system

Abstract

We provide the system. [Solution] A system that utilizes generative AI to include means for communicating requirements and specifications, means for generating test cases, means for generating key points for testing, and means for generating elements that lead to defects.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] Since there are no QA and test engineers for each service, the tests conducted during the release of new features are insufficient, resulting in market bugs.

Means for Solving the Problems

[0005] By utilizing generative AI and conveying requirements and specifications, test cases, key points of testing, and elements leading to defects are generated. As a result, it becomes possible to a certain extent to prevent defects that have slipped through until now and led to market bugs before release.

Brief Description of the Drawings

[0006] [Figure 1] It 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. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 1 of Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 of Embodiment 2. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Form Example 2. [Figure 15] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 3 of Example 3. [Figure 16] This is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Form Example 3. [Figure 17]It is a sequence diagram showing the processing flow of the data processing system in Example 1 of Form Example 1 when combined with an emotion engine. [Figure 18] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. [Figure 19] It is a sequence diagram showing the processing flow of the data processing system in Example 2 of Form Example 2 when combined with an emotion engine. [Figure 20] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Form Example 2 when combined with an emotion engine. [Figure 21] It is a sequence diagram showing the processing flow of the data processing system in Example 3 of Form Example 3 when combined with an emotion engine. [Figure 22] It is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Form Example 3 when combined with an emotion engine. [Figure 23] It is a sequence diagram showing the processing flow of the data processing system in other embodiments.

Embodiments for Carrying Out the Invention

[0007] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)), etc.

[0010] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0011] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

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

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0014] [First Embodiment]

[0015] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0016] As shown in Figure 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.

[0017] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 comprises a computer 36, a reception 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 reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0019] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0021] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0023] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0024] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

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

[0026] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0027] "Example of form 1"

[0028] One embodiment of the present invention provides a system utilizing generative AI. This system includes means for communicating requirements and specifications, means for generating test cases, means for generating key points for testing, and means for generating elements that lead to defects. Specifically, to solve the problem of market bugs occurring due to insufficient testing during new feature releases, the generative AI analyzes the requirements and specifications and generates test cases, key points for testing, and elements that lead to defects based on them.

[0029] "Example of form 2"

[0030] As a concrete example, before the release of a new feature, a generative AI analyzes the requirements and specifications and generates test cases. These generated test cases complement the tests performed manually by test engineers. The generative AI also generates key points for testing, indicating areas where test engineers should focus their testing. Furthermore, the generative AI generates elements that could lead to defects, indicating areas where test engineers should pay particular attention during testing. This makes it possible to prevent defects that previously slipped through the cracks and led to market bugs before release.

[0031] "Example of form 3"

[0032] As a concrete example, before the release of a new feature, a generative AI analyzes the requirements and specifications and generates test cases. These generated test cases complement the tests performed manually by test engineers. The generative AI also generates key points for testing, indicating areas where test engineers should focus their testing. Furthermore, the generative AI generates elements that could lead to defects, indicating areas where test engineers should pay particular attention during testing. This makes it possible to prevent defects that previously slipped through the cracks and led to market bugs before release.

[0033] The following describes the processing flow for each example of the form.

[0034] "Example of form 1"

[0035] Step 1: Before releasing a new feature, the generative AI receives the requirements and specifications.

[0036] Step 2: Generative AI analyzes the requirements and specifications.

[0037] Step 3: Based on the analysis, the generative AI generates test cases.

[0038] Step 4: Generative AI generates key points for testing.

[0039] Step 5: The generative AI generates elements that lead to malfunctions.

[0040] "Example of form 2"

[0041] Step 1: Before releasing a new feature, the generative AI receives the requirements and specifications.

[0042] Step 2: Generative AI analyzes the requirements and specifications.

[0043] Step 3: Based on the analysis, the generative AI generates test cases. The generated test cases complement the tests that test engineers perform manually.

[0044] Step 4: The generative AI generates key points for testing, indicating to the test engineers which areas should be prioritized for testing.

[0045] Step 5: Generative AI generates elements that could lead to bugs, and test engineers highlight areas that require particularly careful testing. This makes it possible to prevent bugs that previously slipped through the cracks and led to market bugs before release.

[0046] (Example 1)

[0047] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0048] When introducing new features, it is necessary to address the problem of defects occurring in the market due to insufficient testing. Furthermore, preventing defects that were previously overlooked and led to market defects is also a crucial challenge.

[0049] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0050] In this invention, the server includes means for analyzing requirements and specifications using an information processing device, means for generating test cases based on the analysis results, and means for extracting important test points from the test cases. This makes it possible to increase the comprehensiveness of testing and prevent defects from occurring in the market.

[0051] An "information processing device" is a device used for inputting, processing, and outputting data, and includes devices such as computers and servers.

[0052] "Requirements and specifications" refer to detailed descriptions of the functions and performance that a system or software must meet, and are documents that serve as the basis for development.

[0053] "Analysis" is the process of examining given information in detail to understand its meaning and structure.

[0054] A "test case" is a specific test scenario designed to verify that a particular function or specification works correctly.

[0055] A "critical test point" refers to a point in a test case that requires particular attention and has the potential to significantly impact the quality and safety of the system.

[0056] A "defect" refers to a malfunction or bug that causes a system or software to fail to function as expected.

[0057] As an embodiment for carrying out this invention, a system utilizing a generative AI model is provided. This system has the function of analyzing requirements and specifications using an information processing device, generating test cases based on the analysis results, and further extracting important test points from the test cases.

[0058] The server uses a generative AI model to analyze the requirements and specifications provided by the user. This analysis utilizes natural language processing techniques and employs common AI models to understand the meaning of the requirements. Specifically, it can use AI models that are widely available as software for natural language processing.

[0059] Based on the analysis results, the server generates test cases. These test cases include specific test scenarios to verify that the system's functions and specifications work correctly. For example, if a user enters a prompt such as "Analyze the requirements for the new payment function and generate test cases," the server will analyze the requirements related to the payment function and generate test cases.

[0060] Furthermore, the server extracts key test points from the generated test cases. These key test points highlight areas requiring particular attention and identify parts that could significantly impact the system's quality and security.

[0061] In this way, the system can increase the comprehensiveness of testing and prevent defects from occurring in the market.

[0062] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0063] Step 1:

[0064] Users input requirements and specifications for the system in text format. This input includes detailed descriptions of new features and expected behavior. The entered data is sent to the server and prepared for analysis.

[0065] Step 2:

[0066] The server uses a generative AI model to analyze the requirements and specifications entered by the user. Specifically, it utilizes natural language processing techniques to understand the grammatical and semantic structure of the input text. This analysis accurately grasps the meaning of the requirements and generates data for use in the next step. The output is structured data of the analyzed requirements.

[0067] Step 3:

[0068] The server generates test cases based on the analysis results. This process uses a generative AI model to create test cases for both normal and abnormal scenarios, covering all possible scenarios. For example, if a user enters the prompt "Analyze the requirements for a new payment function and generate test cases," the server will list test cases related to the payment function. The output will be a list of specific test cases.

[0069] Step 4:

[0070] The server extracts key test points based on the generated test cases. This step identifies points requiring particular attention within the test cases, helping to prioritize the tests. Specifically, security-related test cases and areas that may affect system stability are highlighted. The output is a list of key test points.

[0071] Step 5:

[0072] The server identifies elements that could lead to defects based on the analysis of requirements and specifications and the generated test cases. This process refers to historical data and common bug patterns to identify potential risks. For example, insufficient validation of input values ​​or problems with boundary values ​​may be pointed out. The output is a list of potential defect elements.

[0073] (Application Example 1)

[0074] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server," and the smart device 14 will be referred to as a "terminal."

[0075] In control programs for factory automation equipment, a problem exists where insufficient operational testing occurs when new features are released, leading to market bugs and malfunctions. This problem can reduce the efficiency of the manufacturing line and negatively impact product quality. Therefore, automating operational testing and preventing malfunctions before they occur is essential.

[0076] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0077] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating key points for testing, means for generating elements that lead to defects, means for automatically performing operational tests when new functions are released in the control program of the factory automation equipment, and means for analyzing the results of the operational tests to prevent malfunctions. This enables the automation of operational tests when new functions are released in the factory automation equipment and the prevention of malfunctions.

[0078] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and defect elements based on them.

[0079] "Means of communicating requirements and specifications" refers to methods for clearly defining the functions and performance required by the system and inputting them into a generative AI.

[0080] "Methods for generating test cases" refer to methods for automatically creating specific test items to verify the operation of software or systems based on requirements and specifications.

[0081] "Methods for generating key points for testing" refer to methods for extracting particularly important points and areas to pay attention to in a test, in order to conduct an efficient examination.

[0082] "Means of generating elements that lead to malfunctions" refers to methods for identifying potential problems in a system or software and evaluating the likelihood that these problems will lead to malfunctions.

[0083] "Factory automation equipment" is a general term for machines and devices used to automate manufacturing processes.

[0084] A "control program" is software used to instruct and manage the operation of factory automation equipment.

[0085] "Means for automatically performing operational tests" refers to a method for a generative AI to automatically perform operational tests when a new function of a control program is released.

[0086] "Means of analyzing operational test results and preventing malfunctions" refers to methods for evaluating the results of operational tests, identifying potential malfunctions, and preventing them.

[0087] The system for realizing this invention utilizes generative AI to automate operational testing when new functions are released in the control program of factory automation equipment. The server uses a generative AI model to analyze requirements and specifications and generate test cases. This makes it possible to automatically perform operational testing, analyze the test results, and prevent malfunctions before they occur.

[0088] Specifically, the server uses a generative AI model (e.g., OpenAI® GPT-4®) to receive requirements and specifications as input. Based on this, the AI ​​generates test cases and performs operational tests on the control program of the factory automation equipment. The test results are analyzed on the server to identify potential defects. This can improve the efficiency of the manufacturing line.

[0089] For example, when adding a new transport operation, the server generates a test case that includes "how to operate when the weight of the transported object exceeds a specified value" to verify that the robot operates correctly. An example of a prompt used in this process would be, "The requirements for the new transport operation are a maximum weight of 10 kg and a transport speed of 1 m / s. Please generate a test case based on these requirements."

[0090] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0091] Step 1:

[0092] The server receives requirements and specifications from the user regarding new functions for factory automation equipment. This input data includes specific specifications such as "maximum weight 10 kg, conveying speed 1 m / s." The server then prepares to input this information into the generating AI model.

[0093] Step 2:

[0094] The server uses a generative AI model to generate prompt statements based on the received requirements and specifications. The prompt statements are in the format of, "The requirements for the new transport operation are a maximum weight of 10 kg and a transport speed of 1 m / s. Please generate test cases based on these requirements." The server then inputs these prompt statements into the generative AI model.

[0095] Step 3:

[0096] The generation AI model analyzes the prompt text and generates test cases based on the requirements and specifications. The server receives the generated test cases and uses them as input data for operational testing.

[0097] Step 4:

[0098] The server uses the generated test cases to perform operational tests on the control programs of the factory automation equipment. These operational tests include simulations and actual machine tests to verify that the equipment operates according to specifications.

[0099] Step 5:

[0100] The server collects the results of operational tests and analyzes them using a generative AI model. This analysis identifies potential defects and malfunctions. The server reports the analysis results to the user and prompts them to modify the control program as needed.

[0101] (Example 2)

[0102] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0103] When releasing new features, there is a need to resolve the issue of market bugs arising due to insufficient testing. Furthermore, a system is needed to prevent bugs that slip through the cracks before release and lead to market bugs.

[0104] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0105] In this invention, the server includes means for inputting requirements and specifications, means for analyzing the requirements and specifications using a generation AI model, and means for generating test cases based on the analysis results. This makes it possible to prevent defects that could lead to market bugs before release.

[0106] "Requirements and specifications" are documents that describe in detail the functions, performance, and constraints that a system or software must meet.

[0107] A "generative AI model" is an algorithm or framework that uses artificial intelligence technology to analyze data and generate new information or results.

[0108] "Analysis" is the process of thoroughly examining given data or information to understand its structure and meaning.

[0109] A "test case" is a set of conditions or procedures designed to verify a specific function or behavior of software or a system.

[0110] A "key point" refers to an important point or element that requires particular attention in a specific task or process.

[0111] A "malfunction" refers to a state in which a system or software does not function as expected or does not meet specifications.

[0112] A "market bug" is a defect or flaw discovered after a product has been released to the market, and is a problem that may affect users.

[0113] A "server" is a computer system that provides services to other computers on a network.

[0114] A description of embodiments for carrying out this invention will be given.

[0115] The server first receives requirements and specifications for new features from the user. The user sends specific requirements and specifications to the server in text format. This information becomes the basic data for the generative AI model to analyze.

[0116] Next, the server uses a generative AI model to analyze the received requirements and specifications. The generative AI model utilizes natural language processing techniques to extract the information necessary for generating test cases from the requirements and specifications. Machine learning frameworks such as TENSORFLOW® and PyTorch are used for this analysis.

[0117] Based on the analysis results, the server generates test cases using a generated AI model. The generated test cases include specific test scenarios and procedures, complementing tests performed manually by test engineers. For example, abnormal test cases for the user authentication function are generated.

[0118] Furthermore, the server uses a generative AI model to generate key testing points. This allows test engineers to understand which areas should be tested most thoroughly. The server also generates elements that could lead to defects, highlighting areas that require particularly careful testing. For example, it might point out a potential security vulnerability in the user authentication function.

[0119] As a concrete example, before the release of a new mobile app, a generative AI model analyzes the requirements for "user authentication functionality" and generates test cases. The generated test cases include abnormal case tests during login and tests for the password reset function. An example of a prompt to input to the generative AI model would be, "Generate test cases for user authentication functionality."

[0120] This system allows users to prevent bugs that could lead to market issues before release.

[0121] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0122] Step 1:

[0123] The server receives requirements and specifications for new features from the user as input. The user sends specific requirements and specifications to the server in text format. This input data becomes the basic data for analysis by the generating AI model.

[0124] Step 2:

[0125] The server inputs the received requirements and specifications into a generating AI model for analysis. The generating AI model uses natural language processing technology to analyze the requirements and specifications and extract the information necessary for test case generation. In this analysis process, the input text data is tokenized and semantic analysis is performed to obtain the elements necessary for test case generation as output.

[0126] Step 3:

[0127] The server generates test cases using an AI model based on the analysis results. Specifically, it automatically designs test scenarios and procedures based on the extracted information. In this process, the analysis results are used as input, and specific test cases are generated as output. For example, abnormal test cases for the user authentication function are generated.

[0128] Step 4:

[0129] The server uses a generative AI model to generate key test points. Based on the analysis results, test engineers identify areas that should be tested intensively. This process uses the analysis results as input and generates information indicating key test points as output.

[0130] Step 5:

[0131] The server generates elements that could lead to defects and indicates areas that require particularly careful testing. The generating AI model identifies potential defect elements based on the analysis results and alerts test engineers. This process uses the analysis results as input and generates information indicating defect elements as output.

[0132] Step 6:

[0133] The server outputs generated test cases, key testing points, and potential bugs to the user. Based on this information, the user develops a test plan and conducts the actual tests. The outputted information serves as crucial guidance for the user to prevent market bugs before release.

[0134] (Application Example 2)

[0135] Next, we will describe Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server," and the smart device 14 will be referred to as a "terminal."

[0136] In factory automation equipment, a problem exists where new features are not adequately tested before release, leading to defects in the market. This problem arises because test engineers find it difficult to identify areas that need focused inspection. Furthermore, manually creating test cases is time-consuming, labor-intensive, and inefficient. As a result, it is difficult to prevent defects before release.

[0137] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0138] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating key points for testing, means for generating elements that could lead to defects, means for generating test cases for new functions of factory automation equipment and indicating areas that should be inspected intensively, and means for confirming the generated test cases on an information terminal. This makes it possible to improve the efficiency of testing new functions of factory automation equipment and to prevent defects before release.

[0139] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and key points for testing based on them.

[0140] "Means of communicating requirements and specifications" refers to interfaces and processes for inputting system requirements and specifications into a generative AI and analyzing them.

[0141] "Methods for generating test cases" refers to a function that automatically creates test cases that test engineers should implement based on requirements and specifications analyzed by a generative AI.

[0142] "Methods for generating key points in testing" refers to a function where a generative AI identifies particularly important areas in testing and presents them to the test engineer.

[0143] "Means for generating elements that lead to defects" refers to a function in which a generative AI identifies elements from requirements and specifications that could potentially cause defects and alerts test engineers to them.

[0144] "Factory automation equipment" is a general term for machines and systems used to automate production processes in factories.

[0145] An "information terminal" is a device used to verify generated test cases and key points of testing, and includes smartphones and tablets.

[0146] The system for implementing this invention utilizes generative AI to automatically generate test cases for new functions of factory automation equipment, indicating areas that test engineers should focus on inspecting. The server uses generative AI to analyze requirements and specifications and generates test cases, key testing points, and factors that could lead to defects. This enables test engineers to conduct tests efficiently.

[0147] The server uses the Python programming language and the OpenAI API to input requirements and specifications as prompts into the generative AI model. The generative AI model generates test cases based on the input prompts and returns the results to the server. The server then sends the generated test cases to an information terminal for review by a test engineer.

[0148] Information terminals, such as smartphones and tablets, display generated test cases and key points for testing. Test engineers can use these terminals to review the generated information and identify areas that require focused inspection.

[0149] For example, if the new function of a factory automation device is "automatic object identification and classification," the server will input the following prompt message into the generating AI model.

[0150] Example of a prompt:

[0151] Requirements: The factory automation equipment will be given a new function to automatically identify and classify objects. Please generate test cases for this function.

[0152] By inputting this prompt into the AI ​​model, relevant test cases are generated, allowing test engineers to identify areas where testing should focus.

[0153] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0154] Step 1:

[0155] The server receives requirements and specifications for new features of factory automation equipment. It uses text data of these requirements and specifications provided by the user as input. The server analyzes this data and generates prompts for input into the AI ​​model.

[0156] Step 2:

[0157] The server sends the generated prompt text to the generative AI model via the OpenAI API. Using the prompt text as input, the generative AI model generates test cases based on it. The generated test cases are returned to the server as output.

[0158] Step 3:

[0159] The server analyzes the test cases received from the generated AI model to identify key testing points and elements that could lead to defects. Using the generated test cases as input, the server analyzes them to identify areas that should be inspected intensively. The analysis results are sent to the information terminal.

[0160] Step 4:

[0161] The terminal displays test cases and analysis results received from the server. Using data from the server as input, the terminal visually presents the information for the test engineer to review. The test engineer then reviews the information generated through the terminal and performs the actual testing.

[0162] (Example 3)

[0163] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0164] When releasing new features, traditional manual testing is insufficient, leading to defects in the market. Furthermore, there's a risk of overlooking potential bugs before release, resulting in market bugs. To address these issues, it's necessary to efficiently and effectively generate test cases and identify areas that require focused testing.

[0165] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0166] In this invention, the server includes means for inputting requirements and specifications into an information processing device, means for analyzing the input requirements and specifications using a generation AI model, and means for generating test cases based on the analysis results. This makes it possible to efficiently generate test cases before the release of new functions and prevent potential defects.

[0167] An "information processing device" is a device that has the function of inputting, processing, and outputting data, and includes devices such as computers and servers.

[0168] "Requirements and specifications" are documents that describe in detail the conditions and functions that a system or software must meet.

[0169] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and automatically perform specific tasks.

[0170] "Analysis" is the process of thoroughly examining input data and understanding its structure and meaning.

[0171] A "test case" is a set of conditions or procedures designed to verify a specific function of software or a system.

[0172] "Key areas" are important parts or areas that require special attention during the test.

[0173] A "defective element" is an element or condition in a system or software that has the potential to cause problems.

[0174] A description of embodiments for carrying out this invention will be given.

[0175] The user inputs requirements and specifications for new functions using an information processing device. The input data is sent to the server. The server analyzes these requirements and specifications using a generative AI model. The analysis utilizes natural language processing technology to extract important information from the text data. Specifically, a general generative AI model is used to analyze the input requirements and specifications in detail.

[0176] Based on the analysis results, the server generates test cases. These generated test cases are designed to verify specific functions of the software or system. Furthermore, the server uses a generation AI model to identify areas of focus for testing and extract potential defects. This allows test engineers to understand where testing should be concentrated.

[0177] As a concrete example, if a user wants to generate test cases for the login function of a new mobile app, they would enter the prompt message "Generate test cases for the login function of the new mobile app" on their device. Based on this prompt, the server uses a generation AI model to generate the relevant test cases and outputs them to the device. This entire process allows the user to efficiently prepare test cases and prevent potential bugs. The specific processing flow in Example 3 will be explained using Figure 15.

[0178] Step 1:

[0179] Users input requirements and specifications for new features using a terminal. The entered data is sent to the server in text file or document format. This input data forms the basis for subsequent analysis.

[0180] Step 2:

[0181] The server inputs the received requirements and specifications into a generative AI model. The generative AI model uses natural language processing techniques to analyze the text data and extract important information. This analysis provides the data necessary for generating test cases. Specifically, it identifies functions and conditions related to testing from the requirements.

[0182] Step 3:

[0183] The server generates test cases based on the analysis results. The generation AI model uses the extracted information to determine what tests are needed and creates specific test cases. For example, a test case such as "Verify that the user can log in when they enter the correct credentials" is generated. These generated test cases are output to a terminal for use by test engineers.

