system

Abstract

We provide the system. [Solution] A means for generating a list of test items based on the test content specified by the user, using a generation engine that generates test items, A data generation means that automatically generates various test data based on the aforementioned list of items, A test execution means for conducting a test using the aforementioned test data and recording the results, A means for analyzing the results and providing feedback to the user, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the test process of conventional system development, a large amount of human resources and time are required, and there are problems in the preparation of test data and the comprehensiveness of test items. Furthermore, since the feedback of test results is delayed and it is difficult to analyze the cause of errors, it has been required to solve the problem of reduced development efficiency.

Means for Solving the Problems

[0005] This invention automatically generates a list of test items based on user-specified test content using a generation engine, and then generates various test data based on that list using a data generation means. Furthermore, it introduces a system that provides rapid and accurate feedback by conducting tests using that data, and recording and analyzing the results using a test execution means. This improves the efficiency and comprehensiveness of the testing process.

[0006] A "test item" refers to a specific object of inspection set up to verify the operation of a system.

[0007] A "generation engine" refers to an automated program or algorithm that creates a list of test items based on user-specified information.

[0008] "Data generation means" refers to a function that automatically generates various input and output data according to pre-set conditions and test items.

[0009] "Test execution means" refers to a function or mechanism that uses generated test data to conduct actual tests and records the results.

[0010] "Feedback" refers to the process of analyzing test results and providing users with information about errors and areas for improvement. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] 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), and the like.

[0015] 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.

[0016] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the numbered communication I / F (Interface) is an interface that includes a communication processor, an antenna, and the like. 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).

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 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".

[0032] This invention aims to streamline the testing process in system development and is an automated system mainly consisting of a generation engine, data generation means, test execution means, and feedback means.

[0033] overview

[0034] First, the user inputs the specifications of the system they want to test and the test details through a terminal. This input includes, for example, API endpoints and their arguments, the results to be output, and the corresponding normal and abnormal test cases.

[0035] After this, the generation engine installed on the server starts up and automatically generates a list of test items based on the user's specifications. This list of test items is intended to comprehensively cover the designed test cases and check various system functions.

[0036] Next, the data generation mechanism within the server automatically prepares a wide variety of test data based on the test item list. This includes data assuming normal operation, as well as abnormal case data including boundary values ​​and error inputs.

[0037] The server's test execution mechanism automatically starts the test using the generated test data. Specifically, it inputs data to the specified APIs and system modules and verifies their responses. During the test execution, detailed logs of each step are recorded, and the test results are output.

[0038] Finally, once all tests are complete, the feedback system analyzes the test results and reports them to the user. The feedback includes confirmation of successful cases, details of failed cases, and possible improvements. This information is displayed on the device, allowing the user to take necessary actions based on it.

[0039] Specific example

[0040] For example, when testing the API of a customer information management system, the user inputs specifications for registering, updating, and deleting customer information on a terminal. The server's generation engine then creates test items containing various input patterns, and the data generation mechanism prepares input data corresponding to these patterns. Next, the test execution mechanism executes against the registration API and update API, evaluating accurate data processing and responses. Once all tests are complete, the server's feedback mechanism analyzes the results and displays a final report on the terminal. This allows the user to quickly and accurately identify system problems and consider solutions.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user inputs the specifications and test details of the system to be tested using a terminal. This includes the API endpoint, key input parameters, and test cases including the expected results.

[0044] Step 2:

[0045] Upon receiving input from the terminal, the server activates its generation engine to automatically generate a list of test items based on the user's specifications. This process considers comprehensive test cases in accordance with the system specifications.

[0046] Step 3:

[0047] The data generation mechanism is activated within the server, generating various patterns of test data based on the test item list. Here, data is generated that assumes normal operation, as well as data including boundary values ​​and abnormal values, and is handled according to each test case.

[0048] Step 4:

[0049] The server's test execution mechanism automatically starts the test using the generated test data. It inputs data into the system and APIs according to the test items, records the results, and compares them to the expected results. The results are stored in detail for subsequent analysis.

[0050] Step 5:

[0051] After all tests are completed, the server's feedback mechanism analyzes the test results. It determines whether each test case was successful or not, summarizes the causes and suggested improvements for failed cases, and generates feedback containing this information.

[0052] Step 6:

[0053] The feedback results are displayed on the device, allowing users to review detailed test results, problems, and suggested improvements. Based on this, users can further adjust and modify the system.

[0054] (Example 1)

[0055] Next, we will describe 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."

[0056] The testing process in system development requires enormous time and effort for manually designing test items and preparing data, and can result in variations in test accuracy. This challenge is particularly pronounced in large and complex systems, and there is a need for the automation of efficient and highly accurate testing processes.

[0057] 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.

[0058] In this invention, the server includes means for specifying test content based on system specification information entered by the user via a terminal and generating an item list using a generation AI model; means for automatically generating various test data, including boundary values ​​and error inputs, based on the item list; and means for inputting the test data, conducting the test while verifying the response, and recording a detailed log thereof. This streamlines the testing process, automates a series of processes from test item design to data generation and result evaluation, and enables highly accurate and consistent testing.

[0059] A "generative AI model" is a technology that uses artificial intelligence to automatically generate test items and data in response to user-specified input, thereby reducing human intervention and supporting the testing process.

[0060] "Test content" refers to a verification process performed on specific operations or functions of a system, and includes criteria for confirming expected behavior and output.

[0061] A "list of items" is a list of specific test cases and conditions that should be implemented for the system under test, and serves as a guideline for comprehensively verifying the system's functionality.

[0062] "Test data" refers to input data used to verify the functionality and performance of the system based on the generated list of test items, and is prepared to simulate normal and abnormal system conditions.

[0063] "Feedback" refers to information provided based on the test results, including details about the success or failure of the test, and suggestions for improving the system.

[0064] A "boundary value" is a value set to measure the limits of inputs and conditions for a system to operate, and is an important element for verifying the robustness of a system.

[0065] "Error input" refers to intentionally incorrect data formatted for the purpose of verifying abnormal system behavior and error handling, and is used to evaluate the system's error handling capabilities.

[0066] This invention is a system that provides advanced automation to improve the efficiency of the testing process. In particular, it aims to simplify the process from designing and executing test items to evaluating results in complex system development.

[0067] The server generates a list of test items using a generative AI model. This generative AI model creates a list of items that cover various test cases based on the system specification information entered by the user via the terminal. Prior to this, the user is required to input specific details about the characteristics of the test subject and the expected outcomes into the terminal.

[0068] Based on the generated list of items, the server automatically generates a variety of test data using data generation mechanisms. This process includes various datasets, including not only normal data to confirm normal operation, but also boundary values ​​and error inputs for error handling checks.

[0069] Furthermore, the server uses a test execution mechanism to send input data to specified APIs and system modules and verifies their responses. The data collected during the test is recorded in detail as logs and used for analysis.

[0070] After the test is complete, the server presents the test results to the user through a feedback mechanism. This includes not only details of successful and unsuccessful test cases, but also potential improvements. This allows the user to quickly identify system problems based on the test results and take corrective action.

[0071] As a concrete example, consider API testing in a customer information management system. The user inputs the "specifications for registering, updating, and deleting customer information" into a terminal. The server's generated AI model uses this information to create a wide range of test cases and prepares the relevant test data. After the test is executed, the server analyzes the detailed results and provides accurate feedback.

[0072] Example prompts for generative AI models:

[0073] "Please create API test cases for a customer information management system. The specifications include new registration and update. The abnormal cases to consider are invalid email addresses and excessive field lengths."

[0074] In this way, this invention improves the efficiency and accuracy of the entire development cycle through the real-time automation of system testing.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The user inputs system specification information via a terminal. This input includes the URL endpoint, the arguments to be used, the expected output format, and normal and abnormal test cases. Specifically, the user inputs information such as the "endpoint URL" and "argument details" of the API used to register customer information, and what the "ideal output" should be. The data obtained from this process forms the basis for test design.

[0078] Step 2:

[0079] The server generates a list of test items using a generation AI model based on the specification information entered by the user. The input here is the data entered as API specification information in Step 1, and the output is a "test item list" that covers various test patterns. The generation AI model utilizes prompt statements to automatically complete possible scenarios and build comprehensive test items.

[0080] Step 3:

[0081] The server uses a data generation mechanism to automatically generate various test data based on the test item list. In this step, the test item list is taken as input, and a "test dataset" including boundary values ​​and outliers is output from the normal operational verification data. This prepares test data that can be used to evaluate the system's operation under various conditions.

[0082] Step 4:

[0083] The server uses a test execution mechanism to input each test data into APIs and specified system components, and verifies the responses. The input consists of each generated test data and the configured test sequence, while the output is a detailed response log for each call. Specific operations include sending data to APIs, verifying responses, and retrieving error messages.

[0084] Step 5:

[0085] The server analyzes test results and reports them to the user via a feedback mechanism. The input includes recorded test logs, and this data is analyzed to produce output that provides information on the success or failure of the test, details of failed cases, and areas for further improvement. The user receives this feedback on their device and uses it for future development and adjustments.

[0086] (Application Example 1)

[0087] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] In recent years, factory automation equipment has been required to operate with high precision and stability, making testing robot motion programs crucial. However, conventional testing methods have presented challenges, such as the significant effort and time required for designing test items and generating data, and the difficulty of detecting and analyzing problems in real time. In particular, there is a lack of methods for quickly understanding test results and providing feedback to workers, making the establishment of an efficient testing process essential.

[0089] 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.

[0090] In this invention, the server includes means for generating a list of test items using a generation engine that generates test items, means for automatically generating various data based on the test items, and means for conducting tests using the generated test data. This enables real-time testing of the operation of factory robots and rapid presentation of the results, thereby allowing for early detection and countermeasures against operational abnormalities.

[0091] A "generation engine" is a mechanical and programmatic device that generates a list of items based on the test content.

[0092] "Data generation means" refers to a function or device for automatically creating various test data based on a list of test items.

[0093] "Test execution means" refers to a function or device for conducting tests using generated test data and recording the results.

[0094] "Means of providing feedback" refers to a mechanism or function for analyzing test results and providing that information to users.

[0095] A "device for testing operational programs" is a device that has the function of testing the operational programs of factory robots and presenting the results.

[0096] "Means of presenting test results in real time" refers to a device or function that can immediately show the results obtained during the test to the worker.

[0097] This invention provides an automated system for streamlining the testing process. This system handles everything from generating test items and data to conducting tests and providing feedback on the results. In this embodiment, a server, a terminal, and a factory robot work together in coordination.

[0098] When the server receives test details from the user via a terminal, its generation engine generates test items based on that information. This generation engine creates a list of test items based on system specifications, ensuring comprehensive coverage of the test scope. Next, a data generation mechanism within the server automatically generates diverse test data based on the test item list. This data is designed to handle not only normal operation but also boundary values ​​and abnormal conditions.

[0099] The test execution means issues test commands to the factory robot using the generated test data and performs the operation. When the robot completes the operation, the response information is recorded and analyzed in real time. The analysis results are presented in real time to the worker's smart glasses or head-mounted display via a feedback means.

[0100] As a concrete example, consider testing a robot handling part A. The user sends test conditions to the server via a prompt message such as "Test handling part A". The server receives this, generates a list of corresponding test items and test data, and provides feedback of the results to the user. This allows for immediate correction of any operational abnormalities.

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The user inputs the test details through a terminal. Specifically, they send prompt messages such as "Handling test for part A" via voice input or text input. This input is passed to the server and treated as data that forms the basis for the next test item generation process.

[0104] Step 2:

[0105] The server generates a list of test items using a generation AI model based on the received test data. During this generation process, it analyzes the system's specifications and automatically supplements the conditions to ensure comprehensive coverage of the test items. The generated list of test items then becomes the input for the next data generation process.

[0106] Step 3:

[0107] The server's data generation mechanism automatically generates various test data based on a list of test items. This data includes scenarios for both normal and abnormal operation, and is prepared for test execution. The generated test data then serves as input for sending commands to the factory robots.

[0108] Step 4:

[0109] The server's test execution method involves inputting test data into a robot and having it perform the actions. The robot operates according to the commands, and the response information of those actions is returned to the server. This response information is the data that forms the basis for analyzing the test results.

[0110] Step 5:

[0111] The server analyzes the acquired response information in real time. The analysis compares the response data with expected values ​​to assess the presence or absence of anomalies. The analysis results are prepared as feedback data.

