction of important test items by analyzing design documents using natural language processing. Some or all of the above-described processes in the document analysis unit may be performed using AI, or without AI. For example, the document analysis unit can input the text data of the design document into a generating AI and have the generating AI extract important test items.

[0035] The code analysis unit can automatically analyze program code to identify the test target. For example, the code analysis unit can analyze program code using static analysis techniques to identify parts that need testing. For example, the code analysis unit can analyze the structure of the code to identify changes. The code analysis unit can also analyze the program's behavior during execution using dynamic analysis techniques to identify the test target. For example, the code analysis unit can analyze the program's behavior during execution to identify parts that need testing. Furthermore, the code analysis unit can analyze the scope of impact to identify parts that need testing. For example, the code analysis unit can analyze the scope of impact to identify parts that need testing. This allows for the rapid and accurate identification of the test target by automatically analyzing the program code. Some or all of the above processes in the code analysis unit may be performed using AI, or not. For example, the code analysis unit can input program code data into a generating AI and have the generating AI perform the identification of the test target.

[0036] The procedure manual generation unit can automatically generate detailed and structured test procedures based on extracted information. For example, the procedure manual generation unit can automatically generate detailed and structured test procedures based on extracted test items and test targets. The procedure manual generation unit can create procedures in a consistent format, for example, in Excel format. The procedure manual generation unit can create procedures in Excel format to improve readability. Furthermore, the procedure manual generation unit can create procedures in Word format to improve readability. In addition, the procedure manual generation unit can organize the contents of the procedures into a hierarchical structure to improve readability. This allows for the automatic generation of detailed and structured test procedures, thereby improving the efficiency and quality of the test process. Some or all of the above-described processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input the extracted information into the generation AI and have the generation AI execute the generation of test procedure manuals.

[0037] The continuous learning unit allows the AI ​​to continuously learn based on the results of the tests performed, thereby improving accuracy. For example, the continuous learning unit can analyze past test results to improve the accuracy of the next test procedure. For example, the continuous learning unit can collect test result data and improve accuracy using a learning algorithm. Furthermore, the continuous learning unit can adjust the frequency of training data updates to always apply the latest testing methods. In addition, the continuous learning unit can select the type of learning algorithm and apply the optimal learning method. This allows the AI ​​to continuously learn, improving the accuracy of the test procedure and ensuring the application of the latest testing methods. Some or all of the above-described processes in the continuous learning unit may be performed using AI, or not. For example, the continuous learning unit can input test result data into a generating AI and have the generating AI optimize the learning algorithm.

[0038] The procedure manual generation unit can create procedure manuals in a consistent format, such as Excel or Word. For example, the procedure manual generation unit can create procedure manuals in a consistent format in Excel. For example, the procedure manual generation unit can create procedure manuals in Excel to improve readability. The procedure manual generation unit can also create procedure manuals in Word format. For example, the procedure manual generation unit can create procedure manuals in Word format to improve readability. Furthermore, the procedure manual generation unit can organize the contents of the procedure manuals into a hierarchical structure to improve readability. This improves the quality and readability of the procedure manuals by creating them in a consistent format. Some or all of the above-described processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input extracted information into a generation AI and have the generation AI generate the procedure manuals.

[0039] The document analysis unit can optimize its analysis algorithm by referring to past design document data when analyzing design documents. For example, the document analysis unit can prioritize the extraction of frequently occurring test items based on past design document data. For example, the document analysis unit can analyze past design document data to identify common errors and problems and improve its analysis algorithm. The document analysis unit can also apply analysis algorithms specific to a particular project by referring to past design document data. For example, the document analysis unit can apply analysis algorithms specific to a particular project by referring to past design document data. This optimizes the analysis algorithm and improves analysis accuracy by referring to past design document data. Some or all of the above processes in the document analysis unit may be performed using AI, for example, or without AI. For example, the document analysis unit can input past design document data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0040] The document analysis unit can apply different analysis methods depending on the category of the design document when analyzing it. For example, in the case of a software design document, the document analysis unit can apply an analysis method based on the structure and function of the code. The document analysis unit can also apply an analysis method based on the physical structure and performance of a hardware design document. Furthermore, in the case of a system design document, the document analysis unit can apply an analysis method based on the overall system architecture. This improves the accuracy of the analysis by applying an analysis method appropriate to the category of the design document. Some or all of the above-described processes in the document analysis unit may be performed using AI, for example, or without AI. For example, the document analysis unit can input the category information of the design document into a generating AI and have the generating AI execute the application of the analysis method.

[0041] The document analysis unit can determine the priority of analysis based on the submission date of the design documents when analyzing them. For example, the document analysis unit can prioritize the analysis of design documents with approaching deadlines. The document analysis unit can also postpone the analysis of older design documents. Furthermore, the document analysis unit can automatically adjust the analysis schedule based on the submission date. This enables efficient analysis by determining the priority of analysis based on the submission date of the design documents. Some or all of the above processes in the document analysis unit may be performed using AI, for example, or without AI. For example, the document analysis unit can input design document submission date information into a generating AI and have the generating AI determine the priority of analysis.

[0042] The document analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the design document. For example, the document analysis unit can improve the reliability of its analysis results by referring to technical literature related to the design document. Furthermore, the document analysis unit can improve the accuracy of its analysis results by referring to relevant patent documents related to the design document. In addition, the document analysis unit can ensure the consistency of its analysis results by referring to industry standards related to the design document. This improves the accuracy of the analysis by referring to relevant literature related to the design document. Some or all of the above-described processes in the document analysis unit may be performed using AI, for example, or without AI. For example, the document analysis unit can input relevant literature related to the design document into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0043] The code analysis unit can optimize its analysis algorithm by referring to past code data during code analysis. For example, the code analysis unit can prioritize the detection of frequently occurring errors based on past code data. For example, the code analysis unit can analyze past code data to identify common bugs and problems and improve its analysis algorithm. The code analysis unit can also apply analysis algorithms specific to a particular project by referring to past code data. For example, the code analysis unit can apply analysis algorithms specific to a particular project by referring to past code data. This optimizes the analysis algorithm and improves analysis accuracy by referring to past code data. Some or all of the above processes in the code analysis unit may be performed using AI, for example, or without AI. For example, the code analysis unit can input past code data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0044] The code analysis unit can apply different analysis methods depending on the category of the code during code analysis. For example, in the case of web application code, the code analysis unit can apply an analysis method that emphasizes security. Furthermore, in the case of mobile application code, the code analysis unit can apply an analysis method that emphasizes performance. In addition, in the case of desktop application code, the code analysis unit can apply an analysis method that emphasizes compatibility. This improves analysis accuracy by applying analysis methods appropriate to the code category. Some or all of the above-described processes in the code analysis unit may be performed using AI, for example, or without AI. For example, the code analysis unit can input code category information into a generating AI and have the generating AI execute the application of analysis methods.