[0184] Step 4:

[0185] The server uses a generative AI model to identify key areas for testing. From the analysis results, it generates information indicating areas that test engineers should pay particular attention to. It also extracts potential defect elements and provides guidelines for preventing potential problems. This allows test engineers to conduct tests efficiently.

[0186] Step 5:

[0187] The server outputs the generated test cases, areas of focus, and potential defects to the user's terminal. The user reviews this information and makes corrections or additions as needed. Finally, the test engineer uses these test cases to perform tests and ensure the quality of the new feature.

[0188] (Application Example 3)

[0189] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0190] Prior to the release of new features, there is a need to resolve issues that arise in the market due to insufficient testing. Furthermore, in factory robot control software, a challenge is to proactively identify and prevent potential operational defects.

[0191] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0192] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, and means for performing operational simulations. This makes it possible to identify and prevent potential defects before release.

[0193] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and defect elements.

[0194] "Means of communicating requirements and specifications" refers to an interface for inputting system requirements and specifications into a generative AI and performing analysis.

[0195] "Methods for generating test cases" refers to a function that automatically creates test cases for use by test engineers based on requirements and specifications analyzed by a generative AI.

[0196] "Methods for generating key points for testing" refers to a function in which a generative AI uses analysis results to indicate areas that should be tested with particular emphasis.

[0197] "Means of generating elements that lead to defects" refers to the function of a generative AI that identifies elements that could potentially cause defects through the analysis of requirements and specifications.

[0198] "Means for performing motion simulations" refers to a function that reproduces the operation of a system or robot in a virtual environment based on generated test cases, and uses this to verify operation and identify defects.

[0199] "Methods for identifying potential defects" refers to a function that combines generative AI and behavioral simulation to identify defects that are difficult to detect before release.

[0200] The system for implementing this invention includes a program that utilizes generative AI to analyze requirements and specifications and generate test cases. The server uses a generative AI model to analyze requirements and specifications and generate test cases. Specifically, the server uses a generative AI model (e.g., OpenAI's GPT-4) and automatically generates test cases by inputting requirements and specifications.

[0201] The generated test cases are used to perform operational simulations. The server uses simulation software (e.g., Gazebo) to reproduce the operation of the system or robot in a virtual environment. This simulation allows for the identification of potential defects and the prevention of problems before release.

[0202] As a concrete example, consider a case where a factory robot performs a new assembly operation. The server inputs the "requirements and specifications for the new assembly operation" into a generative AI model and generates test cases. Based on the generated test cases, the robot's operation is simulated using Gazebo to identify any operational defects.

[0203] Examples of prompt statements to input into the generative AI model are as follows:

[0204] "Analyze the requirements and specifications for the new assembly operation and generate test cases. Based on the generated test cases, perform robot motion simulations to identify potential defects."

[0205] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[0206] Step 1:

[0207] The server receives requirements and specifications for new features from the user. It uses the user-provided requirements and specification documents as input. The server then converts these into prompt statements for input into the generating AI model.

[0208] Step 2:

[0209] The server inputs prompt statements into the generative AI model, which then analyzes the requirements and specifications. The generative AI model generates test cases based on the input prompt statements. The output is a list of the generated test cases.

[0210] Step 3:

[0211] The server prepares to perform operational simulations based on the generated test cases. It takes a list of test cases as input and converts them into a format suitable for simulation software (e.g., Gazebo).

[0212] Step 4:

[0213] The server uses simulation software to reproduce the operation of systems and robots in a virtual environment. It uses the converted test cases as input and runs the simulation. The simulation results are obtained as output.

[0214] Step 5:

[0215] The server analyzes the simulation results and identifies potential defects. Using the simulation results as input, it extracts defect elements using a generative AI model. The output is a list of identified defects.

[0216] Step 6:

[0217] The server provides the user with a list of identified bugs. The user can use this to fix problems before release. The output includes a list of bugs provided to the user.

[0218] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0219] "Example of form 1"

[0220] In one embodiment of the present invention, a generative AI and an emotion engine are combined. The generative AI receives requirements and specifications and generates test cases, key testing points, and elements that could lead to defects. Meanwhile, the emotion engine recognizes the user's emotions and adjusts the test cases and key testing points based on those emotions. Specifically, it generates more rigorous test cases and emphasizes key testing points for features that the user might find unsatisfactory.

[0221] "Example of form 2"

[0222] In another embodiment of the present invention, the emotion engine adjusts elements that could lead to malfunctions based on the user's emotions. Specifically, it identifies elements that could lead to malfunctions for features that the user might find frustrating, and strengthens testing for those elements. For example, if the user feels that "feature A is slow," the emotion engine identifies "the performance of feature A" as a malfunctioning element and strengthens testing for that element.

[0223] "Example of form 3"

[0224] In a further embodiment of the present invention, a generative AI and an emotion engine work together. Specifically, the generative AI generates test cases, key testing points, and elements that could lead to defects, and then the emotion engine adjusts these based on the user's emotions. For example, if the user feels that "function B is too complex," the emotion engine will emphasize "ease of use of function B" as a key testing point and increase the number of test cases for that element.

[0225] The following describes the processing flow for each example of the form.

[0226] "Example of form 1"

[0227] Step 1: The generative AI receives the requirements and specifications.

[0228] Step 2: The generative AI generates test cases, key testing points, and factors that could lead to defects based on the received requirements and specifications.

[0229] Step 3: The emotion engine recognizes the user's emotions.

[0230] Step 4: The emotion engine adjusts the test cases and key points of the test generated by the generative AI based on the recognized user emotions.

[0231] "Example of form 2"

[0232] Step 1: The generative AI receives the requirements and specifications.

[0233] Step 2: The generative AI generates test cases, key testing points, and factors that could lead to defects based on the received requirements and specifications.

[0234] Step 3: The emotion engine recognizes the user's emotions.

[0235] Step 4: The emotion engine adjusts the elements that lead to malfunctions identified by the generative AI based on the recognized user emotions.

[0236] "Example of form 3"

[0237] Step 1: The generative AI receives the requirements and specifications.

[0238] Step 2: The generative AI generates test cases, key testing points, and factors that could lead to defects based on the received requirements and specifications.

[0239] Step 3: The emotion engine recognizes the user's emotions.

[0240] Step 4: The emotion engine adjusts the test cases, key points for testing, and factors that could lead to defects, which were generated by the generative AI based on the recognized user emotions.

[0241] (Example 1)

[0242] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0243] When introducing new features, insufficient testing can lead to defects in the market. Furthermore, it's difficult to prevent defects that were previously overlooked and resulted in market defects. Additionally, the lack of adjustments to test scenarios that take user sentiment into account makes it difficult to improve user satisfaction.

[0244] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0245] In this invention, the server includes means for transmitting requirements and specifications using generative artificial intelligence, means for generating test cases, means for generating key points of testing, means for generating elements that lead to defects, and means for recognizing the user's emotions using an emotion analysis engine and adjusting the test cases and key points of testing. This makes it possible to eliminate insufficient testing when introducing new functions and prevent the occurrence of defects in the market. Furthermore, it is possible to prevent defects that were overlooked in the past and to improve user satisfaction by adjusting test cases that take user emotions into consideration.

[0246] "Generative artificial intelligence" is a technology that analyzes requirements and specifications and automatically generates test examples, key points of testing, and elements that could lead to defects based on that analysis.

[0247] "Means of communicating requirements and specifications" refers to methods for conveying the requirements and specifications entered by the user to the system.

[0248] "Means for generating test cases" refers to methods for creating specific test cases to verify the operation of software based on analyzed requirements and specifications.

[0249] "Methods for generating key points for the exam" refer to methods for highlighting points that require particular attention during the exam, thereby enhancing the effectiveness of the exam.

[0250] "Means of generating elements that lead to defects" refers to methods for identifying potential risks by referring to past data and common failure patterns.

[0251] An "emotion analysis engine" is a technology that recognizes the user's emotions and adjusts test examples and key points of the test based on those emotions.

[0252] "Means of recognizing user emotions and adjusting test examples and key points of the test" refers to a method of analyzing user emotions and appropriately modifying test examples and key points of the test based on the results.

[0253] As an embodiment of this invention, a system combining generative artificial intelligence and an emotion analysis engine is used. The user inputs requirements and specifications through a terminal. The server analyzes these requirements and specifications using a generative AI model and generates test examples, key points of the test, and elements that lead to defects.

[0254] Specifically, the server utilizes natural language processing technology to extract key elements from the input requirements and specifications. For example, in response to the requirement "The user registration function requires users to enter an email address and password and then press the registration button to complete registration," it generates specific test examples such as email address format checks and password strength checks.

[0255] Furthermore, the sentiment analysis engine recognizes user emotions and adjusts test cases and test focus accordingly. If users are dissatisfied with a particular feature, the testing for that feature is intensified. For example, if a user feels the UI is difficult to use, additional test cases related to the UI are added and examined in detail.

[0256] As a concrete example, here is an example of a prompt statement to be input to a generative AI model:

[0257] "Analyze the requirements for the new user registration feature, generate necessary test cases and key test points, and enhance UI testing by considering user complaints about the user interface."

[0258] In this way, the server can utilize generative artificial intelligence and an emotion analysis engine to efficiently generate test cases based on user requirements, thereby improving software quality.

[0259] The flow of the specific processing in Example 1 will be explained using Figure 17.

[0260] Step 1:

[0261] Users input requirements and specifications into the system via their terminal. The entered data is sent to the server in text format. This input includes details about the new features and their expected behavior. For example, "The user registration function requires users to enter their email address and password and press the registration button to complete registration."

[0262] Step 2:

[0263] The server analyzes the input requirements and specifications using a generative AI model. It analyzes the input data using natural language processing techniques and extracts important elements. This analysis identifies specific test elements, such as email address format checks and password strength verification. The analysis results are generated as output and used in the next step.

[0264] Step 3:

[0265] The server generates test cases based on the analysis results. The generation AI model automatically creates appropriate test cases for the identified elements. For example, it generates test cases such as "a test case to confirm that registration is successful with a correctly formatted email address" or "a test case to confirm that the password is 8 characters or longer." The output lists specific test cases.

[0266] Step 4:

[0267] The server generates key points for the test. Based on the analysis results, it highlights points that require particular attention during the test. For example, it might present important checkpoints such as "Confirm that the registration process does not time out during network latency." The key points of the test are clearly indicated as output.

[0268] Step 5:

[0269] The server generates elements that lead to defects. The generative AI model refers to historical data and common failure patterns to identify potential risks. For example, it might list "errors that occur when input fields are not properly validated." The output identifies potential defect elements.

[0270] Step 6:

[0271] The server analyzes user emotions using an emotion analysis engine. It recognizes emotions based on user input and feedback, and reflects the results in the test case and key points of the test. For example, if a user feels the UI is difficult to use, the server adds a UI-related test case and examines it in detail. The adjusted test case is then provided as output.

[0272] (Application Example 1)

[0273] Next, Application Example 1 of Form Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0274] In the electronic payment service, there is a problem that market bugs occur due to insufficient testing at the time of releasing a new function, leading to user dissatisfaction. In addition, since test adjustment considering user feelings has not been performed, there is a problem that dissatisfaction with a specific function is not resolved.

[0275] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0276] In this invention, the server includes means for utilizing generative AI, means for conveying requirements and specifications, means for generating test cases, means for generating key points of tests, means for analyzing user feelings and adjusting test cases, and means for strengthening the test of new functions in the electronic payment service. Thereby, it is possible to prevent the occurrence of market bugs at the time of releasing new functions of the electronic payment service and reduce user dissatisfaction.

[0277] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and defect elements based on them.

[0278] "Means for conveying requirements and specifications" is a method for clarifying the functions and performance required by the system and inputting them into generative AI.

[0279] "Means for generating test cases" is a method for creating a specific test scenario for verifying the operation of software based on the requirements and specifications analyzed by generative AI.

[0280] "Means for generating key points of tests" is a method for extracting and emphasizing points or important parts that require special attention in tests.

[0281] "Means for generating elements that lead to defects" refers to methods for identifying and generating elements that could potentially cause problems or bugs in software.

[0282] "Methods for analyzing user emotions and adjusting test cases" refers to methods for analyzing user feedback and emotions and adjusting the content and emphasis of test cases based on that analysis.

[0283] "Means to enhance testing of new features in electronic payment services" refers to methods for conducting more rigorous and detailed testing of newly added features in electronic payment services.

[0284] The system for carrying out this invention includes a program that integrates a generative AI model and an emotion analysis engine. The server uses the generative AI model to analyze requirements and specifications and generates test cases and defect elements. Specifically, the server operates on the cloud and uses OpenAI's GPT-4 as the generative AI model. IBM Watson® Tone Analyzer is used for emotion analysis.

[0285] The device collects user feedback and sends it to the server. This user feedback is analyzed by an emotion analysis engine, and test cases are adjusted based on the results. This allows for more rigorous testing of features that users might find frustrating.

[0286] For example, if a user provides feedback that a new feature of an electronic payment service is "slow," the terminal sends this information to the server. The server uses a sentiment analysis engine to analyze this feedback and sends a prompt to a generative AI model to "enhance the test cases related to payment speed." The generative AI model then generates detailed test cases related to payment speed, thereby enhancing the testing process.

[0287] Examples of prompt statements are as follows:

[0288] User feedback: "Payment is slow."

[0289] Emotion analysis result: Dissatisfaction

[0290] Prompt: Enhance the test cases related to payment speed and generate more detailed tests.

[0291] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[0292] Step 1:

[0293] The terminal collects user feedback. Users input their complaints and opinions about new features of the electronic payment service in text format. The input feedback is then sent from the terminal to the server.

[0294] Step 2:

[0295] The server sends the received user feedback to the sentiment analysis engine. The sentiment analysis engine analyzes the text of the feedback and identifies the user's emotions. The analysis results may output emotions such as "dissatisfied" or "satisfied."

[0296] Step 3:

[0297] The server creates prompts for the generative AI model based on the results of sentiment analysis. These prompts include instructions to adjust test cases according to the user's emotions. For example, specific instructions such as "strengthen the test case regarding payment speed" are generated.

[0298] Step 4:

[0299] The generation AI model analyzes prompts received from the server and generates corresponding test cases. The generated test cases are output as detailed test scenarios for new features of the electronic payment service.

[0300] Step 5:

[0301] The server applies the generated test case to the test environment and conducts actual tests. The test results are recorded as the presence or absence of bugs and points for improving functions, and are used for the next feedback collection.

[0302] (Example 2)

[0303] Next, Example 2 of Embodiment 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0304] When a new function is released, it is required to solve the problem that bugs occur in the market due to insufficient testing. In addition, it is also an issue to improve user satisfaction by adjusting bug elements based on user feelings.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0306] In this invention, the server includes means for inputting requirements and specifications, means for analyzing the input requirements and specifications and generating test cases, and means for specifying key points of tests. Thereby, it is possible to prevent bugs in the market before the release of a new function and perform adjustments based on user feelings.

[0307] The "generative AI model" refers to artificial intelligence technology for analyzing requirements and specifications and automatically generating test cases and bug elements.

[0308] The "requirements and specifications" refer to information indicating detailed conditions and criteria regarding the design and operation of a new function.

[0309] The "test case" refers to a series of conditions and procedures designed to verify specific functions and operations of software or a system.

[0310] "Test focus areas" refer to important parts or functions that require particular attention during testing.

[0311] "Factors that lead to malfunctions" refer to factors or conditions that could potentially cause problems in software or systems.

[0312] "Adjusting bugs based on user emotions" refers to selecting bugs to be tested and improved, and adjusting their priorities, while taking user feedback and emotions into consideration.

[0313] "Providing generated test cases" refers to presenting test cases created by a generative AI model to test engineers and related systems.

[0314] The following system is configured as an embodiment for carrying out this invention.

[0315] The server functions as a platform for running generative AI models. Users input requirements and specifications for new features into a terminal, which then sends this data to the server. The server analyzes the input requirements and specifications using a generative AI model and generates test cases. This generative AI model leverages natural language processing techniques to automatically extract test cases and defect elements from the requirements and specifications.

[0316] As a concrete example, a user enters the prompt "Enter the requirements for new feature C and generate test cases" into the terminal. The terminal sends this prompt to the server, which analyzes the requirements using a generation AI model. As a result of the analysis, a specific test case is generated: "Test the usability of the user interface for new feature C."

[0317] Furthermore, the server uses a generative AI model to identify testing priorities, indicating to test engineers where testing should focus. Additionally, based on user feedback, an emotion engine adjusts elements that could lead to bugs, strengthening testing for features that might cause user dissatisfaction. This allows for proactive prevention of market bugs before release, thereby improving user satisfaction.

[0318] The flow of the specific processing in Example 2 will be explained using Figure 19.

[0319] Step 1:

[0320] The user enters the requirements and specifications for the new feature into the terminal. The entered data includes details of the feature and its expected behavior. This data serves as the foundational information for the generative AI model to analyze.

[0321] Step 2:

[0322] The terminal sends the entered requirements and specifications data to the server. The server receives this data and prepares it for input into the generated AI model.

[0323] Step 3:

[0324] The server analyzes requirements and specification data using a generative AI model. Specifically, it utilizes natural language processing techniques to extract information from the input data for generating test cases. This analysis clarifies the elements necessary for generating test cases.

[0325] Step 4:

[0326] The server generates specific test cases based on the results analyzed by the AI ​​model. For example, it might generate an instruction such as, "Create a test case to measure the response time of new feature C." This test case forms the basis for the tests performed by the test engineers.

[0327] Step 5:

[0328] The server uses a generated AI model to identify areas of focus for testing. This indicates where test engineers should concentrate their testing. For example, it might generate instructions such as, "Focus on testing the usability of the user interface for new feature C."

[0329] Step 6:

[0330] The device sends user feedback to the emotion engine. The emotion engine adjusts factors that could lead to problems based on the user's emotions. For example, if a user feels that "feature A is slow," the emotion engine will strengthen its instructions to focus testing on "the performance of feature A."

[0331] Step 7:

[0332] The server sends generated test cases, key points, and information about potential defects to the terminal. This allows test engineers to perform tests efficiently.

[0333] (Application Example 2)

[0334] Next, we will describe Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server," and the smart device 14 will be referred to as a "terminal."

[0335] When new features are released, insufficient testing can lead to bugs in the market, resulting in decreased user satisfaction. Furthermore, identifying and addressing bugs based on user emotions is difficult, ultimately compromising the user experience.

[0336] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0337] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating critical test areas, means for adjusting elements that could lead to defects based on the user's emotions using an emotion analysis engine, and means for analyzing user feedback and strengthening tests for identified functions. This enables proactive prevention of defects before the release of new features and allows for rapid responses based on user emotions.

[0338] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and elements that could lead to defects.

[0339] "Means of communicating requirements and specifications" refers to interfaces and processes for inputting system requirements and specifications into a generative AI and performing analysis.

[0340] "Methods for generating test cases" refers to a function that automatically creates test cases that test engineers should implement based on requirements and specifications analyzed by a generative AI.

[0341] "Methods for generating key areas of testing" refers to a function in which a generative AI identifies and presents areas that should be tested with particular emphasis based on the analysis results.

[0342] "Means for generating elements that lead to defects" refers to a function in which a generative AI identifies elements that could cause defects through the analysis of requirements and specifications, and presents them to test engineers.

[0343] An "emotion analysis engine" is a technology that analyzes user feedback and emotional data, and adjusts elements that lead to malfunctions based on the user's emotions.

[0344] "Methods for analyzing user feedback and strengthening testing of identified features" refers to processes or functions that analyze user feedback and strengthen testing of features that receive particularly high levels of dissatisfaction.

[0345] The system for implementing this invention involves a server and a terminal working in conjunction. The server uses a generative AI model to analyze requirements and specifications and generate test cases. Specifically, the server analyzes information input through means of communicating requirements and specifications and automatically creates test cases. Furthermore, the server identifies critical areas for testing and presents them to the test engineer.

[0346] The server also uses an emotion analysis engine to analyze user feedback. This allows it to adjust elements that lead to malfunctions based on user emotions and strengthen testing of identified features. The terminal is responsible for collecting user feedback and sending it to the server.

[0347] For example, if a user provides feedback that "payment processing is slow," the server uses a sentiment analysis engine to analyze this feedback and identify payment processing performance as a factor leading to a problem. A generative AI model then strengthens the test cases for this factor and notifies the test engineers.

[0348] An example of a prompt message is: "Analyze the requirements and specifications of the new feature and generate test cases. Also, identify potential bugs based on user feedback and strengthen the tests."

[0349] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[0350] Step 1:

[0351] The server receives requirements and specification data sent from the terminal. This data is used as input for analysis using a generative AI model. As a result of the analysis, test cases are generated, and critical testing areas are identified. This clarifies the areas where test engineers should focus their testing.

[0352] Step 2:

[0353] Users input feedback through their devices. This feedback is sent to a server. The server uses an emotion analysis engine to analyze the feedback and identify elements that may lead to problems based on the user's emotions. The analysis results generate information to strengthen testing for the identified elements.

[0354] Step 3:

[0355] The server notifies the test engineers of the generated test cases and enhanced test information. The test engineers then use this information to conduct tests and proactively prevent defects. This allows potential bugs to be discovered and fixed before release.