[0112] Step 6:

[0113] The feedback mechanism presents the analysis results to the user. Specifically, it displays test results and error messages to workers in real time via smart glasses. This allows users to immediately recognize malfunctions and take appropriate action.

[0114] 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.

[0115] This invention relates to a system that incorporates an emotion engine to recognize user emotions, in addition to a generation engine, data generation means, test execution means, and feedback means, in order to streamline the testing process in system development. The aim of this system is to improve the user's testing experience by analyzing the user's operations and reactions to test results using the emotion engine and reflecting the results in the feedback.

[0116] overview

[0117] First, the user uses a terminal to input the system specifications and test details. For example, they configure a detailed test case on the terminal, including API endpoints, input parameters, and expected test results.

[0118] The server receives information sent from the terminal and automatically generates a list of test items using a generation engine. This list is designed to accommodate a variety of cases and serves as the foundation for comprehensive verification.

[0119] Next, the data generation mechanism within the server generates various test data based on the test item list. Here, test data is generated that includes not only general data but also boundary values ​​and anomaly patterns, enabling testing in all corresponding scenarios.

[0120] The test execution mechanism automatically performs tests using the generated test data and records the results of each test. Specifically, it provides input to the API and verifies whether the response matches the expected output. Details such as the response time and the presence or absence of error messages during the test are also recorded.

[0121] During this process, the emotion engine analyzes the user's responses when they perform input operations or receive test results. This analysis includes identifying emotions using voice input and facial recognition technology, and by understanding the user's state, it determines the impact the test process has on the user.

[0122] Once all tests are complete, a feedback mechanism integrates the test results and the emotion engine's evaluation results and provides them to the user. This feedback includes details of successes and failures, findings from each case, and improvement suggestions based on the user's emotions. For example, if the user is experiencing stress, additional support information and solutions will be provided.

[0123] Specific example

[0124] In API testing for a customer management system, the user inputs detailed API specifications via a terminal, and the server generates a list of test items using a generation engine. The data generation means outputs test data with diverse inputs, and the test execution means verifies the API's operation using this data. Along with the test results, an emotion engine can be used to analyze the user's emotional state from their reactions, and as feedback, it can show how much stress or difficulty the system caused the user and suggest improvement measures.

[0125] The following describes the processing flow.

[0126] Step 1:

[0127] The user uses a terminal to input the specifications of the system under test. This includes detailed API endpoints, parameter settings, the scenario to be tested, and the expected results.

[0128] Step 2:

[0129] The server receives the information entered on the terminal and activates a generation engine to automatically generate a list of test items. The generation engine designs possible test cases based on the specified specifications and creates a list of them.

[0130] Step 3:

[0131] The data generation mechanism within the server automatically creates test data corresponding to the generated list of test items. This process generates a variety of datasets, including both normal and abnormal cases, and prepares data suitable for each test item.

[0132] Step 4:

[0133] The server's test execution mechanism performs tests using prepared test data. During test execution, input processing is performed on APIs and system modules, and it is checked whether the responses and outputs match the expected results. Detailed information such as response speed and error messages are recorded along with the test results.

[0134] Step 5:

[0135] During the test execution and results review, the server operates an emotion engine to analyze the user's emotions. At this stage, it captures the user's voice and facial expressions to recognize the user's emotional state (e.g., stress or relief).

[0136] Step 6:

[0137] After the test is completed, the server's feedback system integrates the test results and analyzed sentiment information to generate a report. The feedback includes successful test cases, details of errors, and insights and improvement suggestions based on user sentiment, which are then provided to the user via the terminal.

[0138] Step 7:

[0139] Users can review feedback results on their devices and use them to make decisions about adjusting or improving the system as needed. This process ensures that the testing phase proceeds efficiently and in a user-friendly manner.

[0140] (Example 2)

[0141] Next, we will describe 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".

[0142] In traditional system development testing processes, challenges included ensuring comprehensiveness and efficiency of test items, as well as improving the user experience. In particular, automatically generating diverse test cases and appropriately analyzing test results proved difficult, resulting in insufficient improvement of the user's testing experience. Furthermore, there was a lack of technology to accurately understand the stress and burden users experienced during testing and to propose improvements.

[0143] 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.

[0144] In this invention, the server includes a generation engine means for generating test items based on test content specified by the user, a data generation means for automatically generating diverse test data based on the item list, and a test execution means for conducting tests using the test data and recording the results. This makes it possible to improve the comprehensiveness and efficiency of test items, integrate the analysis of test results and user emotions, and improve the user experience in the testing process.

[0145] A "generation engine" is a processing device that automatically generates test items based on the test content specified by the user.

[0146] A "data generation means" is a system that automatically generates diverse test data based on the generated list of test items.

[0147] "Test execution means" refers to a device or program that has the function of conducting a test using the generated test data and recording the results.

[0148] A "feedback system" is a system that analyzes test results and user emotions, and uses that information to provide users with appropriate information and improvement suggestions.

[0149] An "emotion engine" is a device that analyzes a user's reactions during or upon receiving test results using speech recognition and image processing technologies to understand the user's emotional state.

[0150] This invention is a system designed to streamline the testing process and improve the user experience. The system includes a generation engine, data generation means, test execution means, feedback means, and an emotion engine. Specific embodiments thereof are described below.

[0151] The user uses a terminal to input detailed specifications of the information processing device under test and the test content. This input includes API endpoints, required input parameters, and expected test results. At this stage, a generative AI model is utilized to suggest optimal test cases and templates based on the prompt messages.

[0152] The server uses a generation engine based on information received from the terminal to automatically generate a list of test items. The generated test items include a variety of cases to ensure comprehensiveness and serve as the foundation for verifying the system's robustness.

[0153] Next, the data generation mechanism within the server generates test data corresponding to the test item list. This includes not only general data but also boundary values ​​and abnormal pattern data. This further enhances the comprehensiveness of the test.

[0154] The test execution method automatically performs tests and records the test results. During the test, various data is input to the API, and the response results and response times are observed in detail. This process ensures effective testing.

[0155] During the test and upon receiving the test results, the emotion engine analyzes the user's responses using speech recognition and image processing technologies. This analysis provides data to understand the stress and burden the user experienced during the test, enabling the provision of appropriate feedback.

[0156] Finally, the feedback mechanism integrates the test results and the emotion engine's evaluation to provide feedback to the user. This feedback includes details of the test's success or failure, areas for improvement, and specific improvement suggestions based on the user's emotions.

[0157] As a concrete example, in API testing for a customer management system, the user inputs detailed API specifications on a terminal, and the server lists the test items. Using the generated data, the test execution system verifies the API's operation, analyzes the test results with an emotion engine, and provides feedback. For example, a prompt might say, "Enter the API endpoint and request parameters for updating customer information, and set up a test case to verify the expected response code 200 and the updated data."

[0158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0159] Step 1:

[0160] The user inputs the specifications and test details of the information processing device via a terminal. Specifically, they input API endpoints, input parameters, and expected test results on the terminal and send them to the server using a digital form or interface. The entered data forms the basis for subsequent test item generation.

[0161] Step 2:

[0162] The server starts the generation engine based on the test specifications received from the user and automatically generates a list of test items. The generation engine analyzes the input data and lists items to cover a wide range of test cases. The resulting list of test items serves as a guideline for generating test data.

[0163] Step 3:

[0164] The data generation mechanism within the server generates various test data according to the test item list. Here, diverse test data such as normal data, boundary values, and anomaly patterns are automatically created. The generated data is then used as input data necessary for the next test execution.

[0165] Step 4:

[0166] The server's test execution mechanism automatically performs tests using the generated test data. Accurate verification is achieved by inputting data to the API and comparing the response with the expected output. The test results obtained here include response time and error messages, enabling detailed performance analysis.

[0167] Step 5:

[0168] The server's emotion engine analyzes the user's reactions during the test and upon receiving the test results. Using technologies such as voice input and facial recognition, it identifies the user's emotional state and evaluates stress points and user reactions within the test process. The output from this analysis provides valuable information for improving the user experience.

[0169] Step 6:

[0170] The server's feedback mechanism integrates test results and sentiment engine evaluations, providing feedback to the user. This feedback includes test success / failure information, areas for improvement, and suggestions based on the user's sentiment. This helps improve future test processes and enhance the user experience.

[0171] (Application Example 2)

[0172] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0173] Traditional testing processes involved manual preparation and analysis of test data, which was burdensome, and made it difficult to effectively reflect user test experiences and feedback. Furthermore, a lack of consideration for users' emotional states limited the potential for improving the user experience. There is a need to resolve these issues and improve the efficiency of the testing process while enhancing the user experience.

[0174] 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.

[0175] In this invention, the server includes means for generating an item list using a generation engine that generates test items, data generation means for automatically generating diverse test data, test execution means for conducting tests and recording results, emotion analysis means for acquiring user voice and facial expression data and identifying emotional states, and means for dynamically adjusting the test process and environment. This enables not only increased efficiency in conventional testing processes but also flexible responses to the user's emotional state.

[0176] A "generation engine" is a device or software that has the function of automatically designing test items and generating a list of items based on those items.

[0177] "Data generation means" refers to a device or program for automatically creating various test data based on an item list.

[0178] "Test execution means" refers to a device or process that performs tests using generated test data and records the results.

[0179] A "feedback mechanism" is a device or function for analyzing test results and communicating those results to the user.

[0180] "Emotion analysis means" refers to technology that acquires a user's voice and facial expression data and identifies their emotional state based on that data.

[0181] A "dynamic adjustment mechanism" is a system for appropriately modifying the testing process and environment based on the evaluation results obtained from the emotion analysis mechanism.

[0182] To realize this invention, the server automatically generates a list of test items based on the test content specified by the user using a generation engine. The generation engine is designed to ensure diversity and comprehensiveness of the tests and creates a list of items that reflect various test conditions.

[0183] Next, the data generation mechanism within the server generates diverse test data based on the test item list. This data includes not only general data but also boundary values ​​and anomaly patterns, and is designed to enable testing in various scenarios.

[0184] The test execution means uses this generated test data to conduct the test and records the results. During the test execution process, the response content and the presence or absence of error messages are also recorded.

[0185] Based on the voice and facial expression data provided by the user's device, the server identifies the user's emotional state through emotion analysis. This analysis utilizes voice recognition software and facial expression analysis technology to understand the user's mental response.

[0186] Furthermore, dynamic adjustment mechanisms adjust the testing process and environment based on the results of the emotion analysis. For example, if the user is experiencing stress, the testing process may be simplified or additional support may be provided as needed.

[0187] For example, if a passenger in an autonomous vehicle shows signs of fatigue while on board, the system will automatically adjust the in-car environment and play relaxing music.

[0188] An example of a prompt message could be: "Analyze the passenger's facial expressions and voice to determine if they are relaxed, and suggest in-car environment settings if they are determined to be relaxed."

[0189] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0190] Step 1:

[0191] The server receives test details from the terminal. It receives test specifications as input, including the API endpoint set by the user, input parameters, and expected test results. Based on this input data, the server automatically generates a list of test items using a generation engine. This process is designed to ensure diversity and comprehensiveness of the test items. A detailed list of test items is obtained as output.

[0192] Step 2:

[0193] The server receives the list of test items generated in the previous step as input. The data generation means generates various test data based on this list. The data includes information corresponding to various scenarios, including boundary values ​​and outliers. A variety of test datasets are obtained as output.

[0194] Step 3:

[0195] The server uses the generated test data. The tests are performed by the test execution method, and the results of each test are recorded. Using the test data as input, a request is made to the API, and the match between the response and the expected output is verified. The test results also record the response content, response time, and whether or not there are any error messages. A detailed report of the test results is generated as output.

[0196] Step 4:

[0197] The user's device acquires voice and facial expression data. This data is sent to a server, where an emotion analysis system analyzes it to identify the user's emotional state. Voice files and image data are used as input, and voice recognition software and facial expression analysis technology are employed. The output is an evaluation result of the user's emotional state.

[0198] Step 5:

[0199] The server receives the results of the emotion analysis as input and adjusts the test process and environment using dynamic adjustment mechanisms. If it is determined that the user is experiencing stress, measures are taken to simplify the test or provide additional support information. As an output, adaptive test adjustments are made to improve the user experience.

[0200] 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.

[0201] Data generation model 58 is a 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> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[0202] 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.

[0203] [Second Embodiment]

[0204] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0216] This invention aims to streamline the testing process in system development and is an automated system mainly consisting of a generation engine, data generation means, test execution means, and feedback means.

