System

Abstract

A system is provided.SOLUTION: A means in which a user inputs specifications and requirements of a verification target through a terminal, a means in which the terminal transmits the input data to a server, a means in which the server confirms consistency of the received data and passes the data to an AI engine, a means in which the AI engine generates test patterns of a quasi-normal system and an abnormal system by referring to a past database and an expert knowledge base, and a means in which the test patterns are converted into a format that is easy for a human to understand; A means for transmitting the test pattern to the terminal, a means for displaying the test pattern received by the terminal and transmitting a correction request by the user, and a means for regenerating the test pattern by passing the data to the AI engine again based on the correction request by the server.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] When verifying the operation of tools and development equipment, it is relatively easy to create normal test patterns, but creating quasi-normal and abnormal test patterns requires deep knowledge and experience. This makes it difficult for inexperienced developers to perform high-quality tests. Creating test patterns manually is also time-consuming and inefficient. [Means for solving the problem]

[0005] The present invention provides a system in which a user inputs specifications and requirements for the verification target via a terminal and sends them to a server. The server checks the consistency of the information and passes the data to an AI engine. The AI ​​engine generates test patterns for quasi-normal and abnormal conditions by referencing a past database and expert knowledge base. The generated test patterns are converted by the server into a format that is easy for humans to understand and sent to the terminal. The user can check the test patterns on the terminal and send correction requests to the server. The server then passes the data to the AI ​​engine again based on the correction requests and regenerates the test patterns. This enables even inexperienced developers to efficiently create high-quality test patterns.

[0006] A "user" is an individual who accesses the system and enters specifications or requirements to be verified.

[0007] A "terminal" is a device operated by a user, which inputs specifications and requirements and communicates with a server.

[0008] "Specification" means a detailed description and conditions regarding the behavior and functionality of the object to be verified.

[0009] "Requirements" refers to the performance and functional standards and conditions that the verification target must meet.

[0010] The "server" is a central computer system that receives data sent by users, checks its integrity, and manages the operation of the AI ​​engine.

[0011] An "AI engine" is software that includes an algorithm that references past databases and expert knowledge bases and generates quasi-normal and abnormal test patterns based on input information.

[0012] A "database" is a storage device or system that stores past verification data and information related to anomaly detection.

[0013] An "expert knowledge base" is a collection of information that accumulates specialized knowledge and rules related to a specific field.

[0014] "Test patterns" refer to specific verification procedures or cases for checking how the verification target operates under specific conditions or scenarios.

[0015] "Quasi-normal state" refers to a state in which a system or device exhibits some abnormal behavior within the normal range.

[0016] "Abnormal" refers to a state in which a system or device clearly deviates from normal operation. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a 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.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0031] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention is a system in which a user inputs the specifications and requirements of a verification target via a terminal and generates test patterns for quasi-normal and abnormal conditions using an AI engine. This system is composed of elements including a server, a terminal, and a user, and a detailed embodiment of the system is described below.

[0039] User Interaction

[0040] The user accesses the system using a terminal. A form is displayed on the terminal screen for entering the specifications and requirements of the tool and development equipment to be verified. The user enters the necessary information into this form and presses the "Submit" button.

[0041] Data transmission

[0042] The terminal converts the specifications and requirements data entered by the user into JSON format and sends it to the server as an HTTP POST request.

[0043] Data reception and preparation for analysis

[0044] The server processes the received JSON data, checks the data integrity, and detects invalid data. If invalid data is included, the server generates an error message and returns it to the terminal. If the integrity is confirmed, the data proceeds to the next step.

[0045] AI-based analysis

[0046] The server passes the data whose integrity has been confirmed to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge.

[0047] Test Pattern Generation

[0048] The server converts the test patterns generated by the AI ​​engine into a format that is easy for humans to understand, such as a list or tree structure. This data is then stored in temporary storage.

[0049] Send results

[0050] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any necessary supplementary explanations or links to reference materials.

[0051] User verification and correction

[0052] The terminal displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If correction requests are required, the user presses the "correct" button and resends the corrections to the server.

[0053] reanalysis

[0054] The server receives the correction request, passes the data to the AI ​​engine again, and regenerates the test pattern. The regenerated test pattern is then sent back to the device.

[0055] Final confirmation

[0056] The user makes a final check of the regenerated test pattern on the terminal, and if there are no problems, presses the "Confirm" button.

[0057] Data storage

[0058] The server permanently saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives this message and is ready to begin verification.

[0059] As a concrete example, consider the case of verifying the operation of a temperature sensor device. When the user inputs the specifications and operational requirements of the temperature sensor, the AI ​​engine generates the following test pattern.

[0060] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[0061] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[0062] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[0063] According to the present invention, regardless of the user's level of experience, high-quality test patterns can be generated efficiently, thereby improving the quality and efficiency of the development process.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] The user accesses the system using a terminal. A form for entering the specifications and requirements of the tool and development equipment to be verified is displayed on the terminal screen. The user enters the necessary information into this form and presses the "Submit" button.

[0067] Step 2:

[0068] The terminal converts the specifications and requirements data entered by the user into JSON format and sends the converted JSON data to the server as an HTTP POST request.

[0069] Step 3:

[0070] The server processes the received JSON data. Specifically, it checks the data for consistency and detects invalid data. If invalid data is included, it generates an error message and returns it to the terminal. If consistency is confirmed, it proceeds to the next step.

[0071] Step 4:

[0072] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge.

[0073] Step 5:

[0074] The server receives the test patterns generated by the AI ​​engine, converts them into a format that is easy for humans to understand, and temporarily stores this data in storage.

[0075] Step 6:

[0076] The server then converts the converted test pattern back into JSON format and sends it to the terminal as an HTTP response, along with supplementary explanations and links to reference materials, if necessary.

[0077] Step 7:

[0078] The terminal displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If the user wants to submit a correction request, he or she presses the "Edit" button and resends the data including the corrections to the server.

[0079] Step 8:

[0080] Based on the received correction request, the server passes the data to the AI ​​engine again, generates a new test pattern, and sends the generated test pattern back to the device.

[0081] Step 9:

[0082] The terminal displays the received test pattern again, and the user performs a final check. If there are no problems, the user presses the "Confirm" button to confirm the test pattern.

[0083] Step 10:

[0084] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[0085] Example 1

[0086] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0087] Conventional test pattern generation methods require users to manually design test cases, which is time-consuming, labor-intensive, and prone to errors. Furthermore, because they rely on the user's experience and knowledge, it is difficult to generate test patterns of consistent quality. In particular, designing test patterns for quasi-normal and abnormal conditions requires advanced expertise. The present invention aims to solve these problems and provide an efficient, high-quality test pattern generation system.

[0088] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0089] In this invention, the server includes a means for a user to input specifications and requirements for the verification target via a terminal, a means for the terminal to convert the input data into JSON format and send it to the server as an HTTP POST request, and a means for the server to check the integrity of the received JSON data and pass the data to the AI ​​engine. This enables users to easily generate high-quality test patterns and improve the quality and efficiency of the development process.

[0090] "Terminal" means a computing device used by a User to input specifications and requirements.

[0091] The term "server" refers to a computer system that receives and processes data sent from a terminal.

[0092] "JSON format" is a standard for describing data in text format, and is an abbreviation for JavaScript (registered trademark) Object Notation.

[0093] "HTTP POST request" refers to the part of the HTTP protocol that allows a client to send data to a server.

[0094] "Integrity" refers to the property of ensuring that data is accurate and consistent.

[0095] "AI engine" refers to an artificial intelligence system that performs data analysis and test pattern generation.

[0096] A "database" refers to a system for efficiently storing and managing data.

[0097] "Expertise base" refers to a dataset that aggregates knowledge in a particular field of expertise.

[0098] "Test patterns" refer to scenarios or cases used to verify systems or equipment.

[0099] "Quasi-normal" refers to operating conditions that deviate slightly from normal conditions but do not pose a serious problem.

[0100] "Abnormal" refers to a situation in which a system or device malfunctions beyond its expected range.

[0101] "Temporary storage" refers to memory or disk space used to temporarily store data.

[0102] "Finish message" refers to a message that notifies the user that a process has been successfully completed.

[0103] MODE FOR CARRYING OUT THE INVENTION

[0104] This system allows users to input specifications and requirements for the verification target via a terminal, and the server processes the data and passes it to an AI engine, which then generates test patterns for quasi-normal and abnormal conditions. The system is composed of the following elements: a terminal, a server, and a user.

[0105] The user enters the specifications and operational requirements of a temperature sensor or other device into a form on the terminal. For example, for a temperature sensor, the user enters information such as the measurement range and response time. Once the input is complete, the user presses the "Submit" button.

[0106] The terminal converts this input data into JSON format. For example, if you enter "measurement range -20°C to 100°C" and "response time 1 second" as the specifications for a temperature sensor, this data will be converted as {"measurement range": "-20°C to 100°C", "response time": "1 second"}. This converted data is sent to the server as an HTTP POST request.