[0045] The code analysis unit can determine the priority of code analysis based on the submission date of the code. For example, the code analysis unit can prioritize the analysis of code with an approaching deadline. The code analysis unit can also postpone the analysis of older code. Furthermore, the code analysis unit can automatically adjust the analysis schedule based on the submission date. This enables efficient analysis by determining the priority of analysis based on the submission date of the code. Some or all of the above processes in the code analysis unit may be performed using AI, for example, or without AI. For example, the code analysis unit can input code submission date information into a generating AI and have the generating AI determine the priority of analysis.

[0046] The code analysis unit can improve the accuracy of its analysis by referring to relevant documentation for the code during the analysis process. For example, the code analysis unit can improve the reliability of its analysis results by referring to relevant technical documentation for the code. Furthermore, the code analysis unit can improve the accuracy of its analysis results by referring to relevant patent documents for the code. In addition, the code analysis unit can ensure the consistency of its analysis results by referring to relevant industry standards for the code. This improves the accuracy of the analysis by referring to relevant documentation for the code. Some or all of the above-described processes in the code analysis unit may be performed using AI, or not. For example, the code analysis unit can input relevant documentation for the code into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0047] The procedure manual generation unit can optimize its generation algorithm by referring to past procedure manual data when generating procedure manuals. For example, the procedure manual generation unit prioritizes the inclusion of frequently occurring procedures based on past procedure manual data. For example, the procedure manual generation unit can analyze past procedure manual data to identify common errors and problems and improve its generation algorithm. The procedure manual generation unit can also apply a generation algorithm specific to a particular project by referring to past procedure manual data. For example, the procedure manual generation unit can apply a generation algorithm specific to a particular project by referring to past procedure manual data. This optimizes the generation algorithm and improves generation accuracy by referring to past procedure manual data. Some or all of the above processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input past procedure manual data into a generation AI and have the generation AI perform the optimization of the generation algorithm.

[0048] The procedure manual generation unit can apply different generation methods depending on the category of the procedure manual when generating it. For example, in the case of a software test procedure manual, the procedure manual generation unit can apply a generation method based on the structure and function of the code. Furthermore, in the case of a hardware test procedure manual, the procedure manual generation unit can apply a generation method based on the physical structure and performance. In addition, in the case of a system test procedure manual, the procedure manual generation unit can apply a generation method based on the overall system architecture. This improves generation accuracy by applying a generation method appropriate to the category of the procedure manual. Some or all of the above-described processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input the category information of the procedure manual into a generation AI and have the generation AI execute the application of the generation method.

[0049] The procedure manual generation unit can determine the generation priority based on the submission date of the procedure manuals when generating them. For example, the procedure manual generation unit can prioritize the generation of procedure manuals with approaching deadlines. The procedure manual generation unit can also postpone the generation of procedure manuals with older submission dates. Furthermore, the procedure manual generation unit can automatically adjust the generation schedule based on the submission dates. This enables efficient generation by determining the generation priority based on the submission dates of the procedure manuals. Some or all of the above-described processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input procedure manual submission date information into a generation AI and have the generation AI determine the generation priority.

[0050] The procedure manual generation unit can improve the accuracy of the generation by referring to relevant literature related to the procedure manual during the generation process. For example, the procedure manual generation unit can improve the reliability of the generation results by referring to technical literature related to the procedure manual. Furthermore, the procedure manual generation unit can improve the accuracy of the generation results by referring to patent documents related to the procedure manual. In addition, the procedure manual generation unit can ensure consistency in the generation results by referring to industry standards related to the procedure manual. This improves the accuracy of the generation by referring to relevant literature related to the procedure manual. Some or all of the above-described processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input relevant literature related to the procedure manual into a generation AI and have the generation AI perform the generation accuracy improvement.

[0051] The continuous learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the continuous learning unit can prioritize learning frequently occurring errors based on past learning data. For example, the continuous learning unit can analyze past learning data to identify common problems and improve the learning algorithm. The continuous learning unit can also apply a learning algorithm specific to a particular project by referring to past learning data. For example, the continuous learning unit can apply a learning algorithm specific to a particular project by referring to past learning data. This optimizes the learning algorithm and improves learning accuracy by referring to past learning data. Some or all of the above processes in the continuous learning unit may be performed using AI, for example, or without AI. For example, the continuous learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0052] The continuous learning unit can apply different learning methods depending on the category of the learning data during learning. For example, in the case of software test data, the continuous learning unit can apply a learning method based on the structure and functionality of the code. The continuous learning unit can also apply a learning method based on the physical structure and performance of hardware test data. Furthermore, in the case of system test data, the continuous learning unit can apply a learning method based on the overall system architecture. This improves learning accuracy by applying a learning method appropriate to the category of the learning data. Some or all of the above processing in the continuous learning unit may be performed using AI, for example, or without AI. For example, the continuous learning unit can input category information of the learning data into a generating AI and have the generating AI execute the application of the learning method.

[0053] The continuous learning unit can determine the priority of learning based on the submission timing of the learning data during the learning process. For example, the continuous learning unit can prioritize learning data with approaching deadlines. The continuous learning unit can also postpone learning data with older submission dates. Furthermore, the continuous learning unit can automatically adjust the learning schedule based on the submission dates. This enables efficient learning by determining the priority of learning based on the submission dates of the learning data. Some or all of the above processing in the continuous learning unit may be performed using AI, for example, or without AI. For example, the continuous learning unit can input learning data submission date information into a generating AI and have the generating AI determine the learning priority.

[0054] The continuous learning unit can improve the accuracy of learning by referring to relevant literature on the learning data during the learning process. For example, the continuous learning unit can improve the reliability of the learning results by referring to technical literature related to the learning data. Furthermore, the continuous learning unit can improve the accuracy of the learning results by referring to patent documents related to the learning data. In addition, the continuous learning unit can ensure the consistency of the learning results by referring to industry standards related to the learning data. This improves the accuracy of learning by referring to relevant literature on the learning data. Some or all of the above processing in the continuous learning unit may be performed using AI, for example, or without AI. For example, the continuous learning unit can input relevant literature on the learning data into a generating AI and have the generating AI perform the learning accuracy improvement.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The document analysis unit can adjust its analysis algorithms by referencing past user feedback when analyzing design documents. For example, it can improve the accuracy of the analysis by considering problems and improvements previously pointed out by the user. It can also prioritize the application of specific analysis methods based on user feedback. Furthermore, it can analyze user feedback to identify common problems and improve the analysis algorithms. In this way, the accuracy and reliability of the analysis are improved by utilizing user feedback.