[0217] overview

[0218] First, the user inputs the specifications of the system they want to test and the test details through a terminal. This input includes, for example, API endpoints and their arguments, the results to be output, and the corresponding normal and abnormal test cases.

[0219] After this, the generation engine installed on the server starts up and automatically generates a list of test items based on the user's specifications. This list of test items is intended to comprehensively cover the designed test cases and check various system functions.

[0220] Next, the data generation mechanism within the server automatically prepares a wide variety of test data based on the test item list. This includes data assuming normal operation, as well as abnormal case data including boundary values ​​and error inputs.

[0221] The server's test execution mechanism automatically starts the test using the generated test data. Specifically, it inputs data to the specified APIs and system modules and verifies their responses. During the test execution, detailed logs of each step are recorded, and the test results are output.

[0222] Finally, once all tests are complete, the feedback system analyzes the test results and reports them to the user. The feedback includes confirmation of successful cases, details of failed cases, and possible improvements. This information is displayed on the device, allowing the user to take necessary actions based on it.

[0223] Specific example

[0224] For example, when testing the API of a customer information management system, the user inputs specifications for registering, updating, and deleting customer information on a terminal. The server's generation engine then creates test items containing various input patterns, and the data generation mechanism prepares input data corresponding to these patterns. Next, the test execution mechanism executes against the registration API and update API, evaluating accurate data processing and responses. Once all tests are complete, the server's feedback mechanism analyzes the results and displays a final report on the terminal. This allows the user to quickly and accurately identify system problems and consider solutions.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The user inputs the specifications and test details of the system to be tested using a terminal. This includes the API endpoint, key input parameters, and test cases including the expected results.

[0228] Step 2:

[0229] Upon receiving input from the terminal, the server activates its generation engine to automatically generate a list of test items based on the user's specifications. This process considers comprehensive test cases in accordance with the system specifications.

[0230] Step 3:

[0231] The data generation mechanism is activated within the server, generating various patterns of test data based on the test item list. Here, data is generated that assumes normal operation, as well as data including boundary values ​​and abnormal values, and is handled according to each test case.

[0232] Step 4:

[0233] The server's test execution mechanism automatically starts the test using the generated test data. It inputs data into the system and APIs according to the test items, records the results, and compares them to the expected results. The results are stored in detail for subsequent analysis.

[0234] Step 5:

[0235] After all tests are completed, the server's feedback mechanism analyzes the test results. It determines whether each test case was successful or not, summarizes the causes and suggested improvements for failed cases, and generates feedback containing this information.

[0236] Step 6:

[0237] The feedback results are displayed on the device, allowing users to review detailed test results, problems, and suggested improvements. Based on this, users can further adjust and modify the system.

[0238] (Example 1)

[0239] Next, we will describe 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."

[0240] The testing process in system development requires enormous time and effort for manually designing test items and preparing data, and can result in variations in test accuracy. This challenge is particularly pronounced in large and complex systems, and there is a need for the automation of efficient and highly accurate testing processes.

[0241] 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.

[0242] In this invention, the server includes means for specifying test content based on system specification information entered by the user via a terminal and generating an item list using a generation AI model; means for automatically generating various test data, including boundary values ​​and error inputs, based on the item list; and means for inputting the test data, conducting the test while verifying the response, and recording a detailed log thereof. This streamlines the testing process, automates a series of processes from test item design to data generation and result evaluation, and enables highly accurate and consistent testing.

[0243] A "generative AI model" is a technology that uses artificial intelligence to automatically generate test items and data in response to user-specified input, thereby reducing human intervention and supporting the testing process.

[0244] "Test content" refers to a verification process performed on specific operations or functions of a system, and includes criteria for confirming expected behavior and output.

[0245] A "list of items" is a list of specific test cases and conditions that should be implemented for the system under test, and serves as a guideline for comprehensively verifying the system's functionality.

[0246] "Test data" refers to input data used to verify the functionality and performance of the system based on the generated list of test items, and is prepared to simulate normal and abnormal system conditions.

[0247] "Feedback" refers to information provided based on the test results, including details about the success or failure of the test, and suggestions for improving the system.

[0248] A "boundary value" is a value set to measure the limits of inputs and conditions for a system to operate, and is an important element for verifying the robustness of a system.

[0249] "Error input" refers to intentionally incorrect data formatted for the purpose of verifying abnormal system behavior and error handling, and is used to evaluate the system's error handling capabilities.

[0250] This invention is a system that provides advanced automation to improve the efficiency of the testing process. In particular, it aims to simplify the process from designing and executing test items to evaluating results in complex system development.

[0251] The server generates a list of test items using a generative AI model. This generative AI model creates a list of items that cover various test cases based on the system specification information entered by the user via the terminal. Prior to this, the user is required to input specific details about the characteristics of the test subject and the expected outcomes into the terminal.

[0252] Based on the generated list of items, the server automatically generates a variety of test data using data generation mechanisms. This process includes various datasets, including not only normal data to confirm normal operation, but also boundary values ​​and error inputs for error handling checks.

[0253] Furthermore, the server uses a test execution mechanism to send input data to specified APIs and system modules and verifies their responses. The data collected during the test is recorded in detail as logs and used for analysis.

[0254] After the test is complete, the server presents the test results to the user through a feedback mechanism. This includes not only details of successful and unsuccessful test cases, but also potential improvements. This allows the user to quickly identify system problems based on the test results and take corrective action.

[0255] As a concrete example, consider API testing in a customer information management system. The user inputs the "specifications for registering, updating, and deleting customer information" into a terminal. The server's generated AI model uses this information to create a wide range of test cases and prepares the relevant test data. After the test is executed, the server analyzes the detailed results and provides accurate feedback.

[0256] Example prompts for generative AI models:

[0257] "Please create API test cases for a customer information management system. The specifications include new registration and update. The abnormal cases to consider are invalid email addresses and excessive field lengths."

[0258] In this way, this invention improves the efficiency and accuracy of the entire development cycle through the real-time automation of system testing.

[0259] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0260] Step 1:

[0261] The user inputs system specification information via a terminal. This input includes the URL endpoint, the arguments to be used, the expected output format, and normal and abnormal test cases. Specifically, the user inputs information such as the "endpoint URL" and "argument details" of the API used to register customer information, and what the "ideal output" should be. The data obtained from this process forms the basis for test design.

[0262] Step 2:

[0263] The server generates a list of test items using a generation AI model based on the specification information entered by the user. The input here is the data entered as API specification information in Step 1, and the output is a "test item list" that covers various test patterns. The generation AI model utilizes prompt statements to automatically complete possible scenarios and build comprehensive test items.

[0264] Step 3:

[0265] The server uses a data generation mechanism to automatically generate various test data based on the test item list. In this step, the test item list is taken as input, and a "test dataset" including boundary values ​​and outliers is output from the normal operational verification data. This prepares test data that can be used to evaluate the system's operation under various conditions.

[0266] Step 4:

[0267] The server uses a test execution mechanism to input each test data into APIs and specified system components, and verifies the responses. The input consists of each generated test data and the configured test sequence, while the output is a detailed response log for each call. Specific operations include sending data to APIs, verifying responses, and retrieving error messages.

[0268] Step 5:

[0269] The server analyzes test results and reports them to the user via a feedback mechanism. The input includes recorded test logs, and this data is analyzed to produce output that provides information on the success or failure of the test, details of failed cases, and areas for further improvement. The user receives this feedback on their device and uses it for future development and adjustments.

[0270] (Application Example 1)

[0271] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0272] In recent years, factory automation equipment has been required to operate with high precision and stability, making testing robot motion programs crucial. However, conventional testing methods have presented challenges, such as the significant effort and time required for designing test items and generating data, and the difficulty of detecting and analyzing problems in real time. In particular, there is a lack of methods for quickly understanding test results and providing feedback to workers, making the establishment of an efficient testing process essential.

[0273] 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.

[0274] In this invention, the server includes means for generating a list of test items using a generation engine that generates test items, means for automatically generating various data based on the test items, and means for conducting tests using the generated test data. This enables real-time testing of the operation of factory robots and rapid presentation of the results, thereby allowing for early detection and countermeasures against operational abnormalities.

[0275] A "generation engine" is a mechanical and programmatic device that generates a list of items based on the test content.

[0276] "Data generation means" refers to a function or device for automatically creating various test data based on a list of test items.

[0277] "Test execution means" refers to a function or device for conducting tests using generated test data and recording the results.

[0278] "Means of providing feedback" refers to a mechanism or function for analyzing test results and providing that information to users.

[0279] A "device for testing operational programs" is a device that has the function of testing the operational programs of factory robots and presenting the results.

[0280] "Means of presenting test results in real time" refers to a device or function that can immediately show the results obtained during the test to the worker.

[0281] This invention provides an automated system for streamlining the testing process. This system handles everything from generating test items and data to conducting tests and providing feedback on the results. In this embodiment, a server, a terminal, and a factory robot work together in coordination.

[0282] When the server receives test details from the user via a terminal, its generation engine generates test items based on that information. This generation engine creates a list of test items based on system specifications, ensuring comprehensive coverage of the test scope. Next, a data generation mechanism within the server automatically generates diverse test data based on the test item list. This data is designed to handle not only normal operation but also boundary values ​​and abnormal conditions.

[0283] The test execution means issues test commands to the factory robot using the generated test data and executes its operations. When the robot completes its operations, its response information is recorded and analyzed in real time. The analysis results are presented in real time to the operator's smart glasses or head-mounted display by the feedback means.

[0284] As a specific example, consider the test by a robot handling part A. The user sends the test conditions to the server through a prompt sentence such as "Handling test of part A". The server receives this, generates a corresponding test item list and test data, and feeds back the results to the user. This enables immediate correction if there are any operational abnormalities.

[0285] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0286] Step 1:

[0287] The user inputs the test content through the terminal. Specifically, a prompt sentence such as "Handling test of part A" is sent by voice input or text input. This input is passed to the server and treated as data for the next test item generation process.

[0288] Step 2:

[0289] The server generates a test item list using the generated AI model based on the received test content. In this generation process, the system specification information is analyzed and the conditions are automatically complemented so that the test items are comprehensively covered. The generated test item list serves as the input for the next data generation process.

[0290] Step 3:

[0291] The server's data generation mechanism automatically generates various test data based on a list of test items. This data includes scenarios for both normal and abnormal operation, and is prepared for test execution. The generated test data then serves as input for sending commands to the factory robots.

[0292] Step 4:

[0293] The server's test execution method involves inputting test data into a robot and having it perform the actions. The robot operates according to the commands, and the response information of those actions is returned to the server. This response information is the data that forms the basis for analyzing the test results.

[0294] Step 5:

[0295] The server analyzes the acquired response information in real time. The analysis compares the response data with expected values ​​to assess the presence or absence of anomalies. The analysis results are prepared as feedback data.

[0296] Step 6:

[0297] The feedback mechanism presents the analysis results to the user. Specifically, it displays test results and error messages to workers in real time via smart glasses. This allows users to immediately recognize malfunctions and take appropriate action.

[0298] 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.

[0299] This invention relates to a system that incorporates an emotion engine to recognize user emotions, in addition to a generation engine, data generation means, test execution means, and feedback means, in order to streamline the testing process in system development. The aim of this system is to improve the user's testing experience by analyzing the user's operations and reactions to test results using the emotion engine and reflecting the results in the feedback.

[0300] overview

[0301] First, the user uses a terminal to input the system specifications and test details. For example, they configure a detailed test case on the terminal, including API endpoints, input parameters, and expected test results.

[0302] The server receives information sent from the terminal and automatically generates a list of test items using a generation engine. This list is designed to accommodate a variety of cases and serves as the foundation for comprehensive verification.

[0303] Next, the data generation mechanism within the server generates various test data based on the test item list. Here, test data is generated that includes not only general data but also boundary values ​​and anomaly patterns, enabling testing in all corresponding scenarios.

[0304] The test execution mechanism automatically performs tests using the generated test data and records the results of each test. Specifically, it provides input to the API and verifies whether the response matches the expected output. Details such as the response time and the presence or absence of error messages during the test are also recorded.

[0305] During this process, the emotion engine analyzes the user's responses when they perform input operations or receive test results. This analysis includes identifying emotions using voice input and facial recognition technology, and by understanding the user's state, it determines the impact the test process has on the user.

[0306] When all the tests are completed, the feedback means integrates the test results and the evaluation results of the emotion engine and provides them to the user. This feedback includes details of success or failure, findings in each case, and improvement suggestions based on the user's emotions. For example, when the user is feeling stressed, additional support information or solutions are presented.