[0107] The server checks the integrity of the received JSON data. For example, it checks whether the data is invalid or missing. If it contains error data, the server generates an error message and returns it to the terminal. If the data is correct, it saves the data to proceed to the next step.

[0108] The server then passes the data, whose integrity has been confirmed, to the AI ​​engine, which then references the database and expert knowledge base. For example, the expert knowledge base contains past test data and existing technical literature. Based on this data, the AI ​​engine generates test patterns for quasi-normal and abnormal conditions.

[0109] The generated test patterns are converted by the server into a format that is easy for humans to understand, such as a list format or a tree structure, and this converted data is stored in temporary storage.

[0110] The server converts this data back into JSON format and sends it to the terminal as an HTTP response. The terminal displays the received test pattern on the screen. The user checks the displayed test pattern. If necessary, they can enter a correction request and press the "Edit" button, and the terminal will resend the corrections to the server.

[0111] The server receives the correction request and passes the data to the AI ​​engine again to regenerate the test pattern. This regenerated test pattern is also sent to the device again, and the user checks it. If there are no final problems, the user presses the "Confirm" button, and the final confirmed information is sent to the server.

[0112] The server permanently saves the confirmed data in the database and notifies the terminal that the saving is complete. The user receives this completion message and ends their use of the system.

[0113] As a concrete example, the following prompt sentences are input to the generative AI model to verify the operation of a temperature sensor device:

[0114] "The specifications and operating requirements for the temperature sensor device have been entered as follows:

[0115] Measurement range: -20°C to 100°C

[0116] Response time: 1 second

[0117] Based on this, generate a test pattern like this:

[0118] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[0119] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[0120] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[0121] The present invention enables users to efficiently generate high-quality test patterns, thereby improving the quality and efficiency of the development process.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1:

[0124] The user uses the terminal to input the specifications and requirements of the object to be verified. The user enters the temperature sensor specifications (e.g., measurement range -20°C to 100°C, response time 1 second) into the form and presses the "Submit" button. The input data is collected by the terminal.

[0125] Input: User-entered specification and requirements data

[0126] Output: Input data collected on the terminal

[0127] Step 2:

[0128] The terminal converts the collected input data into JSON format, for example, {'Measurement range': '-20°C to 100°C', 'Response time': '1 second'}, and then sends it to the server as an HTTP POST request.

[0129] Input: Data entered by the user into the terminal

[0130] Output: Data converted to JSON format

[0131] Step 3:

[0132] The server receives the JSON data sent from the terminal and checks the integrity of the data. If invalid data is included, the server generates an error message and returns it to the terminal. If the data is confirmed to be valid, it proceeds to the next processing step.

[0133] Input: JSON data sent from the terminal

[0134] Output: Consistency checked data or error message

[0135] Step 4:

[0136] The server passes the data whose integrity has been confirmed to the AI ​​engine. For example, it provides measurement range and response time data as input to the AI ​​engine.

[0137] Input: Integrity checked data

[0138] Output: Data passed to the AI ​​engine

[0139] Step 5:

[0140] The AI ​​engine references a database and expert knowledge base to generate test patterns for quasi-normal and abnormal conditions, such as normal operation between 25°C and 30°C, and abnormal operation above 40°C.

[0141] Input: Data passed to the AI ​​engine

[0142] Output: Generated quasi-normal and abnormal test patterns

[0143] Step 6:

[0144] The server receives the test patterns generated by the AI ​​engine and converts them into a format that is easy for humans to understand (e.g., list format or tree structure). This data is stored in temporary storage.

[0145] Input: Test patterns generated by the AI ​​engine

[0146] Output: Test patterns converted into a human-readable format

[0147] Step 7:

[0148] The server converts the converted test pattern back into JSON format and sends it to the terminal as an HTTP response.

[0149] Input: Test patterns converted to a human-readable format

[0150] Output: Test patterns converted to JSON format

[0151] Step 8:

[0152] The terminal displays the received test pattern on the screen. The user checks the test pattern and inputs correction requests as necessary. Then, by pressing the "Correction" button, the terminal resends the correction request to the server.

[0153] Input: Test pattern sent to the terminal

[0154] Output: User correction request

[0155] Step 9:

[0156] The server receives the correction request, passes the data to the AI ​​engine again, and regenerates the test pattern. The regenerated test pattern is then sent back to the device.

[0157] Input: User requested correction

[0158] Output: Regenerated test pattern

[0159] Step 10:

[0160] The user checks the regenerated test pattern on the terminal and, if there are no problems, presses the "Confirm" button, which sends the confirmed test pattern to the server.

[0161] Input: Regenerated test pattern

[0162] Output: Final confirmation by user

[0163] Step 11:

[0164] The server permanently saves the finalized data in the database and notifies the terminal that the saving is complete. The user receives a completion message and ends their use of the system.

[0165] Input: Test pattern confirmed by the user

[0166] Output: Test patterns stored in the database and an end message

[0167] (Application example 1)

[0168] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0169] Conventional methods for verifying the operation of industrial robots require users to manually create numerous test patterns, which often leads to errors. Furthermore, generating abnormal test patterns is difficult, making it difficult to effectively perform abnormality testing for specific operational scenarios. This reduces the efficiency of ensuring the reliability and safety of industrial robots.

[0170] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0171] In this invention, the server includes: a means for a user to input specifications and requirements for the verification target via a terminal; a means for the terminal to transmit the input data to the server; a means for the server to verify the consistency of the received data and pass the data to the AI ​​engine; a means for the AI ​​engine to generate quasi-normal and abnormal test patterns by referring to a past database and an expert knowledge base; a means for converting the test patterns into a human-understandable format and transmitting the converted test patterns to the terminal; a means for the terminal to display the received test patterns and for the user to send a correction request; a means for the server to re-pass the data to the AI ​​engine based on the correction request and re-generate the test patterns; a means for inputting operational specifications and requirements for the industrial robot and generating test patterns; a means for displaying the generated test patterns and performing a final check; a means for saving the finalized test patterns to the server; a means for inputting prompt statements to a generative AI model and generating test patterns based on specific operational scenarios; a means for generating prompt statements for identifying operational scenarios of the industrial robot; a means for generating abnormal test patterns for the industrial robot using the generative AI model; and a means for evaluating the generated test patterns. This eliminates the need for users to manually create numerous test patterns, enabling accurate and efficient operational verification of industrial robots.

[0172] "User" refers to a user who uses the system to input specifications and requirements to be verified.

[0173] "Terminal" means a device used by a user to input specifications and requirements and communicate with a server.

[0174] A "server" is a device that receives data sent from a user via a terminal, processes the data, and checks the consistency of the data.

[0175] An "AI engine" is an algorithm that generates quasi-normal and abnormal test patterns by referencing a past database and expert knowledge base.

[0176] A "database" is a collection of information that stores past data and is used as a reference by an AI engine.

[0177] An "expertise base" is information that accumulates specialized knowledge in a specific field, and is used by the AI ​​engine as a reference when generating test patterns.

[0178] A "test pattern" is a specific scenario for verifying the behavior of the target system.

[0179] "Quasi-normal" refers to a situation or scenario that is nearly normal but contains some abnormalities.

[0180] An "abnormal situation" is a situation or scenario in which the subject of verification does not operate normally.

[0181] "Behavioral specifications" are requirements that define how the object to be verified should behave.

[0182] "Requirements" are conditions or standards that the object of verification must meet.

[0183] A "prompt" is an instruction sentence to be input to a generative AI model and is used to identify a specific behavior scenario.

[0184] A "generative AI model" is a trained algorithm that allows an AI engine to generate test patterns based on prompt sentences.

[0185] An "anomaly detection algorithm" is a specific computational method or program for detecting abnormal patterns.

[0186] This invention is a system that streamlines operational verification of industrial robots by allowing users to input specifications and requirements for the object to be verified via a terminal, and generating test patterns for quasi-normal and abnormal conditions using a server and an AI engine.

[0187] Users use devices such as smartphones and tablets to enter the operational specifications and requirements of the industrial robot to be verified into a form. The entered data is converted to JSON format by the device and sent to the server as an HTTP POST request.

[0188] The server checks the integrity of the received JSON data and verifies that it does not contain any invalid data. Once the integrity is confirmed, the server passes the data to the AI ​​engine, which then references its past database and expert knowledge base to generate quasi-normal and abnormal test patterns.

[0189] The generated test patterns are converted by the server into a human-readable format, usually expressed as a list or tree structure, and the converted data is stored in temporary storage.

[0190] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response. The user can check the received test pattern on the device and enter correction requests as necessary. If corrections are required, the user enters the corrections and sends it back to the server.

[0191] The server receives the correction request and passes the data to the AI ​​engine again to regenerate the test pattern. The regenerated test pattern is then sent back to the device for final confirmation by the user. When the user presses the "Confirm" button, the confirmed test pattern is permanently saved in the database by the server.

[0192] For example, consider the case of verifying an industrial robot's operational scenario. The user inputs the robot's operational specifications and requirements, such as temperature range, load capacity, and operational pattern. In this case, the AI ​​engine generates the following test patterns:

[0193] Normal condition: The robot operates normally within a temperature range of 20°C-30°C and moves the specified object accurately.