[0057] The code analysis unit monitors code changes in real time during program code analysis and can perform analysis immediately when changes occur. For example, when a code change is detected, it identifies the changed parts and performs a rapid analysis. It can also refer to the change history to compare with past changes and identify the scope of impact. Furthermore, it can prioritize the analysis of frequently changing parts, improving test efficiency. As a result, by responding to code changes in real time, the accuracy and efficiency of testing are improved.

[0058] The procedure manual generation unit can adjust the content of the generated procedure manuals according to the user's skill level. For example, it can provide detailed procedures to novice users and concise procedures to experienced users. It can also progressively increase the detail of the procedure manuals according to the user's skill level. Furthermore, it can adjust the format and expression of the procedure manuals based on the user's skill level. By providing procedure manuals tailored to the user's skill level, the comprehension and execution efficiency of the procedures are improved.

[0059] The continuous learning unit can incorporate user feedback in real time during the learning process and adjust the learning algorithm accordingly. For example, it can select learning data and adjust algorithm parameters based on user feedback. It can also analyze user feedback to identify common problems and improve the learning algorithm. Furthermore, it can utilize user feedback to improve the accuracy and efficiency of learning. In this way, leveraging user feedback improves the accuracy and reliability of learning.

[0060] The procedure manual generation unit can adjust the content of the generated procedure manuals according to the project's progress. For example, it can provide detailed procedure manuals in the initial stages of the project and simplify them as the project progresses. It can also progressively increase the detail of the procedure manuals as the project progresses. Furthermore, it can adjust the format and expression of the procedure manuals based on the project's progress. By providing procedure manuals tailored to the project's progress, the understanding and execution efficiency of the procedure manuals are improved.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The document analysis unit analyzes the design document and extracts important test items. The document analysis unit uses natural language processing technology to analyze the design document and automatically identifies the functions and conditions that should be tested through morphological analysis, grammatical analysis, and semantic analysis. Step 2: The code analysis unit analyzes the program code to identify the test target. The code analysis unit uses static and dynamic analysis techniques to analyze the program code and identify the code structure, changes, and scope of impact. Step 3: The procedure manual generation unit generates test procedures based on the information extracted by the document analysis unit and the code analysis unit. The procedure manual generation unit automatically generates detailed and structured test procedures based on the extracted test items and test targets, and creates the procedures in a consistent format in Excel or Word format. Step 4: The continuous learning unit learns from the results of the tests performed and improves the accuracy of the procedure manual generation unit. The continuous learning unit analyzes past test results and uses a learning algorithm to improve the accuracy of the next test procedure manual.

[0063] (Example of form 2) The test document AI agent according to an embodiment of the present invention is a system that reads design documents and programs, and automatically generates detailed test procedures in cooperation with procedure creation tools such as Excel and Word. The test document AI agent analyzes the design documents using natural language processing and extracts important test items. For example, it automatically identifies functions and conditions that should be tested from within the design documents. Next, the test document AI agent automatically analyzes the program code to identify the test targets. For example, it scans and extracts the parts of the code that require testing. Furthermore, based on the extracted information, the test document AI agent automatically generates detailed and structured test procedures. For example, it creates procedures in a consistent format in Excel or Word format. Finally, the test document AI agent continuously learns from the results of the tests performed and improves its accuracy. For example, it analyzes past test results to improve the accuracy of the next test procedures. This mechanism enables improved development speed, improved test quality, and optimization of human resources. Specifically, it saves time by reducing manual work and improves the efficiency and quality of software development by generating high-quality test procedures with fewer errors. Furthermore, as the AI ​​continuously learns, it always applies the latest testing methodologies and flexibly adapts to project changes. This allows the test document AI agent to improve the efficiency and quality of software development.

[0064] The test document AI agent according to this embodiment comprises a document analysis unit, a code analysis unit, a procedure manual generation unit, and a continuous learning unit. The document analysis unit analyzes the design document and extracts important test items. For example, the document analysis unit analyzes the design document using natural language processing technology and automatically identifies functions and conditions to be tested. For example, the document analysis unit can divide the sentences of the design document using morphological analysis and extract important keywords. The document analysis unit can also analyze the structure of sentences using grammatical analysis and identify test items. Furthermore, the document analysis unit can understand the meaning of sentences using semantic analysis and extract test items. The code analysis unit analyzes the program code to identify the test target. For example, the code analysis unit analyzes the program code using static analysis technology and identifies parts that need to be tested. For example, the code analysis unit can analyze the structure of the code and identify changes. Furthermore, the code analysis unit can analyze the program's operation during execution using dynamic analysis technology and identify the test target. Furthermore, the code analysis unit can analyze the scope of impact and identify parts that need to be tested. The procedure manual generation unit generates test procedures based on information extracted by the document analysis unit and the code analysis unit. For example, the procedure manual generation unit automatically generates detailed and structured test procedures based on extracted test items and test targets. The procedure manual generation unit can create procedures in a consistent format, for example, in Excel format. It can also create procedures in Word format. Furthermore, the procedure manual generation unit can organize the contents of the procedures into a hierarchical structure to improve readability. The continuous learning unit improves the accuracy of the procedure manual generation unit by learning from the results of the tests that have been performed. For example, the continuous learning unit analyzes past test results to improve the accuracy of the next test procedures. For example, the continuous learning unit can collect test result data and improve accuracy using a learning algorithm. Furthermore, the continuous learning unit can adjust the frequency of updating the learning data to always apply the latest testing methods. Furthermore, the continuous learning unit can select the type of learning algorithm and apply the optimal learning method.As a result, the test document AI agent according to this embodiment analyzes design documents and program code and automatically generates test procedures, thereby improving development speed and test quality.

[0065] The document analysis unit analyzes design documents and extracts important test items. For example, the document analysis unit analyzes design documents using natural language processing technology to automatically identify functions and conditions that should be tested. Specifically, the document analysis unit uses morphological analysis to divide sentences in the design document and extract important keywords. Morphological analysis is a technology that divides sentences into words and phrases and identifies the meaning and role of each. This allows for the efficient extraction of important information related to testing from the design document. The document analysis unit also uses grammatical analysis to analyze the structure of sentences and identify test items. Grammatical analysis is a technology that analyzes the structure of sentences and identifies sentence elements such as subjects, predicates, and objects. This allows for an understanding of the context of the design document and the accurate identification of functions and conditions that should be tested. Furthermore, the document analysis unit uses semantic analysis to understand the meaning of sentences and extract test items. Semantic analysis is a technology that understands the meaning of sentences and identifies appropriate test items based on the context. This allows for a deep understanding of the content of the design document and the accurate identification of functions and conditions that should be tested. The document analysis department can combine these technologies to analyze design documents and efficiently extract important test items. This significantly streamlines test preparation work and improves test quality.