[0356] (Example 3)

[0357] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0358] When introducing new features, there is a need to address the problem of defects occurring in the market due to insufficient testing. Furthermore, there is the challenge of preventing defects that slip through the cracks before implementation and lead to market defects.

[0359] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0360] In this invention, the server includes means for inputting information, means for generating prompt statements, and means for generating test cases. This makes it possible to eliminate insufficient testing when introducing new functions and prevent defects from occurring in the market.

[0361] A "generative AI model" is an artificial intelligence technology that uses natural language processing to analyze requirements and specifications and generate test cases and key areas.

[0362] A "prompt statement" is an input statement created by the user to give specific instructions to the generating AI model.

[0363] A "test case" is a set of specific test procedures and conditions designed to verify the functionality and performance of software.

[0364] "Key areas for testing" refer to parts of the software that require particular attention during testing, and are identified by a generative AI model.

[0365] "Factors that lead to defects" refer to factors or conditions in software that could potentially cause defects.

[0366] An "emotion engine" is a technology used to refine test cases and key aspects based on user emotions and feedback.

[0367] A "server" is a computer system that hosts generative AI models and emotion engines, processes user input, and provides results.

[0368] The following system configurations are possible as embodiments for carrying out this invention.

[0369] The user inputs the requirements and specifications for the new feature using a terminal. The terminal can input detailed information using a text editor or a dedicated interface. Next, the user creates prompt statements for the generating AI model. Prompt statements are used to give specific instructions to the generating AI model, and may take the form of, for example, "Generate a case to test the input validation for new feature A."

[0370] The terminal sends a prompt message created by the user to the server. The server hosts a generative AI model, and upon receiving the prompt message, it analyzes the requirements and specifications using natural language processing techniques. Specifically, it can use generative AI models such as OpenAI's GPT series. Based on the analysis results, the server generates test cases and further identifies critical areas for testing and elements that could lead to defects.

[0371] The generated test cases and key areas are adjusted by the sentiment engine based on user emotions and feedback. For example, if a user feels that "feature B is too complex," the sentiment engine will highlight "ease of use of feature B" as a key area for testing and increase the number of test cases for that element.

[0372] Finally, the server sends the generated test cases and adjustment results to the terminal. The terminal receives this and displays it to the user. Based on this information, the user can work with the test engineer to plan and execute tests. In this way, it becomes possible to prevent defects in the market before release. The specific processing flow in Example 3 will be explained using Figure 21.

[0373] Step 1:

[0374] The user inputs the requirements and specifications for the new feature using a terminal. The entered information is saved on the terminal as text data. This data is used to generate subsequent prompt messages.

[0375] Step 2:

[0376] The user creates prompts for the generated AI model. These prompts are text data containing specific instructions based on requirements and specifications. For example, they might say, "Generate a case to test input validation for new feature A."

[0377] Step 3:

[0378] The terminal sends a prompt message to the server. The sent prompt message is input into the AI ​​model on the server. The server analyzes the prompt message and processes the data based on the requirements and specifications.

[0379] Step 4:

[0380] The server generates test cases using a generative AI model. The generative AI model analyzes the prompt text using natural language processing techniques and outputs appropriate test cases. This output is saved to the server as text data.

[0381] Step 5:

[0382] The server uses a generated AI model to identify critical test areas and elements that could lead to defects. The generated AI model analyzes prompts and requirements / specifications, outputting data that highlights specific areas.

[0383] Step 6:

[0384] The server uses the sentiment engine to refine the generated test cases and highlight key areas. The sentiment engine receives user feedback as input and uses it to emphasize or add to test cases.

[0385] Step 7:

[0386] The server sends the final test cases and adjustment results to the terminal. The terminal receives this and displays it to the user. The user then uses this to create a test plan and implements it in cooperation with the test engineer.

[0387] (Application Example 3)

[0388] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0389] Insufficient testing before the release of new features has led to bugs appearing in the market, and this issue needs to be resolved. Furthermore, there is a challenge in being unable to tailor test cases based on user sentiment, making it difficult to highlight particularly sensitive behaviors or features.

[0390] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0391] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating key points for testing, means for generating elements that could lead to defects, means for adjusting test cases based on user emotions using an emotion engine, and means for analyzing operator feedback and highlighting actions and functions that require particular attention. This makes it possible to prevent defects before release and to adjust test cases based on user emotions.

[0392] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases, key points for testing, and elements that could lead to defects.

[0393] "Means of communicating requirements and specifications" refers to the means of inputting system requirements and specifications into a generative AI for analysis.

[0394] "Means for generating test cases" refers to methods for automatically generating test cases based on requirements and specifications analyzed by a generative AI.

[0395] "Methods for generating key points for testing" refer to methods by which a generative AI, based on its analysis results, indicates areas that should be prioritized and checked during testing.

[0396] "Means for generating elements that lead to malfunctions" refers to the means by which a generative AI identifies and displays elements that could cause malfunctions based on its analysis results.

[0397] An "emotion engine" is a technology that analyzes user emotions and adjusts system behavior and test cases based on the results.

[0398] "Means for adjusting test cases based on user emotions" refers to means for adjusting generated test cases based on the user emotions analyzed by the emotion engine.

[0399] "Means for analyzing operator feedback and highlighting actions or functions that require special attention" refers to means for analyzing feedback from operators and highlighting actions or functions that require special attention.

[0400] The system for implementing this invention consists primarily of a server containing a program that combines a generative AI and an emotion engine. The server receives requirements and specifications as input and generates test cases using the generative AI. The generated test cases include key points for testing and elements that could lead to defects, thereby enabling the prevention of defects before release.

[0401] Furthermore, the emotion engine analyzes the user's emotions and adjusts test cases based on the results. Specifically, if a user is dissatisfied with a particular feature, it highlights test cases related to that feature and adjusts the testing focus accordingly.

[0402] This system utilizes high-performance servers and software such as Python and TensorFlow. Data processing and calculations are performed by a generative AI model that analyzes requirements and specifications, and an emotion engine that analyzes user feedback.

[0403] As a concrete example, in factory robot control software, if an operator provides feedback that "the movement is not smooth," the emotion engine will increase the number of test cases related to that movement and adjust the testing to focus on smoothness.

[0404] An example of a prompt to input into the generated AI model is, "Analyze the operating requirements of the factory robot and generate test cases to ensure smooth operation."

[0405] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[0406] Step 1:

[0407] The server receives requirements and specifications from the user as input. This input data includes detailed requirements and specifications for the control software of the factory robot. The server sends prompt messages to the generating AI model to analyze this data.

[0408] Step 2:

[0409] The generation AI model analyzes the requirements and specifications received from the server and generates test cases. This analysis determines what tests are necessary based on the requirements and outputs specific test cases. The generated test cases include key points for testing and elements that could lead to defects.

[0410] Step 3:

[0411] The server sends the generated test cases to the sentiment engine. The sentiment engine receives user sentiment data as input and adjusts the test cases. Specifically, if a user is dissatisfied with a particular feature, it highlights the test cases related to that feature and adjusts the testing focus accordingly.

[0412] Step 4:

[0413] The server provides the operator with a set of test cases. The operator then tests the factory robot's control software based on these test cases. This testing helps prevent defects before release.

[0414] Step 5:

[0415] The operator provides test results as feedback to the server. The server analyzes this feedback and readjusts the test cases and test focus as needed. This feedback loop improves the accuracy and efficiency of the tests.

[0416] (Other examples)

[0417] Next, other embodiments will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0418] In conventional systems, the process of analyzing the requirements and specifications of new functions and generating test cases is often done manually, which is time-consuming and labor-intensive, and also carries the risk of defects due to human error. Therefore, there is a need for a method that can efficiently and accurately analyze requirements and generate test cases.

[0419] The identification processing performed by the identification processing unit 290 of the data processing device 12 in other embodiments is realized by the following means.

[0420] In this invention, the server includes means for receiving requirements and specifications input from a user, means for generating prompts to instruct the AI ​​model to analyze the received requirements and specifications and inputting them into the AI ​​model, and means for generating test cases based on the analysis results from the AI ​​model. This makes it possible to efficiently and accurately analyze requirements and automatically generate test cases.

[0421] An "information processing device" is a computer system that receives input from a user, processes the data, and outputs analysis results.

[0422] "Requirements and specifications" are documents that specifically describe the functions and conditions that users need in developing new features.

[0423] A "prompt" is a set of instructions generated to tell a generative AI model to perform a specific analysis task.

[0424] A "generative AI model" is an artificial intelligence model that analyzes data based on input prompts and outputs the analysis results.

[0425] A "test case" is a specific test case generated based on requirements and specifications to verify the operation of the system.

[0426] "Important test points" refer to points in a test case that deserve particular attention, or areas where defects are likely to occur.

[0427] "Factors that lead to defects" are factors that can cause malfunctions or errors in the operation of a system.

[0428] ---

[0429] This invention begins with the user entering the requirements and specifications for a new function. The user accesses a dedicated input form on the system using a web browser and enters the requirements and specifications. For example, they might enter the requirement, "Add a function that allows users to log in."

[0430] The server receives requirements and specifications submitted by the user and stores them in a database. This data is used for subsequent processing.

[0431] Next, the server generates a prompt message instructing it to analyze the received requirements and specifications. This prompt message provides specific analysis tasks to the generating AI model. An example of a prompt message is: "Analyze the following requirements and specifications and generate relevant test cases."

[0432] The server inputs the generated prompt text into the generative AI model. OpenAI's GPT-4 is used as the generative AI model. The server sends the prompt text to the generative AI model via an API.

[0433] The generating AI model analyzes requirements and specifications based on prompt statements and outputs the analysis results. These analysis results contain the information necessary for generating test cases.

[0434] The server receives the analysis results from the generated AI model and generates test cases. This process uses a test case generation module implemented in Python. The generated test cases are stored in a database.

[0435] Furthermore, the server extracts key test points from the generated test cases. This is done using an algorithm employing data mining techniques. The extracted test points are displayed on the terminal via a web interface for the user to review.

[0436] Finally, the server identifies elements that lead to defects based on the analysis results and test cases. This identification uses an anomaly detection algorithm with a machine learning model. The identified defect elements are notified to the user, and corrections are made as needed.

[0437] In this way, it becomes possible to efficiently and accurately analyze requirements and automatically generate test cases.

[0438] The flow of specific processing in other embodiments will be explained using Figure 23.

[0439] Step 1:

[0440] The user accesses a dedicated input form on the system using a web browser and enters the requirements and specifications for the new feature. The entered data is sent from the user's terminal to the server. The server stores the received requirements and specifications in a database. In this step, the input is the requirements and specifications entered by the user, and the output is the requirements and specifications stored in the database.

[0441] Step 2:

[0442] The server generates a prompt message to instruct the system to analyze the stored requirements and specifications. Specifically, based on the content of the requirements and specifications, the server creates a prompt message that reads, "Analyze the following requirements and specifications and generate the relevant test examples." The input for this step is the requirements and specifications stored in the database, and the output is the generated prompt message.

[0443] Step 3:

[0444] The server inputs the generated prompt text into the generation AI model. The server sends the prompt text to the generation AI model via the API. The generation AI model analyzes the requirements and specifications based on the prompt text and outputs the analysis results. In this step, the input is the generated prompt text, and the output is the analysis results from the generation AI model.

[0445] Step 4:

[0446] The server receives the analysis results from the generative AI model and generates test cases. Specifically, it uses a test case generation module implemented in Python to create test cases based on the analysis results. The input for this step is the analysis results from the generative AI model, and the output is the generated test cases.

[0447] Step 5:

[0448] The server extracts key test points from the generated test cases. Using an algorithm employing data mining techniques, it identifies particularly noteworthy points within the test cases. The input for this step is the generated test cases, and the output is the extracted key test points.

[0449] Step 6:

[0450] The server identifies elements that could lead to defects based on analysis results and test examples. An anomaly detection algorithm using a machine learning model is then used to identify potential defect elements. The input for this step is the analysis results and test examples, and the output is the identified defect elements. The identified defect elements are notified to the user, and corrections are made as needed.

[0451] 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.

[0452] 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 the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0453] Other examples of generative AI include Gemini® (registered trademark) (Internet search). <url: https: gemini.google.com ?hl="ja">) are some examples.

[0454] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0455] [Second Embodiment]

[0456] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0457] 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.

[0458] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0459] 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.

[0460] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0461] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0462] 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.

[0463] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0464] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0465] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0466] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0467] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0468] "Example of form 1"

[0469] One embodiment of the present invention provides a system utilizing generative AI. This system includes means for communicating requirements and specifications, means for generating test cases, means for generating key points for testing, and means for generating elements that lead to defects. Specifically, to solve the problem of market bugs occurring due to insufficient testing during new feature releases, the generative AI analyzes the requirements and specifications and generates test cases, key points for testing, and elements that lead to defects based on them.

[0470] "Example of form 2"

[0471] As a concrete example, before the release of a new feature, a generative AI analyzes the requirements and specifications and generates test cases. These generated test cases complement the tests performed manually by test engineers. The generative AI also generates key points for testing, indicating areas where test engineers should focus their testing. Furthermore, the generative AI generates elements that could lead to defects, indicating areas where test engineers should pay particular attention during testing. This makes it possible to prevent defects that previously slipped through the cracks and led to market bugs before release.

[0472] "Example of form 3"

[0473] As a concrete example, before the release of a new feature, a generative AI analyzes the requirements and specifications and generates test cases. These generated test cases complement the tests performed manually by test engineers. The generative AI also generates key points for testing, indicating areas where test engineers should focus their testing. Furthermore, the generative AI generates elements that could lead to defects, indicating areas where test engineers should pay particular attention during testing. This makes it possible to prevent defects that previously slipped through the cracks and led to market bugs before release.

[0474] The following describes the processing flow for each example of the form.

[0475] "Example of form 1"

[0476] Step 1: Before releasing a new feature, the generative AI receives the requirements and specifications.

[0477] Step 2: Generative AI analyzes the requirements and specifications.

[0478] Step 3: Based on the analysis, the generative AI generates test cases.

[0479] Step 4: Generative AI generates key points for testing.

[0480] Step 5: The generative AI generates elements that lead to malfunctions.

[0481] "Example of form 2"

[0482] Step 1: Before releasing a new feature, the generative AI receives the requirements and specifications.

[0483] Step 2: Generative AI analyzes the requirements and specifications.

[0484] Step 3: Based on the analysis, the generative AI generates test cases. The generated test cases complement the tests that test engineers perform manually.

[0485] Step 4: The generative AI generates key points for testing, indicating to the test engineers which areas should be prioritized for testing.

[0486] Step 5: Generative AI generates elements that could lead to bugs, and test engineers highlight areas that require particularly careful testing. This makes it possible to prevent bugs that previously slipped through the cracks and led to market bugs before release.

[0487] (Example 1)

[0488] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0489] When introducing new features, it is necessary to address the problem of defects occurring in the market due to insufficient testing. Furthermore, preventing defects that were previously overlooked and led to market defects is also a crucial challenge.

[0490] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0491] In this invention, the server includes means for analyzing requirements and specifications using an information processing device, means for generating test cases based on the analysis results, and means for extracting important test points from the test cases. This makes it possible to increase the comprehensiveness of testing and prevent defects from occurring in the market.

[0492] An "information processing device" is a device used for inputting, processing, and outputting data, and includes devices such as computers and servers.

[0493] "Requirements and specifications" refer to detailed descriptions of the functions and performance that a system or software must meet, and are documents that serve as the basis for development.

[0494] "Analysis" is the process of examining given information in detail to understand its meaning and structure.

[0495] A "test case" is a specific test scenario designed to verify that a particular function or specification works correctly.

[0496] A "critical test point" refers to a point in a test case that requires particular attention and has the potential to significantly impact the quality and safety of the system.

[0497] A "defect" refers to a malfunction or bug that causes a system or software to fail to function as expected.

[0498] As an embodiment for carrying out this invention, a system utilizing a generative AI model is provided. This system has the function of analyzing requirements and specifications using an information processing device, generating test cases based on the analysis results, and further extracting important test points from the test cases.

[0499] The server uses a generative AI model to analyze the requirements and specifications provided by the user. This analysis utilizes natural language processing techniques and employs common AI models to understand the meaning of the requirements. Specifically, it can use AI models that are widely available as software for natural language processing.

[0500] Based on the analysis results, the server generates test cases. These test cases include specific test scenarios to verify that the system's functions and specifications work correctly. For example, if a user enters a prompt such as "Analyze the requirements for the new payment function and generate test cases," the server will analyze the requirements related to the payment function and generate test cases.

[0501] Furthermore, the server extracts key test points from the generated test cases. These key test points highlight areas requiring particular attention and identify parts that could significantly impact the system's quality and security.

[0502] In this way, the system can increase the comprehensiveness of testing and prevent defects from occurring in the market.

[0503] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0504] Step 1:

[0505] Users input requirements and specifications for the system in text format. This input includes detailed descriptions of new features and expected behavior. The entered data is sent to the server and prepared for analysis.

[0506] Step 2:

[0507] The server uses a generative AI model to analyze the requirements and specifications entered by the user. Specifically, it utilizes natural language processing techniques to understand the grammatical and semantic structure of the input text. This analysis accurately grasps the meaning of the requirements and generates data for use in the next step. The output is structured data of the analyzed requirements.

[0508] Step 3:

[0509] The server generates test cases based on the analysis results. This process uses a generative AI model to create test cases for both normal and abnormal scenarios, covering all possible scenarios. For example, if a user enters the prompt "Analyze the requirements for a new payment function and generate test cases," the server will list test cases related to the payment function. The output will be a list of specific test cases.

[0510] Step 4:

[0511] The server extracts key test points based on the generated test cases. This step identifies points requiring particular attention within the test cases, helping to prioritize the tests. Specifically, security-related test cases and areas that may affect system stability are highlighted. The output is a list of key test points.

[0512] Step 5:

[0513] The server identifies elements that could lead to defects based on the analysis of requirements and specifications and the generated test cases. This process refers to historical data and common bug patterns to identify potential risks. For example, insufficient validation of input values ​​or problems with boundary values ​​may be pointed out. The output is a list of potential defect elements.

[0514] (Application Example 1)

[0515] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0516] In control programs for factory automation equipment, a problem exists where insufficient operational testing occurs when new features are released, leading to market bugs and malfunctions. This problem can reduce the efficiency of the manufacturing line and negatively impact product quality. Therefore, automating operational testing and preventing malfunctions before they occur is essential.

[0517] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0518] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating key points for testing, means for generating elements that lead to defects, means for automatically performing operational tests when new functions are released in the control program of the factory automation equipment, and means for analyzing the results of the operational tests to prevent malfunctions. This enables the automation of operational tests when new functions are released in the factory automation equipment and the prevention of malfunctions.

[0519] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and defect elements based on them.

[0520] "Means of communicating requirements and specifications" refers to methods for clearly defining the functions and performance required by the system and inputting them into a generative AI.

[0521] "Methods for generating test cases" refer to methods for automatically creating specific test items to verify the operation of software or systems based on requirements and specifications.

[0522] "Methods for generating key points for testing" refer to methods for extracting particularly important points and areas to pay attention to in a test, in order to conduct an efficient examination.

[0523] "Means of generating elements that lead to malfunctions" refers to methods for identifying potential problems in a system or software and evaluating the likelihood that these problems will lead to malfunctions.

[0524] "Factory automation equipment" is a general term for machines and devices used to automate manufacturing processes.

[0525] A "control program" is software used to instruct and manage the operation of factory automation equipment.

[0526] "Means for automatically performing operational tests" refers to a method for a generative AI to automatically perform operational tests when a new function of a control program is released.

[0527] "Means of analyzing operational test results and preventing malfunctions" refers to methods for evaluating the results of operational tests, identifying potential malfunctions, and preventing them.

[0528] The system for realizing this invention utilizes generative AI to automate operational testing when new functions are released in the control program of factory automation equipment. The server uses a generative AI model to analyze requirements and specifications and generate test cases. This makes it possible to automatically perform operational testing, analyze the test results, and prevent malfunctions before they occur.

[0529] Specifically, the server uses a generative AI model (e.g., OpenAI GPT-4) to receive requirements and specifications as input. Based on this, the AI ​​generates test cases and performs operational tests on the control programs of factory automation equipment. The test results are analyzed on the server to identify potential defects. This can improve the efficiency of the manufacturing line.

[0530] For example, when adding a new transport operation, the server generates a test case that includes "how to operate when the weight of the transported object exceeds a specified value" to verify that the robot operates correctly. An example of a prompt used in this process would be, "The requirements for the new transport operation are a maximum weight of 10 kg and a transport speed of 1 m / s. Please generate a test case based on these requirements."

[0531] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0532] Step 1:

[0533] The server receives requirements and specifications from the user regarding new functions for factory automation equipment. This input data includes specific specifications such as "maximum weight 10 kg, conveying speed 1 m / s." The server then prepares to input this information into the generating AI model.

[0534] Step 2:

[0535] The server uses a generative AI model to generate prompt statements based on the received requirements and specifications. The prompt statements are in the format of, "The requirements for the new transport operation are a maximum weight of 10 kg and a transport speed of 1 m / s. Please generate test cases based on these requirements." The server then inputs these prompt statements into the generative AI model.