[0307] Specific example

[0308] In the case of an API test for a customer management system, the user inputs the API specifications in detail through the terminal, and the server lists the test items with the generation engine. The data generation means outputs test data with diversified inputs, and the test execution means verifies the operation of the API with these data. Along with the test results, the emotion engine is used to analyze the emotional state from the user's reaction, and as feedback, it can show how much stress or difficulty the system has imposed on the user and propose improvement measures.

[0309] The following describes the process flow.

[0310] Step 1:

[0311] The user uses the terminal to input the specifications of the system to be tested. This includes detailed endpoints of the API, parameter settings, scenarios to be tested, and expected results.

[0312] Step 2:

[0313] Receive the information input on the terminal, and the server activates the generation engine to automatically generate a test item list. The generation engine designs possible test cases based on the specified specifications and creates a list of them.

[0314] Step 3:

[0315] The data generation mechanism within the server automatically creates test data corresponding to the generated list of test items. This process generates a variety of datasets, including both normal and abnormal cases, and prepares data suitable for each test item.

[0316] Step 4:

[0317] The server's test execution mechanism performs tests using prepared test data. During test execution, input processing is performed on APIs and system modules, and it is checked whether the responses and outputs match the expected results. Detailed information such as response speed and error messages are recorded along with the test results.

[0318] Step 5:

[0319] During the test execution and results review, the server operates an emotion engine to analyze the user's emotions. At this stage, it captures the user's voice and facial expressions to recognize the user's emotional state (e.g., stress or relief).

[0320] Step 6:

[0321] After the test is completed, the server's feedback system integrates the test results and analyzed sentiment information to generate a report. The feedback includes successful test cases, details of errors, and insights and improvement suggestions based on user sentiment, which are then provided to the user via the terminal.

[0322] Step 7:

[0323] Users can review feedback results on their devices and use them to make decisions about adjusting or improving the system as needed. This process ensures that the testing phase proceeds efficiently and in a user-friendly manner.

[0324] (Example 2)

[0325] Next, we will describe 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".

[0326] In traditional system development testing processes, challenges included ensuring comprehensiveness and efficiency of test items, as well as improving the user experience. In particular, automatically generating diverse test cases and appropriately analyzing test results proved difficult, resulting in insufficient improvement of the user's testing experience. Furthermore, there was a lack of technology to accurately understand the stress and burden users experienced during testing and to propose improvements.

[0327] 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.

[0328] In this invention, the server includes a generation engine means for generating test items based on test content specified by the user, a data generation means for automatically generating diverse test data based on the item list, and a test execution means for conducting tests using the test data and recording the results. This makes it possible to improve the comprehensiveness and efficiency of test items, integrate the analysis of test results and user emotions, and improve the user experience in the testing process.

[0329] A "generation engine" is a processing device that automatically generates test items based on the test content specified by the user.

[0330] A "data generation means" is a system that automatically generates diverse test data based on the generated list of test items.

[0331] "Test execution means" refers to a device or program that has the function of conducting a test using the generated test data and recording the results.

[0332] A "feedback system" is a system that analyzes test results and user emotions, and uses that information to provide users with appropriate information and improvement suggestions.

[0333] An "emotion engine" is a device that analyzes a user's reactions during or upon receiving test results using speech recognition and image processing technologies to understand the user's emotional state.

[0334] This invention is a system designed to streamline the testing process and improve the user experience. The system includes a generation engine, data generation means, test execution means, feedback means, and an emotion engine. Specific embodiments thereof are described below.

[0335] The user uses a terminal to input detailed specifications of the information processing device under test and the test content. This input includes API endpoints, required input parameters, and expected test results. At this stage, a generative AI model is utilized to suggest optimal test cases and templates based on the prompt messages.

[0336] The server uses a generation engine based on information received from the terminal to automatically generate a list of test items. The generated test items include a variety of cases to ensure comprehensiveness and serve as the foundation for verifying the system's robustness.

[0337] Next, the data generation mechanism within the server generates test data corresponding to the test item list. This includes not only general data but also boundary values ​​and abnormal pattern data. This further enhances the comprehensiveness of the test.

[0338] The test execution method automatically performs tests and records the test results. During the test, various data is input to the API, and the response results and response times are observed in detail. This process ensures effective testing.

[0339] During the test and upon receiving the test results, the emotion engine analyzes the user's responses using speech recognition and image processing technologies. This analysis provides data to understand the stress and burden the user experienced during the test, enabling the provision of appropriate feedback.

[0340] Finally, the feedback mechanism integrates the test results and the emotion engine's evaluation to provide feedback to the user. This feedback includes details of the test's success or failure, areas for improvement, and specific improvement suggestions based on the user's emotions.

[0341] As a concrete example, in API testing for a customer management system, the user inputs detailed API specifications on a terminal, and the server lists the test items. Using the generated data, the test execution system verifies the API's operation, analyzes the test results with an emotion engine, and provides feedback. For example, a prompt might say, "Enter the API endpoint and request parameters for updating customer information, and set up a test case to verify the expected response code 200 and the updated data."

[0342] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0343] Step 1:

[0344] The user inputs the specifications and test details of the information processing device via a terminal. Specifically, they input API endpoints, input parameters, and expected test results on the terminal and send them to the server using a digital form or interface. The entered data forms the basis for subsequent test item generation.

[0345] Step 2:

[0346] The server starts the generation engine based on the test specifications received from the user and automatically generates a list of test items. The generation engine analyzes the input data and lists items to cover a wide range of test cases. The resulting list of test items serves as a guideline for generating test data.

[0347] Step 3:

[0348] The data generation mechanism within the server generates various test data according to the test item list. Here, diverse test data such as normal data, boundary values, and anomaly patterns are automatically created. The generated data is then used as input data necessary for the next test execution.

[0349] Step 4:

[0350] The server's test execution mechanism automatically performs tests using the generated test data. Accurate verification is achieved by inputting data to the API and comparing the response with the expected output. The test results obtained here include response time and error messages, enabling detailed performance analysis.

[0351] Step 5:

[0352] The server's emotion engine analyzes the user's reactions during the test and upon receiving the test results. Using technologies such as voice input and facial recognition, it identifies the user's emotional state and evaluates stress points and user reactions within the test process. The output from this analysis provides valuable information for improving the user experience.

[0353] Step 6:

[0354] The server's feedback mechanism integrates test results and sentiment engine evaluations, providing feedback to the user. This feedback includes test success / failure information, areas for improvement, and suggestions based on the user's sentiment. This helps improve future test processes and enhance the user experience.

[0355] (Application Example 2)

[0356] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0357] Traditional testing processes involved manual preparation and analysis of test data, which was burdensome, and made it difficult to effectively reflect user test experiences and feedback. Furthermore, a lack of consideration for users' emotional states limited the potential for improving the user experience. There is a need to resolve these issues and improve the efficiency of the testing process while enhancing the user experience.

[0358] 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.

[0359] In this invention, the server includes means for generating an item list using a generation engine that generates test items, data generation means for automatically generating diverse test data, test execution means for conducting tests and recording results, emotion analysis means for acquiring user voice and facial expression data and identifying emotional states, and means for dynamically adjusting the test process and environment. This enables not only increased efficiency in conventional testing processes but also flexible responses to the user's emotional state.

[0360] A "generation engine" is a device or software that has the function of automatically designing test items and generating a list of items based on those items.

[0361] "Data generation means" refers to a device or program for automatically creating various test data based on an item list.

[0362] "Test execution means" refers to a device or process that performs tests using generated test data and records the results.

[0363] A "feedback mechanism" is a device or function for analyzing test results and communicating those results to the user.

[0364] "Emotion analysis means" refers to technology that acquires a user's voice and facial expression data and identifies their emotional state based on that data.

[0365] A "dynamic adjustment mechanism" is a system for appropriately modifying the testing process and environment based on the evaluation results obtained from the emotion analysis mechanism.

[0366] To realize this invention, the server automatically generates a list of test items based on the test content specified by the user using a generation engine. The generation engine is designed to ensure diversity and comprehensiveness of the tests and creates a list of items that reflect various test conditions.

[0367] Next, the data generation mechanism within the server generates diverse test data based on the test item list. This data includes not only general data but also boundary values ​​and anomaly patterns, and is designed to enable testing in various scenarios.

[0368] The test execution means uses this generated test data to conduct the test and records the results. During the test execution process, the response content and the presence or absence of error messages are also recorded.

[0369] Based on the voice and facial expression data provided by the user's device, the server identifies the user's emotional state through emotion analysis. This analysis utilizes voice recognition software and facial expression analysis technology to understand the user's mental response.

[0370] Furthermore, dynamic adjustment mechanisms adjust the testing process and environment based on the results of the emotion analysis. For example, if the user is experiencing stress, the testing process may be simplified or additional support may be provided as needed.

[0371] For example, if a passenger in an autonomous vehicle shows signs of fatigue while on board, the system will automatically adjust the in-car environment and play relaxing music.

[0372] An example of a prompt message could be: "Analyze the passenger's facial expressions and voice to determine if they are relaxed, and suggest in-car environment settings if they are determined to be relaxed."

[0373] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0374] Step 1:

[0375] The server receives test details from the terminal. It receives test specifications as input, including the API endpoint set by the user, input parameters, and expected test results. Based on this input data, the server automatically generates a list of test items using a generation engine. This process is designed to ensure diversity and comprehensiveness of the test items. A detailed list of test items is obtained as output.

[0376] Step 2:

[0377] The server receives the list of test items generated in the previous step as input. The data generation means generates various test data based on this list. The data includes information corresponding to various scenarios, including boundary values ​​and outliers. A variety of test datasets are obtained as output.

[0378] Step 3:

[0379] The server uses the generated test data. The tests are performed by the test execution method, and the results of each test are recorded. Using the test data as input, a request is made to the API, and the match between the response and the expected output is verified. The test results also record the response content, response time, and whether or not there are any error messages. A detailed report of the test results is generated as output.

[0380] Step 4:

[0381] The user's device acquires voice and facial expression data. This data is sent to a server, where an emotion analysis system analyzes it to identify the user's emotional state. Voice files and image data are used as input, and voice recognition software and facial expression analysis technology are employed. The output is an evaluation result of the user's emotional state.

[0382] Step 5:

[0383] The server receives the results of the emotion analysis as input and adjusts the test process and environment using dynamic adjustment mechanisms. If it is determined that the user is experiencing stress, measures are taken to simplify the test or provide additional support information. As an output, adaptive test adjustments are made to improve the user experience.

[0384] 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.

[0385] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[0386] 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.

[0387] [Third Embodiment]

[0388] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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).

[0394] 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.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0400] This invention aims to streamline the testing process in system development and is an automated system mainly consisting of a generation engine, data generation means, test execution means, and feedback means.

[0401] overview

[0402] First, the user inputs the specifications of the system they want to test and the test details through a terminal. This input includes, for example, API endpoints and their arguments, the results to be output, and the corresponding normal and abnormal test cases.

[0403] After this, the generation engine installed on the server starts up and automatically generates a list of test items based on the user's specifications. This list of test items is intended to comprehensively cover the designed test cases and check various system functions.

[0404] Next, the data generation mechanism within the server automatically prepares a wide variety of test data based on the test item list. This includes data assuming normal operation, as well as abnormal case data including boundary values ​​and error inputs.

[0405] The server's test execution mechanism automatically starts the test using the generated test data. Specifically, it inputs data to the specified APIs and system modules and verifies their responses. During the test execution, detailed logs of each step are recorded, and the test results are output.

[0406] Finally, once all tests are complete, the feedback system analyzes the test results and reports them to the user. The feedback includes confirmation of successful cases, details of failed cases, and possible improvements. This information is displayed on the device, allowing the user to take necessary actions based on it.

[0407] Specific example

[0408] For example, when testing the API of a customer information management system, the user inputs specifications for registering, updating, and deleting customer information on a terminal. The server's generation engine then creates test items containing various input patterns, and the data generation mechanism prepares input data corresponding to these patterns. Next, the test execution mechanism executes against the registration API and update API, evaluating accurate data processing and responses. Once all tests are complete, the server's feedback mechanism analyzes the results and displays a final report on the terminal. This allows the user to quickly and accurately identify system problems and consider solutions.

[0409] The following describes the processing flow.