[0194] Quasi-normal pattern: Operation is not affected even if the ambient temperature temporarily exceeds 30°C.

[0195] Abnormal pattern: The robot begins to malfunction when the environmental temperature exceeds 50°C.

[0196] Examples of prompt sentences to be input to the generative AI model include the following:

[0197] "Generate test patterns to identify operating scenarios for industrial robot model XYZ-123. Specifications are temperature 0-50°C, humidity 20-80%, and load capacity up to 50kg."

[0198] "Please tell me the abnormality test pattern for the model XYZ-123 robot that includes a temperature sensor function."

[0199] The software used is Python and its libraries (requests, json), and the hardware is a smartphone or tablet connected to the internet.The AI ​​engine utilizes a generative AI model to efficiently generate test patterns.

[0200] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0201] Step 1:

[0202] The user inputs the specifications and requirements to be verified into the terminal, including the operating scenario of the industrial robot and environmental conditions (e.g., temperature range, humidity, load capacity). The input data is saved on the terminal.

[0203] Step 2:

[0204] The terminal converts the input data into JSON format. Specifically, it converts the specifications and requirements entered by the user into a JSON object and sends it to the server as an HTTP POST request. Here, the input data is serialized and sent.

[0205] Step 3:

[0206] The server receives the received JSON data and checks its integrity. The server parses the JSON data and checks for invalid data or defects. The result of the integrity check becomes the output data. If integrity is confirmed, proceed to the next step.

[0207] Step 4:

[0208] The server passes the data whose integrity has been confirmed to the AI ​​engine, which then references the database and expert knowledge base to generate test patterns for quasi-normal and abnormal conditions. In this process, the AI ​​engine analyzes the input data and makes predictions and generates patterns. The output is the generated test patterns.

[0209] Step 5:

[0210] The server converts the test patterns generated by the AI ​​engine into a format that is easy for humans to understand, including formats such as lists and tree structures. Specifically, it converts the data structure of the test patterns and saves them as output data.

[0211] Step 6:

[0212] The server reconverts the converted test pattern into JSON format and sends it to the terminal as an HTTP response. The server serializes the parsed data and prepares it for transmission. The terminal displays the received data on the screen.

[0213] Step 7:

[0214] The user checks the received test pattern on the terminal and inputs correction requests as necessary. The user evaluates the test pattern and inputs corrections if they find any errors or deficiencies. The correction requests are sent from the terminal to the server.

[0215] Step 8:

[0216] The server receives the correction request and passes the data to the AI ​​engine again to regenerate the test pattern. Reanalysis is performed based on the new input data, and new test patterns are generated. During this process, the AI ​​engine again refers to the database and expert knowledge base.

[0217] Step 9:

[0218] The user checks the regenerated test pattern on the terminal and presses the "Confirm" button if there are no problems. The final checked test pattern is sent to the server. The output is the final checked test pattern.

[0219] Step 10:

[0220] The server permanently saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user confirms the received message and is ready for verification.

[0221] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0222] The present invention enables the generation of more accurate test patterns by combining an emotion engine that recognizes the user's emotions with a system in which a user inputs the specifications and requirements of the object to be verified via a terminal and generates quasi-normal and abnormal test patterns using an AI engine. This system is composed of the elements of a server, a terminal, a user, and an emotion engine, and detailed embodiments are described below.

[0223] User Interaction

[0224] The user accesses the system using a terminal. A form is displayed on the terminal screen for entering the specifications and requirements of the tool to be verified and the development equipment. The user enters the necessary information into this form and presses the "Submit" button. In parallel, the emotion engine analyzes the user's facial expressions and voice, recognizing emotions in real time.

[0225] Data transmission

[0226] The device converts the specifications and requirements data entered by the user into JSON format, simultaneously collecting the emotion data recognized by the emotion engine, and sends this data to the server as an HTTP POST request.

[0227] Data reception and preparation for analysis

[0228] The server processes the received JSON data. Specifically, it checks the data for consistency and detects invalid data. If invalid data is included, it generates an error message and returns it to the terminal. If consistency is confirmed, it proceeds to the next step.

[0229] AI-based analysis

[0230] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge. The user's emotional data provided by the emotion engine is also used for analysis, and the difficulty and details of the test patterns are adjusted.

[0231] Test Pattern Generation

[0232] The server receives the test patterns generated by the AI ​​engine. The server converts the test patterns into a format that is easy for humans to understand. Specifically, they are often expressed in list format or tree structure. This data is temporarily stored in storage.

[0233] Send results

[0234] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any necessary supplementary explanations or links to reference materials.

[0235] User verification and correction

[0236] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. In parallel, the emotion engine continues to monitor the user's emotions. If the user wishes to send a correction request, they press the "Edit" button and the data including the corrections is resent to the server.

[0237] reanalysis

[0238] The server receives the correction request and passes the data to the AI ​​engine again to generate a new test pattern, taking into account the newly collected emotion data. The generated test pattern is then sent back to the device.

[0239] Final confirmation

[0240] The user makes a final check of the regenerated test pattern on the terminal, and if there are no problems, presses the "Confirm" button to confirm the test pattern.

[0241] Data storage

[0242] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[0243] As a concrete example, consider the case of verifying the operation of a temperature sensor device. If a user inputs the specifications and operational requirements of a temperature sensor and the emotion engine determines that the user is expressing "anxiety," the AI ​​engine generates a test pattern with more details or additional explanations. For example, it generates the following test pattern:

[0244] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[0245] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[0246] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[0247] According to the present invention, by utilizing the emotion engine, the user can generate more accurate test patterns, thereby realizing a more user-friendly and efficient development process.

[0248] The processing flow will be explained below.

[0249] Step 1:

[0250] The user accesses the system using a terminal. A form for entering the specifications and requirements of the tool and development equipment to be verified is displayed on the terminal screen. The user enters the necessary information into this form and presses the "Submit" button.

[0251] Step 2:

[0252] The device converts the specifications and requirements data entered by the user into JSON format. At the same time, the emotion engine analyzes the user's facial expressions and voice to recognize emotions in real time. The recognized emotion data is also included in the JSON format.

[0253] Step 3:

[0254] The device sends the converted JSON data of specifications and requirements and emotion data to the server as an HTTP POST request.

[0255] Step 4:

[0256] The server processes the received JSON data. Specifically, it first checks the data for consistency and detects invalid data. If invalid data is included, it generates an error message and returns it to the terminal.

[0257] Step 5:

[0258] The server passes the data whose integrity has been confirmed to the AI ​​engine, which then references the received database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge.

[0259] Step 6:

[0260] When generating test patterns, the AI ​​engine takes into account the user's emotional data provided by the emotion engine. For example, if the user is feeling "anxious" or "stressed," the AI ​​engine will adjust the explanation of the test pattern to be more detailed or simpler.

[0261] Step 7:

[0262] The server receives the test patterns generated by the AI ​​engine, converts them into a format that is easy for humans to understand, and temporarily stores the test patterns in storage.

[0263] Step 8:

[0264] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any supplementary explanations or links to reference materials, if necessary.

[0265] Step 9:

[0266] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. In parallel, the emotion engine continues to monitor the user's emotions.

[0267] Step 10:

[0268] When the user wishes to send a correction request, the data including the corrections is resent to the server by pressing the "correct" button.

[0269] Step 11:

[0270] The server receives the correction request and passes the data to the AI ​​engine again to generate a new test pattern, taking into account the recollected emotion data. The generated test pattern is then sent back to the device.

[0271] Step 12:

[0272] The terminal displays the received test pattern again, and the user performs a final check. If there are no problems, the user presses the "Confirm" button to confirm the test pattern.

[0273] Step 13:

[0274] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the terminal and sends a completion message.

[0275] Step 14:

[0276] The user receives a completion message, and the emotion engine also collects and saves the final emotion data. Verification preparation is complete, and the user is ready to proceed to the next step.

[0277] As a concrete example, consider the case of verifying the operation of a temperature sensor device. If the user inputs the specifications and operational requirements of the temperature sensor and the emotion engine detects "anxiety," the AI ​​engine generates a test pattern with a more detailed explanation. On the other hand, if the emotion is recognized as "calm," it generates a standard test pattern. For example, the following test pattern may be generated:

[0278] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[0279] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[0280] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[0281] This specific flow provides optimal test patterns according to the user's emotions, realizing more efficient and high-quality verification.

[0282] Example 2

[0283] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0284] Conventional test pattern generation systems generate test patterns based on specifications and requirements entered by the user, but the generated test patterns do not always reflect the user's intentions or emotions. Furthermore, particularly for abnormality test patterns, flexible adjustments that take into account the user's emotions and level of understanding are required. However, conventional systems were unable to achieve this, making it difficult to achieve a user-friendly and efficient development process.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0286] In this invention, the server includes means for converting data input by the terminal into JSON format and sending it to the server, means for checking the consistency of the received data and, if invalid data is detected, generating an error message and sending it to the terminal, and means for passing the consistent data to the AI ​​engine. This enables the AI ​​engine to refer to the past database and expert knowledge base and generate quasi-normal and abnormal test patterns that take user emotion data into consideration.