[0536] Step 3:

[0537] The generation AI model analyzes the prompt text and generates test cases based on the requirements and specifications. The server receives the generated test cases and uses them as input data for operational testing.

[0538] Step 4:

[0539] The server uses the generated test cases to perform operational tests on the control programs of the factory automation equipment. These operational tests include simulations and actual machine tests to verify that the equipment operates according to specifications.

[0540] Step 5:

[0541] The server collects the results of operational tests and analyzes them using a generative AI model. This analysis identifies potential defects and malfunctions. The server reports the analysis results to the user and prompts them to modify the control program as needed.

[0542] (Example 2)

[0543] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0544] When releasing new features, there is a need to resolve the issue of market bugs arising due to insufficient testing. Furthermore, a system is needed to prevent bugs that slip through the cracks before release and lead to market bugs.

[0545] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0546] In this invention, the server includes means for inputting requirements and specifications, means for analyzing the requirements and specifications using a generation AI model, and means for generating test cases based on the analysis results. This makes it possible to prevent defects that could lead to market bugs before release.

[0547] "Requirements and specifications" are documents that describe in detail the functions, performance, and constraints that a system or software must meet.

[0548] A "generative AI model" is an algorithm or framework that uses artificial intelligence technology to analyze data and generate new information or results.

[0549] "Analysis" is the process of thoroughly examining given data or information to understand its structure and meaning.

[0550] A "test case" is a set of conditions or procedures designed to verify a specific function or behavior of software or a system.

[0551] A "key point" refers to an important point or element that requires particular attention in a specific task or process.

[0552] A "malfunction" refers to a state in which a system or software does not function as expected or does not meet specifications.

[0553] A "market bug" is a defect or flaw discovered after a product has been released to the market, and is a problem that may affect users.

[0554] A "server" is a computer system that provides services to other computers on a network.

[0555] A description of embodiments for carrying out this invention will be given.

[0556] The server first receives requirements and specifications for new features from the user. The user sends specific requirements and specifications to the server in text format. This information becomes the basic data for the generative AI model to analyze.

[0557] Next, the server uses a generative AI model to analyze the received requirements and specifications. The generative AI model utilizes natural language processing techniques to extract the information necessary for generating test cases from the requirements and specifications. Machine learning frameworks such as TensorFlow and PyTorch are used for this analysis.

[0558] Based on the analysis results, the server generates test cases using a generated AI model. The generated test cases include specific test scenarios and procedures, complementing tests performed manually by test engineers. For example, abnormal test cases for the user authentication function are generated.

[0559] Furthermore, the server uses a generative AI model to generate key testing points. This allows test engineers to understand which areas should be tested most thoroughly. The server also generates elements that could lead to defects, highlighting areas that require particularly careful testing. For example, it might point out a potential security vulnerability in the user authentication function.

[0560] As a concrete example, before the release of a new mobile app, a generative AI model analyzes the requirements for "user authentication functionality" and generates test cases. The generated test cases include abnormal case tests during login and tests for the password reset function. An example of a prompt to input to the generative AI model would be, "Generate test cases for user authentication functionality."

[0561] This system allows users to prevent bugs that could lead to market issues before release.

[0562] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0563] Step 1:

[0564] The server receives requirements and specifications for new features from the user as input. The user sends specific requirements and specifications to the server in text format. This input data becomes the basic data for analysis by the generating AI model.

[0565] Step 2:

[0566] The server inputs the received requirements and specifications into a generating AI model for analysis. The generating AI model uses natural language processing technology to analyze the requirements and specifications and extract the information necessary for test case generation. In this analysis process, the input text data is tokenized and semantic analysis is performed to obtain the elements necessary for test case generation as output.

[0567] Step 3:

[0568] The server generates test cases using an AI model based on the analysis results. Specifically, it automatically designs test scenarios and procedures based on the extracted information. In this process, the analysis results are used as input, and specific test cases are generated as output. For example, abnormal test cases for the user authentication function are generated.

[0569] Step 4:

[0570] The server uses a generative AI model to generate key test points. Based on the analysis results, test engineers identify areas that should be tested intensively. This process uses the analysis results as input and generates information indicating key test points as output.

[0571] Step 5:

[0572] The server generates elements that could lead to defects and indicates areas that require particularly careful testing. The generating AI model identifies potential defect elements based on the analysis results and alerts test engineers. This process uses the analysis results as input and generates information indicating defect elements as output.

[0573] Step 6:

[0574] The server outputs generated test cases, key testing points, and potential bugs to the user. Based on this information, the user develops a test plan and conducts the actual tests. The outputted information serves as crucial guidance for the user to prevent market bugs before release.

[0575] (Application Example 2)

[0576] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0577] In factory automation equipment, a problem exists where new features are not adequately tested before release, leading to defects in the market. This problem arises because test engineers find it difficult to identify areas that need focused inspection. Furthermore, manually creating test cases is time-consuming, labor-intensive, and inefficient. As a result, it is difficult to prevent defects before release.

[0578] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0579] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating key points for testing, means for generating elements that could lead to defects, means for generating test cases for new functions of factory automation equipment and indicating areas that should be inspected intensively, and means for confirming the generated test cases on an information terminal. This makes it possible to improve the efficiency of testing new functions of factory automation equipment and to prevent defects before release.

[0580] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and key points for testing based on them.

[0581] "Means of communicating requirements and specifications" refers to interfaces and processes for inputting system requirements and specifications into a generative AI and analyzing them.

[0582] "Methods for generating test cases" refers to a function that automatically creates test cases that test engineers should implement based on requirements and specifications analyzed by a generative AI.

[0583] "Methods for generating key points in testing" refers to a function where a generative AI identifies particularly important areas in testing and presents them to the test engineer.

[0584] "Means for generating elements that lead to defects" refers to a function in which a generative AI identifies elements from requirements and specifications that could potentially cause defects and alerts test engineers to them.

[0585] "Factory automation equipment" is a general term for machines and systems used to automate production processes in factories.

[0586] An "information terminal" is a device used to verify generated test cases and key points of testing, and includes smartphones and tablets.

[0587] The system for implementing this invention utilizes generative AI to automatically generate test cases for new functions of factory automation equipment, indicating areas that test engineers should focus on inspecting. The server uses generative AI to analyze requirements and specifications and generates test cases, key testing points, and factors that could lead to defects. This enables test engineers to conduct tests efficiently.

[0588] The server uses the Python programming language and the OpenAI API to input requirements and specifications as prompts into the generative AI model. The generative AI model generates test cases based on the input prompts and returns the results to the server. The server then sends the generated test cases to an information terminal for review by a test engineer.

[0589] Information terminals, such as smartphones and tablets, display generated test cases and key points for testing. Test engineers can use these terminals to review the generated information and identify areas that require focused inspection.

[0590] For example, if the new function of a factory automation device is "automatic object identification and classification," the server will input the following prompt message into the generating AI model.

[0591] Example of a prompt:

[0592] Requirements: The factory automation equipment will be given a new function to automatically identify and classify objects. Please generate test cases for this function.

[0593] By inputting this prompt into the AI ​​model, relevant test cases are generated, allowing test engineers to identify areas where testing should focus.

[0594] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0595] Step 1:

[0596] The server receives requirements and specifications for new features of factory automation equipment. It uses text data of these requirements and specifications provided by the user as input. The server analyzes this data and generates prompts for input into the AI ​​model.

[0597] Step 2:

[0598] The server sends the generated prompt text to the generative AI model via the OpenAI API. Using the prompt text as input, the generative AI model generates test cases based on it. The generated test cases are returned to the server as output.

[0599] Step 3:

[0600] The server analyzes the test cases received from the generated AI model to identify key testing points and elements that could lead to defects. Using the generated test cases as input, the server analyzes them to identify areas that should be inspected intensively. The analysis results are sent to the information terminal.

[0601] Step 4:

[0602] The terminal displays test cases and analysis results received from the server. Using data from the server as input, the terminal visually presents the information for the test engineer to review. The test engineer then reviews the information generated through the terminal and performs the actual testing.

[0603] (Example 3)

[0604] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0605] When releasing new features, traditional manual testing is insufficient, leading to defects in the market. Furthermore, there's a risk of overlooking potential bugs before release, resulting in market bugs. To address these issues, it's necessary to efficiently and effectively generate test cases and identify areas that require focused testing.

[0606] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0607] In this invention, the server includes means for inputting requirements and specifications into an information processing device, means for analyzing the input requirements and specifications using a generation AI model, and means for generating test cases based on the analysis results. This makes it possible to efficiently generate test cases before the release of new functions and prevent potential defects.

[0608] An "information processing device" is a device that has the function of inputting, processing, and outputting data, and includes devices such as computers and servers.

[0609] "Requirements and specifications" are documents that describe in detail the conditions and functions that a system or software must meet.

[0610] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and automatically perform specific tasks.

[0611] "Analysis" is the process of thoroughly examining input data and understanding its structure and meaning.

[0612] A "test case" is a set of conditions or procedures designed to verify a specific function of software or a system.

[0613] "Key areas" are important parts or areas that require special attention during the test.

[0614] A "defective element" is an element or condition in a system or software that has the potential to cause problems.

[0615] A description of embodiments for carrying out this invention will be given.

[0616] The user inputs requirements and specifications for new functions using an information processing device. The input data is sent to the server. The server analyzes these requirements and specifications using a generative AI model. The analysis utilizes natural language processing technology to extract important information from the text data. Specifically, a general generative AI model is used to analyze the input requirements and specifications in detail.

[0617] Based on the analysis results, the server generates test cases. These generated test cases are designed to verify specific functions of the software or system. Furthermore, the server uses a generation AI model to identify areas of focus for testing and extract potential defects. This allows test engineers to understand where testing should be concentrated.

[0618] As a concrete example, if a user wants to generate test cases for the login function of a new mobile app, they would enter the prompt message "Generate test cases for the login function of the new mobile app" on their device. Based on this prompt, the server uses a generation AI model to generate the relevant test cases and outputs them to the device. This entire process allows the user to efficiently prepare test cases and prevent potential bugs. The specific processing flow in Example 3 will be explained using Figure 15.

[0619] Step 1:

[0620] Users input requirements and specifications for new features using a terminal. The entered data is sent to the server in text file or document format. This input data forms the basis for subsequent analysis.

[0621] Step 2:

[0622] The server inputs the received requirements and specifications into a generative AI model. The generative AI model uses natural language processing techniques to analyze the text data and extract important information. This analysis provides the data necessary for generating test cases. Specifically, it identifies functions and conditions related to testing from the requirements.

[0623] Step 3:

[0624] The server generates test cases based on the analysis results. The generation AI model uses the extracted information to determine what tests are needed and creates specific test cases. For example, a test case such as "Verify that the user can log in when they enter the correct credentials" is generated. These generated test cases are output to a terminal for use by test engineers.

[0625] Step 4:

[0626] The server uses a generative AI model to identify key areas for testing. From the analysis results, it generates information indicating areas that test engineers should pay particular attention to. It also extracts potential defect elements and provides guidelines for preventing potential problems. This allows test engineers to conduct tests efficiently.

[0627] Step 5:

[0628] The server outputs the generated test cases, areas of focus, and potential defects to the user's terminal. The user reviews this information and makes corrections or additions as needed. Finally, the test engineer uses these test cases to perform tests and ensure the quality of the new feature.

[0629] (Application Example 3)

[0630] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0631] Prior to the release of new features, there is a need to resolve issues that arise in the market due to insufficient testing. Furthermore, in factory robot control software, a challenge is to proactively identify and prevent potential operational defects.

[0632] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0633] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, and means for performing operational simulations. This makes it possible to identify and prevent potential defects before release.

[0634] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and defect elements.

[0635] "Means of communicating requirements and specifications" refers to an interface for inputting system requirements and specifications into a generative AI and performing analysis.

[0636] "Methods for generating test cases" refers to a function that automatically creates test cases for use by test engineers based on requirements and specifications analyzed by a generative AI.

[0637] "Methods for generating key points for testing" refers to a function in which a generative AI uses analysis results to indicate areas that should be tested with particular emphasis.

[0638] "Means of generating elements that lead to defects" refers to the function of a generative AI that identifies elements that could potentially cause defects through the analysis of requirements and specifications.

[0639] "Means for performing motion simulations" refers to a function that reproduces the operation of a system or robot in a virtual environment based on generated test cases, and uses this to verify operation and identify defects.

[0640] "Methods for identifying potential defects" refers to a function that combines generative AI and behavioral simulation to identify defects that are difficult to detect before release.

[0641] The system for implementing this invention includes a program that utilizes generative AI to analyze requirements and specifications and generate test cases. The server uses a generative AI model to analyze requirements and specifications and generate test cases. Specifically, the server uses a generative AI model (e.g., OpenAI's GPT-4) and automatically generates test cases by inputting requirements and specifications.

[0642] The generated test cases are used to perform operational simulations. The server uses simulation software (e.g., Gazebo) to reproduce the operation of the system or robot in a virtual environment. This simulation allows for the identification of potential defects and the prevention of problems before release.

[0643] As a concrete example, consider a case where a factory robot performs a new assembly operation. The server inputs the "requirements and specifications for the new assembly operation" into a generative AI model and generates test cases. Based on the generated test cases, the robot's operation is simulated using Gazebo to identify any operational defects.

[0644] Examples of prompt statements to input into the generative AI model are as follows:

[0645] "Analyze the requirements and specifications for the new assembly operation and generate test cases. Based on the generated test cases, perform robot motion simulations to identify potential defects."

[0646] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[0647] Step 1:

[0648] The server receives requirements and specifications for new features from the user. It uses the user-provided requirements and specification documents as input. The server then converts these into prompt statements for input into the generating AI model.

[0649] Step 2:

[0650] The server inputs prompt statements into the generative AI model, which then analyzes the requirements and specifications. The generative AI model generates test cases based on the input prompt statements. The output is a list of the generated test cases.

[0651] Step 3:

[0652] The server prepares to perform operational simulations based on the generated test cases. It takes a list of test cases as input and converts them into a format suitable for simulation software (e.g., Gazebo).

[0653] Step 4:

[0654] The server uses simulation software to reproduce the operation of systems and robots in a virtual environment. It uses the converted test cases as input and runs the simulation. The simulation results are obtained as output.

[0655] Step 5:

[0656] The server analyzes the simulation results and identifies potential defects. Using the simulation results as input, it extracts defect elements using a generative AI model. The output is a list of identified defects.

[0657] Step 6:

[0658] The server provides the user with a list of identified bugs. The user can use this to fix problems before release. The output includes a list of bugs provided to the user.

[0659] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0660] "Example of form 1"

[0661] In one embodiment of the present invention, a generative AI and an emotion engine are combined. The generative AI receives requirements and specifications and generates test cases, key testing points, and elements that could lead to defects. Meanwhile, the emotion engine recognizes the user's emotions and adjusts the test cases and key testing points based on those emotions. Specifically, it generates more rigorous test cases and emphasizes key testing points for features that the user might find unsatisfactory.

[0662] "Example of form 2"

[0663] In another embodiment of the present invention, the emotion engine adjusts elements that could lead to malfunctions based on the user's emotions. Specifically, it identifies elements that could lead to malfunctions for features that the user might find frustrating, and strengthens testing for those elements. For example, if the user feels that "feature A is slow," the emotion engine identifies "the performance of feature A" as a malfunctioning element and strengthens testing for that element.

[0664] "Example of form 3"

[0665] In a further embodiment of the present invention, a generative AI and an emotion engine work together. Specifically, the generative AI generates test cases, key testing points, and elements that could lead to defects, and then the emotion engine adjusts these based on the user's emotions. For example, if the user feels that "function B is too complex," the emotion engine will emphasize "ease of use of function B" as a key testing point and increase the number of test cases for that element.

[0666] The following describes the processing flow for each example of the form.

[0667] "Example of form 1"

[0668] Step 1: The generative AI receives the requirements and specifications.

[0669] Step 2: The generative AI generates test cases, key testing points, and factors that could lead to defects based on the received requirements and specifications.

[0670] Step 3: The emotion engine recognizes the user's emotions.

[0671] Step 4: The emotion engine adjusts the test cases and key points of the test generated by the generative AI based on the recognized user emotions.

[0672] "Example of form 2"

[0673] Step 1: The generative AI receives the requirements and specifications.

[0674] Step 2: The generative AI generates test cases, key testing points, and factors that could lead to defects based on the received requirements and specifications.

[0675] Step 3: The emotion engine recognizes the user's emotions.

[0676] Step 4: The emotion engine adjusts the elements that lead to malfunctions identified by the generative AI based on the recognized user emotions.

[0677] "Example of form 3"

[0678] Step 1: The generative AI receives the requirements and specifications.

[0679] Step 2: The generative AI generates test cases, key testing points, and factors that could lead to defects based on the received requirements and specifications.

[0680] Step 3: The emotion engine recognizes the user's emotions.

[0681] Step 4: The emotion engine adjusts the test cases, key points for testing, and factors that could lead to defects, which were generated by the generative AI based on the recognized user emotions.

[0682] (Example 1)

[0683] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0684] When introducing new features, insufficient testing can lead to defects in the market. Furthermore, it's difficult to prevent defects that were previously overlooked and resulted in market defects. Additionally, the lack of adjustments to test scenarios that take user sentiment into account makes it difficult to improve user satisfaction.

[0685] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0686] In this invention, the server includes means for transmitting requirements and specifications using generative artificial intelligence, means for generating test cases, means for generating key points of testing, means for generating elements that lead to defects, and means for recognizing the user's emotions using an emotion analysis engine and adjusting the test cases and key points of testing. This makes it possible to eliminate insufficient testing when introducing new functions and prevent the occurrence of defects in the market. Furthermore, it is possible to prevent defects that were overlooked in the past and to improve user satisfaction by adjusting test cases that take user emotions into consideration.

[0687] "Generative artificial intelligence" is a technology that analyzes requirements and specifications and automatically generates test examples, key points of testing, and elements that could lead to defects based on that analysis.

[0688] "Means of communicating requirements and specifications" refers to methods for conveying the requirements and specifications entered by the user to the system.

[0689] "Means for generating test cases" refers to methods for creating specific test cases to verify the operation of software based on analyzed requirements and specifications.

[0690] "Methods for generating key points for the exam" refer to methods for highlighting points that require particular attention during the exam, thereby enhancing the effectiveness of the exam.

[0691] "Means of generating elements that lead to defects" refers to methods for identifying potential risks by referring to past data and common failure patterns.

[0692] An "emotion analysis engine" is a technology that recognizes the user's emotions and adjusts test examples and key points of the test based on those emotions.

[0693] "Means of recognizing user emotions and adjusting test examples and key points of the test" refers to a method of analyzing user emotions and appropriately modifying test examples and key points of the test based on the results.

[0694] As an embodiment of this invention, a system combining generative artificial intelligence and an emotion analysis engine is used. The user inputs requirements and specifications through a terminal. The server analyzes these requirements and specifications using a generative AI model and generates test examples, key points of the test, and elements that lead to defects.

[0695] Specifically, the server utilizes natural language processing technology to extract key elements from the input requirements and specifications. For example, in response to the requirement "The user registration function requires users to enter an email address and password and then press the registration button to complete registration," it generates specific test examples such as email address format checks and password strength checks.

[0696] Furthermore, the sentiment analysis engine recognizes user emotions and adjusts test cases and test focus accordingly. If users are dissatisfied with a particular feature, the testing for that feature is intensified. For example, if a user feels the UI is difficult to use, additional test cases related to the UI are added and examined in detail.

[0697] As a concrete example, here is an example of a prompt statement to be input to a generative AI model:

[0698] "Analyze the requirements for the new user registration feature, generate necessary test cases and key test points, and enhance UI testing by considering user complaints about the user interface."

[0699] In this way, the server can utilize generative artificial intelligence and an emotion analysis engine to efficiently generate test cases based on user requirements, thereby improving software quality.

[0700] The flow of the specific processing in Example 1 will be explained using Figure 17.

[0701] Step 1:

[0702] Users input requirements and specifications into the system via their terminal. The entered data is sent to the server in text format. This input includes details about the new features and their expected behavior. For example, "The user registration function requires users to enter their email address and password and press the registration button to complete registration."

[0703] Step 2:

[0704] The server analyzes the input requirements and specifications using a generative AI model. It analyzes the input data using natural language processing techniques and extracts important elements. This analysis identifies specific test elements, such as email address format checks and password strength verification. The analysis results are generated as output and used in the next step.

[0705] Step 3:

[0706] The server generates test cases based on the analysis results. The generation AI model automatically creates appropriate test cases for the identified elements. For example, it generates test cases such as "a test case to confirm that registration is successful with a correctly formatted email address" or "a test case to confirm that the password is 8 characters or longer." The output lists specific test cases.

[0707] Step 4:

[0708] The server generates key points for the test. Based on the analysis results, it highlights points that require particular attention during the test. For example, it might present important checkpoints such as "Confirm that the registration process does not time out during network latency." The key points of the test are clearly indicated as output.

[0709] Step 5:

[0710] The server generates elements that lead to defects. The generative AI model refers to historical data and common failure patterns to identify potential risks. For example, it might list "errors that occur when input fields are not properly validated." The output identifies potential defect elements.

[0711] Step 6:

[0712] The server analyzes user emotions using an emotion analysis engine. It recognizes emotions based on user input and feedback, and reflects the results in the test case and key points of the test. For example, if a user feels the UI is difficult to use, the server adds a UI-related test case and examines it in detail. The adjusted test case is then provided as output.