[0410] Step 1:

[0411] The user inputs the specifications and test details of the system to be tested using a terminal. This includes the API endpoint, key input parameters, and test cases including the expected results.

[0412] Step 2:

[0413] Upon receiving input from the terminal, the server activates its generation engine to automatically generate a list of test items based on the user's specifications. This process considers comprehensive test cases in accordance with the system specifications.

[0414] Step 3:

[0415] The data generation mechanism is activated within the server, generating various patterns of test data based on the test item list. Here, data is generated that assumes normal operation, as well as data including boundary values ​​and abnormal values, and is handled according to each test case.

[0416] Step 4:

[0417] The server's test execution mechanism automatically starts the test using the generated test data. It inputs data into the system and APIs according to the test items, records the results, and compares them to the expected results. The results are stored in detail for subsequent analysis.

[0418] Step 5:

[0419] After all tests are completed, the server's feedback mechanism analyzes the test results. It determines whether each test case was successful or not, summarizes the causes and suggested improvements for failed cases, and generates feedback containing this information.

[0420] Step 6:

[0421] The feedback results are displayed on the device, allowing users to review detailed test results, problems, and suggested improvements. Based on this, users can further adjust and modify the system.

[0422] (Example 1)

[0423] Next, we will describe 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."

[0424] The testing process in system development requires enormous time and effort for manually designing test items and preparing data, and can result in variations in test accuracy. This challenge is particularly pronounced in large and complex systems, and there is a need for the automation of efficient and highly accurate testing processes.

[0425] 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.

[0426] In this invention, the server includes means for specifying test content based on system specification information entered by the user via a terminal and generating an item list using a generation AI model; means for automatically generating various test data, including boundary values ​​and error inputs, based on the item list; and means for inputting the test data, conducting the test while verifying the response, and recording a detailed log thereof. This streamlines the testing process, automates a series of processes from test item design to data generation and result evaluation, and enables highly accurate and consistent testing.

[0427] A "generative AI model" is a technology that uses artificial intelligence to automatically generate test items and data in response to user-specified input, thereby reducing human intervention and supporting the testing process.

[0428] "Test content" refers to a verification process performed on specific operations or functions of a system, and includes criteria for confirming expected behavior and output.

[0429] A "list of items" is a list of specific test cases and conditions that should be implemented for the system under test, and serves as a guideline for comprehensively verifying the system's functionality.

[0430] "Test data" refers to input data used to verify the functionality and performance of the system based on the generated list of test items, and is prepared to simulate normal and abnormal system conditions.

[0431] "Feedback" refers to information provided based on the test results, including details about the success or failure of the test, and suggestions for improving the system.

[0432] A "boundary value" is a value set to measure the limits of inputs and conditions for a system to operate, and is an important element for verifying the robustness of a system.

[0433] "Error input" refers to intentionally incorrect data formatted for the purpose of verifying abnormal system behavior and error handling, and is used to evaluate the system's error handling capabilities.

[0434] This invention is a system that provides advanced automation to improve the efficiency of the testing process. In particular, it aims to simplify the process from designing and executing test items to evaluating results in complex system development.

[0435] The server generates a list of test items using a generative AI model. This generative AI model creates a list of items that cover various test cases based on the system specification information entered by the user via the terminal. Prior to this, the user is required to input specific details about the characteristics of the test subject and the expected outcomes into the terminal.

[0436] Based on the generated list of items, the server automatically generates a variety of test data using data generation mechanisms. This process includes various datasets, including not only normal data to confirm normal operation, but also boundary values ​​and error inputs for error handling checks.

[0437] Furthermore, the server uses a test execution mechanism to send input data to specified APIs and system modules and verifies their responses. The data collected during the test is recorded in detail as logs and used for analysis.

[0438] After the test is complete, the server presents the test results to the user through a feedback mechanism. This includes not only details of successful and unsuccessful test cases, but also potential improvements. This allows the user to quickly identify system problems based on the test results and take corrective action.

[0439] As a concrete example, consider API testing in a customer information management system. The user inputs the "specifications for registering, updating, and deleting customer information" into a terminal. The server's generated AI model uses this information to create a wide range of test cases and prepares the relevant test data. After the test is executed, the server analyzes the detailed results and provides accurate feedback.

[0440] Example prompts for generative AI models:

[0441] "Please create API test cases for a customer information management system. The specifications include new registration and update. The abnormal cases to consider are invalid email addresses and excessive field lengths."

[0442] In this way, this invention improves the efficiency and accuracy of the entire development cycle through the real-time automation of system testing.

[0443] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0444] Step 1:

[0445] The user inputs system specification information via a terminal. This input includes the URL endpoint, the arguments to be used, the expected output format, and normal and abnormal test cases. Specifically, the user inputs information such as the "endpoint URL" and "argument details" of the API used to register customer information, and what the "ideal output" should be. The data obtained from this process forms the basis for test design.

[0446] Step 2:

[0447] The server generates a list of test items using a generation AI model based on the specification information entered by the user. The input here is the data entered as API specification information in Step 1, and the output is a "test item list" that covers various test patterns. The generation AI model utilizes prompt statements to automatically complete possible scenarios and build comprehensive test items.

[0448] Step 3:

[0449] The server uses a data generation mechanism to automatically generate various test data based on the test item list. In this step, the test item list is taken as input, and a "test dataset" including boundary values ​​and outliers is output from the normal operational verification data. This prepares test data that can be used to evaluate the system's operation under various conditions.

[0450] Step 4:

[0451] The server uses a test execution mechanism to input each test data into APIs and specified system components, and verifies the responses. The input consists of each generated test data and the configured test sequence, while the output is a detailed response log for each call. Specific operations include sending data to APIs, verifying responses, and retrieving error messages.

[0452] Step 5:

[0453] The server analyzes test results and reports them to the user via a feedback mechanism. The input includes recorded test logs, and this data is analyzed to produce output that provides information on the success or failure of the test, details of failed cases, and areas for further improvement. The user receives this feedback on their device and uses it for future development and adjustments.

[0454] (Application Example 1)

[0455] Next, we will explain Application Example 1. In the following explanation, 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."

[0456] In recent years, factory automation equipment has been required to operate with high precision and stability, making testing robot motion programs crucial. However, conventional testing methods have presented challenges, such as the significant effort and time required for designing test items and generating data, and the difficulty of detecting and analyzing problems in real time. In particular, there is a lack of methods for quickly understanding test results and providing feedback to workers, making the establishment of an efficient testing process essential.

[0457] 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.

[0458] In this invention, the server includes means for generating a list of test items using a generation engine that generates test items, means for automatically generating various data based on the test items, and means for conducting tests using the generated test data. This enables real-time testing of the operation of factory robots and rapid presentation of the results, thereby allowing for early detection and countermeasures against operational abnormalities.

[0459] A "generation engine" is a mechanical and programmatic device that generates a list of items based on the test content.

[0460] "Data generation means" refers to a function or device for automatically creating various test data based on a list of test items.

[0461] "Test execution means" refers to a function or device for conducting tests using generated test data and recording the results.

[0462] "Means of providing feedback" refers to a mechanism or function for analyzing test results and providing that information to users.

[0463] A "device for testing operational programs" is a device that has the function of testing the operational programs of factory robots and presenting the results.

[0464] "Means of presenting test results in real time" refers to a device or function that can immediately show the results obtained during the test to the worker.

[0465] This invention provides an automated system for streamlining the testing process. This system handles everything from generating test items and data to conducting tests and providing feedback on the results. In this embodiment, a server, a terminal, and a factory robot work together in coordination.

[0466] When the server receives test details from the user via a terminal, its generation engine generates test items based on that information. This generation engine creates a list of test items based on system specifications, ensuring comprehensive coverage of the test scope. Next, a data generation mechanism within the server automatically generates diverse test data based on the test item list. This data is designed to handle not only normal operation but also boundary values ​​and abnormal conditions.

[0467] The test execution means issues test commands to the factory robot using the generated test data and performs the operation. When the robot completes the operation, the response information is recorded and analyzed in real time. The analysis results are presented in real time to the worker's smart glasses or head-mounted display via a feedback means.

[0468] As a concrete example, consider testing a robot handling part A. The user sends test conditions to the server via a prompt message such as "Test handling part A". The server receives this, generates a list of corresponding test items and test data, and provides feedback of the results to the user. This allows for immediate correction of any operational abnormalities.

[0469] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0470] Step 1:

[0471] The user inputs the test details through a terminal. Specifically, they send prompt messages such as "Handling test for part A" via voice input or text input. This input is passed to the server and treated as data that forms the basis for the next test item generation process.

[0472] Step 2:

[0473] The server generates a list of test items using a generation AI model based on the received test data. During this generation process, it analyzes the system's specifications and automatically supplements the conditions to ensure comprehensive coverage of the test items. The generated list of test items then becomes the input for the next data generation process.

[0474] Step 3:

[0475] The server's data generation mechanism automatically generates various test data based on a list of test items. This data includes scenarios for both normal and abnormal operation, and is prepared for test execution. The generated test data then serves as input for sending commands to the factory robots.

[0476] Step 4:

[0477] The server's test execution method involves inputting test data into a robot and having it perform the actions. The robot operates according to the commands, and the response information of those actions is returned to the server. This response information is the data that forms the basis for analyzing the test results.

[0478] Step 5:

[0479] The server analyzes the acquired response information in real time. The analysis compares the response data with expected values ​​to assess the presence or absence of anomalies. The analysis results are prepared as feedback data.

[0480] Step 6:

[0481] The feedback mechanism presents the analysis results to the user. Specifically, it displays test results and error messages to workers in real time via smart glasses. This allows users to immediately recognize malfunctions and take appropriate action.

[0482] 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.

[0483] This invention relates to a system that incorporates an emotion engine to recognize user emotions, in addition to a generation engine, data generation means, test execution means, and feedback means, in order to streamline the testing process in system development. The aim of this system is to improve the user's testing experience by analyzing the user's operations and reactions to test results using the emotion engine and reflecting the results in the feedback.

[0484] overview

[0485] First, the user uses a terminal to input the system specifications and test details. For example, they configure a detailed test case on the terminal, including API endpoints, input parameters, and expected test results.

[0486] The server receives information sent from the terminal and automatically generates a list of test items using a generation engine. This list is designed to accommodate a variety of cases and serves as the foundation for comprehensive verification.

[0487] Next, the data generation mechanism within the server generates various test data based on the test item list. Here, test data is generated that includes not only general data but also boundary values ​​and anomaly patterns, enabling testing in all corresponding scenarios.

[0488] The test execution mechanism automatically performs tests using the generated test data and records the results of each test. Specifically, it provides input to the API and verifies whether the response matches the expected output. Details such as the response time and the presence or absence of error messages during the test are also recorded.

[0489] During this process, the emotion engine analyzes the user's responses when they perform input operations or receive test results. This analysis includes identifying emotions using voice input and facial recognition technology, and by understanding the user's state, it determines the impact the test process has on the user.

[0490] Once all tests are complete, a feedback mechanism integrates the test results and the emotion engine's evaluation results and provides them to the user. This feedback includes details of successes and failures, findings from each case, and improvement suggestions based on the user's emotions. For example, if the user is experiencing stress, additional support information and solutions will be provided.

[0491] Specific example

[0492] In API testing for a customer management system, the user inputs detailed API specifications via a terminal, and the server generates a list of test items using a generation engine. The data generation means outputs test data with diverse inputs, and the test execution means verifies the API's operation using this data. Along with the test results, an emotion engine can be used to analyze the user's emotional state from their reactions, and as feedback, it can show how much stress or difficulty the system caused the user and suggest improvement measures.

[0493] The following describes the processing flow.

[0494] Step 1:

[0495] The user uses a terminal to input the specifications of the system under test. This includes detailed API endpoints, parameter settings, the scenario to be tested, and the expected results.

[0496] Step 2:

[0497] The server receives the information entered on the terminal and activates a generation engine to automatically generate a list of test items. The generation engine designs possible test cases based on the specified specifications and creates a list of them.

[0498] Step 3:

[0499] The data generation mechanism within the server automatically creates test data corresponding to the generated list of test items. This process generates a variety of datasets, including both normal and abnormal cases, and prepares data suitable for each test item.

[0500] Step 4:

[0501] The server's test execution mechanism performs tests using prepared test data. During test execution, input processing is performed on APIs and system modules, and it is checked whether the responses and outputs match the expected results. Detailed information such as response speed and error messages are recorded along with the test results.