[0287] A "terminal" is an electronic device used by a user to input specifications and requirements for a verification target, and is used to input, send, receive, and display data.

[0288] A "server" is a computer system that receives data sent from a terminal, checks the integrity of the data, detects fraudulent data, and provides the data to the AI ​​engine.

[0289] An "AI engine" is a program that incorporates artificial intelligence technology to generate quasi-normal and abnormal test patterns by referencing past databases and expert knowledge bases.

[0290] The "emotion engine" is a program that incorporates technology that analyzes the user's facial expressions and voice input and recognizes emotions in real time.

[0291] A "specification" is a document or data that describes in detail the functions and characteristics of the object to be verified.

[0292] "Requirements" are documents or data that describe the conditions and constraints that the verification target must satisfy.

[0293] "JSON format" is an abbreviation for JavaScript Object Notation, and is a data exchange format that represents structured text data in a format that is easy for humans to read and computers to analyze.

[0294] An "HTTP POST request" is a request format for sending data from a client (terminal) to a server using the POST method of the Hypertext Transfer Protocol.

[0295] "Integrity check" is the process of verifying whether the received data is formally correct and contains all required fields.

[0296] "Invalid data" refers to data that cannot be processed normally, such as data that has an incorrect data format or is missing required fields.

[0297] A "test pattern" refers to a scenario or case for verifying the behavior of a system under specific conditions.

[0298] A "quasi-normal" situation refers to a situation in which the system is temporarily placed in an unstable state, but is expected to return to a normal state.

[0299] "Abnormal situation" refers to a situation in which the system is placed in an abnormal condition and is expected to not function normally.

[0300] "Emotion data" is data that indicates the user's emotional state and is obtained through facial expression and voice analysis.

[0301] "Storage" refers to a storage device for temporarily or permanently storing data or information.

[0302] The "list format" is a format in which data is arranged in bullet points.

[0303] A "tree structure" is a format in which data is arranged hierarchically, and is a structure of nodes (data elements) that have parent-child relationships.

[0304] An "HTTP response" is a response message sent by a server in response to a request from a client.

[0305] This invention enables the generation of more accurate test patterns by combining an emotion engine that recognizes the user's emotions with a system in which a user inputs the specifications and requirements of the object to be verified via a terminal and generates test patterns for quasi-normal and abnormal conditions using an AI engine. This system is composed of the following elements: a server, a terminal, a user, and an emotion engine.

[0306] Hardware and software used

[0307] Terminal: An electronic device used by a user to input specifications and requirements, such as a personal computer or smartphone.

[0308] Server: A computer system that processes data reception, integrity checks, AI analysis, data storage, etc.

[0309] AI engine: A program that implements machine learning algorithms and runs on a high-performance GPU (Graphics Processing Unit) server.

[0310] Emotion engine: A software component that analyzes the user's facial expressions and voice to generate emotion data.

[0311] Natural language description of the program

[0312] 1. User input: The user accesses the system using a terminal and enters the specifications and requirements to be verified into the displayed form. Once the input is complete, the emotion engine captures the user's facial expressions and voice to recognize their emotions.

[0313] 2. Data transmission: The device converts the input specifications and requirements data into JSON format and sends it to the server as an HTTP POST request along with the emotion data obtained from the emotion engine.

[0314] 3. Data integrity check: The server checks the integrity of the received data. If invalid data is included, it generates an error message and returns it to the terminal. If the data is confirmed to be valid, it proceeds to the next step.

[0315] 4. AI analysis: The server passes the consistent data to the AI ​​engine, which then refers to the database and expert knowledge base to generate quasi-normal and abnormal test patterns. The AI ​​engine also takes into account the emotional data provided by the emotion engine to adjust the difficulty and details of the test patterns.

[0316] 5. Test pattern generation: The server receives the test patterns generated by the AI ​​engine and converts them into a format that is easy for humans to understand. The converted data is temporarily stored in storage.

[0317] 6. Result notification: The server reconverts the converted test pattern into JSON format and sends it to the terminal as an HTTP response, including supplementary explanations and links to reference materials as needed.

[0318] 7. User confirmation and correction: The device displays the received test pattern on the screen. The user confirms the displayed test pattern and inputs correction requests as necessary. The emotion engine continues to monitor the user's emotions and updates the emotion data as necessary.

[0319] 8. Re-analysis: The server receives the correction request and passes the data to the AI ​​engine again to generate a new test pattern, taking into account the newly collected emotion data. The generated test pattern is then sent back to the device.

[0320] 9. Final confirmation: The user checks the regenerated test pattern on the terminal one last time, and if there are no problems, presses the "Confirm" button to confirm the test pattern.

[0321] 10. Data saving: The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[0322] Specific examples

[0323] As a concrete example, consider the case of verifying the operation of a temperature sensor device. If a user inputs the specifications and operational requirements of the temperature sensor and the emotion engine determines that the user is expressing "anxiety," the AI ​​engine generates a test pattern with more details or additional explanations.

[0324] Example of generated test pattern

[0325] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[0326] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[0327] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[0328] Prompt Sentence Examples

[0329] "To verify the operation of a temperature sensor device, please generate test patterns for normal, quasi-normal, and abnormal conditions. The specifications and requirements are as follows."

[0330] "Generate highly accurate test patterns based on user input and emotion data."

[0331] The present invention enables highly accurate test pattern generation that takes user feelings into consideration, thereby realizing a user-friendly and efficient development process.

[0332] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0333] Step 1: User Input

[0334] Users access the system using a terminal and enter the specifications and requirements to be verified into the displayed form. This involves entering detailed information using text areas and drop-down lists. At the same time, the terminal's built-in camera and microphone capture the user's facial expressions and voice, which are then analyzed by the emotion engine to generate emotion data in real time.

[0335] Input: The user inputs specifications and requirements, and the device captures facial expressions and voice

[0336] Output: Input specifications, requirements, and sentiment data

[0337] Step 2: Sending data

[0338] The device converts the specifications and requirements data entered by the user into JSON format, and simultaneously collects the emotion data recognized by the emotion engine, consolidates them into a single data packet, and sends the data packet to the server as an HTTP POST request.

[0339] Input: Input specifications, requirements, and sentiment data

[0340] Output: JSON formatted data packet

[0341] Step 3: Verify data integrity

[0342] The server analyzes the received data packet and checks the integrity of the data. Specifically, it checks the JSON format, confirms the existence of required fields, and detects invalid data. If invalid data is included, the server generates an error message and returns it to the terminal. If the data is normal, it proceeds to the next step.

[0343] Input: JSON formatted data packet

[0344] Output: Data that has been verified to be consistent, or an error message

[0345] Step 4: Analysis by AI engine

[0346] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and knowledge. Emotional data is also taken into account, and the difficulty and details of the test patterns are adjusted based on the user's emotional state.

[0347] Input: Integrity checked data

[0348] Output: Generated quasi-normal and abnormal test patterns

[0349] Step 5: Formatting and temporarily saving the test pattern

[0350] The server converts the test patterns received from the AI ​​engine into a format that is easy for humans to understand, such as a list format or tree structure. The converted data is temporarily stored in storage.

[0351] Input: Generated test pattern

[0352] Output: Formatted test pattern

[0353] Step 6: Notification of results

[0354] The server then converts the formatted test pattern back into JSON format and sends it to the device as an HTTP response, adding any necessary supplementary explanations or links to reference material.

[0355] Input: Formatted test pattern

[0356] Output: Test pattern in JSON format sent to the terminal

[0357] Step 7: User review and correction

[0358] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. At the same time, the emotion engine continues to monitor the user's emotions and updates the data as necessary.

[0359] Input: Test pattern in JSON format sent to the terminal

[0360] Output: User-entered correction requests

[0361] Step 8: Reprocessing

[0362] The server receives the correction request and passes the data back to the AI ​​engine to generate a new test pattern, taking into account the corrections and the newly collected emotion data. The generated test pattern is then sent back to the device.

[0363] Input: The correction request entered by the user

[0364] Output: Regenerated test pattern

[0365] Step 9: Final check

[0366] The user makes a final check of the regenerated test pattern on the terminal, and if there are no problems, presses the "Confirm" button to confirm the test pattern.

[0367] Input: Regenerated test pattern

[0368] Output: User-defined test pattern

[0369] Step 10: Save Data

[0370] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[0371] Input: User-defined test pattern

[0372] Output: Test pattern stored in the database, end message sent to the terminal

[0373] (Application example 2)

[0374] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0375] In the development of autonomous vehicles, it is necessary to create highly accurate test patterns based on specifications and requirements so that drivers can use the vehicle with confidence. However, current test pattern generation systems generate test patterns with insufficient accuracy that takes into account the driver's emotions, making it impossible to alleviate driver anxiety. Another issue is the lack of systems that can flexibly respond to the driver's emotions when checking and modifying test patterns.