[0066] The code analysis unit analyzes program code to identify test targets. For example, the code analysis unit analyzes program code using static analysis techniques to identify parts that need testing. Static analysis is a technique that analyzes program code without execution to evaluate the structure and quality of the code. This allows for the prior identification of potential bugs and problem areas in the code. Specifically, the code analysis unit analyzes the structure of the code and identifies the parts that have been changed. Structural code analysis is a technique that analyzes the dependencies between modules and functions in the code and evaluates the impact of changes on other parts. This allows for the efficient identification of test targets related to the changed parts. The code analysis unit also analyzes the program's behavior during execution using dynamic analysis techniques to identify test targets. Dynamic analysis is a technique that analyzes the program while it is running and evaluates its behavior and performance during execution. This allows for the identification of problems and bugs that occur during execution and the accurate identification of test targets. Furthermore, the code analysis unit analyzes the scope of impact to identify parts that need testing. Scope of impact analysis is a technique that evaluates the impact of code changes on other parts and identifies the scope that needs testing. This allows for the efficient identification of test targets and improves the quality of the tests. The code analysis unit can combine these technologies to analyze program code and efficiently identify test targets. This significantly streamlines test preparation work and improves test quality.

[0067] The procedure manual generation unit generates test procedures based on information extracted by the document analysis unit and the code analysis unit. For example, the procedure manual generation unit automatically generates detailed and structured test procedures based on extracted test items and test targets. Specifically, the procedure manual generation unit can create procedures in a consistent format using Excel. Excel-formatted procedures organize test items and procedures in a table format, improving readability. The procedure manual generation unit can also create procedures in Word format. Word-formatted procedures organize test items and procedures in a document format, allowing for the addition of detailed explanations and annotations. Furthermore, the procedure manual generation unit can organize the contents of the procedures in a hierarchical structure, improving readability. Hierarchical procedures organize test items and procedures hierarchically, making important information easier to see. By combining these technologies, the procedure manual generation unit can automatically generate test procedures, significantly streamlining test preparation work. This improves test quality.

[0068] The continuous learning unit improves the accuracy of the procedure manual generation unit by learning from the results of tests that have been conducted. For example, the continuous learning unit analyzes past test results to improve the accuracy of the next test manual. Specifically, the continuous learning unit can collect test result data and improve accuracy using a learning algorithm. A learning algorithm is a technology that learns patterns and trends based on past test results to improve the accuracy of the next test manual. This allows the continuous learning unit to always apply the latest testing methods and improve test quality. The continuous learning unit can also adjust the update frequency of the learning data to always apply the latest testing methods. By adjusting the update frequency of the learning data, it can quickly incorporate the latest testing methods and technologies and improve test quality. Furthermore, the continuous learning unit can select the type of learning algorithm and apply the optimal learning method. By selecting the type of learning algorithm, it can apply the optimal learning method to improve the accuracy of the test manual and improve test quality. By combining these technologies, the continuous learning unit can improve the accuracy of the test manual and improve test quality. As a result, the test document AI agent according to this embodiment analyzes design documents and program code and automatically generates test procedures, thereby improving development speed and test quality.

[0069] The document analysis unit can analyze design documents using natural language processing and extract important test items. For example, the document analysis unit can analyze design documents using morphological analysis techniques and extract important keywords. For example, the document analysis unit can use morphological analysis to segment sentences in design documents and identify functions and conditions to be tested. Furthermore, the document analysis unit can analyze sentence structure using grammatical analysis techniques and identify test items. The document analysis unit can also use grammatical analysis techniques to analyze sentence structure and identify functions and conditions to be tested. In addition, the document analysis unit can use semantic analysis techniques to understand the meaning of sentences and extract test items. This allows for the efficient extraction of important test items by analyzing design documents using natural language processing. Some or all of the above-described processes in the document analysis unit may be performed using AI, or without AI. For example, the document analysis unit can input the text data of the design document into a generating AI and have the generating AI extract important test items.

[0070] The code analysis unit can automatically analyze program code to identify the test target. For example, the code analysis unit can analyze program code using static analysis techniques to identify parts that need testing. For example, the code analysis unit can analyze the structure of the code to identify changes. The code analysis unit can also analyze the program's behavior during execution using dynamic analysis techniques to identify the test target. For example, the code analysis unit can analyze the program's behavior during execution to identify parts that need testing. Furthermore, the code analysis unit can analyze the scope of impact to identify parts that need testing. For example, the code analysis unit can analyze the scope of impact to identify parts that need testing. This allows for the rapid and accurate identification of the test target by automatically analyzing the program code. Some or all of the above processes in the code analysis unit may be performed using AI, or not. For example, the code analysis unit can input program code data into a generating AI and have the generating AI perform the identification of the test target.

[0071] The procedure manual generation unit can automatically generate detailed and structured test procedures based on extracted information. For example, the procedure manual generation unit can automatically generate detailed and structured test procedures based on extracted test items and test targets. The procedure manual generation unit can create procedures in a consistent format, for example, in Excel format. The procedure manual generation unit can create procedures in Excel format to improve readability. Furthermore, the procedure manual generation unit can create procedures in Word format to improve readability. In addition, the procedure manual generation unit can organize the contents of the procedures into a hierarchical structure to improve readability. This allows for the automatic generation of detailed and structured test procedures, thereby improving the efficiency and quality of the test process. Some or all of the above-described processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input the extracted information into the generation AI and have the generation AI execute the generation of test procedure manuals.

[0072] The continuous learning unit allows the AI ​​to continuously learn based on the results of the tests performed, thereby improving accuracy. For example, the continuous learning unit can analyze past test results to improve the accuracy of the next test procedure. For example, the continuous learning unit can collect test result data and improve accuracy using a learning algorithm. Furthermore, the continuous learning unit can adjust the frequency of training data updates to always apply the latest testing methods. In addition, the continuous learning unit can select the type of learning algorithm and apply the optimal learning method. This allows the AI ​​to continuously learn, improving the accuracy of the test procedure and ensuring the application of the latest testing methods. Some or all of the above-described processes in the continuous learning unit may be performed using AI, or not. For example, the continuous learning unit can input test result data into a generating AI and have the generating AI optimize the learning algorithm.