[0713] (Application Example 1)

[0714] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0715] In electronic payment services, a problem exists where insufficient testing during the release of new features leads to market bugs and user dissatisfaction. Furthermore, a lack of testing adjustments that take user sentiment into account means that dissatisfaction with specific features remains unresolved.

[0716] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0717] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating key points for testing, means for analyzing user sentiment and adjusting test cases, and means for enhancing testing of new features in the electronic payment service. This makes it possible to prevent market bugs from occurring when new features of the electronic payment service are released and to reduce user dissatisfaction.

[0718] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and defect elements based on them.

[0719] "Means of communicating requirements and specifications" refers to methods for clearly defining the functions and performance required by the system and inputting them into a generative AI.

[0720] "Methods for generating test cases" refers to methods for creating specific test scenarios to verify the operation of software based on requirements and specifications analyzed by a generative AI.

[0721] "Methods for generating key points for testing" refer to methods for extracting and highlighting points and important aspects that require particular attention in a test.

[0722] "Means for generating elements that lead to defects" refers to methods for identifying and generating elements that could potentially cause problems or bugs in software.

[0723] "Methods for analyzing user emotions and adjusting test cases" refers to methods for analyzing user feedback and emotions and adjusting the content and emphasis of test cases based on that analysis.

[0724] "Means to enhance testing of new features in electronic payment services" refers to methods for conducting more rigorous and detailed testing of newly added features in electronic payment services.

[0725] The system for carrying out this invention includes a program that integrates a generative AI model and an emotion analysis engine. The server uses the generative AI model to analyze requirements and specifications and generates test cases and defect elements. Specifically, the server operates on the cloud and uses OpenAI's GPT-4 as the generative AI model. IBM Watson Tone Analyzer is used for emotion analysis.

[0726] The device collects user feedback and sends it to the server. This user feedback is analyzed by an emotion analysis engine, and test cases are adjusted based on the results. This allows for more rigorous testing of features that users might find frustrating.

[0727] For example, if a user provides feedback that a new feature of an electronic payment service is "slow," the terminal sends this information to the server. The server uses a sentiment analysis engine to analyze this feedback and sends a prompt to a generative AI model to "enhance the test cases related to payment speed." The generative AI model then generates detailed test cases related to payment speed, thereby enhancing the testing process.

[0728] Examples of prompt statements are as follows:

[0729] User feedback: "Payment is slow."

[0730] Emotion analysis result: Dissatisfaction

[0731] Prompt: Enhance the test cases related to payment speed and generate more detailed tests.

[0732] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[0733] Step 1:

[0734] The terminal collects user feedback. Users input their complaints and opinions about new features of the electronic payment service in text format. The input feedback is then sent from the terminal to the server.

[0735] Step 2:

[0736] The server sends the received user feedback to the sentiment analysis engine. The sentiment analysis engine analyzes the text of the feedback and identifies the user's emotions. The analysis results may output emotions such as "dissatisfied" or "satisfied."

[0737] Step 3:

[0738] The server creates prompts for the generative AI model based on the results of sentiment analysis. These prompts include instructions to adjust test cases according to the user's emotions. For example, specific instructions such as "strengthen the test case regarding payment speed" are generated.

[0739] Step 4:

[0740] The generation AI model analyzes prompts received from the server and generates corresponding test cases. The generated test cases are output as detailed test scenarios for new features of the electronic payment service.

[0741] Step 5:

[0742] The server applies the generated test cases to the test environment and performs the actual tests. The test results are recorded as bugs and areas for improvement, and this information is used to gather feedback for future tests.

[0743] (Example 2)

[0744] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0745] When releasing new features, there is a need to resolve issues that arise in the market due to insufficient testing. Furthermore, improving user satisfaction by adjusting bug factors based on user sentiment is also a challenge.

[0746] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0747] In this invention, the server includes means for inputting requirements and specifications, means for analyzing the input requirements and specifications and generating test cases, and means for identifying areas of focus for testing. This makes it possible to prevent defects in the market before the release of new features and to make adjustments based on user sentiment.

[0748] A "generative AI model" refers to artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and defect elements.

[0749] "Requirements and specifications" refer to information that outlines the detailed conditions and criteria for the design and operation of new features.

[0750] A "test case" refers to a set of conditions or procedures designed to verify specific functions or behaviors of software or a system.

[0751] "Test focus areas" refer to important parts or functions that require particular attention during testing.

[0752] "Factors that lead to malfunctions" refer to factors or conditions that could potentially cause problems in software or systems.

[0753] "Adjusting bugs based on user emotions" refers to selecting bugs to be tested and improved, and adjusting their priorities, while taking user feedback and emotions into consideration.

[0754] "Providing generated test cases" refers to presenting test cases created by a generative AI model to test engineers and related systems.

[0755] The following system is configured as an embodiment for carrying out this invention.

[0756] The server functions as a platform for running generative AI models. Users input requirements and specifications for new features into a terminal, which then sends this data to the server. The server analyzes the input requirements and specifications using a generative AI model and generates test cases. This generative AI model leverages natural language processing techniques to automatically extract test cases and defect elements from the requirements and specifications.

[0757] As a concrete example, a user enters the prompt "Enter the requirements for new feature C and generate test cases" into the terminal. The terminal sends this prompt to the server, which analyzes the requirements using a generation AI model. As a result of the analysis, a specific test case is generated: "Test the usability of the user interface for new feature C."

[0758] Furthermore, the server uses a generative AI model to identify testing priorities, indicating to test engineers where testing should focus. Additionally, based on user feedback, an emotion engine adjusts elements that could lead to bugs, strengthening testing for features that might cause user dissatisfaction. This allows for proactive prevention of market bugs before release, thereby improving user satisfaction.

[0759] The flow of the specific processing in Example 2 will be explained using Figure 19.

[0760] Step 1:

[0761] The user enters the requirements and specifications for the new feature into the terminal. The entered data includes details of the feature and its expected behavior. This data serves as the foundational information for the generative AI model to analyze.

[0762] Step 2:

[0763] The terminal sends the entered requirements and specifications data to the server. The server receives this data and prepares it for input into the generated AI model.

[0764] Step 3:

[0765] The server analyzes requirements and specification data using a generative AI model. Specifically, it utilizes natural language processing techniques to extract information from the input data for generating test cases. This analysis clarifies the elements necessary for generating test cases.

[0766] Step 4:

[0767] The server generates specific test cases based on the results analyzed by the AI ​​model. For example, it might generate an instruction such as, "Create a test case to measure the response time of new feature C." This test case forms the basis for the tests performed by the test engineers.

[0768] Step 5:

[0769] The server uses a generated AI model to identify areas of focus for testing. This indicates where test engineers should concentrate their testing. For example, it might generate instructions such as, "Focus on testing the usability of the user interface for new feature C."

[0770] Step 6:

[0771] The device sends user feedback to the emotion engine. The emotion engine adjusts factors that could lead to problems based on the user's emotions. For example, if a user feels that "feature A is slow," the emotion engine will strengthen its instructions to focus testing on "the performance of feature A."

[0772] Step 7:

[0773] The server sends generated test cases, key points, and information about potential defects to the terminal. This allows test engineers to perform tests efficiently.

[0774] (Application Example 2)

[0775] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0776] When new features are released, insufficient testing can lead to bugs in the market, resulting in decreased user satisfaction. Furthermore, identifying and addressing bugs based on user emotions is difficult, ultimately compromising the user experience.

[0777] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0778] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating critical test areas, means for adjusting elements that could lead to defects based on the user's emotions using an emotion analysis engine, and means for analyzing user feedback and strengthening tests for identified functions. This enables proactive prevention of defects before the release of new features and allows for rapid responses based on user emotions.

[0779] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and elements that could lead to defects.

[0780] "Means of communicating requirements and specifications" refers to interfaces and processes for inputting system requirements and specifications into a generative AI and performing analysis.

[0781] "Methods for generating test cases" refers to a function that automatically creates test cases that test engineers should implement based on requirements and specifications analyzed by a generative AI.

[0782] "Methods for generating key areas of testing" refers to a function in which a generative AI identifies and presents areas that should be tested with particular emphasis based on the analysis results.

[0783] "Means for generating elements that lead to defects" refers to a function in which a generative AI identifies elements that could cause defects through the analysis of requirements and specifications, and presents them to test engineers.

[0784] An "emotion analysis engine" is a technology that analyzes user feedback and emotional data, and adjusts elements that lead to malfunctions based on the user's emotions.

[0785] "Methods for analyzing user feedback and strengthening testing of identified features" refers to processes or functions that analyze user feedback and strengthen testing of features that receive particularly high levels of dissatisfaction.

[0786] The system for implementing this invention involves a server and a terminal working in conjunction. The server uses a generative AI model to analyze requirements and specifications and generate test cases. Specifically, the server analyzes information input through means of communicating requirements and specifications and automatically creates test cases. Furthermore, the server identifies critical areas for testing and presents them to the test engineer.

[0787] The server also uses an emotion analysis engine to analyze user feedback. This allows it to adjust elements that lead to malfunctions based on user emotions and strengthen testing of identified features. The terminal is responsible for collecting user feedback and sending it to the server.

[0788] For example, if a user provides feedback that "payment processing is slow," the server uses a sentiment analysis engine to analyze this feedback and identify payment processing performance as a factor leading to a problem. A generative AI model then strengthens the test cases for this factor and notifies the test engineers.

[0789] An example of a prompt message is: "Analyze the requirements and specifications of the new feature and generate test cases. Also, identify potential bugs based on user feedback and strengthen the tests."

[0790] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[0791] Step 1:

[0792] The server receives requirements and specification data sent from the terminal. This data is used as input for analysis using a generative AI model. As a result of the analysis, test cases are generated, and critical testing areas are identified. This clarifies the areas where test engineers should focus their testing.

[0793] Step 2:

[0794] Users input feedback through their devices. This feedback is sent to a server. The server uses an emotion analysis engine to analyze the feedback and identify elements that may lead to problems based on the user's emotions. The analysis results generate information to strengthen testing for the identified elements.

[0795] Step 3:

[0796] The server notifies the test engineers of the generated test cases and enhanced test information. The test engineers then use this information to conduct tests and proactively prevent defects. This allows potential bugs to be discovered and fixed before release.

[0797] (Example 3)

[0798] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0799] When introducing new features, there is a need to address the problem of defects occurring in the market due to insufficient testing. Furthermore, there is the challenge of preventing defects that slip through the cracks before implementation and lead to market defects.

[0800] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0801] In this invention, the server includes means for inputting information, means for generating prompt statements, and means for generating test cases. This makes it possible to eliminate insufficient testing when introducing new functions and prevent defects from occurring in the market.

[0802] A "generative AI model" is an artificial intelligence technology that uses natural language processing to analyze requirements and specifications and generate test cases and key areas.

[0803] A "prompt statement" is an input statement created by the user to give specific instructions to the generating AI model.

[0804] A "test case" is a set of specific test procedures and conditions designed to verify the functionality and performance of software.

[0805] "Key areas for testing" refer to parts of the software that require particular attention during testing, and are identified by a generative AI model.

[0806] "Factors that lead to defects" refer to factors or conditions in software that could potentially cause defects.

[0807] An "emotion engine" is a technology used to refine test cases and key aspects based on user emotions and feedback.

[0808] A "server" is a computer system that hosts generative AI models and emotion engines, processes user input, and provides results.

[0809] The following system configurations are possible as embodiments for carrying out this invention.

[0810] The user inputs the requirements and specifications for the new feature using a terminal. The terminal can input detailed information using a text editor or a dedicated interface. Next, the user creates prompt statements for the generating AI model. Prompt statements are used to give specific instructions to the generating AI model, and may take the form of, for example, "Generate a case to test the input validation for new feature A."

[0811] The terminal sends a prompt message created by the user to the server. The server hosts a generative AI model, and upon receiving the prompt message, it analyzes the requirements and specifications using natural language processing techniques. Specifically, it can use generative AI models such as OpenAI's GPT series. Based on the analysis results, the server generates test cases and further identifies critical areas for testing and elements that could lead to defects.

[0812] The generated test cases and key areas are adjusted by the sentiment engine based on user emotions and feedback. For example, if a user feels that "feature B is too complex," the sentiment engine will highlight "ease of use of feature B" as a key area for testing and increase the number of test cases for that element.

[0813] Finally, the server sends the generated test cases and adjustment results to the terminal. The terminal receives this and displays it to the user. Based on this information, the user can work with the test engineer to plan and execute tests. In this way, it becomes possible to prevent defects in the market before release. The specific processing flow in Example 3 will be explained using Figure 21.

[0814] Step 1:

[0815] The user inputs the requirements and specifications for the new feature using a terminal. The entered information is saved on the terminal as text data. This data is used to generate subsequent prompt messages.

[0816] Step 2:

[0817] The user creates prompts for the generated AI model. These prompts are text data containing specific instructions based on requirements and specifications. For example, they might say, "Generate a case to test input validation for new feature A."

[0818] Step 3:

[0819] The terminal sends a prompt message to the server. The sent prompt message is input into the AI ​​model on the server. The server analyzes the prompt message and processes the data based on the requirements and specifications.

[0820] Step 4:

[0821] The server generates test cases using a generative AI model. The generative AI model analyzes the prompt text using natural language processing techniques and outputs appropriate test cases. This output is saved to the server as text data.

[0822] Step 5:

[0823] The server uses a generated AI model to identify critical test areas and elements that could lead to defects. The generated AI model analyzes prompts and requirements / specifications, outputting data that highlights specific areas.

[0824] Step 6:

[0825] The server uses the sentiment engine to refine the generated test cases and highlight key areas. The sentiment engine receives user feedback as input and uses it to emphasize or add to test cases.

[0826] Step 7:

[0827] The server sends the final test cases and adjustment results to the terminal. The terminal receives this and displays it to the user. The user then uses this to create a test plan and implements it in cooperation with the test engineer.

[0828] (Application Example 3)

[0829] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0830] Insufficient testing before the release of new features has led to bugs appearing in the market, and this issue needs to be resolved. Furthermore, there is a challenge in being unable to tailor test cases based on user sentiment, making it difficult to highlight particularly sensitive behaviors or features.

[0831] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0832] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating key points for testing, means for generating elements that could lead to defects, means for adjusting test cases based on user emotions using an emotion engine, and means for analyzing operator feedback and highlighting actions and functions that require particular attention. This makes it possible to prevent defects before release and to adjust test cases based on user emotions.

[0833] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases, key points for testing, and elements that could lead to defects.

[0834] "Means of communicating requirements and specifications" refers to the means of inputting system requirements and specifications into a generative AI for analysis.

[0835] "Means for generating test cases" refers to methods for automatically generating test cases based on requirements and specifications analyzed by a generative AI.

[0836] "Methods for generating key points for testing" refer to methods by which a generative AI, based on its analysis results, indicates areas that should be prioritized and checked during testing.

[0837] "Means for generating elements that lead to malfunctions" refers to the means by which a generative AI identifies and displays elements that could cause malfunctions based on its analysis results.

[0838] An "emotion engine" is a technology that analyzes user emotions and adjusts system behavior and test cases based on the results.

[0839] "Means for adjusting test cases based on user emotions" refers to means for adjusting generated test cases based on the user emotions analyzed by the emotion engine.

[0840] "Means for analyzing operator feedback and highlighting actions or functions that require special attention" refers to means for analyzing feedback from operators and highlighting actions or functions that require special attention.

[0841] The system for implementing this invention consists primarily of a server containing a program that combines a generative AI and an emotion engine. The server receives requirements and specifications as input and generates test cases using the generative AI. The generated test cases include key points for testing and elements that could lead to defects, thereby enabling the prevention of defects before release.

[0842] Furthermore, the emotion engine analyzes the user's emotions and adjusts test cases based on the results. Specifically, if a user is dissatisfied with a particular feature, it highlights test cases related to that feature and adjusts the testing focus accordingly.

[0843] This system utilizes high-performance servers and software such as Python and TensorFlow. Data processing and calculations are performed by a generative AI model that analyzes requirements and specifications, and an emotion engine that analyzes user feedback.

[0844] As a concrete example, in factory robot control software, if an operator provides feedback that "the movement is not smooth," the emotion engine will increase the number of test cases related to that movement and adjust the testing to focus on smoothness.

[0845] An example of a prompt to input into the generated AI model is, "Analyze the operating requirements of the factory robot and generate test cases to ensure smooth operation."

[0846] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[0847] Step 1:

[0848] The server receives requirements and specifications from the user as input. This input data includes detailed requirements and specifications for the control software of the factory robot. The server sends prompt messages to the generating AI model to analyze this data.

[0849] Step 2:

[0850] The generation AI model analyzes the requirements and specifications received from the server and generates test cases. This analysis determines what tests are necessary based on the requirements and outputs specific test cases. The generated test cases include key points for testing and elements that could lead to defects.

[0851] Step 3:

[0852] The server sends the generated test cases to the sentiment engine. The sentiment engine receives user sentiment data as input and adjusts the test cases. Specifically, if a user is dissatisfied with a particular feature, it highlights the test cases related to that feature and adjusts the testing focus accordingly.

[0853] Step 4:

[0854] The server provides the operator with a set of test cases. The operator then tests the factory robot's control software based on these test cases. This testing helps prevent defects before release.

[0855] Step 5:

[0856] The operator provides test results as feedback to the server. The server analyzes this feedback and readjusts the test cases and test focus as needed. This feedback loop improves the accuracy and efficiency of the tests.

[0857] (Other examples)

[0858] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[0859] 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.

[0860] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0861] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[0862] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0863] [Third Embodiment]

[0864] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0865] 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.

[0866] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0867] 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.

[0868] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0869] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0870] 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.

[0871] 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.

[0872] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0873] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0874] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0875] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0876] "Example of form 1"

[0877] One embodiment of the present invention provides a system utilizing generative AI. This system includes means for communicating requirements and specifications, means for generating test cases, means for generating key points for testing, and means for generating elements that lead to defects. Specifically, to solve the problem of market bugs occurring due to insufficient testing during new feature releases, the generative AI analyzes the requirements and specifications and generates test cases, key points for testing, and elements that lead to defects based on them.

[0878] "Example of form 2"

[0879] As a concrete example, before the release of a new feature, a generative AI analyzes the requirements and specifications and generates test cases. These generated test cases complement the tests performed manually by test engineers. The generative AI also generates key points for testing, indicating areas where test engineers should focus their testing. Furthermore, the generative AI generates elements that could lead to defects, indicating areas where test engineers should pay particular attention during testing. This makes it possible to prevent defects that previously slipped through the cracks and led to market bugs before release.

[0880] "Example of form 3"

[0881] As a concrete example, before the release of a new feature, a generative AI analyzes the requirements and specifications and generates test cases. These generated test cases complement the tests performed manually by test engineers. The generative AI also generates key points for testing, indicating areas where test engineers should focus their testing. Furthermore, the generative AI generates elements that could lead to defects, indicating areas where test engineers should pay particular attention during testing. This makes it possible to prevent defects that previously slipped through the cracks and led to market bugs before release.

[0882] The following describes the processing flow for each example of the form.

[0883] "Example of form 1"

[0884] Step 1: Before releasing a new feature, the generative AI receives the requirements and specifications.

[0885] Step 2: Generative AI analyzes the requirements and specifications.

[0886] Step 3: Based on the analysis, the generative AI generates test cases.

[0887] Step 4: Generative AI generates key points for testing.

[0888] Step 5: The generative AI generates elements that lead to malfunctions.

[0889] "Example of form 2"

[0890] Step 1: Before releasing a new feature, the generative AI receives the requirements and specifications.

[0891] Step 2: Generative AI analyzes the requirements and specifications.

[0892] Step 3: Based on the analysis, the generative AI generates test cases. The generated test cases complement the tests that test engineers perform manually.

[0893] Step 4: The generative AI generates key points for testing, indicating to the test engineers which areas should be prioritized for testing.

[0894] Step 5: Generative AI generates elements that could lead to bugs, and test engineers highlight areas that require particularly careful testing. This makes it possible to prevent bugs that previously slipped through the cracks and led to market bugs before release.

[0895] (Example 1)

[0896] Next, we will describe Embodiment 1 of Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0897] When introducing new features, it is necessary to address the problem of defects occurring in the market due to insufficient testing. Furthermore, preventing defects that were previously overlooked and led to market defects is also a crucial challenge.

[0898] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0899] In this invention, the server includes means for analyzing requirements and specifications using an information processing device, means for generating test cases based on the analysis results, and means for extracting important test points from the test cases. This makes it possible to increase the comprehensiveness of testing and prevent defects from occurring in the market.

[0900] An "information processing device" is a device used for inputting, processing, and outputting data, and includes devices such as computers and servers.

[0901] "Requirements and specifications" refer to detailed descriptions of the functions and performance that a system or software must meet, and are documents that serve as the basis for development.

[0902] "Analysis" is the process of examining given information in detail to understand its meaning and structure.

[0903] A "test case" is a specific test scenario designed to verify that a particular function or specification works correctly.

[0904] A "critical test point" refers to a point in a test case that requires particular attention and has the potential to significantly impact the quality and safety of the system.

[0905] A "defect" refers to a malfunction or bug that causes a system or software to fail to function as expected.