[0376] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to input specifications and requirements for the verification target via a terminal, means for the terminal to transmit the input data to the server, means for the server to verify the consistency of the received data and pass the data to the AI ​​engine, means for the AI ​​engine to generate quasi-normal and abnormal test patterns by referring to a past database and an expert knowledge base, means for the AI ​​engine to adjust the difficulty and details of the test patterns based on the user's emotional data using an emotion engine that recognizes the user's emotions in real time, means for converting the test patterns into a format that is easy for humans to understand and transmitting them to the terminal, means for the terminal to display the received test patterns and for the user to send a correction request, and means for the server to re-pass the data to the AI ​​engine based on the correction request and regenerate the test patterns. This enables the generation of highly accurate test patterns based on the driver's emotions, making it possible to provide a system that reduces driver anxiety and allows for flexible response.

[0377] A "terminal" is an electronic device that allows a user to input specifications and requirements, and is a device that communicates with a server.

[0378] The "server" is a central device that receives input data and generates and transmits test patterns using an AI engine and emotion engine.

[0379] An "AI engine" is an artificial intelligence system that references a database and expert knowledge base to generate test patterns for quasi-normal and abnormal conditions.

[0380] The "emotion engine" is a system that analyzes the user's facial expressions and voice in real time to recognize the user's emotions.

[0381] "Specifications and requirements" are data that indicate the detailed conditions and required performance of the product or system being verified.

[0382] A "test pattern" is a test pattern used to check the operation and performance of the object to be verified based on specifications and requirements.

[0383] A "database" is a repository of information that stores past data and specialized knowledge.

[0384] An "expertise base" is information that systematically compiles knowledge in a particular field.

[0385] "Real-time" refers to the time characteristic of being able to respond immediately to user operations and emotional changes.

[0386] "Integrity" means making sure that data is accurate and consistent.

[0387] An "anomaly detection algorithm" is a computational method for detecting abnormal behavior or situations.

[0388] This invention relates to a test pattern generation system for autonomous vehicles. Users input specifications and requirements via a terminal, and an AI engine is used to generate test patterns for quasi-normal and abnormal conditions. By combining this with an emotion engine, it is possible to generate test patterns with even greater accuracy. This system is composed of the following elements: a server, a terminal, a user, and an emotion engine.

[0389] Basic program structure

[0390] Data collection

[0391] Users access the system using a terminal and input their specifications and requirements, which can include specifications such as maximum speed, minimum speed, braking distance, etc. These data are finally converted into JSON format.

[0392] emotion recognition

[0393] In parallel, the emotion engine analyzes the user's facial expressions and voice in real time to obtain emotion data. The emotion engine uses an image analysis module (e.g., OpenCV) and an audio analysis module (e.g., Pyaudio).

[0394] From data transmission to analysis preparation

[0395] The device collects specifications, requirements, and emotion data and sends them to the server as an HTTP POST request. The server checks the integrity of the received data and, if invalid data is included, generates an error message and returns it to the device. If the integrity is confirmed, the device proceeds to the next step.

[0396] AI-based test pattern generation

[0397] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge. The user's emotional data provided by the emotion engine is also used for analysis; for example, if the user expresses "anxiety," a detailed test pattern is generated.

[0398] Test pattern conversion and transmission

[0399] The server receives the test patterns generated by the AI ​​engine and converts them into a format that is easy for humans to understand. This is often expressed in list format or tree structure. The converted data is temporarily stored in storage, then converted back into JSON format and sent to the device as an HTTP response.

[0400] Verify and correct users

[0401] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If there are correction requests, the user presses the "correct" button and the data is sent to the server again. The server again passes the data to the AI ​​engine and generates a new test pattern. During this time, the emotion engine continues to monitor the user's emotions.

[0402] Final confirmation and data storage

[0403] The user performs a final check, and if there are no problems, presses the "Confirm" button to confirm the test pattern. The server saves the finalized test pattern in the database. Once saving is complete, the server notifies the terminal and sends a completion message.

[0404] Examples and prompts

[0405] For example, suppose the emotion engine recognizes that the user appears anxious when the maximum speed of an autonomous vehicle is set to 120 km / h, the minimum speed to 0 km / h, and the braking distance to 3.5 m. In this case, the AI ​​engine generates a detailed test pattern. An example of a prompt sentence could be, "Please generate a vehicle operation test pattern with a maximum speed of 120 km / h, a minimum speed of 0 km / h, and a braking distance of 3.5 m. The driver appears anxious."

[0406] In this way, the system of the present invention enables the generation of highly accurate test patterns that take user emotions into consideration, thereby supporting the development of safer self-driving vehicles.

[0407] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0408] Step 1:

[0409] The user uses the terminal to input the specifications and requirements of the vehicle to be verified. The terminal screen displays a form for inputting maximum speed, minimum speed, braking distance, etc. When the user inputs this data and presses the submit button, the data is converted into JSON format. For example, the input data could be specification information such as "maximum speed: 120 km / h, minimum speed: 0 km / h, braking distance: 3.5 m."

[0410] Step 2:

[0411] The emotion engine analyzes the user's facial expressions and voice in real time and generates emotion data. The emotion engine captures the user's facial expressions and voice using the device's built-in camera and microphone. Images are processed using an image analysis library such as OpenCV, and audio is analyzed using an audio analysis library such as Pyaudio. An example of the generated emotion data is "Emotion: Anxiety."

[0412] Step 3:

[0413] The device converts the input specification and requirement data and the emotion data generated by the emotion engine into JSON format and sends it to the server as an HTTP POST request. An example of the data sent is as follows:

[0414] json

[0415] {

[0416] "specs": {

[0417] "max_speed": 120,

[0418] "min_speed": 0,

[0419] "braking_distance": 3.5

[0420] },

[0421] "emotion": "anxiety"

[0422] }

[0423] Step 4:

[0424] The server checks the integrity of the received data. It verifies that the JSON formatted data is correctly formed and that all required fields are included. If the data is inconsistent, the server generates an error message and returns it to the terminal. If the integrity is confirmed, it proceeds to the next step.

[0425] Step 5:

[0426] The server passes the consistent data to the AI ​​engine. The AI ​​engine refers to the database and expert knowledge base and generates quasi-normal and abnormal test patterns based on the user's input data. The emotion data provided by the emotion engine is also taken into consideration; for example, if the user expresses "anxiety," a detailed test pattern is generated. The AI ​​engine uses the generative AI model to generate test patterns based on the prompt sentence.

[0427] Step 6:

[0428] The server converts the test patterns received from the AI ​​engine into a format that is easy for humans to understand. The converted test patterns are temporarily stored in a list format or tree structure format. As a specific example, the following test patterns are generated:

[0429] Normal pattern: The vehicle is driven normally between 0km / h and 120km / h.

[0430] Quasi-normal pattern: The vehicle briefly exceeds 120 km / h but quickly returns to the normal range.

[0431] Abnormal pattern: When the vehicle exceeds 150 km / h, the brake system exhibits abnormal operation.

[0432] Step 7:

[0433] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any reference materials or supplementary explanations as needed.

[0434] Step 8:

[0435] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If there are correction requests, the user presses the "correct" button and the data including the corrections is sent again to the server. A specific example would be a correction such as "Maximum speed: 130 km / h."

[0436] Step 9:

[0437] The server then passes the data back to the AI ​​engine based on the requested corrections, generating a new test pattern. This takes into account the newly acquired emotion data. The new test pattern is then sent back to the device, where the user can view it on the screen.

[0438] Step 10:

[0439] The user performs a final check, and if there are no problems, presses the "Confirm" button to confirm the test pattern. The server saves the confirmed test pattern in the database. Once saving is complete, the server notifies the user and sends a completion message to the terminal. This completes processing for the entire system, and the terminal is ready for verification.

[0440] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0441] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0442] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0443] [Second embodiment]

[0444] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0445] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0446] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0447] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0448] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0449] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0450] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0451] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0452] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0453] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0454] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0455] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0456] The present invention is a system in which a user inputs the specifications and requirements of a verification target via a terminal and generates test patterns for quasi-normal and abnormal conditions using an AI engine. This system is composed of elements including a server, a terminal, and a user, and a detailed embodiment of the system is described below.

[0457] User Interaction

[0458] The user accesses the system using a terminal. A form is displayed on the terminal screen for entering the specifications and requirements of the tool and development equipment to be verified. The user enters the necessary information into this form and presses the "Submit" button.

[0459] Data transmission

[0460] The terminal converts the specifications and requirements data entered by the user into JSON format and sends it to the server as an HTTP POST request.

[0461] Data reception and preparation for analysis

[0462] The server processes the received JSON data, checks the data integrity, and detects invalid data. If invalid data is included, the server generates an error message and returns it to the terminal. If the integrity is confirmed, the data proceeds to the next step.

[0463] AI-based analysis

[0464] The server passes the data whose integrity has been confirmed to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge.

[0465] Test Pattern Generation

[0466] The server converts the test patterns generated by the AI ​​engine into a format that is easy for humans to understand, such as a list or tree structure. This data is then stored in temporary storage.

[0467] Send results

[0468] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any necessary supplementary explanations or links to reference materials.