[0073] The procedure manual generation unit can create procedure manuals in a consistent format, such as Excel or Word. For example, the procedure manual generation unit can create procedure manuals in a consistent format in Excel. For example, the procedure manual generation unit can create procedure manuals in Excel to improve readability. The procedure manual generation unit can also create procedure manuals in Word format. For example, the procedure manual generation unit can create procedure manuals in Word format to improve readability. Furthermore, the procedure manual generation unit can organize the contents of the procedure manuals into a hierarchical structure to improve readability. This improves the quality and readability of the procedure manuals by creating them in a consistent format. Some or all of the above-described processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input extracted information into a generation AI and have the generation AI generate the procedure manuals.

[0074] The document analysis unit can estimate the user's emotions and adjust the analysis method of the design document based on the estimated user emotions. For example, if the user is stressed, the document analysis unit can reduce the level of detail in the analysis and provide concise results. For example, if the user is relaxed, the document analysis unit can provide detailed analysis results to allow the user to understand more deeply. Also, if the user is in a hurry, the document analysis unit can prioritize analysis speed and provide results quickly. By adjusting the analysis method of the design document according to the user's emotions, the document analysis unit can provide analysis results that are appropriate for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the document analysis unit may be performed using AI, for example, or without AI. For example, the document analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0075] The document analysis unit can optimize its analysis algorithm by referring to past design document data when analyzing design documents. For example, the document analysis unit can prioritize the extraction of frequently occurring test items based on past design document data. For example, the document analysis unit can analyze past design document data to identify common errors and problems and improve its analysis algorithm. The document analysis unit can also apply analysis algorithms specific to a particular project by referring to past design document data. For example, the document analysis unit can apply analysis algorithms specific to a particular project by referring to past design document data. This optimizes the analysis algorithm and improves analysis accuracy by referring to past design document data. Some or all of the above processes in the document analysis unit may be performed using AI, for example, or without AI. For example, the document analysis unit can input past design document data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0076] The document analysis unit can apply different analysis methods depending on the category of the design document when analyzing it. For example, in the case of a software design document, the document analysis unit can apply an analysis method based on the structure and function of the code. The document analysis unit can also apply an analysis method based on the physical structure and performance of a hardware design document. Furthermore, in the case of a system design document, the document analysis unit can apply an analysis method based on the overall system architecture. This improves the accuracy of the analysis by applying an analysis method appropriate to the category of the design document. Some or all of the above-described processes in the document analysis unit may be performed using AI, for example, or without AI. For example, the document analysis unit can input the category information of the design document into a generating AI and have the generating AI execute the application of the analysis method.

[0077] The document analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is tense, the document analysis unit can provide a simple and highly visible display method. For example, if the user is relaxed, the document analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the document analysis unit can provide a display method that gets straight to the point. By adjusting the display method of the analysis results according to the user's emotions, a display method suitable for the user can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the document analysis unit may be performed using AI, for example, or without AI. For example, the document analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0078] The document analysis unit can determine the priority of analysis based on the submission date of the design documents when analyzing them. For example, the document analysis unit can prioritize the analysis of design documents with approaching deadlines. The document analysis unit can also postpone the analysis of older design documents. Furthermore, the document analysis unit can automatically adjust the analysis schedule based on the submission date. This enables efficient analysis by determining the priority of analysis based on the submission date of the design documents. Some or all of the above processes in the document analysis unit may be performed using AI, for example, or without AI. For example, the document analysis unit can input design document submission date information into a generating AI and have the generating AI determine the priority of analysis.

[0079] The document analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the design document. For example, the document analysis unit can improve the reliability of its analysis results by referring to technical literature related to the design document. Furthermore, the document analysis unit can improve the accuracy of its analysis results by referring to relevant patent documents related to the design document. In addition, the document analysis unit can ensure the consistency of its analysis results by referring to industry standards related to the design document. This improves the accuracy of the analysis by referring to relevant literature related to the design document. Some or all of the above-described processes in the document analysis unit may be performed using AI, for example, or without AI. For example, the document analysis unit can input relevant literature related to the design document into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0080] The code analysis unit can estimate the user's emotions and adjust the code analysis method based on the estimated emotions. For example, if the user is stressed, the code analysis unit can reduce the level of detail in the analysis and provide concise results. For example, if the user is relaxed, the code analysis unit can provide detailed analysis results to allow the user to understand more deeply. Also, if the user is in a hurry, the code analysis unit can prioritize analysis speed and provide results quickly. By adjusting the code analysis method according to the user's emotions, the code analysis unit can provide analysis results that are appropriate for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the code analysis unit may be performed using AI, for example, or not using AI. For example, the code analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0081] The code analysis unit can optimize its analysis algorithm by referring to past code data during code analysis. For example, the code analysis unit can prioritize the detection of frequently occurring errors based on past code data. For example, the code analysis unit can analyze past code data to identify common bugs and problems and improve its analysis algorithm. The code analysis unit can also apply analysis algorithms specific to a particular project by referring to past code data. For example, the code analysis unit can apply analysis algorithms specific to a particular project by referring to past code data. This optimizes the analysis algorithm and improves analysis accuracy by referring to past code data. Some or all of the above processes in the code analysis unit may be performed using AI, for example, or without AI. For example, the code analysis unit can input past code data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0082] The code analysis unit can apply different analysis methods depending on the category of the code during code analysis. For example, in the case of web application code, the code analysis unit can apply an analysis method that emphasizes security. Furthermore, in the case of mobile application code, the code analysis unit can apply an analysis method that emphasizes performance. In addition, in the case of desktop application code, the code analysis unit can apply an analysis method that emphasizes compatibility. This improves analysis accuracy by applying analysis methods appropriate to the code category. Some or all of the above-described processes in the code analysis unit may be performed using AI, for example, or without AI. For example, the code analysis unit can input code category information into a generating AI and have the generating AI execute the application of analysis methods.

[0083] The code analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the code analysis unit can provide a simple and highly visible display method. For example, if the user is relaxed, the code analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the code analysis unit can provide a display method that gets straight to the point. By adjusting the display method of the analysis results according to the user's emotions, a display method suitable for the user can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the code analysis unit may be performed using AI, for example, or without AI. For example, the code analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0084] The code analysis unit can determine the priority of code analysis based on the submission date of the code. For example, the code analysis unit can prioritize the analysis of code with an approaching deadline. The code analysis unit can also postpone the analysis of older code. Furthermore, the code analysis unit can automatically adjust the analysis schedule based on the submission date. This enables efficient analysis by determining the priority of analysis based on the submission date of the code. Some or all of the above processes in the code analysis unit may be performed using AI, for example, or without AI. For example, the code analysis unit can input code submission date information into a generating AI and have the generating AI determine the priority of analysis.