[0502] Step 5:

[0503] During the test execution and results review, the server operates an emotion engine to analyze the user's emotions. At this stage, it captures the user's voice and facial expressions to recognize the user's emotional state (e.g., stress or relief).

[0504] Step 6:

[0505] After the test is completed, the server's feedback system integrates the test results and analyzed sentiment information to generate a report. The feedback includes successful test cases, details of errors, and insights and improvement suggestions based on user sentiment, which are then provided to the user via the terminal.

[0506] Step 7:

[0507] Users can review feedback results on their devices and use them to make decisions about adjusting or improving the system as needed. This process ensures that the testing phase proceeds efficiently and in a user-friendly manner.

[0508] (Example 2)

[0509] Next, we will describe 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."

[0510] In traditional system development testing processes, challenges included ensuring comprehensiveness and efficiency of test items, as well as improving the user experience. In particular, automatically generating diverse test cases and appropriately analyzing test results proved difficult, resulting in insufficient improvement of the user's testing experience. Furthermore, there was a lack of technology to accurately understand the stress and burden users experienced during testing and to propose improvements.

[0511] 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.

[0512] In this invention, the server includes a generation engine means for generating test items based on test content specified by the user, a data generation means for automatically generating diverse test data based on the item list, and a test execution means for conducting tests using the test data and recording the results. This makes it possible to improve the comprehensiveness and efficiency of test items, integrate the analysis of test results and user emotions, and improve the user experience in the testing process.

[0513] A "generation engine" is a processing device that automatically generates test items based on the test content specified by the user.

[0514] A "data generation means" is a system that automatically generates diverse test data based on the generated list of test items.

[0515] "Test execution means" refers to a device or program that has the function of conducting a test using the generated test data and recording the results.

[0516] A "feedback system" is a system that analyzes test results and user emotions, and uses that information to provide users with appropriate information and improvement suggestions.

[0517] An "emotion engine" is a device that analyzes a user's reactions during or upon receiving test results using speech recognition and image processing technologies to understand the user's emotional state.

[0518] This invention is a system designed to streamline the testing process and improve the user experience. The system includes a generation engine, data generation means, test execution means, feedback means, and an emotion engine. Specific embodiments thereof are described below.

[0519] The user uses a terminal to input detailed specifications of the information processing device under test and the test content. This input includes API endpoints, required input parameters, and expected test results. At this stage, a generative AI model is utilized to suggest optimal test cases and templates based on the prompt messages.

[0520] The server uses a generation engine based on information received from the terminal to automatically generate a list of test items. The generated test items include a variety of cases to ensure comprehensiveness and serve as the foundation for verifying the system's robustness.

[0521] Next, the data generation mechanism within the server generates test data corresponding to the test item list. This includes not only general data but also boundary values ​​and abnormal pattern data. This further enhances the comprehensiveness of the test.

[0522] The test execution method automatically performs tests and records the test results. During the test, various data is input to the API, and the response results and response times are observed in detail. This process ensures effective testing.

[0523] During the test and upon receiving the test results, the emotion engine analyzes the user's responses using speech recognition and image processing technologies. This analysis provides data to understand the stress and burden the user experienced during the test, enabling the provision of appropriate feedback.

[0524] Finally, the feedback mechanism integrates the test results and the emotion engine's evaluation to provide feedback to the user. This feedback includes details of the test's success or failure, areas for improvement, and specific improvement suggestions based on the user's emotions.

[0525] As a concrete example, in API testing for a customer management system, the user inputs detailed API specifications on a terminal, and the server lists the test items. Using the generated data, the test execution system verifies the API's operation, analyzes the test results with an emotion engine, and provides feedback. For example, a prompt might say, "Enter the API endpoint and request parameters for updating customer information, and set up a test case to verify the expected response code 200 and the updated data."

[0526] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0527] Step 1:

[0528] The user inputs the specifications and test details of the information processing device via a terminal. Specifically, they input API endpoints, input parameters, and expected test results on the terminal and send them to the server using a digital form or interface. The entered data forms the basis for subsequent test item generation.

[0529] Step 2:

[0530] The server starts the generation engine based on the test specifications received from the user and automatically generates a list of test items. The generation engine analyzes the input data and lists items to cover a wide range of test cases. The resulting list of test items serves as a guideline for generating test data.

[0531] Step 3:

[0532] The data generation mechanism within the server generates various test data according to the test item list. Here, diverse test data such as normal data, boundary values, and anomaly patterns are automatically created. The generated data is then used as input data necessary for the next test execution.

[0533] Step 4:

[0534] The server's test execution mechanism automatically performs tests using the generated test data. Accurate verification is achieved by inputting data to the API and comparing the response with the expected output. The test results obtained here include response time and error messages, enabling detailed performance analysis.

[0535] Step 5:

[0536] The server's emotion engine analyzes the user's reactions during the test and upon receiving the test results. Using technologies such as voice input and facial recognition, it identifies the user's emotional state and evaluates stress points and user reactions within the test process. The output from this analysis provides valuable information for improving the user experience.

[0537] Step 6:

[0538] The server's feedback mechanism integrates test results and sentiment engine evaluations, providing feedback to the user. This feedback includes test success / failure information, areas for improvement, and suggestions based on the user's sentiment. This helps improve future test processes and enhance the user experience.

[0539] (Application Example 2)

[0540] Next, we will explain Application Example 2. In the following explanation, 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."

[0541] Traditional testing processes involved manual preparation and analysis of test data, which was burdensome, and made it difficult to effectively reflect user test experiences and feedback. Furthermore, a lack of consideration for users' emotional states limited the potential for improving the user experience. There is a need to resolve these issues and improve the efficiency of the testing process while enhancing the user experience.

[0542] 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.

[0543] In this invention, the server includes means for generating an item list using a generation engine that generates test items, data generation means for automatically generating diverse test data, test execution means for conducting tests and recording results, emotion analysis means for acquiring user voice and facial expression data and identifying emotional states, and means for dynamically adjusting the test process and environment. This enables not only increased efficiency in conventional testing processes but also flexible responses to the user's emotional state.

[0544] A "generation engine" is a device or software that has the function of automatically designing test items and generating a list of items based on those items.

[0545] "Data generation means" refers to a device or program for automatically creating various test data based on an item list.

[0546] "Test execution means" refers to a device or process that performs tests using generated test data and records the results.

[0547] A "feedback mechanism" is a device or function for analyzing test results and communicating those results to the user.

[0548] "Emotion analysis means" refers to technology that acquires a user's voice and facial expression data and identifies their emotional state based on that data.

[0549] A "dynamic adjustment mechanism" is a system for appropriately modifying the testing process and environment based on the evaluation results obtained from the emotion analysis mechanism.

[0550] To realize this invention, the server automatically generates a list of test items based on the test content specified by the user using a generation engine. The generation engine is designed to ensure diversity and comprehensiveness of the tests and creates a list of items that reflect various test conditions.

[0551] Next, the data generation mechanism within the server generates diverse test data based on the test item list. This data includes not only general data but also boundary values ​​and anomaly patterns, and is designed to enable testing in various scenarios.

[0552] The test execution means uses this generated test data to conduct the test and records the results. During the test execution process, the response content and the presence or absence of error messages are also recorded.

[0553] Based on the voice and facial expression data provided by the user's device, the server identifies the user's emotional state through emotion analysis. This analysis utilizes voice recognition software and facial expression analysis technology to understand the user's mental response.

[0554] Furthermore, dynamic adjustment mechanisms adjust the testing process and environment based on the results of the emotion analysis. For example, if the user is experiencing stress, the testing process may be simplified or additional support may be provided as needed.

[0555] For example, if a passenger in an autonomous vehicle shows signs of fatigue while on board, the system will automatically adjust the in-car environment and play relaxing music.

[0556] An example of a prompt message could be: "Analyze the passenger's facial expressions and voice to determine if they are relaxed, and suggest in-car environment settings if they are determined to be relaxed."

[0557] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0558] Step 1:

[0559] The server receives test details from the terminal. It receives test specifications as input, including the API endpoint set by the user, input parameters, and expected test results. Based on this input data, the server automatically generates a list of test items using a generation engine. This process is designed to ensure diversity and comprehensiveness of the test items. A detailed list of test items is obtained as output.

[0560] Step 2:

[0561] The server receives the list of test items generated in the previous step as input. The data generation means generates various test data based on this list. The data includes information corresponding to various scenarios, including boundary values ​​and outliers. A variety of test datasets are obtained as output.

[0562] Step 3:

[0563] The server uses the generated test data. The tests are performed by the test execution method, and the results of each test are recorded. Using the test data as input, a request is made to the API, and the match between the response and the expected output is verified. The test results also record the response content, response time, and whether or not there are any error messages. A detailed report of the test results is generated as output.

[0564] Step 4:

[0565] The user's device acquires voice and facial expression data. This data is sent to a server, where an emotion analysis system analyzes it to identify the user's emotional state. Voice files and image data are used as input, and voice recognition software and facial expression analysis technology are employed. The output is an evaluation result of the user's emotional state.

[0566] Step 5:

[0567] The server receives the results of the emotion analysis as input and adjusts the test process and environment using dynamic adjustment mechanisms. If it is determined that the user is experiencing stress, measures are taken to simplify the test or provide additional support information. As an output, adaptive test adjustments are made to improve the user experience.

[0568] 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.

[0569] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[0570] 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.

[0571] [Fourth Embodiment]

[0572] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0573] 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.

[0574] 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).

[0575] 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.

[0576] 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.

[0577] 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).

[0578] 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.

[0579] 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.

[0580] 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.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0585] This invention aims to streamline the testing process in system development and is an automated system mainly consisting of a generation engine, data generation means, test execution means, and feedback means.

[0586] overview

[0587] First, the user inputs the specifications of the system they want to test and the test details through a terminal. This input includes, for example, API endpoints and their arguments, the results to be output, and the corresponding normal and abnormal test cases.

[0588] After this, the generation engine installed on the server starts up and automatically generates a list of test items based on the user's specifications. This list of test items is intended to comprehensively cover the designed test cases and check various system functions.

[0589] Next, the data generation mechanism within the server automatically prepares a wide variety of test data based on the test item list. This includes data assuming normal operation, as well as abnormal case data including boundary values ​​and error inputs.

[0590] The server's test execution mechanism automatically starts the test using the generated test data. Specifically, it inputs data to the specified APIs and system modules and verifies their responses. During the test execution, detailed logs of each step are recorded, and the test results are output.

[0591] Finally, once all tests are complete, the feedback system analyzes the test results and reports them to the user. The feedback includes confirmation of successful cases, details of failed cases, and possible improvements. This information is displayed on the device, allowing the user to take necessary actions based on it.

[0592] Specific example

[0593] For example, when testing the API of a customer information management system, the user inputs specifications for registering, updating, and deleting customer information on a terminal. The server's generation engine then creates test items containing various input patterns, and the data generation mechanism prepares input data corresponding to these patterns. Next, the test execution mechanism executes against the registration API and update API, evaluating accurate data processing and responses. Once all tests are complete, the server's feedback mechanism analyzes the results and displays a final report on the terminal. This allows the user to quickly and accurately identify system problems and consider solutions.

[0594] The following describes the processing flow.

[0595] Step 1:

[0596] The user inputs the specifications and test details of the system to be tested using a terminal. This includes the API endpoint, key input parameters, and test cases including the expected results.

[0597] Step 2:

[0598] Upon receiving input from the terminal, the server activates its generation engine to automatically generate a list of test items based on the user's specifications. This process considers comprehensive test cases in accordance with the system specifications.

[0599] Step 3:

[0600] The data generation mechanism is activated within the server, generating various patterns of test data based on the test item list. Here, data is generated that assumes normal operation, as well as data including boundary values ​​and abnormal values, and is handled according to each test case.

[0601] Step 4:

[0602] The server's test execution mechanism automatically starts the test using the generated test data. It inputs data into the system and APIs according to the test items, records the results, and compares them to the expected results. The results are stored in detail for subsequent analysis.

[0603] Step 5:

[0604] After all tests are completed, the server's feedback mechanism analyzes the test results. It determines whether each test case was successful or not, summarizes the causes and suggested improvements for failed cases, and generates feedback containing this information.

[0605] Step 6:

[0606] The feedback results are displayed on the device, allowing users to review detailed test results, problems, and suggested improvements. Based on this, users can further adjust and modify the system.

[0607] (Example 1)

[0608] Next, we will describe 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".