[0469] User verification and correction

[0470] The terminal displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If correction requests are required, the user presses the "correct" button and resends the corrections to the server.

[0471] reanalysis

[0472] The server receives the correction request, passes the data to the AI ​​engine again, and regenerates the test pattern. The regenerated test pattern is then sent back to the device.

[0473] Final confirmation

[0474] The user makes a final check of the regenerated test pattern on the terminal, and if there are no problems, presses the "Confirm" button.

[0475] Data storage

[0476] The server permanently saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives this message and is ready to begin verification.

[0477] As a concrete example, consider the case of verifying the operation of a temperature sensor device. When the user inputs the specifications and operational requirements of the temperature sensor, the AI ​​engine generates the following test pattern.

[0478] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[0479] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[0480] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[0481] According to the present invention, regardless of the user's level of experience, high-quality test patterns can be generated efficiently, thereby improving the quality and efficiency of the development process.

[0482] The processing flow will be explained below.

[0483] Step 1:

[0484] The user accesses the system using a terminal. A form for entering the specifications and requirements of the tool and development equipment to be verified is displayed on the terminal screen. The user enters the necessary information into this form and presses the "Submit" button.

[0485] Step 2:

[0486] The terminal converts the specifications and requirements data entered by the user into JSON format and sends the converted JSON data to the server as an HTTP POST request.

[0487] Step 3:

[0488] The server processes the received JSON data. Specifically, it checks the data for consistency and detects invalid data. If invalid data is included, it generates an error message and returns it to the terminal. If consistency is confirmed, it proceeds to the next step.

[0489] Step 4:

[0490] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge.

[0491] Step 5:

[0492] The server receives the test patterns generated by the AI ​​engine, converts them into a format that is easy for humans to understand, and temporarily stores this data in storage.

[0493] Step 6:

[0494] The server then converts the converted test pattern back into JSON format and sends it to the terminal as an HTTP response, along with supplementary explanations and links to reference materials, if necessary.

[0495] Step 7:

[0496] The terminal displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If the user wants to submit a correction request, he or she presses the "Edit" button and resends the data including the corrections to the server.

[0497] Step 8:

[0498] Based on the received correction request, the server passes the data to the AI ​​engine again, generates a new test pattern, and sends the generated test pattern back to the device.

[0499] Step 9:

[0500] The terminal displays the received test pattern again, and the user performs a final check. If there are no problems, the user presses the "Confirm" button to confirm the test pattern.

[0501] Step 10:

[0502] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[0503] Example 1

[0504] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0505] Conventional test pattern generation methods require users to manually design test cases, which is time-consuming, labor-intensive, and prone to errors. Furthermore, because they rely on the user's experience and knowledge, it is difficult to generate test patterns of consistent quality. In particular, designing test patterns for quasi-normal and abnormal conditions requires advanced expertise. The present invention aims to solve these problems and provide an efficient, high-quality test pattern generation system.

[0506] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0507] In this invention, the server includes a means for a user to input specifications and requirements for the verification target via a terminal, a means for the terminal to convert the input data into JSON format and send it to the server as an HTTP POST request, and a means for the server to check the integrity of the received JSON data and pass the data to the AI ​​engine. This enables users to easily generate high-quality test patterns and improve the quality and efficiency of the development process.

[0508] "Terminal" means a computing device used by a User to input specifications and requirements.

[0509] The term "server" refers to a computer system that receives and processes data sent from a terminal.

[0510] "JSON format" is a standard for describing data in text format and is an abbreviation for JavaScript Object Notation.

[0511] "HTTP POST request" refers to the part of the HTTP protocol that allows a client to send data to a server.

[0512] "Integrity" refers to the property of ensuring that data is accurate and consistent.

[0513] "AI engine" refers to an artificial intelligence system that performs data analysis and test pattern generation.

[0514] A "database" refers to a system for efficiently storing and managing data.

[0515] "Expertise base" refers to a dataset that aggregates knowledge in a particular field of expertise.

[0516] "Test patterns" refer to scenarios or cases used to verify systems or equipment.

[0517] "Quasi-normal" refers to operating conditions that deviate slightly from normal conditions but do not pose a serious problem.

[0518] "Abnormal" refers to a situation in which a system or device malfunctions beyond its expected range.

[0519] "Temporary storage" refers to memory or disk space used to temporarily store data.

[0520] "Finish message" refers to a message that notifies the user that a process has been successfully completed.

[0521] MODE FOR CARRYING OUT THE INVENTION

[0522] This system allows users to input specifications and requirements for the verification target via a terminal, and the server processes the data and passes it to an AI engine, which then generates test patterns for quasi-normal and abnormal conditions. The system is composed of the following elements: a terminal, a server, and a user.

[0523] The user enters the specifications and operational requirements of a temperature sensor or other device into a form on the terminal. For example, for a temperature sensor, the user enters information such as the measurement range and response time. Once the input is complete, the user presses the "Submit" button.

[0524] The terminal converts this input data into JSON format. For example, if you enter "measurement range -20°C to 100°C" and "response time 1 second" as the specifications for a temperature sensor, this data will be converted as {"measurement range": "-20°C to 100°C", "response time": "1 second"}. This converted data is sent to the server as an HTTP POST request.

[0525] The server checks the integrity of the received JSON data. For example, it checks whether the data is invalid or missing. If it contains error data, the server generates an error message and returns it to the terminal. If the data is correct, it saves the data to proceed to the next step.

[0526] The server then passes the data, whose integrity has been confirmed, to the AI ​​engine, which then references the database and expert knowledge base. For example, the expert knowledge base contains past test data and existing technical literature. Based on this data, the AI ​​engine generates test patterns for quasi-normal and abnormal conditions.

[0527] The generated test patterns are converted by the server into a format that is easy for humans to understand, such as a list format or a tree structure, and this converted data is stored in temporary storage.

[0528] The server converts this data back into JSON format and sends it to the terminal as an HTTP response. The terminal displays the received test pattern on the screen. The user checks the displayed test pattern. If necessary, they can enter a correction request and press the "Edit" button, and the terminal will resend the corrections to the server.

[0529] The server receives the correction request and passes the data to the AI ​​engine again to regenerate the test pattern. This regenerated test pattern is also sent to the device again, and the user checks it. If there are no final problems, the user presses the "Confirm" button, and the final confirmed information is sent to the server.

[0530] The server permanently saves the confirmed data in the database and notifies the terminal that the saving is complete. The user receives this completion message and ends their use of the system.

[0531] As a concrete example, the following prompt sentences are input to the generative AI model to verify the operation of a temperature sensor device:

[0532] "The specifications and operating requirements for the temperature sensor device have been entered as follows:

[0533] Measurement range: -20°C to 100°C

[0534] Response time: 1 second

[0535] Based on this, generate a test pattern like this:

[0536] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[0537] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[0538] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[0539] The present invention enables users to efficiently generate high-quality test patterns, thereby improving the quality and efficiency of the development process.

[0540] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0541] Step 1:

[0542] The user uses the terminal to input the specifications and requirements of the object to be verified. The user enters the temperature sensor specifications (e.g., measurement range -20°C to 100°C, response time 1 second) into the form and presses the "Submit" button. The input data is collected by the terminal.

[0543] Input: User-entered specification and requirements data

[0544] Output: Input data collected on the terminal

[0545] Step 2:

[0546] The terminal converts the collected input data into JSON format, for example, {'Measurement range': '-20°C to 100°C', 'Response time': '1 second'}, and then sends it to the server as an HTTP POST request.

[0547] Input: Data entered by the user into the terminal

[0548] Output: Data converted to JSON format

[0549] Step 3:

[0550] The server receives the JSON data sent from the terminal and checks the integrity of the data. If invalid data is included, the server generates an error message and returns it to the terminal. If the data is confirmed to be valid, it proceeds to the next processing step.

[0551] Input: JSON data sent from the terminal

[0552] Output: Consistency checked data or error message

[0553] Step 4:

[0554] The server passes the data whose integrity has been confirmed to the AI ​​engine. For example, it provides measurement range and response time data as input to the AI ​​engine.

[0555] Input: Integrity checked data

[0556] Output: Data passed to the AI ​​engine

[0557] Step 5:

[0558] The AI ​​engine references a database and expert knowledge base to generate test patterns for quasi-normal and abnormal conditions, such as normal operation between 25°C and 30°C, and abnormal operation above 40°C.

[0559] Input: Data passed to the AI ​​engine

[0560] Output: Generated quasi-normal and abnormal test patterns

[0561] Step 6:

[0562] The server receives the test patterns generated by the AI ​​engine and converts them into a format that is easy for humans to understand (e.g., list format or tree structure). This data is stored in temporary storage.

[0563] Input: Test patterns generated by the AI ​​engine

[0564] Output: Test patterns converted into a human-readable format

[0565] Step 7:

[0566] The server converts the converted test pattern back into JSON format and sends it to the terminal as an HTTP response.