[0906] As an embodiment for carrying out this invention, a system utilizing a generative AI model is provided. This system has the function of analyzing requirements and specifications using an information processing device, generating test cases based on the analysis results, and further extracting important test points from the test cases.

[0907] The server uses a generative AI model to analyze the requirements and specifications provided by the user. This analysis utilizes natural language processing techniques and employs common AI models to understand the meaning of the requirements. Specifically, it can use AI models that are widely available as software for natural language processing.

[0908] Based on the analysis results, the server generates test cases. These test cases include specific test scenarios to verify that the system's functions and specifications work correctly. For example, if a user enters a prompt such as "Analyze the requirements for the new payment function and generate test cases," the server will analyze the requirements related to the payment function and generate test cases.

[0909] Furthermore, the server extracts key test points from the generated test cases. These key test points highlight areas requiring particular attention and identify parts that could significantly impact the system's quality and security.

[0910] In this way, the system can increase the comprehensiveness of testing and prevent defects from occurring in the market.

[0911] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0912] Step 1:

[0913] Users input requirements and specifications for the system in text format. This input includes detailed descriptions of new features and expected behavior. The entered data is sent to the server and prepared for analysis.

[0914] Step 2:

[0915] The server uses a generative AI model to analyze the requirements and specifications entered by the user. Specifically, it utilizes natural language processing techniques to understand the grammatical and semantic structure of the input text. This analysis accurately grasps the meaning of the requirements and generates data for use in the next step. The output is structured data of the analyzed requirements.

[0916] Step 3:

[0917] The server generates test cases based on the analysis results. This process uses a generative AI model to create test cases for both normal and abnormal scenarios, covering all possible scenarios. For example, if a user enters the prompt "Analyze the requirements for a new payment function and generate test cases," the server will list test cases related to the payment function. The output will be a list of specific test cases.

[0918] Step 4:

[0919] The server extracts key test points based on the generated test cases. This step identifies points requiring particular attention within the test cases, helping to prioritize the tests. Specifically, security-related test cases and areas that may affect system stability are highlighted. The output is a list of key test points.

[0920] Step 5:

[0921] The server identifies elements that could lead to defects based on the analysis of requirements and specifications and the generated test cases. This process refers to historical data and common bug patterns to identify potential risks. For example, insufficient validation of input values ​​or problems with boundary values ​​may be pointed out. The output is a list of potential defect elements.

[0922] (Application Example 1)

[0923] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0924] In control programs for factory automation equipment, a problem exists where insufficient operational testing occurs when new features are released, leading to market bugs and malfunctions. This problem can reduce the efficiency of the manufacturing line and negatively impact product quality. Therefore, automating operational testing and preventing malfunctions before they occur is essential.

[0925] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0926] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating key points for testing, means for generating elements that lead to defects, means for automatically performing operational tests when new functions are released in the control program of the factory automation equipment, and means for analyzing the results of the operational tests to prevent malfunctions. This enables the automation of operational tests when new functions are released in the factory automation equipment and the prevention of malfunctions.

[0927] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and defect elements based on them.

[0928] "Means of communicating requirements and specifications" refers to methods for clearly defining the functions and performance required by the system and inputting them into a generative AI.

[0929] "Methods for generating test cases" refer to methods for automatically creating specific test items to verify the operation of software or systems based on requirements and specifications.

[0930] "Methods for generating key points for testing" refer to methods for extracting particularly important points and areas to pay attention to in a test, in order to conduct an efficient examination.

[0931] "Means of generating elements that lead to malfunctions" refers to methods for identifying potential problems in a system or software and evaluating the likelihood that these problems will lead to malfunctions.

[0932] "Factory automation equipment" is a general term for machines and devices used to automate manufacturing processes.

[0933] A "control program" is software used to instruct and manage the operation of factory automation equipment.

[0934] "Means for automatically performing operational tests" refers to a method for a generative AI to automatically perform operational tests when a new function of a control program is released.

[0935] "Means of analyzing operational test results and preventing malfunctions" refers to methods for evaluating the results of operational tests, identifying potential malfunctions, and preventing them.

[0936] The system for realizing this invention utilizes generative AI to automate operational testing when new functions are released in the control program of factory automation equipment. The server uses a generative AI model to analyze requirements and specifications and generate test cases. This makes it possible to automatically perform operational testing, analyze the test results, and prevent malfunctions before they occur.

[0937] Specifically, the server uses a generative AI model (e.g., OpenAI GPT-4) to receive requirements and specifications as input. Based on this, the AI ​​generates test cases and performs operational tests on the control programs of factory automation equipment. The test results are analyzed on the server to identify potential defects. This can improve the efficiency of the manufacturing line.

[0938] For example, when adding a new transport operation, the server generates a test case that includes "how to operate when the weight of the transported object exceeds a specified value" to verify that the robot operates correctly. An example of a prompt used in this process would be, "The requirements for the new transport operation are a maximum weight of 10 kg and a transport speed of 1 m / s. Please generate a test case based on these requirements."

[0939] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0940] Step 1:

[0941] The server receives requirements and specifications from the user regarding new functions for factory automation equipment. This input data includes specific specifications such as "maximum weight 10 kg, conveying speed 1 m / s." The server then prepares to input this information into the generating AI model.

[0942] Step 2:

[0943] The server uses a generative AI model to generate prompt statements based on the received requirements and specifications. The prompt statements are in the format of, "The requirements for the new transport operation are a maximum weight of 10 kg and a transport speed of 1 m / s. Please generate test cases based on these requirements." The server then inputs these prompt statements into the generative AI model.

[0944] Step 3:

[0945] The generation AI model analyzes the prompt text and generates test cases based on the requirements and specifications. The server receives the generated test cases and uses them as input data for operational testing.

[0946] Step 4:

[0947] The server uses the generated test cases to perform operational tests on the control programs of the factory automation equipment. These operational tests include simulations and actual machine tests to verify that the equipment operates according to specifications.

[0948] Step 5:

[0949] The server collects the results of operational tests and analyzes them using a generative AI model. This analysis identifies potential defects and malfunctions. The server reports the analysis results to the user and prompts them to modify the control program as needed.

[0950] (Example 2)

[0951] Next, we will describe Example 2 of the morphological example. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0952] When releasing new features, there is a need to resolve the issue of market bugs arising due to insufficient testing. Furthermore, a system is needed to prevent bugs that slip through the cracks before release and lead to market bugs.

[0953] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0954] In this invention, the server includes means for inputting requirements and specifications, means for analyzing the requirements and specifications using a generation AI model, and means for generating test cases based on the analysis results. This makes it possible to prevent defects that could lead to market bugs before release.

[0955] "Requirements and specifications" are documents that describe in detail the functions, performance, and constraints that a system or software must meet.

[0956] A "generative AI model" is an algorithm or framework that uses artificial intelligence technology to analyze data and generate new information or results.

[0957] "Analysis" is the process of thoroughly examining given data or information to understand its structure and meaning.

[0958] A "test case" is a set of conditions or procedures designed to verify a specific function or behavior of software or a system.

[0959] A "key point" refers to an important point or element that requires particular attention in a specific task or process.

[0960] A "malfunction" refers to a state in which a system or software does not function as expected or does not meet specifications.

[0961] A "market bug" is a defect or flaw discovered after a product has been released to the market, and is a problem that may affect users.

[0962] A "server" is a computer system that provides services to other computers on a network.

[0963] A description of embodiments for carrying out this invention will be given.

[0964] The server first receives requirements and specifications for new features from the user. The user sends specific requirements and specifications to the server in text format. This information becomes the basic data for the generative AI model to analyze.

[0965] Next, the server uses a generative AI model to analyze the received requirements and specifications. The generative AI model utilizes natural language processing techniques to extract the information necessary for generating test cases from the requirements and specifications. Machine learning frameworks such as TensorFlow and PyTorch are used for this analysis.

[0966] Based on the analysis results, the server generates test cases using a generated AI model. The generated test cases include specific test scenarios and procedures, complementing tests performed manually by test engineers. For example, abnormal test cases for the user authentication function are generated.

[0967] Furthermore, the server uses a generative AI model to generate key testing points. This allows test engineers to understand which areas should be tested most thoroughly. The server also generates elements that could lead to defects, highlighting areas that require particularly careful testing. For example, it might point out a potential security vulnerability in the user authentication function.

[0968] As a concrete example, before the release of a new mobile app, a generative AI model analyzes the requirements for "user authentication functionality" and generates test cases. The generated test cases include abnormal case tests during login and tests for the password reset function. An example of a prompt to input to the generative AI model would be, "Generate test cases for user authentication functionality."

[0969] This system allows users to prevent bugs that could lead to market issues before release.

[0970] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0971] Step 1:

[0972] The server receives requirements and specifications for new features from the user as input. The user sends specific requirements and specifications to the server in text format. This input data becomes the basic data for analysis by the generating AI model.

[0973] Step 2:

[0974] The server inputs the received requirements and specifications into a generating AI model for analysis. The generating AI model uses natural language processing technology to analyze the requirements and specifications and extract the information necessary for test case generation. In this analysis process, the input text data is tokenized and semantic analysis is performed to obtain the elements necessary for test case generation as output.

[0975] Step 3:

[0976] The server generates test cases using an AI model based on the analysis results. Specifically, it automatically designs test scenarios and procedures based on the extracted information. In this process, the analysis results are used as input, and specific test cases are generated as output. For example, abnormal test cases for the user authentication function are generated.

[0977] Step 4:

[0978] The server uses a generative AI model to generate key test points. Based on the analysis results, test engineers identify areas that should be tested intensively. This process uses the analysis results as input and generates information indicating key test points as output.

[0979] Step 5:

[0980] The server generates elements that could lead to defects and indicates areas that require particularly careful testing. The generating AI model identifies potential defect elements based on the analysis results and alerts test engineers. This process uses the analysis results as input and generates information indicating defect elements as output.

[0981] Step 6:

[0982] The server outputs generated test cases, key testing points, and potential bugs to the user. Based on this information, the user develops a test plan and conducts the actual tests. The outputted information serves as crucial guidance for the user to prevent market bugs before release.

[0983] (Application Example 2)

[0984] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0985] In factory automation equipment, a problem exists where new features are not adequately tested before release, leading to defects in the market. This problem arises because test engineers find it difficult to identify areas that need focused inspection. Furthermore, manually creating test cases is time-consuming, labor-intensive, and inefficient. As a result, it is difficult to prevent defects before release.

[0986] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0987] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating key points for testing, means for generating elements that could lead to defects, means for generating test cases for new functions of factory automation equipment and indicating areas that should be inspected intensively, and means for confirming the generated test cases on an information terminal. This makes it possible to improve the efficiency of testing new functions of factory automation equipment and to prevent defects before release.

[0988] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and key points for testing based on them.

[0989] "Means of communicating requirements and specifications" refers to interfaces and processes for inputting system requirements and specifications into a generative AI and analyzing them.

[0990] "Methods for generating test cases" refers to a function that automatically creates test cases that test engineers should implement based on requirements and specifications analyzed by a generative AI.

[0991] "Methods for generating key points in testing" refers to a function where a generative AI identifies particularly important areas in testing and presents them to the test engineer.

[0992] "Means for generating elements that lead to defects" refers to a function in which a generative AI identifies elements from requirements and specifications that could potentially cause defects and alerts test engineers to them.

[0993] "Factory automation equipment" is a general term for machines and systems used to automate production processes in factories.

[0994] An "information terminal" is a device used to verify generated test cases and key points of testing, and includes smartphones and tablets.

[0995] The system for implementing this invention utilizes generative AI to automatically generate test cases for new functions of factory automation equipment, indicating areas that test engineers should focus on inspecting. The server uses generative AI to analyze requirements and specifications and generates test cases, key testing points, and factors that could lead to defects. This enables test engineers to conduct tests efficiently.

[0996] The server uses the Python programming language and the OpenAI API to input requirements and specifications as prompts into the generative AI model. The generative AI model generates test cases based on the input prompts and returns the results to the server. The server then sends the generated test cases to an information terminal for review by a test engineer.

[0997] Information terminals, such as smartphones and tablets, display generated test cases and key points for testing. Test engineers can use these terminals to review the generated information and identify areas that require focused inspection.

[0998] For example, if the new function of a factory automation device is "automatic object identification and classification," the server will input the following prompt message into the generating AI model.

[0999] Example of a prompt:

[1000] Requirements: The factory automation equipment will be given a new function to automatically identify and classify objects. Please generate test cases for this function.

[1001] By inputting this prompt into the AI ​​model, relevant test cases are generated, allowing test engineers to identify areas where testing should focus.

[1002] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1003] Step 1:

[1004] The server receives requirements and specifications for new features of factory automation equipment. It uses text data of these requirements and specifications provided by the user as input. The server analyzes this data and generates prompts for input into the AI ​​model.

[1005] Step 2:

[1006] The server sends the generated prompt text to the generative AI model via the OpenAI API. Using the prompt text as input, the generative AI model generates test cases based on it. The generated test cases are returned to the server as output.

[1007] Step 3:

[1008] The server analyzes the test cases received from the generated AI model to identify key testing points and elements that could lead to defects. Using the generated test cases as input, the server analyzes them to identify areas that should be inspected intensively. The analysis results are sent to the information terminal.

[1009] Step 4:

[1010] The terminal displays test cases and analysis results received from the server. Using data from the server as input, the terminal visually presents the information for the test engineer to review. The test engineer then reviews the information generated through the terminal and performs the actual testing.

[1011] (Example 3)

[1012] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1013] When releasing new features, traditional manual testing is insufficient, leading to defects in the market. Furthermore, there's a risk of overlooking potential bugs before release, resulting in market bugs. To address these issues, it's necessary to efficiently and effectively generate test cases and identify areas that require focused testing.

[1014] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1015] In this invention, the server includes means for inputting requirements and specifications into an information processing device, means for analyzing the input requirements and specifications using a generation AI model, and means for generating test cases based on the analysis results. This makes it possible to efficiently generate test cases before the release of new functions and prevent potential defects.

[1016] An "information processing device" is a device that has the function of inputting, processing, and outputting data, and includes devices such as computers and servers.

[1017] "Requirements and specifications" are documents that describe in detail the conditions and functions that a system or software must meet.

[1018] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and automatically perform specific tasks.

[1019] "Analysis" is the process of thoroughly examining input data and understanding its structure and meaning.

[1020] A "test case" is a set of conditions or procedures designed to verify a specific function of software or a system.

[1021] "Key areas" are important parts or areas that require special attention during the test.

[1022] A "defective element" is an element or condition in a system or software that has the potential to cause problems.

[1023] A description of embodiments for carrying out this invention will be given.

[1024] The user inputs requirements and specifications for new functions using an information processing device. The input data is sent to the server. The server analyzes these requirements and specifications using a generative AI model. The analysis utilizes natural language processing technology to extract important information from the text data. Specifically, a general generative AI model is used to analyze the input requirements and specifications in detail.

[1025] Based on the analysis results, the server generates test cases. These generated test cases are designed to verify specific functions of the software or system. Furthermore, the server uses a generation AI model to identify areas of focus for testing and extract potential defects. This allows test engineers to understand where testing should be concentrated.

[1026] As a concrete example, if a user wants to generate test cases for the login function of a new mobile app, they would enter the prompt message "Generate test cases for the login function of the new mobile app" on their device. Based on this prompt, the server uses a generation AI model to generate the relevant test cases and outputs them to the device. This entire process allows the user to efficiently prepare test cases and prevent potential bugs. The specific processing flow in Example 3 will be explained using Figure 15.

[1027] Step 1:

[1028] Users input requirements and specifications for new features using a terminal. The entered data is sent to the server in text file or document format. This input data forms the basis for subsequent analysis.

[1029] Step 2:

[1030] The server inputs the received requirements and specifications into a generative AI model. The generative AI model uses natural language processing techniques to analyze the text data and extract important information. This analysis provides the data necessary for generating test cases. Specifically, it identifies functions and conditions related to testing from the requirements.

[1031] Step 3:

[1032] The server generates test cases based on the analysis results. The generation AI model uses the extracted information to determine what tests are needed and creates specific test cases. For example, a test case such as "Verify that the user can log in when they enter the correct credentials" is generated. These generated test cases are output to a terminal for use by test engineers.

[1033] Step 4:

[1034] The server uses a generative AI model to identify key areas for testing. From the analysis results, it generates information indicating areas that test engineers should pay particular attention to. It also extracts potential defect elements and provides guidelines for preventing potential problems. This allows test engineers to conduct tests efficiently.

[1035] Step 5:

[1036] The server outputs the generated test cases, areas of focus, and potential defects to the user's terminal. The user reviews this information and makes corrections or additions as needed. Finally, the test engineer uses these test cases to perform tests and ensure the quality of the new feature.

[1037] (Application Example 3)

[1038] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1039] Prior to the release of new features, there is a need to resolve issues that arise in the market due to insufficient testing. Furthermore, in factory robot control software, a challenge is to proactively identify and prevent potential operational defects.

[1040] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[1041] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, and means for performing operational simulations. This makes it possible to identify and prevent potential defects before release.

[1042] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and defect elements.

[1043] "Means of communicating requirements and specifications" refers to an interface for inputting system requirements and specifications into a generative AI and performing analysis.

[1044] "Methods for generating test cases" refers to a function that automatically creates test cases for use by test engineers based on requirements and specifications analyzed by a generative AI.

[1045] "Methods for generating key points for testing" refers to a function in which a generative AI uses analysis results to indicate areas that should be tested with particular emphasis.

[1046] "Means of generating elements that lead to defects" refers to the function of a generative AI that identifies elements that could potentially cause defects through the analysis of requirements and specifications.

[1047] "Means for performing motion simulations" refers to a function that reproduces the operation of a system or robot in a virtual environment based on generated test cases, and uses this to verify operation and identify defects.

[1048] "Methods for identifying potential defects" refers to a function that combines generative AI and behavioral simulation to identify defects that are difficult to detect before release.

[1049] The system for implementing this invention includes a program that utilizes generative AI to analyze requirements and specifications and generate test cases. The server uses a generative AI model to analyze requirements and specifications and generate test cases. Specifically, the server uses a generative AI model (e.g., OpenAI's GPT-4) and automatically generates test cases by inputting requirements and specifications.

[1050] The generated test cases are used to perform operational simulations. The server uses simulation software (e.g., Gazebo) to reproduce the operation of the system or robot in a virtual environment. This simulation allows for the identification of potential defects and the prevention of problems before release.

[1051] As a concrete example, consider a case where a factory robot performs a new assembly operation. The server inputs the "requirements and specifications for the new assembly operation" into a generative AI model and generates test cases. Based on the generated test cases, the robot's operation is simulated using Gazebo to identify any operational defects.

[1052] Examples of prompt statements to input into the generative AI model are as follows:

[1053] "Analyze the requirements and specifications for the new assembly operation and generate test cases. Based on the generated test cases, perform robot motion simulations to identify potential defects."

[1054] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[1055] Step 1:

[1056] The server receives requirements and specifications for new features from the user. It uses the user-provided requirements and specification documents as input. The server then converts these into prompt statements for input into the generating AI model.

[1057] Step 2:

[1058] The server inputs prompt statements into the generative AI model, which then analyzes the requirements and specifications. The generative AI model generates test cases based on the input prompt statements. The output is a list of the generated test cases.

[1059] Step 3:

[1060] The server prepares to perform operational simulations based on the generated test cases. It takes a list of test cases as input and converts them into a format suitable for simulation software (e.g., Gazebo).

[1061] Step 4:

[1062] The server uses simulation software to reproduce the operation of systems and robots in a virtual environment. It uses the converted test cases as input and runs the simulation. The simulation results are obtained as output.

[1063] Step 5:

[1064] The server analyzes the simulation results and identifies potential defects. Using the simulation results as input, it extracts defect elements using a generative AI model. The output is a list of identified defects.

[1065] Step 6:

[1066] The server provides the user with a list of identified bugs. The user can use this to fix problems before release. The output includes a list of bugs provided to the user.

[1067] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1068] "Example of form 1"

[1069] In one embodiment of the present invention, a generative AI and an emotion engine are combined. The generative AI receives requirements and specifications and generates test cases, key testing points, and elements that could lead to defects. Meanwhile, the emotion engine recognizes the user's emotions and adjusts the test cases and key testing points based on those emotions. Specifically, it generates more rigorous test cases and emphasizes key testing points for features that the user might find unsatisfactory.

[1070] "Example of form 2"

[1071] In another embodiment of the present invention, the emotion engine adjusts elements that could lead to malfunctions based on the user's emotions. Specifically, it identifies elements that could lead to malfunctions for features that the user might find frustrating, and strengthens testing for those elements. For example, if the user feels that "feature A is slow," the emotion engine identifies "the performance of feature A" as a malfunctioning element and strengthens testing for that element.

[1072] "Example of form 3"

[1073] In a further embodiment of the present invention, a generative AI and an emotion engine work together. Specifically, the generative AI generates test cases, key testing points, and elements that could lead to defects, and then the emotion engine adjusts these based on the user's emotions. For example, if the user feels that "function B is too complex," the emotion engine will emphasize "ease of use of function B" as a key testing point and increase the number of test cases for that element.

[1074] The following describes the processing flow for each example of the form.

[1075] "Example of form 1"

[1076] Step 1: The generative AI receives the requirements and specifications.