[0609] The testing process in system development requires enormous time and effort for manually designing test items and preparing data, and can result in variations in test accuracy. This challenge is particularly pronounced in large and complex systems, and there is a need for the automation of efficient and highly accurate testing processes.

[0610] 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.

[0611] In this invention, the server includes means for specifying test content based on system specification information entered by the user via a terminal and generating an item list using a generation AI model; means for automatically generating various test data, including boundary values ​​and error inputs, based on the item list; and means for inputting the test data, conducting the test while verifying the response, and recording a detailed log thereof. This streamlines the testing process, automates a series of processes from test item design to data generation and result evaluation, and enables highly accurate and consistent testing.

[0612] A "generative AI model" is a technology that uses artificial intelligence to automatically generate test items and data in response to user-specified input, thereby reducing human intervention and supporting the testing process.

[0613] "Test content" refers to a verification process performed on specific operations or functions of a system, and includes criteria for confirming expected behavior and output.

[0614] A "list of items" is a list of specific test cases and conditions that should be implemented for the system under test, and serves as a guideline for comprehensively verifying the system's functionality.

[0615] "Test data" refers to input data used to verify the functionality and performance of the system based on the generated list of test items, and is prepared to simulate normal and abnormal system conditions.

[0616] "Feedback" refers to information provided based on the test results, including details about the success or failure of the test, and suggestions for improving the system.

[0617] A "boundary value" is a value set to measure the limits of inputs and conditions for a system to operate, and is an important element for verifying the robustness of a system.

[0618] "Error input" refers to intentionally incorrect data formatted for the purpose of verifying abnormal system behavior and error handling, and is used to evaluate the system's error handling capabilities.

[0619] This invention is a system that provides advanced automation to improve the efficiency of the testing process. In particular, it aims to simplify the process from designing and executing test items to evaluating results in complex system development.

[0620] The server generates a list of test items using a generative AI model. This generative AI model creates a list of items that cover various test cases based on the system specification information entered by the user via the terminal. Prior to this, the user is required to input specific details about the characteristics of the test subject and the expected outcomes into the terminal.

[0621] Based on the generated list of items, the server automatically generates a variety of test data using data generation mechanisms. This process includes various datasets, including not only normal data to confirm normal operation, but also boundary values ​​and error inputs for error handling checks.

[0622] Furthermore, the server uses a test execution mechanism to send input data to specified APIs and system modules and verifies their responses. The data collected during the test is recorded in detail as logs and used for analysis.

[0623] After the test is complete, the server presents the test results to the user through a feedback mechanism. This includes not only details of successful and unsuccessful test cases, but also potential improvements. This allows the user to quickly identify system problems based on the test results and take corrective action.

[0624] As a concrete example, consider API testing in a customer information management system. The user inputs the "specifications for registering, updating, and deleting customer information" into a terminal. The server's generated AI model uses this information to create a wide range of test cases and prepares the relevant test data. After the test is executed, the server analyzes the detailed results and provides accurate feedback.

[0625] Example prompts for generative AI models:

[0626] "Please create API test cases for a customer information management system. The specifications include new registration and update. The abnormal cases to consider are invalid email addresses and excessive field lengths."

[0627] In this way, this invention improves the efficiency and accuracy of the entire development cycle through the real-time automation of system testing.

[0628] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0629] Step 1:

[0630] The user inputs system specification information via a terminal. This input includes the URL endpoint, the arguments to be used, the expected output format, and normal and abnormal test cases. Specifically, the user inputs information such as the "endpoint URL" and "argument details" of the API used to register customer information, and what the "ideal output" should be. The data obtained from this process forms the basis for test design.

[0631] Step 2:

[0632] The server generates a list of test items using a generation AI model based on the specification information entered by the user. The input here is the data entered as API specification information in Step 1, and the output is a "test item list" that covers various test patterns. The generation AI model utilizes prompt statements to automatically complete possible scenarios and build comprehensive test items.

[0633] Step 3:

[0634] The server uses a data generation mechanism to automatically generate various test data based on the test item list. In this step, the test item list is taken as input, and a "test dataset" including boundary values ​​and outliers is output from the normal operational verification data. This prepares test data that can be used to evaluate the system's operation under various conditions.

[0635] Step 4:

[0636] The server uses a test execution mechanism to input each test data into APIs and specified system components, and verifies the responses. The input consists of each generated test data and the configured test sequence, while the output is a detailed response log for each call. Specific operations include sending data to APIs, verifying responses, and retrieving error messages.

[0637] Step 5:

[0638] The server analyzes test results and reports them to the user via a feedback mechanism. The input includes recorded test logs, and this data is analyzed to produce output that provides information on the success or failure of the test, details of failed cases, and areas for further improvement. The user receives this feedback on their device and uses it for future development and adjustments.

[0639] (Application Example 1)

[0640] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0641] In recent years, factory automation equipment has been required to operate with high precision and stability, making testing robot motion programs crucial. However, conventional testing methods have presented challenges, such as the significant effort and time required for designing test items and generating data, and the difficulty of detecting and analyzing problems in real time. In particular, there is a lack of methods for quickly understanding test results and providing feedback to workers, making the establishment of an efficient testing process essential.

[0642] 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.

[0643] In this invention, the server includes means for generating a list of test items using a generation engine that generates test items, means for automatically generating various data based on the test items, and means for conducting tests using the generated test data. This enables real-time testing of the operation of factory robots and rapid presentation of the results, thereby allowing for early detection and countermeasures against operational abnormalities.

[0644] A "generation engine" is a mechanical and programmatic device that generates a list of items based on the test content.

[0645] "Data generation means" refers to a function or device for automatically creating various test data based on a list of test items.

[0646] "Test execution means" refers to a function or device for conducting tests using generated test data and recording the results.

[0647] "Means of providing feedback" refers to a mechanism or function for analyzing test results and providing that information to users.

[0648] A "device for testing operational programs" is a device that has the function of testing the operational programs of factory robots and presenting the results.

[0649] "Means of presenting test results in real time" refers to a device or function that can immediately show the results obtained during the test to the worker.

[0650] This invention provides an automated system for streamlining the testing process. This system handles everything from generating test items and data to conducting tests and providing feedback on the results. In this embodiment, a server, a terminal, and a factory robot work together in coordination.

[0651] When the server receives test details from the user via a terminal, its generation engine generates test items based on that information. This generation engine creates a list of test items based on system specifications, ensuring comprehensive coverage of the test scope. Next, a data generation mechanism within the server automatically generates diverse test data based on the test item list. This data is designed to handle not only normal operation but also boundary values ​​and abnormal conditions.

[0652] The test execution means issues test commands to the factory robot using the generated test data and performs the operation. When the robot completes the operation, the response information is recorded and analyzed in real time. The analysis results are presented in real time to the worker's smart glasses or head-mounted display via a feedback means.

[0653] As a concrete example, consider testing a robot handling part A. The user sends test conditions to the server via a prompt message such as "Test handling part A". The server receives this, generates a list of corresponding test items and test data, and provides feedback of the results to the user. This allows for immediate correction of any operational abnormalities.

[0654] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0655] Step 1:

[0656] The user inputs the test details through a terminal. Specifically, they send prompt messages such as "Handling test for part A" via voice input or text input. This input is passed to the server and treated as data that forms the basis for the next test item generation process.

[0657] Step 2:

[0658] The server generates a list of test items using a generation AI model based on the received test data. During this generation process, it analyzes the system's specifications and automatically supplements the conditions to ensure comprehensive coverage of the test items. The generated list of test items then becomes the input for the next data generation process.

[0659] Step 3:

[0660] The server's data generation mechanism automatically generates various test data based on a list of test items. This data includes scenarios for both normal and abnormal operation, and is prepared for test execution. The generated test data then serves as input for sending commands to the factory robots.

[0661] Step 4:

[0662] The server's test execution method involves inputting test data into a robot and having it perform the actions. The robot operates according to the commands, and the response information of those actions is returned to the server. This response information is the data that forms the basis for analyzing the test results.

[0663] Step 5:

[0664] The server analyzes the acquired response information in real time. The analysis compares the response data with expected values ​​to assess the presence or absence of anomalies. The analysis results are prepared as feedback data.

[0665] Step 6:

[0666] The feedback mechanism presents the analysis results to the user. Specifically, it displays test results and error messages to workers in real time via smart glasses. This allows users to immediately recognize malfunctions and take appropriate action.

[0667] 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.

[0668] This invention relates to a system that incorporates an emotion engine to recognize user emotions, in addition to a generation engine, data generation means, test execution means, and feedback means, in order to streamline the testing process in system development. The aim of this system is to improve the user's testing experience by analyzing the user's operations and reactions to test results using the emotion engine and reflecting the results in the feedback.

[0669] overview

[0670] First, the user uses a terminal to input the system specifications and test details. For example, they configure a detailed test case on the terminal, including API endpoints, input parameters, and expected test results.

[0671] The server receives information sent from the terminal and automatically generates a list of test items using a generation engine. This list is designed to accommodate a variety of cases and serves as the foundation for comprehensive verification.

[0672] Next, the data generation mechanism within the server generates various test data based on the test item list. Here, test data is generated that includes not only general data but also boundary values ​​and anomaly patterns, enabling testing in all corresponding scenarios.

[0673] The test execution mechanism automatically performs tests using the generated test data and records the results of each test. Specifically, it provides input to the API and verifies whether the response matches the expected output. Details such as the response time and the presence or absence of error messages during the test are also recorded.

[0674] During this process, the emotion engine analyzes the user's responses when they perform input operations or receive test results. This analysis includes identifying emotions using voice input and facial recognition technology, and by understanding the user's state, it determines the impact the test process has on the user.

[0675] Once all tests are complete, a feedback mechanism integrates the test results and the emotion engine's evaluation results and provides them to the user. This feedback includes details of successes and failures, findings from each case, and improvement suggestions based on the user's emotions. For example, if the user is experiencing stress, additional support information and solutions will be provided.

[0676] Specific example

[0677] In API testing for a customer management system, the user inputs detailed API specifications via a terminal, and the server generates a list of test items using a generation engine. The data generation means outputs test data with diverse inputs, and the test execution means verifies the API's operation using this data. Along with the test results, an emotion engine can be used to analyze the user's emotional state from their reactions, and as feedback, it can show how much stress or difficulty the system caused the user and suggest improvement measures.

[0678] The following describes the processing flow.

[0679] Step 1:

[0680] The user uses a terminal to input the specifications of the system under test. This includes detailed API endpoints, parameter settings, the scenario to be tested, and the expected results.

[0681] Step 2:

[0682] The server receives the information entered on the terminal and activates a generation engine to automatically generate a list of test items. The generation engine designs possible test cases based on the specified specifications and creates a list of them.

[0683] Step 3:

[0684] The data generation mechanism within the server automatically creates test data corresponding to the generated list of test items. This process generates a variety of datasets, including both normal and abnormal cases, and prepares data suitable for each test item.

[0685] Step 4:

[0686] The server's test execution mechanism performs tests using prepared test data. During test execution, input processing is performed on APIs and system modules, and it is checked whether the responses and outputs match the expected results. Detailed information such as response speed and error messages are recorded along with the test results.

[0687] Step 5:

[0688] During the test execution and results review, the server operates an emotion engine to analyze the user's emotions. At this stage, it captures the user's voice and facial expressions to recognize the user's emotional state (e.g., stress or relief).

[0689] Step 6:

[0690] After the test is completed, the server's feedback system integrates the test results and analyzed sentiment information to generate a report. The feedback includes successful test cases, details of errors, and insights and improvement suggestions based on user sentiment, which are then provided to the user via the terminal.

[0691] Step 7:

[0692] Users can review feedback results on their devices and use them to make decisions about adjusting or improving the system as needed. This process ensures that the testing phase proceeds efficiently and in a user-friendly manner.

[0693] (Example 2)

[0694] Next, we will describe 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".

[0695] In traditional system development testing processes, challenges included ensuring comprehensiveness and efficiency of test items, as well as improving the user experience. In particular, automatically generating diverse test cases and appropriately analyzing test results proved difficult, resulting in insufficient improvement of the user's testing experience. Furthermore, there was a lack of technology to accurately understand the stress and burden users experienced during testing and to propose improvements.

[0696] 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.

[0697] In this invention, the server includes a generation engine means for generating test items based on test content specified by the user, a data generation means for automatically generating diverse test data based on the item list, and a test execution means for conducting tests using the test data and recording the results. This makes it possible to improve the comprehensiveness and efficiency of test items, integrate the analysis of test results and user emotions, and improve the user experience in the testing process.