[0085] The code analysis unit can improve the accuracy of its analysis by referring to relevant documentation for the code during the analysis process. For example, the code analysis unit can improve the reliability of its analysis results by referring to relevant technical documentation for the code. Furthermore, the code analysis unit can improve the accuracy of its analysis results by referring to relevant patent documents for the code. In addition, the code analysis unit can ensure the consistency of its analysis results by referring to relevant industry standards for the code. This improves the accuracy of the analysis by referring to relevant documentation for the code. Some or all of the above-described processes in the code analysis unit may be performed using AI, or not. For example, the code analysis unit can input relevant documentation for the code into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0086] The procedure manual generation unit can estimate the user's emotions and adjust the procedure manual generation method based on the estimated user emotions. For example, if the user is stressed, the procedure manual generation unit can generate a concise and easy-to-understand procedure manual. For example, if the user is relaxed, the procedure manual generation unit can generate a detailed procedure manual to allow the user to understand it more deeply. The procedure manual generation unit can also provide a quickly generated procedure manual if the user is in a hurry. By adjusting the procedure manual generation method according to the user's emotions, the system can provide a procedure manual that is suitable for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0087] The procedure manual generation unit can optimize its generation algorithm by referring to past procedure manual data when generating procedure manuals. For example, the procedure manual generation unit prioritizes the inclusion of frequently occurring procedures based on past procedure manual data. For example, the procedure manual generation unit can analyze past procedure manual data to identify common errors and problems and improve its generation algorithm. The procedure manual generation unit can also apply a generation algorithm specific to a particular project by referring to past procedure manual data. For example, the procedure manual generation unit can apply a generation algorithm specific to a particular project by referring to past procedure manual data. This optimizes the generation algorithm and improves generation accuracy by referring to past procedure manual data. Some or all of the above processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input past procedure manual data into a generation AI and have the generation AI perform the optimization of the generation algorithm.

[0088] The procedure manual generation unit can apply different generation methods depending on the category of the procedure manual when generating it. For example, in the case of a software test procedure manual, the procedure manual generation unit can apply a generation method based on the structure and function of the code. Furthermore, in the case of a hardware test procedure manual, the procedure manual generation unit can apply a generation method based on the physical structure and performance. In addition, in the case of a system test procedure manual, the procedure manual generation unit can apply a generation method based on the overall system architecture. This improves generation accuracy by applying a generation method appropriate to the category of the procedure manual. Some or all of the above-described processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input the category information of the procedure manual into a generation AI and have the generation AI execute the application of the generation method.

[0089] The procedure manual generation unit can estimate the user's emotions and adjust the display method of the procedure manual based on the estimated user emotions. For example, if the user is nervous, the procedure manual generation unit can provide a simple and highly visible display method. For example, if the user is relaxed, the procedure manual generation unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the procedure manual generation unit can provide a display method that gets straight to the point. By adjusting the display method of the procedure manual according to the user's emotions, a display method suitable for the user can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input user emotion data into the generative AI and have the generative AI perform emotion estimation.

[0090] The procedure manual generation unit can determine the generation priority based on the submission date of the procedure manuals when generating them. For example, the procedure manual generation unit can prioritize the generation of procedure manuals with approaching deadlines. The procedure manual generation unit can also postpone the generation of procedure manuals with older submission dates. Furthermore, the procedure manual generation unit can automatically adjust the generation schedule based on the submission dates. This enables efficient generation by determining the generation priority based on the submission dates of the procedure manuals. Some or all of the above-described processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input procedure manual submission date information into a generation AI and have the generation AI determine the generation priority.

[0091] The procedure manual generation unit can improve the accuracy of the generation by referring to relevant literature related to the procedure manual during the generation process. For example, the procedure manual generation unit can improve the reliability of the generation results by referring to technical literature related to the procedure manual. Furthermore, the procedure manual generation unit can improve the accuracy of the generation results by referring to patent documents related to the procedure manual. In addition, the procedure manual generation unit can ensure consistency in the generation results by referring to industry standards related to the procedure manual. This improves the accuracy of the generation by referring to relevant literature related to the procedure manual. Some or all of the above-described processes in the procedure manual generation unit may be performed using AI, for example, or without AI. For example, the procedure manual generation unit can input relevant literature related to the procedure manual into a generation AI and have the generation AI perform the generation accuracy improvement.

[0092] The continuous learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is stressed, the continuous learning unit can select concise and easy-to-understand training data. If the user is relaxed, for example, the continuous learning unit can select detailed training data to allow the user to understand it more deeply. The continuous learning unit can also select data that allows for rapid learning if the user is in a hurry. By selecting training data according to the user's emotions, the continuous learning unit can provide training data that is appropriate for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the continuous learning unit may be performed using AI, for example, or without AI. For example, the continuous learning unit can input the user's emotion data into a generative AI and have the generative AI perform emotion estimation.

[0093] The continuous learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the continuous learning unit can prioritize learning frequently occurring errors based on past learning data. For example, the continuous learning unit can analyze past learning data to identify common problems and improve the learning algorithm. The continuous learning unit can also apply a learning algorithm specific to a particular project by referring to past learning data. For example, the continuous learning unit can apply a learning algorithm specific to a particular project by referring to past learning data. This optimizes the learning algorithm and improves learning accuracy by referring to past learning data. Some or all of the above processes in the continuous learning unit may be performed using AI, for example, or without AI. For example, the continuous learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0094] The continuous learning unit can apply different learning methods depending on the category of the learning data during learning. For example, in the case of software test data, the continuous learning unit can apply a learning method based on the structure and functionality of the code. The continuous learning unit can also apply a learning method based on the physical structure and performance of hardware test data. Furthermore, in the case of system test data, the continuous learning unit can apply a learning method based on the overall system architecture. This improves learning accuracy by applying a learning method appropriate to the category of the learning data. Some or all of the above processing in the continuous learning unit may be performed using AI, for example, or without AI. For example, the continuous learning unit can input category information of the learning data into a generating AI and have the generating AI execute the application of the learning method.

[0095] The continuous learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the continuous learning unit can reduce the learning frequency to alleviate the burden. For example, if the user is relaxed, the continuous learning unit can increase the learning frequency to promote deeper understanding. The continuous learning unit can also adjust the learning frequency to allow the user to learn quickly if they are in a hurry. This allows the continuous learning unit to provide a learning frequency that is appropriate for the user by adjusting the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the continuous learning unit may be performed using AI, for example, or without AI. For example, the continuous learning unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0096] The continuous learning unit can determine the priority of learning based on the submission timing of the learning data during the learning process. For example, the continuous learning unit can prioritize learning data with approaching deadlines. The continuous learning unit can also postpone learning data with older submission dates. Furthermore, the continuous learning unit can automatically adjust the learning schedule based on the submission dates. This enables efficient learning by determining the priority of learning based on the submission dates of the learning data. Some or all of the above processing in the continuous learning unit may be performed using AI, for example, or without AI. For example, the continuous learning unit can input learning data submission date information into a generating AI and have the generating AI determine the learning priority.