[1077] Step 2: The generative AI generates test cases, key testing points, and factors that could lead to defects based on the received requirements and specifications.

[1078] Step 3: The emotion engine recognizes the user's emotions.

[1079] Step 4: The emotion engine adjusts the test cases and key points of the test generated by the generative AI based on the recognized user emotions.

[1080] "Example of form 2"

[1081] Step 1: The generative AI receives the requirements and specifications.

[1082] Step 2: The generative AI generates test cases, key testing points, and factors that could lead to defects based on the received requirements and specifications.

[1083] Step 3: The emotion engine recognizes the user's emotions.

[1084] Step 4: The emotion engine adjusts the elements that lead to malfunctions identified by the generative AI based on the recognized user emotions.

[1085] "Example of form 3"

[1086] Step 1: The generative AI receives the requirements and specifications.

[1087] Step 2: The generative AI generates test cases, key testing points, and factors that could lead to defects based on the received requirements and specifications.

[1088] Step 3: The emotion engine recognizes the user's emotions.

[1089] Step 4: The emotion engine adjusts the test cases, key points for testing, and factors that could lead to defects, which were generated by the generative AI based on the recognized user emotions.

[1090] (Example 1)

[1091] Next, we will describe Embodiment 1 of Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1092] When introducing new features, insufficient testing can lead to defects in the market. Furthermore, it's difficult to prevent defects that were previously overlooked and resulted in market defects. Additionally, the lack of adjustments to test scenarios that take user sentiment into account makes it difficult to improve user satisfaction.

[1093] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1094] In this invention, the server includes means for transmitting requirements and specifications using generative artificial intelligence, means for generating test cases, means for generating key points of testing, means for generating elements that lead to defects, and means for recognizing the user's emotions using an emotion analysis engine and adjusting the test cases and key points of testing. This makes it possible to eliminate insufficient testing when introducing new functions and prevent the occurrence of defects in the market. Furthermore, it is possible to prevent defects that were overlooked in the past and to improve user satisfaction by adjusting test cases that take user emotions into consideration.

[1095] "Generative artificial intelligence" is a technology that analyzes requirements and specifications and automatically generates test examples, key points of testing, and elements that could lead to defects based on that analysis.

[1096] "Means of communicating requirements and specifications" refers to methods for conveying the requirements and specifications entered by the user to the system.

[1097] "Means for generating test cases" refers to methods for creating specific test cases to verify the operation of software based on analyzed requirements and specifications.

[1098] "Methods for generating key points for the exam" refer to methods for highlighting points that require particular attention during the exam, thereby enhancing the effectiveness of the exam.

[1099] "Means of generating elements that lead to defects" refers to methods for identifying potential risks by referring to past data and common failure patterns.

[1100] An "emotion analysis engine" is a technology that recognizes the user's emotions and adjusts test examples and key points of the test based on those emotions.

[1101] "Means of recognizing user emotions and adjusting test examples and key points of the test" refers to a method of analyzing user emotions and appropriately modifying test examples and key points of the test based on the results.

[1102] As an embodiment of this invention, a system combining generative artificial intelligence and an emotion analysis engine is used. The user inputs requirements and specifications through a terminal. The server analyzes these requirements and specifications using a generative AI model and generates test examples, key points of the test, and elements that lead to defects.

[1103] Specifically, the server utilizes natural language processing technology to extract key elements from the input requirements and specifications. For example, in response to the requirement "The user registration function requires users to enter an email address and password and then press the registration button to complete registration," it generates specific test examples such as email address format checks and password strength checks.

[1104] Furthermore, the sentiment analysis engine recognizes user emotions and adjusts test cases and test focus accordingly. If users are dissatisfied with a particular feature, the testing for that feature is intensified. For example, if a user feels the UI is difficult to use, additional test cases related to the UI are added and examined in detail.

[1105] As a concrete example, here is an example of a prompt statement to be input to a generative AI model:

[1106] "Analyze the requirements for the new user registration feature, generate necessary test cases and key test points, and enhance UI testing by considering user complaints about the user interface."

[1107] In this way, the server can utilize generative artificial intelligence and an emotion analysis engine to efficiently generate test cases based on user requirements, thereby improving software quality.

[1108] The flow of the specific processing in Example 1 will be explained using Figure 17.

[1109] Step 1:

[1110] Users input requirements and specifications into the system via their terminal. The entered data is sent to the server in text format. This input includes details about the new features and their expected behavior. For example, "The user registration function requires users to enter their email address and password and press the registration button to complete registration."

[1111] Step 2:

[1112] The server analyzes the input requirements and specifications using a generative AI model. It analyzes the input data using natural language processing techniques and extracts important elements. This analysis identifies specific test elements, such as email address format checks and password strength verification. The analysis results are generated as output and used in the next step.

[1113] Step 3:

[1114] The server generates test cases based on the analysis results. The generation AI model automatically creates appropriate test cases for the identified elements. For example, it generates test cases such as "a test case to confirm that registration is successful with a correctly formatted email address" or "a test case to confirm that the password is 8 characters or longer." The output lists specific test cases.

[1115] Step 4:

[1116] The server generates key points for the test. Based on the analysis results, it highlights points that require particular attention during the test. For example, it might present important checkpoints such as "Confirm that the registration process does not time out during network latency." The key points of the test are clearly indicated as output.

[1117] Step 5:

[1118] The server generates elements that lead to defects. The generative AI model refers to historical data and common failure patterns to identify potential risks. For example, it might list "errors that occur when input fields are not properly validated." The output identifies potential defect elements.

[1119] Step 6:

[1120] The server analyzes user emotions using an emotion analysis engine. It recognizes emotions based on user input and feedback, and reflects the results in the test case and key points of the test. For example, if a user feels the UI is difficult to use, the server adds a UI-related test case and examines it in detail. The adjusted test case is then provided as output.

[1121] (Application Example 1)

[1122] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1123] In electronic payment services, a problem exists where insufficient testing during the release of new features leads to market bugs and user dissatisfaction. Furthermore, a lack of testing adjustments that take user sentiment into account means that dissatisfaction with specific features remains unresolved.

[1124] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1125] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating key points for testing, means for analyzing user sentiment and adjusting test cases, and means for enhancing testing of new features in the electronic payment service. This makes it possible to prevent market bugs from occurring when new features of the electronic payment service are released and to reduce user dissatisfaction.

[1126] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and defect elements based on them.

[1127] "Means of communicating requirements and specifications" refers to methods for clearly defining the functions and performance required by the system and inputting them into a generative AI.

[1128] "Methods for generating test cases" refers to methods for creating specific test scenarios to verify the operation of software based on requirements and specifications analyzed by a generative AI.

[1129] "Methods for generating key points for testing" refer to methods for extracting and highlighting points and important aspects that require particular attention in a test.

[1130] "Means for generating elements that lead to defects" refers to methods for identifying and generating elements that could potentially cause problems or bugs in software.

[1131] "Methods for analyzing user emotions and adjusting test cases" refers to methods for analyzing user feedback and emotions and adjusting the content and emphasis of test cases based on that analysis.

[1132] "Means to enhance testing of new features in electronic payment services" refers to methods for conducting more rigorous and detailed testing of newly added features in electronic payment services.

[1133] The system for carrying out this invention includes a program that integrates a generative AI model and an emotion analysis engine. The server uses the generative AI model to analyze requirements and specifications and generates test cases and defect elements. Specifically, the server operates on the cloud and uses OpenAI's GPT-4 as the generative AI model. IBM Watson Tone Analyzer is used for emotion analysis.

[1134] The device collects user feedback and sends it to the server. This user feedback is analyzed by an emotion analysis engine, and test cases are adjusted based on the results. This allows for more rigorous testing of features that users might find frustrating.

[1135] For example, if a user provides feedback that a new feature of an electronic payment service is "slow," the terminal sends this information to the server. The server uses a sentiment analysis engine to analyze this feedback and sends a prompt to a generative AI model to "enhance the test cases related to payment speed." The generative AI model then generates detailed test cases related to payment speed, thereby enhancing the testing process.

[1136] Examples of prompt statements are as follows:

[1137] User feedback: "Payment is slow."

[1138] Emotion analysis result: Dissatisfaction

[1139] Prompt: Enhance the test cases related to payment speed and generate more detailed tests.

[1140] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[1141] Step 1:

[1142] The terminal collects user feedback. Users input their complaints and opinions about new features of the electronic payment service in text format. The input feedback is then sent from the terminal to the server.

[1143] Step 2:

[1144] The server sends the received user feedback to the sentiment analysis engine. The sentiment analysis engine analyzes the text of the feedback and identifies the user's emotions. The analysis results may output emotions such as "dissatisfied" or "satisfied."

[1145] Step 3:

[1146] The server creates prompts for the generative AI model based on the results of sentiment analysis. These prompts include instructions to adjust test cases according to the user's emotions. For example, specific instructions such as "strengthen the test case regarding payment speed" are generated.

[1147] Step 4:

[1148] The generation AI model analyzes prompts received from the server and generates corresponding test cases. The generated test cases are output as detailed test scenarios for new features of the electronic payment service.

[1149] Step 5:

[1150] The server applies the generated test cases to the test environment and performs the actual tests. The test results are recorded as bugs and areas for improvement, and this information is used to gather feedback for future tests.

[1151] (Example 2)

[1152] Next, we will describe Example 2 of the morphological example. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1153] When releasing new features, there is a need to resolve issues that arise in the market due to insufficient testing. Furthermore, improving user satisfaction by adjusting bug factors based on user sentiment is also a challenge.

[1154] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1155] In this invention, the server includes means for inputting requirements and specifications, means for analyzing the input requirements and specifications and generating test cases, and means for identifying areas of focus for testing. This makes it possible to prevent defects in the market before the release of new features and to make adjustments based on user sentiment.

[1156] A "generative AI model" refers to artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and defect elements.

[1157] "Requirements and specifications" refer to information that outlines the detailed conditions and criteria for the design and operation of new features.

[1158] A "test case" refers to a set of conditions or procedures designed to verify specific functions or behaviors of software or a system.

[1159] "Test focus areas" refer to important parts or functions that require particular attention during testing.

[1160] "Factors that lead to malfunctions" refer to factors or conditions that could potentially cause problems in software or systems.

[1161] "Adjusting bugs based on user emotions" refers to selecting bugs to be tested and improved, and adjusting their priorities, while taking user feedback and emotions into consideration.

[1162] "Providing generated test cases" refers to presenting test cases created by a generative AI model to test engineers and related systems.

[1163] The following system is configured as an embodiment for carrying out this invention.

[1164] The server functions as a platform for running generative AI models. Users input requirements and specifications for new features into a terminal, which then sends this data to the server. The server analyzes the input requirements and specifications using a generative AI model and generates test cases. This generative AI model leverages natural language processing techniques to automatically extract test cases and defect elements from the requirements and specifications.

[1165] As a concrete example, a user enters the prompt "Enter the requirements for new feature C and generate test cases" into the terminal. The terminal sends this prompt to the server, which analyzes the requirements using a generation AI model. As a result of the analysis, a specific test case is generated: "Test the usability of the user interface for new feature C."

[1166] Furthermore, the server uses a generative AI model to identify testing priorities, indicating to test engineers where testing should focus. Additionally, based on user feedback, an emotion engine adjusts elements that could lead to bugs, strengthening testing for features that might cause user dissatisfaction. This allows for proactive prevention of market bugs before release, thereby improving user satisfaction.

[1167] The flow of the specific processing in Example 2 will be explained using Figure 19.

[1168] Step 1:

[1169] The user enters the requirements and specifications for the new feature into the terminal. The entered data includes details of the feature and its expected behavior. This data serves as the foundational information for the generative AI model to analyze.

[1170] Step 2:

[1171] The terminal sends the entered requirements and specifications data to the server. The server receives this data and prepares it for input into the generated AI model.

[1172] Step 3:

[1173] The server analyzes requirements and specification data using a generative AI model. Specifically, it utilizes natural language processing techniques to extract information from the input data for generating test cases. This analysis clarifies the elements necessary for generating test cases.

[1174] Step 4:

[1175] The server generates specific test cases based on the results analyzed by the AI ​​model. For example, it might generate an instruction such as, "Create a test case to measure the response time of new feature C." This test case forms the basis for the tests performed by the test engineers.

[1176] Step 5:

[1177] The server uses a generated AI model to identify areas of focus for testing. This indicates where test engineers should concentrate their testing. For example, it might generate instructions such as, "Focus on testing the usability of the user interface for new feature C."

[1178] Step 6:

[1179] The device sends user feedback to the emotion engine. The emotion engine adjusts factors that could lead to problems based on the user's emotions. For example, if a user feels that "feature A is slow," the emotion engine will strengthen its instructions to focus testing on "the performance of feature A."

[1180] Step 7:

[1181] The server sends generated test cases, key points, and information about potential defects to the terminal. This allows test engineers to perform tests efficiently.

[1182] (Application Example 2)

[1183] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1184] When new features are released, insufficient testing can lead to bugs in the market, resulting in decreased user satisfaction. Furthermore, identifying and addressing bugs based on user emotions is difficult, ultimately compromising the user experience.

[1185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1186] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating critical test areas, means for adjusting elements that could lead to defects based on the user's emotions using an emotion analysis engine, and means for analyzing user feedback and strengthening tests for identified functions. This enables proactive prevention of defects before the release of new features and allows for rapid responses based on user emotions.

[1187] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and elements that could lead to defects.

[1188] "Means of communicating requirements and specifications" refers to interfaces and processes for inputting system requirements and specifications into a generative AI and performing analysis.

[1189] "Methods for generating test cases" refers to a function that automatically creates test cases that test engineers should implement based on requirements and specifications analyzed by a generative AI.

[1190] "Methods for generating key areas of testing" refers to a function in which a generative AI identifies and presents areas that should be tested with particular emphasis based on the analysis results.

[1191] "Means for generating elements that lead to defects" refers to a function in which a generative AI identifies elements that could cause defects through the analysis of requirements and specifications, and presents them to test engineers.

[1192] An "emotion analysis engine" is a technology that analyzes user feedback and emotional data, and adjusts elements that lead to malfunctions based on the user's emotions.

[1193] "Methods for analyzing user feedback and strengthening testing of identified features" refers to processes or functions that analyze user feedback and strengthen testing of features that receive particularly high levels of dissatisfaction.

[1194] The system for implementing this invention involves a server and a terminal working in conjunction. The server uses a generative AI model to analyze requirements and specifications and generate test cases. Specifically, the server analyzes information input through means of communicating requirements and specifications and automatically creates test cases. Furthermore, the server identifies critical areas for testing and presents them to the test engineer.

[1195] The server also uses an emotion analysis engine to analyze user feedback. This allows it to adjust elements that lead to malfunctions based on user emotions and strengthen testing of identified features. The terminal is responsible for collecting user feedback and sending it to the server.

[1196] For example, if a user provides feedback that "payment processing is slow," the server uses a sentiment analysis engine to analyze this feedback and identify payment processing performance as a factor leading to a problem. A generative AI model then strengthens the test cases for this factor and notifies the test engineers.

[1197] An example of a prompt message is: "Analyze the requirements and specifications of the new feature and generate test cases. Also, identify potential bugs based on user feedback and strengthen the tests."

[1198] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[1199] Step 1:

[1200] The server receives requirements and specification data sent from the terminal. This data is used as input for analysis using a generative AI model. As a result of the analysis, test cases are generated, and critical testing areas are identified. This clarifies the areas where test engineers should focus their testing.

[1201] Step 2:

[1202] Users input feedback through their devices. This feedback is sent to a server. The server uses an emotion analysis engine to analyze the feedback and identify elements that may lead to problems based on the user's emotions. The analysis results generate information to strengthen testing for the identified elements.

[1203] Step 3:

[1204] The server notifies the test engineers of the generated test cases and enhanced test information. The test engineers then use this information to conduct tests and proactively prevent defects. This allows potential bugs to be discovered and fixed before release.

[1205] (Example 3)

[1206] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1207] When introducing new features, there is a need to address the problem of defects occurring in the market due to insufficient testing. Furthermore, there is the challenge of preventing defects that slip through the cracks before implementation and lead to market defects.

[1208] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1209] In this invention, the server includes means for inputting information, means for generating prompt statements, and means for generating test cases. This makes it possible to eliminate insufficient testing when introducing new functions and prevent defects from occurring in the market.

[1210] A "generative AI model" is an artificial intelligence technology that uses natural language processing to analyze requirements and specifications and generate test cases and key areas.

[1211] A "prompt statement" is an input statement created by the user to give specific instructions to the generating AI model.

[1212] A "test case" is a set of specific test procedures and conditions designed to verify the functionality and performance of software.

[1213] "Key areas for testing" refer to parts of the software that require particular attention during testing, and are identified by a generative AI model.

[1214] "Factors that lead to defects" refer to factors or conditions in software that could potentially cause defects.

[1215] An "emotion engine" is a technology used to refine test cases and key aspects based on user emotions and feedback.

[1216] A "server" is a computer system that hosts generative AI models and emotion engines, processes user input, and provides results.

[1217] The following system configurations are possible as embodiments for carrying out this invention.

[1218] The user inputs the requirements and specifications for the new feature using a terminal. The terminal can input detailed information using a text editor or a dedicated interface. Next, the user creates prompt statements for the generating AI model. Prompt statements are used to give specific instructions to the generating AI model, and may take the form of, for example, "Generate a case to test the input validation for new feature A."

[1219] The terminal sends a prompt message created by the user to the server. The server hosts a generative AI model, and upon receiving the prompt message, it analyzes the requirements and specifications using natural language processing techniques. Specifically, it can use generative AI models such as OpenAI's GPT series. Based on the analysis results, the server generates test cases and further identifies critical areas for testing and elements that could lead to defects.

[1220] The generated test cases and key areas are adjusted by the sentiment engine based on user emotions and feedback. For example, if a user feels that "feature B is too complex," the sentiment engine will highlight "ease of use of feature B" as a key area for testing and increase the number of test cases for that element.

[1221] Finally, the server sends the generated test cases and adjustment results to the terminal. The terminal receives this and displays it to the user. Based on this information, the user can work with the test engineer to plan and execute tests. In this way, it becomes possible to prevent defects in the market before release. The specific processing flow in Example 3 will be explained using Figure 21.

[1222] Step 1:

[1223] The user inputs the requirements and specifications for the new feature using a terminal. The entered information is saved on the terminal as text data. This data is used to generate subsequent prompt messages.

[1224] Step 2:

[1225] The user creates prompts for the generated AI model. These prompts are text data containing specific instructions based on requirements and specifications. For example, they might say, "Generate a case to test input validation for new feature A."

[1226] Step 3:

[1227] The terminal sends a prompt message to the server. The sent prompt message is input into the AI ​​model on the server. The server analyzes the prompt message and processes the data based on the requirements and specifications.

[1228] Step 4:

[1229] The server generates test cases using a generative AI model. The generative AI model analyzes the prompt text using natural language processing techniques and outputs appropriate test cases. This output is saved to the server as text data.

[1230] Step 5:

[1231] The server uses a generated AI model to identify critical test areas and elements that could lead to defects. The generated AI model analyzes prompts and requirements / specifications, outputting data that highlights specific areas.

[1232] Step 6:

[1233] The server uses the sentiment engine to refine the generated test cases and highlight key areas. The sentiment engine receives user feedback as input and uses it to emphasize or add to test cases.

[1234] Step 7:

[1235] The server sends the final test cases and adjustment results to the terminal. The terminal receives this and displays it to the user. The user then uses this to create a test plan and implements it in cooperation with the test engineer.

[1236] (Application Example 3)

[1237] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1238] Insufficient testing before the release of new features has led to bugs appearing in the market, and this issue needs to be resolved. Furthermore, there is a challenge in being unable to tailor test cases based on user sentiment, making it difficult to highlight particularly sensitive behaviors or features.

[1239] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[1240] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating key points for testing, means for generating elements that could lead to defects, means for adjusting test cases based on user emotions using an emotion engine, and means for analyzing operator feedback and highlighting actions and functions that require particular attention. This makes it possible to prevent defects before release and to adjust test cases based on user emotions.

[1241] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases, key points for testing, and elements that could lead to defects.

[1242] "Means of communicating requirements and specifications" refers to the means of inputting system requirements and specifications into a generative AI for analysis.

[1243] "Means for generating test cases" refers to methods for automatically generating test cases based on requirements and specifications analyzed by a generative AI.

[1244] "Methods for generating key points for testing" refer to methods by which a generative AI, based on its analysis results, indicates areas that should be prioritized and checked during testing.

[1245] "Means for generating elements that lead to malfunctions" refers to the means by which a generative AI identifies and displays elements that could cause malfunctions based on its analysis results.

[1246] An "emotion engine" is a technology that analyzes user emotions and adjusts system behavior and test cases based on the results.

[1247] "Means for adjusting test cases based on user emotions" refers to means for adjusting generated test cases based on the user emotions analyzed by the emotion engine.

[1248] "Means for analyzing operator feedback and highlighting actions or functions that require special attention" refers to means for analyzing feedback from operators and highlighting actions or functions that require special attention.

[1249] The system for implementing this invention consists primarily of a server containing a program that combines a generative AI and an emotion engine. The server receives requirements and specifications as input and generates test cases using the generative AI. The generated test cases include key points for testing and elements that could lead to defects, thereby enabling the prevention of defects before release.