[0698] A "generation engine" is a processing device that automatically generates test items based on the test content specified by the user.

[0699] A "data generation means" is a system that automatically generates diverse test data based on the generated list of test items.

[0700] "Test execution means" refers to a device or program that has the function of conducting a test using the generated test data and recording the results.

[0701] A "feedback system" is a system that analyzes test results and user emotions, and uses that information to provide users with appropriate information and improvement suggestions.

[0702] An "emotion engine" is a device that analyzes a user's reactions during or upon receiving test results using speech recognition and image processing technologies to understand the user's emotional state.

[0703] This invention is a system designed to streamline the testing process and improve the user experience. The system includes a generation engine, data generation means, test execution means, feedback means, and an emotion engine. Specific embodiments thereof are described below.

[0704] The user uses a terminal to input detailed specifications of the information processing device under test and the test content. This input includes API endpoints, required input parameters, and expected test results. At this stage, a generative AI model is utilized to suggest optimal test cases and templates based on the prompt messages.

[0705] The server uses a generation engine based on information received from the terminal to automatically generate a list of test items. The generated test items include a variety of cases to ensure comprehensiveness and serve as the foundation for verifying the system's robustness.

[0706] Next, the data generation mechanism within the server generates test data corresponding to the test item list. This includes not only general data but also boundary values ​​and abnormal pattern data. This further enhances the comprehensiveness of the test.

[0707] The test execution method automatically performs tests and records the test results. During the test, various data is input to the API, and the response results and response times are observed in detail. This process ensures effective testing.

[0708] During the test and upon receiving the test results, the emotion engine analyzes the user's responses using speech recognition and image processing technologies. This analysis provides data to understand the stress and burden the user experienced during the test, enabling the provision of appropriate feedback.

[0709] Finally, the feedback mechanism integrates the test results and the emotion engine's evaluation to provide feedback to the user. This feedback includes details of the test's success or failure, areas for improvement, and specific improvement suggestions based on the user's emotions.

[0710] As a concrete example, in API testing for a customer management system, the user inputs detailed API specifications on a terminal, and the server lists the test items. Using the generated data, the test execution system verifies the API's operation, analyzes the test results with an emotion engine, and provides feedback. For example, a prompt might say, "Enter the API endpoint and request parameters for updating customer information, and set up a test case to verify the expected response code 200 and the updated data."

[0711] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0712] Step 1:

[0713] The user inputs the specifications and test details of the information processing device via a terminal. Specifically, they input API endpoints, input parameters, and expected test results on the terminal and send them to the server using a digital form or interface. The entered data forms the basis for subsequent test item generation.

[0714] Step 2:

[0715] The server starts the generation engine based on the test specifications received from the user and automatically generates a list of test items. The generation engine analyzes the input data and lists items to cover a wide range of test cases. The resulting list of test items serves as a guideline for generating test data.

[0716] Step 3:

[0717] The data generation mechanism within the server generates various test data according to the test item list. Here, diverse test data such as normal data, boundary values, and anomaly patterns are automatically created. The generated data is then used as input data necessary for the next test execution.

[0718] Step 4:

[0719] The server's test execution mechanism automatically performs tests using the generated test data. Accurate verification is achieved by inputting data to the API and comparing the response with the expected output. The test results obtained here include response time and error messages, enabling detailed performance analysis.

[0720] Step 5:

[0721] The server's emotion engine analyzes the user's reactions during the test and upon receiving the test results. Using technologies such as voice input and facial recognition, it identifies the user's emotional state and evaluates stress points and user reactions within the test process. The output from this analysis provides valuable information for improving the user experience.

[0722] Step 6:

[0723] The server's feedback mechanism integrates test results and sentiment engine evaluations, providing feedback to the user. This feedback includes test success / failure information, areas for improvement, and suggestions based on the user's sentiment. This helps improve future test processes and enhance the user experience.

[0724] (Application Example 2)

[0725] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0726] Traditional testing processes involved manual preparation and analysis of test data, which was burdensome, and made it difficult to effectively reflect user test experiences and feedback. Furthermore, a lack of consideration for users' emotional states limited the potential for improving the user experience. There is a need to resolve these issues and improve the efficiency of the testing process while enhancing the user experience.

[0727] 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.

[0728] In this invention, the server includes means for generating an item list using a generation engine that generates test items, data generation means for automatically generating diverse test data, test execution means for conducting tests and recording results, emotion analysis means for acquiring user voice and facial expression data and identifying emotional states, and means for dynamically adjusting the test process and environment. This enables not only increased efficiency in conventional testing processes but also flexible responses to the user's emotional state.

[0729] A "generation engine" is a device or software that has the function of automatically designing test items and generating a list of items based on those items.

[0730] "Data generation means" refers to a device or program for automatically creating various test data based on an item list.

[0731] "Test execution means" refers to a device or process that performs tests using generated test data and records the results.

[0732] A "feedback mechanism" is a device or function for analyzing test results and communicating those results to the user.

[0733] "Emotion analysis means" refers to technology that acquires a user's voice and facial expression data and identifies their emotional state based on that data.

[0734] A "dynamic adjustment mechanism" is a system for appropriately modifying the testing process and environment based on the evaluation results obtained from the emotion analysis mechanism.

[0735] To realize this invention, the server automatically generates a list of test items based on the test content specified by the user using a generation engine. The generation engine is designed to ensure diversity and comprehensiveness of the tests and creates a list of items that reflect various test conditions.

[0736] Next, the data generation mechanism within the server generates diverse test data based on the test item list. This data includes not only general data but also boundary values ​​and anomaly patterns, and is designed to enable testing in various scenarios.

[0737] The test execution means uses this generated test data to conduct the test and records the results. During the test execution process, the response content and the presence or absence of error messages are also recorded.

[0738] Based on the voice and facial expression data provided by the user's device, the server identifies the user's emotional state through emotion analysis. This analysis utilizes voice recognition software and facial expression analysis technology to understand the user's mental response.

[0739] Furthermore, dynamic adjustment mechanisms adjust the testing process and environment based on the results of the emotion analysis. For example, if the user is experiencing stress, the testing process may be simplified or additional support may be provided as needed.

[0740] For example, if a passenger in an autonomous vehicle shows signs of fatigue while on board, the system will automatically adjust the in-car environment and play relaxing music.

[0741] An example of a prompt message could be: "Analyze the passenger's facial expressions and voice to determine if they are relaxed, and suggest in-car environment settings if they are determined to be relaxed."

[0742] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0743] Step 1:

[0744] The server receives test details from the terminal. It receives test specifications as input, including the API endpoint set by the user, input parameters, and expected test results. Based on this input data, the server automatically generates a list of test items using a generation engine. This process is designed to ensure diversity and comprehensiveness of the test items. A detailed list of test items is obtained as output.

[0745] Step 2:

[0746] The server receives the list of test items generated in the previous step as input. The data generation means generates various test data based on this list. The data includes information corresponding to various scenarios, including boundary values ​​and outliers. A variety of test datasets are obtained as output.

[0747] Step 3:

[0748] The server uses the generated test data. The tests are performed by the test execution method, and the results of each test are recorded. Using the test data as input, a request is made to the API, and the match between the response and the expected output is verified. The test results also record the response content, response time, and whether or not there are any error messages. A detailed report of the test results is generated as output.

[0749] Step 4:

[0750] The user's device acquires voice and facial expression data. This data is sent to a server, where an emotion analysis system analyzes it to identify the user's emotional state. Voice files and image data are used as input, and voice recognition software and facial expression analysis technology are employed. The output is an evaluation result of the user's emotional state.

[0751] Step 5:

[0752] The server receives the results of the emotion analysis as input and adjusts the test process and environment using dynamic adjustment mechanisms. If it is determined that the user is experiencing stress, measures are taken to simplify the test or provide additional support information. As an output, adaptive test adjustments are made to improve the user experience.

[0753] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0754] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[0755] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0756] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0757] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0758] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0759] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0760] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0761] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0762] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0763] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0764] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0765] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0766] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0767] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0768] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0769] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0770] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0771] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0772] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0773] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0774] The following is further disclosed regarding the embodiments described above.

[0775] (Claim 1)

[0776] A means for generating a list of test items based on the test content specified by the user, using a generation engine that generates test items,

[0777] A data generation means that automatically generates various test data based on the aforementioned list of items,

[0778] A test execution means for conducting a test using the aforementioned test data and recording the results,

[0779] A means for analyzing the results and providing feedback to the user,

[0780] A system that includes this.

[0781] (Claim 2)

[0782] The system according to claim 1, wherein the generation engine is configured to automatically complete test items based on system specification information.

[0783] (Claim 3)

[0784] The system according to claim 1, wherein the test execution means operates to verify the presence or absence of a response and error message to the input of test data.

[0785] "Example 1"

[0786] (Claim 1)

[0787] A means for specifying test content based on system specification information entered by the user via a terminal, and generating an item list using a generation AI model,

[0788] A means for automatically generating various test data, including boundary values ​​and error inputs, based on the aforementioned list of items,

[0789] A means for inputting the aforementioned test data, conducting the test while verifying the response, and recording a detailed log thereof,

[0790] A means of analyzing test results and providing users with feedback that includes confirmation of successful cases and details of unsuccessful cases,

[0791] A system that includes this.

[0792] (Claim 2)

[0793] The system according to claim 1, wherein the generating AI model is configured to automatically generate and complete test items using prompt statements based on test content specified by the user.

[0794] (Claim 3)

[0795] The system according to claim 1, wherein the test execution means operates to verify in detail the response to the input of test data and the presence or absence of error messages, and to record the results step by step.

[0796] "Application Example 1"

[0797] (Claim 1)

[0798] A means for generating a list of test items based on the test content specified by the user, using a generation engine that generates test items,

[0799] A data generation means that automatically generates various test data based on the aforementioned list of items,

[0800] A test execution means for conducting a test using the aforementioned test data and recording the results,

[0801] A means for analyzing the results and providing feedback to the user,

[0802] A device for testing operational programs, with a means for presenting test results in real time,

[0803] A system that includes this.

[0804] (Claim 2)

[0805] The system according to claim 1, wherein the generation engine is configured to automatically complete test items based on system specification information.

[0806] (Claim 3)

[0807] The system according to claim 1, wherein the test execution means operates to verify the presence or absence of responses and error messages to the input of test data, and displays the verification results via a video device.

[0808] "Example 2 of combining an emotion engine"

[0809] (Claim 1)

[0810] A generation engine means that generates test items based on the test content specified by the user,

[0811] A data generation means that automatically generates various test data based on the aforementioned list of items,

[0812] A test execution means for conducting a test using the aforementioned test data and recording the results,

[0813] The above results are used to analyze the user's emotions using speech recognition and image processing technologies, and to provide feedback.

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1, wherein the generation engine is configured to automatically complete test items and optimize test cases based on the specifications of the information processing device.

[0817] (Claim 3)

[0818] The system according to claim 1, wherein the test execution means operates to measure the response time to the input of test data and to verify the presence or absence of error messages, and evaluates the performance of the system.

[0819] "Application example 2 when combining with an emotional engine"

[0820] (Claim 1)

[0821] A means for generating a list of test items based on the test content specified by the user, using a generation engine that generates test items,

[0822] A data generation means that automatically generates various test data based on the aforementioned list of items,

[0823] A test execution means for conducting a test using the aforementioned test data and recording the results,

[0824] A means for analyzing the results and providing feedback to the user,

[0825] An emotion analysis means that acquires user voice and facial expression data and uses it to identify the emotional state,

[0826] Based on the evaluation of the aforementioned emotion analysis means, means for dynamically adjusting the test process and environment,

[0827] A system that includes this.

[0828] (Claim 2)

[0829] The system according to claim 1, wherein the generation engine is configured to automatically complete test items based on system specification information.

[0830] (Claim 3)

[0831] The system according to claim 1, wherein the test execution means operates to verify the presence or absence of a response and error message to the input of test data. [Explanation of symbols]

[0832] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for generating a list of test items based on the test content specified by the user, using a generation engine that generates test items, A data generation means that automatically generates various test data based on the aforementioned list of items, A test execution means for conducting a test using the aforementioned test data and recording the results, A means for analyzing the results and providing feedback to the user, A system that includes this.

2. The system according to claim 1, wherein the generation engine is configured to automatically complete test items based on system specification information.

3. The system according to claim 1, wherein the test execution means operates to verify the presence or absence of a response to the input of test data and error messages.

Images