[0097] The continuous learning unit can improve the accuracy of learning by referring to relevant literature on the learning data during the learning process. For example, the continuous learning unit can improve the reliability of the learning results by referring to technical literature related to the learning data. Furthermore, the continuous learning unit can improve the accuracy of the learning results by referring to patent documents related to the learning data. In addition, the continuous learning unit can ensure the consistency of the learning results by referring to industry standards related to the learning data. This improves the accuracy of learning by referring to relevant literature on the learning data. Some or all of the above processing in the continuous learning unit may be performed using AI, for example, or without AI. For example, the continuous learning unit can input relevant literature on the learning data into a generating AI and have the generating AI perform the learning accuracy improvement.

[0098] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0099] The document analysis unit can adjust its analysis algorithms by referencing past user feedback when analyzing design documents. For example, it can improve the accuracy of the analysis by considering problems and improvements previously pointed out by the user. It can also prioritize the application of specific analysis methods based on user feedback. Furthermore, it can analyze user feedback to identify common problems and improve the analysis algorithms. In this way, the accuracy and reliability of the analysis are improved by utilizing user feedback.

[0100] The code analysis unit monitors code changes in real time during program code analysis and can perform analysis immediately when changes occur. For example, when a code change is detected, it identifies the changed parts and performs a rapid analysis. It can also refer to the change history to compare with past changes and identify the scope of impact. Furthermore, it can prioritize the analysis of frequently changing parts, improving test efficiency. As a result, by responding to code changes in real time, the accuracy and efficiency of testing are improved.

[0101] The procedure manual generation unit can adjust the content of the generated procedure manuals according to the user's skill level. For example, it can provide detailed procedures to novice users and concise procedures to experienced users. It can also progressively increase the detail of the procedure manuals according to the user's skill level. Furthermore, it can adjust the format and expression of the procedure manuals based on the user's skill level. By providing procedure manuals tailored to the user's skill level, the comprehension and execution efficiency of the procedures are improved.

[0102] The continuous learning unit can incorporate user feedback in real time during the learning process and adjust the learning algorithm accordingly. For example, it can select learning data and adjust algorithm parameters based on user feedback. It can also analyze user feedback to identify common problems and improve the learning algorithm. Furthermore, it can utilize user feedback to improve the accuracy and efficiency of learning. In this way, leveraging user feedback improves the accuracy and reliability of learning.

[0103] The procedure manual generation unit can adjust the content of the generated procedure manuals according to the project's progress. For example, it can provide detailed procedure manuals in the initial stages of the project and simplify them as the project progresses. It can also progressively increase the detail of the procedure manuals as the project progresses. Furthermore, it can adjust the format and expression of the procedure manuals based on the project's progress. By providing procedure manuals tailored to the project's progress, the understanding and execution efficiency of the procedure manuals are improved.

[0104] The document analysis unit can estimate the user's emotions and adjust the notification method of the analysis results based on the estimated emotions. For example, if the user is stressed, the notification can be kept to a minimum and only important information can be provided. If the user is relaxed, a detailed notification can be provided to allow the user to understand it more deeply. Also, if the user is in a hurry, a concise notification can be provided. In this way, by adjusting the notification method of the analysis results according to the user's emotions, a notification method that is appropriate for the user can be provided.

[0105] The code analysis unit can estimate the user's emotions and adjust the feedback method of the analysis results based on those estimated emotions. For example, if the user is nervous, it can provide simple and highly visible feedback. If the user is relaxed, it can provide detailed feedback to allow the user to understand more deeply. If the user is in a hurry, it can provide concise feedback. In this way, by adjusting the feedback method of the analysis results according to the user's emotions, it can provide feedback that is appropriate for the user.

[0106] The procedure manual generation unit can estimate the user's emotions and adjust the content of the procedure manual based on those emotions. For example, if the user is stressed, it can provide a concise and easy-to-understand procedure manual. If the user is relaxed, it can provide a detailed procedure manual to allow for deeper understanding. Furthermore, if the user is in a hurry, it can provide a procedure manual that can be executed quickly. In this way, by adjusting the content of the procedure manual according to the user's emotions, it can provide a procedure manual that is appropriate for the user.

[0107] The continuous learning unit can estimate the user's emotions and adjust the learning pace based on those emotions. For example, if the user is stressed, the learning pace can be slowed to reduce the burden. If the user is relaxed, the learning pace can be accelerated to promote deeper understanding. Furthermore, if the user is in a hurry, the learning pace can be adjusted to allow for faster learning. In this way, by adjusting the learning pace according to the user's emotions, a learning pace tailored to the user can be provided.