[0567] Input: Test patterns converted to a human-readable format

[0568] Output: Test patterns converted to JSON format

[0569] Step 8:

[0570] The terminal displays the received test pattern on the screen. The user checks the test pattern and inputs correction requests as necessary. Then, by pressing the "Correction" button, the terminal resends the correction request to the server.

[0571] Input: Test pattern sent to the terminal

[0572] Output: User correction request

[0573] Step 9:

[0574] The server receives the correction request, passes the data to the AI ​​engine again, and regenerates the test pattern. The regenerated test pattern is then sent back to the device.

[0575] Input: User requested correction

[0576] Output: Regenerated test pattern

[0577] Step 10:

[0578] The user checks the regenerated test pattern on the terminal and, if there are no problems, presses the "Confirm" button, which sends the confirmed test pattern to the server.

[0579] Input: Regenerated test pattern

[0580] Output: Final confirmation by user

[0581] Step 11:

[0582] The server permanently saves the finalized data in the database and notifies the terminal that the saving is complete. The user receives a completion message and ends their use of the system.

[0583] Input: Test pattern confirmed by the user

[0584] Output: Test patterns stored in the database and an end message

[0585] (Application example 1)

[0586] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0587] Conventional methods for verifying the operation of industrial robots require users to manually create numerous test patterns, which often leads to errors. Furthermore, generating abnormal test patterns is difficult, making it difficult to effectively perform abnormality testing for specific operational scenarios. This reduces the efficiency of ensuring the reliability and safety of industrial robots.

[0588] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0589] In this invention, the server includes: a means for a user to input specifications and requirements for the verification target via a terminal; a means for the terminal to transmit the input data to the server; a means for the server to verify the consistency of the received data and pass the data to the AI ​​engine; a means for the AI ​​engine to generate quasi-normal and abnormal test patterns by referring to a past database and an expert knowledge base; a means for converting the test patterns into a human-understandable format and transmitting the converted test patterns to the terminal; a means for the terminal to display the received test patterns and for the user to send a correction request; a means for the server to re-pass the data to the AI ​​engine based on the correction request and re-generate the test patterns; a means for inputting operational specifications and requirements for the industrial robot and generating test patterns; a means for displaying the generated test patterns and performing a final check; a means for saving the finalized test patterns to the server; a means for inputting prompt statements to a generative AI model and generating test patterns based on specific operational scenarios; a means for generating prompt statements for identifying operational scenarios of the industrial robot; a means for generating abnormal test patterns for the industrial robot using the generative AI model; and a means for evaluating the generated test patterns. This eliminates the need for users to manually create numerous test patterns, enabling accurate and efficient operational verification of industrial robots.

[0590] "User" refers to a user who uses the system to input specifications and requirements to be verified.

[0591] "Terminal" means a device used by a user to input specifications and requirements and communicate with a server.

[0592] A "server" is a device that receives data sent from a user via a terminal, processes the data, and checks the consistency of the data.

[0593] An "AI engine" is an algorithm that generates quasi-normal and abnormal test patterns by referencing a past database and expert knowledge base.

[0594] A "database" is a collection of information that stores past data and is used as a reference by an AI engine.

[0595] An "expertise base" is information that accumulates specialized knowledge in a specific field, and is used by the AI ​​engine as a reference when generating test patterns.

[0596] A "test pattern" is a specific scenario for verifying the behavior of the target system.

[0597] "Quasi-normal" refers to a situation or scenario that is nearly normal but contains some abnormalities.

[0598] An "abnormal situation" is a situation or scenario in which the subject of verification does not operate normally.

[0599] "Behavioral specifications" are requirements that define how the object to be verified should behave.

[0600] "Requirements" are conditions or standards that the object of verification must meet.

[0601] A "prompt" is an instruction sentence to be input to a generative AI model and is used to identify a specific behavior scenario.

[0602] A "generative AI model" is a trained algorithm that allows an AI engine to generate test patterns based on prompt sentences.

[0603] An "anomaly detection algorithm" is a specific computational method or program for detecting abnormal patterns.

[0604] This invention is a system that streamlines operational verification of industrial robots by allowing users to input specifications and requirements for the object to be verified via a terminal, and generating test patterns for quasi-normal and abnormal conditions using a server and an AI engine.

[0605] Users use devices such as smartphones and tablets to enter the operational specifications and requirements of the industrial robot to be verified into a form. The entered data is converted to JSON format by the device and sent to the server as an HTTP POST request.

[0606] The server checks the integrity of the received JSON data and verifies that it does not contain any invalid data. Once the integrity is confirmed, the server passes the data to the AI ​​engine, which then references its past database and expert knowledge base to generate quasi-normal and abnormal test patterns.

[0607] The generated test patterns are converted by the server into a human-readable format, usually expressed as a list or tree structure, and the converted data is stored in temporary storage.

[0608] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response. The user can check the received test pattern on the device and enter correction requests as necessary. If corrections are required, the user enters the corrections and sends it back to the server.

[0609] The server receives the correction request and passes the data to the AI ​​engine again to regenerate the test pattern. The regenerated test pattern is then sent back to the device for final confirmation by the user. When the user presses the "Confirm" button, the confirmed test pattern is permanently saved in the database by the server.

[0610] For example, consider the case of verifying an industrial robot's operational scenario. The user inputs the robot's operational specifications and requirements, such as temperature range, load capacity, and operational pattern. In this case, the AI ​​engine generates the following test patterns:

[0611] Normal condition: The robot operates normally within a temperature range of 20°C-30°C and moves the specified object accurately.

[0612] Quasi-normal pattern: Operation is not affected even if the ambient temperature temporarily exceeds 30°C.

[0613] Abnormal pattern: The robot begins to malfunction when the environmental temperature exceeds 50°C.

[0614] Examples of prompt sentences to be input to the generative AI model include the following:

[0615] "Generate test patterns to identify operating scenarios for industrial robot model XYZ-123. Specifications are temperature 0-50°C, humidity 20-80%, and load capacity up to 50kg."

[0616] "Please tell me the abnormality test pattern for the model XYZ-123 robot that includes a temperature sensor function."

[0617] The software used is Python and its libraries (requests, json), and the hardware is a smartphone or tablet connected to the internet.The AI ​​engine utilizes a generative AI model to efficiently generate test patterns.

[0618] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0619] Step 1:

[0620] The user inputs the specifications and requirements to be verified into the terminal, including the operating scenario of the industrial robot and environmental conditions (e.g., temperature range, humidity, load capacity). The input data is saved on the terminal.

[0621] Step 2:

[0622] The terminal converts the input data into JSON format. Specifically, it converts the specifications and requirements entered by the user into a JSON object and sends it to the server as an HTTP POST request. Here, the input data is serialized and sent.

[0623] Step 3:

[0624] The server receives the received JSON data and checks its integrity. The server parses the JSON data and checks for invalid data or defects. The result of the integrity check becomes the output data. If integrity is confirmed, proceed to the next step.

[0625] Step 4:

[0626] The server passes the data whose integrity has been confirmed to the AI ​​engine, which then references the database and expert knowledge base to generate test patterns for quasi-normal and abnormal conditions. In this process, the AI ​​engine analyzes the input data and makes predictions and generates patterns. The output is the generated test patterns.

[0627] Step 5:

[0628] The server converts the test patterns generated by the AI ​​engine into a format that is easy for humans to understand, including formats such as lists and tree structures. Specifically, it converts the data structure of the test patterns and saves them as output data.

[0629] Step 6:

[0630] The server reconverts the converted test pattern into JSON format and sends it to the terminal as an HTTP response. The server serializes the parsed data and prepares it for transmission. The terminal displays the received data on the screen.

[0631] Step 7:

[0632] The user checks the received test pattern on the terminal and inputs correction requests as necessary. The user evaluates the test pattern and inputs corrections if they find any errors or deficiencies. The correction requests are sent from the terminal to the server.

[0633] Step 8:

[0634] The server receives the correction request and passes the data to the AI ​​engine again to regenerate the test pattern. Reanalysis is performed based on the new input data, and new test patterns are generated. During this process, the AI ​​engine again refers to the database and expert knowledge base.

[0635] Step 9:

[0636] The user checks the regenerated test pattern on the terminal and presses the "Confirm" button if there are no problems. The final checked test pattern is sent to the server. The output is the final checked test pattern.

[0637] Step 10:

[0638] The server permanently saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user confirms the received message and is ready for verification.

[0639] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0640] The present invention enables the generation of more accurate test patterns by combining an emotion engine that recognizes the user's emotions with a system in which a user inputs the specifications and requirements of the object to be verified via a terminal and generates quasi-normal and abnormal test patterns using an AI engine. This system is composed of the elements of a server, a terminal, a user, and an emotion engine, and detailed embodiments are described below.

[0641] User Interaction

[0642] The user accesses the system using a terminal. A form is displayed on the terminal screen for entering the specifications and requirements of the tool to be verified and the development equipment. The user enters the necessary information into this form and presses the "Submit" button. In parallel, the emotion engine analyzes the user's facial expressions and voice, recognizing emotions in real time.

[0643] Data transmission

[0644] The device converts the specifications and requirements data entered by the user into JSON format, simultaneously collecting the emotion data recognized by the emotion engine, and sends this data to the server as an HTTP POST request.