[1250] Furthermore, the emotion engine analyzes the user's emotions and adjusts test cases based on the results. Specifically, if a user is dissatisfied with a particular feature, it highlights test cases related to that feature and adjusts the testing focus accordingly.

[1251] This system utilizes high-performance servers and software such as Python and TensorFlow. Data processing and calculations are performed by a generative AI model that analyzes requirements and specifications, and an emotion engine that analyzes user feedback.

[1252] As a concrete example, in factory robot control software, if an operator provides feedback that "the movement is not smooth," the emotion engine will increase the number of test cases related to that movement and adjust the testing to focus on smoothness.

[1253] An example of a prompt to input into the generated AI model is, "Analyze the operating requirements of the factory robot and generate test cases to ensure smooth operation."

[1254] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[1255] Step 1:

[1256] The server receives requirements and specifications from the user as input. This input data includes detailed requirements and specifications for the control software of the factory robot. The server sends prompt messages to the generating AI model to analyze this data.

[1257] Step 2:

[1258] The generation AI model analyzes the requirements and specifications received from the server and generates test cases. This analysis determines what tests are necessary based on the requirements and outputs specific test cases. The generated test cases include key points for testing and elements that could lead to defects.

[1259] Step 3:

[1260] The server sends the generated test cases to the sentiment engine. The sentiment engine receives user sentiment data as input and adjusts the test cases. Specifically, if a user is dissatisfied with a particular feature, it highlights the test cases related to that feature and adjusts the testing focus accordingly.

[1261] Step 4:

[1262] The server provides the operator with a set of test cases. The operator then tests the factory robot's control software based on these test cases. This testing helps prevent defects before release.

[1263] Step 5:

[1264] The operator provides test results as feedback to the server. The server analyzes this feedback and readjusts the test cases and test focus as needed. This feedback loop improves the accuracy and efficiency of the tests.

[1265] (Other examples)

[1266] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[1267] 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.

[1268] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1269] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[1270] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1271] [Fourth Embodiment]

[1272] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1273] 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.

[1274] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1275] 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.

[1276] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1277] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1278] 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.

[1279] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1280] 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.

[1281] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1282] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1283] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1284] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[1285] "Example of form 1"

[1286] One embodiment of the present invention provides a system utilizing generative AI. This system includes means for communicating requirements and specifications, means for generating test cases, means for generating key points for testing, and means for generating elements that lead to defects. Specifically, to solve the problem of market bugs occurring due to insufficient testing during new feature releases, the generative AI analyzes the requirements and specifications and generates test cases, key points for testing, and elements that lead to defects based on them.

[1287] "Example of form 2"

[1288] As a concrete example, before the release of a new feature, a generative AI analyzes the requirements and specifications and generates test cases. These generated test cases complement the tests performed manually by test engineers. The generative AI also generates key points for testing, indicating areas where test engineers should focus their testing. Furthermore, the generative AI generates elements that could lead to defects, indicating areas where test engineers should pay particular attention during testing. This makes it possible to prevent defects that previously slipped through the cracks and led to market bugs before release.

[1289] "Example of form 3"

[1290] As a concrete example, before the release of a new feature, a generative AI analyzes the requirements and specifications and generates test cases. These generated test cases complement the tests performed manually by test engineers. The generative AI also generates key points for testing, indicating areas where test engineers should focus their testing. Furthermore, the generative AI generates elements that could lead to defects, indicating areas where test engineers should pay particular attention during testing. This makes it possible to prevent defects that previously slipped through the cracks and led to market bugs before release.

[1291] The following describes the processing flow for each example of the form.

[1292] "Example of form 1"

[1293] Step 1: Before releasing a new feature, the generative AI receives the requirements and specifications.

[1294] Step 2: Generative AI analyzes the requirements and specifications.

[1295] Step 3: Based on the analysis, the generative AI generates test cases.

[1296] Step 4: Generative AI generates key points for testing.

[1297] Step 5: The generative AI generates elements that lead to malfunctions.

[1298] "Example of form 2"

[1299] Step 1: Before releasing a new feature, the generative AI receives the requirements and specifications.

[1300] Step 2: Generative AI analyzes the requirements and specifications.

[1301] Step 3: Based on the analysis, the generative AI generates test cases. The generated test cases complement the tests that test engineers perform manually.

[1302] Step 4: The generative AI generates key points for testing, indicating to the test engineers which areas should be prioritized for testing.

[1303] Step 5: Generative AI generates elements that could lead to bugs, and test engineers highlight areas that require particularly careful testing. This makes it possible to prevent bugs that previously slipped through the cracks and led to market bugs before release.

[1304] (Example 1)

[1305] Next, we will describe Embodiment 1 of Example Form 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1306] When introducing new features, it is necessary to address the problem of defects occurring in the market due to insufficient testing. Furthermore, preventing defects that were previously overlooked and led to market defects is also a crucial challenge.

[1307] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1308] In this invention, the server includes means for analyzing requirements and specifications using an information processing device, means for generating test cases based on the analysis results, and means for extracting important test points from the test cases. This makes it possible to increase the comprehensiveness of testing and prevent defects from occurring in the market.

[1309] An "information processing device" is a device used for inputting, processing, and outputting data, and includes devices such as computers and servers.

[1310] "Requirements and specifications" refer to detailed descriptions of the functions and performance that a system or software must meet, and are documents that serve as the basis for development.

[1311] "Analysis" is the process of examining given information in detail to understand its meaning and structure.

[1312] A "test case" is a specific test scenario designed to verify that a particular function or specification works correctly.

[1313] A "critical test point" refers to a point in a test case that requires particular attention and has the potential to significantly impact the quality and safety of the system.

[1314] A "defect" refers to a malfunction or bug that causes a system or software to fail to function as expected.

[1315] As an embodiment for carrying out this invention, a system utilizing a generative AI model is provided. This system has the function of analyzing requirements and specifications using an information processing device, generating test cases based on the analysis results, and further extracting important test points from the test cases.

[1316] The server uses a generative AI model to analyze the requirements and specifications provided by the user. This analysis utilizes natural language processing techniques and employs common AI models to understand the meaning of the requirements. Specifically, it can use AI models that are widely available as software for natural language processing.

[1317] Based on the analysis results, the server generates test cases. These test cases include specific test scenarios to verify that the system's functions and specifications work correctly. For example, if a user enters a prompt such as "Analyze the requirements for the new payment function and generate test cases," the server will analyze the requirements related to the payment function and generate test cases.

[1318] Furthermore, the server extracts key test points from the generated test cases. These key test points highlight areas requiring particular attention and identify parts that could significantly impact the system's quality and security.

[1319] In this way, the system can increase the comprehensiveness of testing and prevent defects from occurring in the market.

[1320] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1321] Step 1:

[1322] Users input requirements and specifications for the system in text format. This input includes detailed descriptions of new features and expected behavior. The entered data is sent to the server and prepared for analysis.

[1323] Step 2:

[1324] The server uses a generative AI model to analyze the requirements and specifications entered by the user. Specifically, it utilizes natural language processing techniques to understand the grammatical and semantic structure of the input text. This analysis accurately grasps the meaning of the requirements and generates data for use in the next step. The output is structured data of the analyzed requirements.

[1325] Step 3:

[1326] The server generates test cases based on the analysis results. This process uses a generative AI model to create test cases for both normal and abnormal scenarios, covering all possible scenarios. For example, if a user enters the prompt "Analyze the requirements for a new payment function and generate test cases," the server will list test cases related to the payment function. The output will be a list of specific test cases.

[1327] Step 4:

[1328] The server extracts key test points based on the generated test cases. This step identifies points requiring particular attention within the test cases, helping to prioritize the tests. Specifically, security-related test cases and areas that may affect system stability are highlighted. The output is a list of key test points.

[1329] Step 5:

[1330] The server identifies elements that could lead to defects based on the analysis of requirements and specifications and the generated test cases. This process refers to historical data and common bug patterns to identify potential risks. For example, insufficient validation of input values ​​or problems with boundary values ​​may be pointed out. The output is a list of potential defect elements.

[1331] (Application Example 1)

[1332] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1333] In control programs for factory automation equipment, a problem exists where insufficient operational testing occurs when new features are released, leading to market bugs and malfunctions. This problem can reduce the efficiency of the manufacturing line and negatively impact product quality. Therefore, automating operational testing and preventing malfunctions before they occur is essential.

[1334] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1335] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating key points for testing, means for generating elements that lead to defects, means for automatically performing operational tests when new functions are released in the control program of the factory automation equipment, and means for analyzing the results of the operational tests to prevent malfunctions. This enables the automation of operational tests when new functions are released in the factory automation equipment and the prevention of malfunctions.

[1336] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and defect elements based on them.

[1337] "Means of communicating requirements and specifications" refers to methods for clearly defining the functions and performance required by the system and inputting them into a generative AI.

[1338] "Methods for generating test cases" refer to methods for automatically creating specific test items to verify the operation of software or systems based on requirements and specifications.

[1339] "Methods for generating key points for testing" refer to methods for extracting particularly important points and areas to pay attention to in a test, in order to conduct an efficient examination.

[1340] "Means of generating elements that lead to malfunctions" refers to methods for identifying potential problems in a system or software and evaluating the likelihood that these problems will lead to malfunctions.

[1341] "Factory automation equipment" is a general term for machines and devices used to automate manufacturing processes.

[1342] A "control program" is software used to instruct and manage the operation of factory automation equipment.

[1343] "Means for automatically performing operational tests" refers to a method for a generative AI to automatically perform operational tests when a new function of a control program is released.

[1344] "Means of analyzing operational test results and preventing malfunctions" refers to methods for evaluating the results of operational tests, identifying potential malfunctions, and preventing them.

[1345] The system for realizing this invention utilizes generative AI to automate operational testing when new functions are released in the control program of factory automation equipment. The server uses a generative AI model to analyze requirements and specifications and generate test cases. This makes it possible to automatically perform operational testing, analyze the test results, and prevent malfunctions before they occur.

[1346] Specifically, the server uses a generative AI model (e.g., OpenAI GPT-4) to receive requirements and specifications as input. Based on this, the AI ​​generates test cases and performs operational tests on the control programs of factory automation equipment. The test results are analyzed on the server to identify potential defects. This can improve the efficiency of the manufacturing line.

[1347] For example, when adding a new transport operation, the server generates a test case that includes "how to operate when the weight of the transported object exceeds a specified value" to verify that the robot operates correctly. An example of a prompt used in this process would be, "The requirements for the new transport operation are a maximum weight of 10 kg and a transport speed of 1 m / s. Please generate a test case based on these requirements."

[1348] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1349] Step 1:

[1350] The server receives requirements and specifications from the user regarding new functions for factory automation equipment. This input data includes specific specifications such as "maximum weight 10 kg, conveying speed 1 m / s." The server then prepares to input this information into the generating AI model.

[1351] Step 2:

[1352] The server uses a generative AI model to generate prompt statements based on the received requirements and specifications. The prompt statements are in the format of, "The requirements for the new transport operation are a maximum weight of 10 kg and a transport speed of 1 m / s. Please generate test cases based on these requirements." The server then inputs these prompt statements into the generative AI model.

[1353] Step 3:

[1354] The generation AI model analyzes the prompt text and generates test cases based on the requirements and specifications. The server receives the generated test cases and uses them as input data for operational testing.

[1355] Step 4:

[1356] The server uses the generated test cases to perform operational tests on the control programs of the factory automation equipment. These operational tests include simulations and actual machine tests to verify that the equipment operates according to specifications.

[1357] Step 5:

[1358] The server collects the results of operational tests and analyzes them using a generative AI model. This analysis identifies potential defects and malfunctions. The server reports the analysis results to the user and prompts them to modify the control program as needed.

[1359] (Example 2)

[1360] Next, we will describe Example 2 of the morphological example. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1361] When releasing new features, there is a need to resolve the issue of market bugs arising due to insufficient testing. Furthermore, a system is needed to prevent bugs that slip through the cracks before release and lead to market bugs.

[1362] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1363] In this invention, the server includes means for inputting requirements and specifications, means for analyzing the requirements and specifications using a generation AI model, and means for generating test cases based on the analysis results. This makes it possible to prevent defects that could lead to market bugs before release.

[1364] "Requirements and specifications" are documents that describe in detail the functions, performance, and constraints that a system or software must meet.

[1365] A "generative AI model" is an algorithm or framework that uses artificial intelligence technology to analyze data and generate new information or results.

[1366] "Analysis" is the process of thoroughly examining given data or information to understand its structure and meaning.

[1367] A "test case" is a set of conditions or procedures designed to verify a specific function or behavior of software or a system.

[1368] A "key point" refers to an important point or element that requires particular attention in a specific task or process.

[1369] A "malfunction" refers to a state in which a system or software does not function as expected or does not meet specifications.

[1370] A "market bug" is a defect or flaw discovered after a product has been released to the market, and is a problem that may affect users.

[1371] A "server" is a computer system that provides services to other computers on a network.

[1372] A description of embodiments for carrying out this invention will be given.

[1373] The server first receives requirements and specifications for new features from the user. The user sends specific requirements and specifications to the server in text format. This information becomes the basic data for the generative AI model to analyze.

[1374] Next, the server uses a generative AI model to analyze the received requirements and specifications. The generative AI model utilizes natural language processing techniques to extract the information necessary for generating test cases from the requirements and specifications. Machine learning frameworks such as TensorFlow and PyTorch are used for this analysis.

[1375] Based on the analysis results, the server generates test cases using a generated AI model. The generated test cases include specific test scenarios and procedures, complementing tests performed manually by test engineers. For example, abnormal test cases for the user authentication function are generated.

[1376] Furthermore, the server uses a generative AI model to generate key testing points. This allows test engineers to understand which areas should be tested most thoroughly. The server also generates elements that could lead to defects, highlighting areas that require particularly careful testing. For example, it might point out a potential security vulnerability in the user authentication function.

[1377] As a concrete example, before the release of a new mobile app, a generative AI model analyzes the requirements for "user authentication functionality" and generates test cases. The generated test cases include abnormal case tests during login and tests for the password reset function. An example of a prompt to input to the generative AI model would be, "Generate test cases for user authentication functionality."

[1378] This system allows users to prevent bugs that could lead to market issues before release.

[1379] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1380] Step 1:

[1381] The server receives requirements and specifications for new features from the user as input. The user sends specific requirements and specifications to the server in text format. This input data becomes the basic data for analysis by the generating AI model.

[1382] Step 2:

[1383] The server inputs the received requirements and specifications into a generating AI model for analysis. The generating AI model uses natural language processing technology to analyze the requirements and specifications and extract the information necessary for test case generation. In this analysis process, the input text data is tokenized and semantic analysis is performed to obtain the elements necessary for test case generation as output.

[1384] Step 3:

[1385] The server generates test cases using an AI model based on the analysis results. Specifically, it automatically designs test scenarios and procedures based on the extracted information. In this process, the analysis results are used as input, and specific test cases are generated as output. For example, abnormal test cases for the user authentication function are generated.

[1386] Step 4:

[1387] The server uses a generative AI model to generate key test points. Based on the analysis results, test engineers identify areas that should be tested intensively. This process uses the analysis results as input and generates information indicating key test points as output.

[1388] Step 5:

[1389] The server generates elements that could lead to defects and indicates areas that require particularly careful testing. The generating AI model identifies potential defect elements based on the analysis results and alerts test engineers. This process uses the analysis results as input and generates information indicating defect elements as output.

[1390] Step 6:

[1391] The server outputs generated test cases, key testing points, and potential bugs to the user. Based on this information, the user develops a test plan and conducts the actual tests. The outputted information serves as crucial guidance for the user to prevent market bugs before release.

[1392] (Application Example 2)

[1393] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1394] In factory automation equipment, a problem exists where new features are not adequately tested before release, leading to defects in the market. This problem arises because test engineers find it difficult to identify areas that need focused inspection. Furthermore, manually creating test cases is time-consuming, labor-intensive, and inefficient. As a result, it is difficult to prevent defects before release.

[1395] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1396] In this invention, the server includes means for communicating requirements and specifications using generative AI, means for generating test cases, means for generating key points for testing, means for generating elements that could lead to defects, means for generating test cases for new functions of factory automation equipment and indicating areas that should be inspected intensively, and means for confirming the generated test cases on an information terminal. This makes it possible to improve the efficiency of testing new functions of factory automation equipment and to prevent defects before release.

[1397] "Generative AI" is an artificial intelligence technology that analyzes requirements and specifications and automatically generates test cases and key points for testing based on them.

[1398] "Means of communicating requirements and specifications" refers to interfaces and processes for inputting system requirements and specifications into a generative AI and analyzing them.

[1399] "Methods for generating test cases" refers to a function that automatically creates test cases that test engineers should implement based on requirements and specifications analyzed by a generative AI.

[1400] "Methods for generating key points in testing" refers to a function where a generative AI identifies particularly important areas in testing and presents them to the test engineer.

[1401] "Means for generating elements that lead to defects" refers to a function in which a generative AI identifies elements from requirements and specifications that could potentially cause defects and alerts test engineers to them.

[1402] "Factory automation equipment" is a general term for machines and systems used to automate production processes in factories.

[1403] An "information terminal" is a device used to verify generated test cases and key points of testing, and includes smartphones and tablets.

[1404] The system for implementing this invention utilizes generative AI to automatically generate test cases for new functions of factory automation equipment, indicating areas that test engineers should focus on inspecting. The server uses generative AI to analyze requirements and specifications and generates test cases, key testing points, and factors that could lead to defects. This enables test engineers to conduct tests efficiently.

[1405] The server uses the Python programming language and the OpenAI API to input requirements and specifications as prompts into the generative AI model. The generative AI model generates test cases based on the input prompts and returns the results to the server. The server then sends the generated test cases to an information terminal for review by a test engineer.

[1406] Information terminals, such as smartphones and tablets, display generated test cases and key points for testing. Test engineers can use these terminals to review the generated information and identify areas that require focused inspection.

[1407] For example, if the new function of a factory automation device is "automatic object identification and classification," the server will input the following prompt message into the generating AI model.

[1408] Example of a prompt:

[1409] Requirements: The factory automation equipment will be given a new function to automatically identify and classify objects. Please generate test cases for this function.

[1410] By inputting this prompt into the AI ​​model, relevant test cases are generated, allowing test engineers to identify areas where testing should focus.

[1411] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1412] Step 1:

[1413] The server receives requirements and specifications for new features of factory automation equipment. It uses text data of these requirements and specifications provided by the user as input. The server analyzes this data and generates prompts for input into the AI ​​model.

[1414] Step 2:

[1415] The server sends the generated prompt text to the generative AI model via the OpenAI API. Using the prompt text as input, the generative AI model generates test cases based on it. The generated test cases are returned to the server as output.

[1416] Step 3:

[1417] The server analyzes the test cases received from the generated AI model to identify key testing points and elements that could lead to defects. Using the generated test cases as input, the server analyzes them to identify areas that should be inspected intensively. The analysis results are sent to the information terminal.

[1418] Step 4:

[1419] The terminal displays test cases and analysis results received from the server. Using data from the server as input, the terminal visually presents the information for the test engineer to review. The test engineer then reviews the information generated through the terminal and performs the actual testing.

[1420] (Example 3)

[1421] Next, we will describe Embodiment 3 of Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1422] When releasing new features, traditional manual testing is insufficient, leading to defects in the market. Furthermore, there's a risk of overlooking potential bugs before release, resulting in market bugs. To address these issues, it's necessary to efficiently and effectively generate test cases and identify areas that require focused testing.

[1423] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1424] In this invention, the server includes means for inputting requirements and specifications into an information processing device, means for analyzing the input requirements and specifications using a generation AI model, and means for generating test cases based on the analysis results. This makes it possible to efficiently generate test cases before the release of new functions and prevent potential defects.

[1425] An "information processing device" is a device that has the function of inputting, processing, and outputting data, and includes devices such as computers and servers.

[1426] "Requirements and specifications" are documents that describe in detail the conditions and functions that a system or software must meet.

[1427] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and automatically perform specific tasks.

[1428] "Analysis" is the process of thoroughly examining input data and understanding its structure and meaning.

[1429] A "test case" is a set of conditions or pr...

Claims

1. Equipped with a processor, The aforementioned processor, We receive the requirements and specifications entered by the user, Using text containing the requirements and specifications, generate a prompt instructing the system to extract and analyze the functions and constraints included in those requirements and specifications. The prompt is input to a generative AI model that analyzes the requirements and specifications and generates structured data corresponding to those requirements and specifications. Based on the analysis results, which are structured data including the functions and constraints generated by the aforementioned AI model, test examples of normal and abnormal systems corresponding to the functions and constraints are generated. From the aforementioned test examples, test points that may affect the quality or safety of the system are extracted. Based on the analysis results and test examples, identify elements that lead to defects by referring to past data and common bug patterns. system.

2. The system according to claim 1, wherein the processor generates prompts instructing the system to perform an analysis to identify elements leading to defects based on the requirements and specifications, by referring to the historical data and common bug patterns, in order to solve the problem of defects occurring in the market due to insufficient testing when introducing new functions.

3. The system according to claim 1, wherein the processor generates prompts instructing the system to identify defects based on the analysis results and on elements leading to defects identified by referring to the past data and common bug patterns, in order to prevent defects that have been overlooked in the past and led to defects in the market before introduction.

Images