[0108] The procedure manual generation unit can estimate the user's emotions and adjust the procedure manual format based on those emotions. For example, if the user is nervous, it can provide a simple and highly visible format. If the user is relaxed, it can provide a format that includes detailed information. If the user is in a hurry, it can provide a format that gets straight to the point. In this way, by adjusting the procedure manual format according to the user's emotions, it can provide a format that is suitable for the user.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The document analysis unit analyzes the design document and extracts important test items. The document analysis unit uses natural language processing technology to analyze the design document and automatically identifies the functions and conditions that should be tested through morphological analysis, grammatical analysis, and semantic analysis. Step 2: The code analysis unit analyzes the program code to identify the test target. The code analysis unit uses static and dynamic analysis techniques to analyze the program code and identify the code structure, changes, and scope of impact. Step 3: The procedure manual generation unit generates test procedures based on the information extracted by the document analysis unit and the code analysis unit. The procedure manual generation unit automatically generates detailed and structured test procedures based on the extracted test items and test targets, and creates the procedures in a consistent format in Excel or Word format. Step 4: The continuous learning unit learns from the results of the tests performed and improves the accuracy of the procedure manual generation unit. The continuous learning unit analyzes past test results and uses a learning algorithm to improve the accuracy of the next test procedure manual.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0112] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0113] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements described above, including the document analysis unit, code analysis unit, procedure manual generation unit, and continuous learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the document analysis unit is implemented by the control unit 46A of the smart device 14, which analyzes the design document using natural language processing technology and extracts important test items. The code analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the program code using static analysis technology and identifies the parts that require testing. The procedure manual generation unit is implemented by the control unit 46A of the smart device 14, which automatically generates a detailed and structured test manual based on the extracted information. The continuous learning unit is implemented by the identification processing unit 290 of the data processing unit 12, which learns from the results of the tests performed and improves the accuracy of the procedure manual generation unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0119] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0122] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0123] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0125] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0126] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the document analysis unit, code analysis unit, procedure manual generation unit, and continuous learning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the document analysis unit is implemented by the control unit 46A of the smart glasses 214, which analyzes the design document using natural language processing technology and extracts important test items. The code analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the program code using static analysis technology and identifies the parts that require testing. The procedure manual generation unit is implemented by the control unit 46A of the smart glasses 214, which automatically generates a detailed and structured test manual based on the extracted information. The continuous learning unit is implemented by the identification processing unit 290 of the data processing unit 12, which learns from the results of the tests performed and improves the accuracy of the procedure manual generation unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0131] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0132] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0139] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the document analysis unit, code analysis unit, procedure manual generation unit, and continuous learning unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the document analysis unit is implemented by the control unit 46A of the headset terminal 314, which analyzes the design document using natural language processing technology and extracts important test items. The code analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the program code using static analysis technology and identifies the parts that require testing. The procedure manual generation unit is implemented by the control unit 46A of the headset terminal 314, which automatically generates a detailed and structured test manual based on the extracted information. The continuous learning unit is implemented by the identification processing unit 290 of the data processing unit 12, which learns from the results of the tests performed and improves the accuracy of the procedure manual generation unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

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

[0148] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

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

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

[0153] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

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

[0155] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0156] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements described above, including the document analysis unit, code analysis unit, procedure manual generation unit, and continuous learning unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the document analysis unit is implemented by the control unit 46A of the robot 414, which analyzes the design document using natural language processing technology and extracts important test items. The code analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the program code using static analysis technology and identifies the parts that require testing. The procedure manual generation unit is implemented by the control unit 46A of the robot 414, which automatically generates a detailed and structured test manual based on the extracted information. The continuous learning unit is implemented by the identification processing unit 290 of the data processing unit 12, which learns from the results of the tests performed and improves the accuracy of the procedure manual generation unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0164] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0166] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0167] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0168] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0169] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0172] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0173] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0174] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0175] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0176] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0177] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0179] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0180] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0181] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0182] (Note 1) The document analysis unit analyzes the design documents and extracts important test items, A code analysis unit that analyzes program code to identify the test target, A procedure manual generation unit generates a test procedure manual based on the information extracted by the document analysis unit and the code analysis unit, The system includes a continuous learning unit that learns from the results of the tests performed to improve the accuracy of the procedure manual generation unit. A system characterized by the following features. (Note 2) The aforementioned document analysis unit, Analyze the design document using natural language processing to extract important test items. The system described in Appendix 1, characterized by the features described herein. (Note 3) The code analysis unit, Automatically analyze program code to identify test targets. The system described in Appendix 1, characterized by the features described herein. (Note 4) The procedure document generation unit, Based on the extracted information, a detailed and structured test procedure manual is automatically generated. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned continuous learning unit, Based on the test results, the AI ​​continuously learns and improves its accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 6) The procedure document generation unit, Create instruction manuals in a consistent format using Excel or Word. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned document analysis unit, We estimate the user's emotions and adjust the design document analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned document analysis unit, When analyzing design documents, the analysis algorithm is optimized by referring to past design document data. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned document analysis unit, When analyzing design documents, different analysis methods are applied depending on the category of the design document. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned document analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned document analysis unit, When analyzing design documents, the priority of the analysis is determined based on when the design documents were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned document analysis unit, When analyzing design documents, referencing related literature to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 13) The code analysis unit, It estimates user sentiment and adjusts the code analysis method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The code analysis unit, During code analysis, the analysis algorithm is optimized by referring to past code data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The code analysis unit, When analyzing code, different analysis methods are applied depending on the category of the code. The system described in Appendix 1, characterized by the features described herein. (Note 16) The code analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The code analysis unit, During code analysis, the priority of analysis is determined based on when the code was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The code analysis unit, When analyzing code, referencing relevant literature improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 19) The procedure document generation unit, The system estimates the user's emotions and adjusts the method of generating the instruction manual based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The procedure document generation unit, When generating procedure manuals, the generation algorithm is optimized by referring to past procedure manual data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The procedure document generation unit, When generating procedure manuals, different generation methods are applied depending on the category of the procedure manual. The system described in Appendix 1, characterized by the features described herein. (Note 22) The procedure document generation unit, The system estimates the user's emotions and adjusts how the instruction manual is displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The procedure document generation unit, When generating procedure manuals, the generation priority is determined based on the submission date of the procedure manuals. The system described in Appendix 1, characterized by the features described herein. (Note 24) The procedure document generation unit, When generating procedure manuals, we improve the accuracy of the generation by referring to related literature for the procedure manuals. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned continuous learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned continuous learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned continuous learning unit, During training, different training methods are applied depending on the category of the training data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned continuous learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned continuous learning unit, During training, the training priority is determined based on when the training data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned continuous learning unit, During training, we improve the accuracy of the learning process by referring to relevant literature on the training data. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The document analysis unit analyzes the design documents and extracts important test items, A code analysis unit that analyzes program code to identify the test target, A procedure manual generation unit generates a test procedure manual based on the information extracted by the document analysis unit and the code analysis unit, The system includes a continuous learning unit that learns from the results of the tests performed to improve the accuracy of the procedure manual generation unit. A system characterized by the following features.

2. The aforementioned document analysis unit, Analyze the design document using natural language processing to extract important test items. The system according to feature 1.

3. The code analysis unit, Automatically analyze program code to identify test targets. The system according to feature 1.

4. The procedure document generation unit, Based on the extracted information, a detailed and structured test procedure manual is automatically generated. The system according to feature 1.

5. The aforementioned continuous learning unit, Based on the test results, the AI ​​continuously learns and improves its accuracy. The system according to feature 1.

6. The procedure document generation unit, Create instruction manuals in a consistent format using Excel or Word. The system according to feature 1.

7. The aforementioned document analysis unit, We estimate the user's emotions and adjust the design document analysis method based on the estimated user emotions. The system according to feature 1.

8. The aforementioned document analysis unit, When analyzing design documents, the analysis algorithm is optimized by referring to past design document data. The system according to feature 1.

9. The aforementioned document analysis unit, When analyzing design documents, different analysis methods are applied depending on the category of the design document. The system according to feature 1.

Images