[0645] Data reception and preparation for analysis

[0646] The server processes the received JSON data. Specifically, it checks the data for consistency and detects invalid data. If invalid data is included, it generates an error message and returns it to the terminal. If consistency is confirmed, it proceeds to the next step.

[0647] AI-based analysis

[0648] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge. The user's emotional data provided by the emotion engine is also used for analysis, and the difficulty and details of the test patterns are adjusted.

[0649] Test Pattern Generation

[0650] The server receives the test patterns generated by the AI ​​engine. The server converts the test patterns into a format that is easy for humans to understand. Specifically, they are often expressed in list format or tree structure. This data is temporarily stored in storage.

[0651] Send results

[0652] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any necessary supplementary explanations or links to reference materials.

[0653] User verification and correction

[0654] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. In parallel, the emotion engine continues to monitor the user's emotions. If the user wishes to send a correction request, they press the "Edit" button and the data including the corrections is resent to the server.

[0655] reanalysis

[0656] The server receives the correction request and passes the data to the AI ​​engine again to generate a new test pattern, taking into account the newly collected emotion data. The generated test pattern is then sent back to the device.

[0657] Final confirmation

[0658] The user makes a final check of the regenerated test pattern on the terminal, and if there are no problems, presses the "Confirm" button to confirm the test pattern.

[0659] Data storage

[0660] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[0661] As a concrete example, consider the case of verifying the operation of a temperature sensor device. If a user inputs the specifications and operational requirements of a temperature sensor and the emotion engine determines that the user is expressing "anxiety," the AI ​​engine generates a test pattern with more details or additional explanations. For example, it generates the following test pattern:

[0662] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[0663] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[0664] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[0665] According to the present invention, by utilizing the emotion engine, the user can generate more accurate test patterns, thereby realizing a more user-friendly and efficient development process.

[0666] The processing flow will be explained below.

[0667] Step 1:

[0668] The user accesses the system using a terminal. A form for entering the specifications and requirements of the tool and development equipment to be verified is displayed on the terminal screen. The user enters the necessary information into this form and presses the "Submit" button.

[0669] Step 2:

[0670] The device converts the specifications and requirements data entered by the user into JSON format. At the same time, the emotion engine analyzes the user's facial expressions and voice to recognize emotions in real time. The recognized emotion data is also included in the JSON format.

[0671] Step 3:

[0672] The device sends the converted JSON data of specifications and requirements and emotion data to the server as an HTTP POST request.

[0673] Step 4:

[0674] The server processes the received JSON data. Specifically, it first checks the data for consistency and detects invalid data. If invalid data is included, it generates an error message and returns it to the terminal.

[0675] Step 5:

[0676] The server passes the data whose integrity has been confirmed to the AI ​​engine, which then references the received database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge.

[0677] Step 6:

[0678] When generating test patterns, the AI ​​engine takes into account the user's emotional data provided by the emotion engine. For example, if the user is feeling "anxious" or "stressed," the AI ​​engine will adjust the explanation of the test pattern to be more detailed or simpler.

[0679] Step 7:

[0680] The server receives the test patterns generated by the AI ​​engine, converts them into a format that is easy for humans to understand, and temporarily stores the test patterns in storage.

[0681] Step 8:

[0682] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any supplementary explanations or links to reference materials, if necessary.

[0683] Step 9:

[0684] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. In parallel, the emotion engine continues to monitor the user's emotions.

[0685] Step 10:

[0686] When the user wishes to send a correction request, the data including the corrections is resent to the server by pressing the "correct" button.

[0687] Step 11:

[0688] The server receives the correction request and passes the data to the AI ​​engine again to generate a new test pattern, taking into account the recollected emotion data. The generated test pattern is then sent back to the device.

[0689] Step 12:

[0690] The terminal displays the received test pattern again, and the user performs a final check. If there are no problems, the user presses the "Confirm" button to confirm the test pattern.

[0691] Step 13:

[0692] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the terminal and sends a completion message.

[0693] Step 14:

[0694] The user receives a completion message, and the emotion engine also collects and saves the final emotion data. Verification preparation is complete, and the user is ready to proceed to the next step.

[0695] As a concrete example, consider the case of verifying the operation of a temperature sensor device. If the user inputs the specifications and operational requirements of the temperature sensor and the emotion engine detects "anxiety," the AI ​​engine generates a test pattern with a more detailed explanation. On the other hand, if the emotion is recognized as "calm," it generates a standard test pattern. For example, the following test pattern may be generated:

[0696] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[0697] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[0698] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[0699] This specific flow provides optimal test patterns according to the user's emotions, realizing more efficient and high-quality verification.

[0700] Example 2

[0701] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0702] Conventional test pattern generation systems generate test patterns based on specifications and requirements entered by the user, but the generated test patterns do not always reflect the user's intentions or emotions. Furthermore, particularly for abnormality test patterns, flexible adjustments that take into account the user's emotions and level of understanding are required. However, conventional systems were unable to achieve this, making it difficult to achieve a user-friendly and efficient development process.

[0703] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0704] In this invention, the server includes means for converting data input by the terminal into JSON format and sending it to the server, means for checking the consistency of the received data and, if invalid data is detected, generating an error message and sending it to the terminal, and means for passing the consistent data to the AI ​​engine. This enables the AI ​​engine to refer to the past database and expert knowledge base and generate quasi-normal and abnormal test patterns that take user emotion data into consideration.

[0705] A "terminal" is an electronic device used by a user to input specifications and requirements for a verification target, and is used to input, send, receive, and display data.

[0706] A "server" is a computer system that receives data sent from a terminal, checks the integrity of the data, detects fraudulent data, and provides the data to the AI ​​engine.

[0707] An "AI engine" is a program that incorporates artificial intelligence technology to generate quasi-normal and abnormal test patterns by referencing past databases and expert knowledge bases.

[0708] The "emotion engine" is a program that incorporates technology that analyzes the user's facial expressions and voice input and recognizes emotions in real time.

[0709] A "specification" is a document or data that describes in detail the functions and characteristics of the object to be verified.

[0710] "Requirements" are documents or data that describe the conditions and constraints that the verification target must satisfy.

[0711] "JSON format" is an abbreviation for JavaScript Object Notation, and is a data exchange format that represents structured text data in a format that is easy for humans to read and computers to analyze.

[0712] An "HTTP POST request" is a request format for sending data from a client (terminal) to a server using the POST method of the Hypertext Transfer Protocol.

[0713] "Integrity check" is the process of verifying whether the received data is formally correct and contains all required fields.

[0714] "Invalid data" refers to data that cannot be processed normally, such as data that has an incorrect data format or is missing required fields.

[0715] A "test pattern" refers to a scenario or case for verifying the behavior of a system under specific conditions.

[0716] A "quasi-normal" situation refers to a situation in which the system is temporarily placed in an unstable state, but is expected to return to a normal state.

[0717] "Abnormal situation" refers to a situation in which the system is placed in an abnormal condition and is expected to not function normally.

[0718] "Emotion data" is data that indicates the user's emotional state and is obtained through facial expression and voice analysis.

[0719] "Storage" refers to a storage device for temporarily or permanently storing data or information.

[0720] The "list format" is a format in which data is arranged in bullet points.

[0721] A "tree structure" is a format in which data is arranged hierarchically, and is a structure of nodes (data elements) that have parent-child relationships.

[0722] An "HTTP response" is a response message sent by a server in response to a request from a client.

[0723] This invention enables the generation of more accurate test patterns by combining an emotion engine that recognizes the user's emotions with a system in which a user inputs the specifications and requirements of the object to be verified via a terminal and generates test patterns for quasi-normal and abnormal conditions using an AI engine. This system is composed of the following elements: a server, a terminal, a user, and an emotion engine.

[0724] Hardware and software used

[0725] Terminal: An electronic device used by a user to input specifications and requirements, such as a personal computer or smartphone.

[0726] Server: A computer system that processes data reception, integrity checks, AI analysis, data storage, etc.

[0727] AI engine: A program that implements machine learning algorithms and runs on a high-performance GPU (Graphics Processing Unit) server.

[0728] Emotion engine: A software component that analyzes the user's facial expressions and voice to generate emotion data.

[0729] Natural language description of the program

[0730] 1. User input: The user accesses the system using a terminal and enters the specifications and requirements to be verified into the displayed form. Once the input is complete, the emotion engine captures the user's facial expressions and voice to recognize their emotions.

[0731] 2. Data transmission: The device converts the input specifications and requirements data into JSON format and sends it to the server as an HTTP POST request along with the emotion data obtained from the emotion engine.

[0732] 3. Data integrity check: The server checks the integrity of the received data. If invalid data is included, it generates an error message and returns it to the terminal. If the data is confirmed to be valid, it proceeds to the next step.

[0733] 4. AI analysis: The server passes the consistent data to the AI ​​engine, which then refers to the database and expert knowledge base to generate quasi-normal and abnormal test patterns. The AI ​​engine also takes into account the emotional data provided by the emotion engine to adjust the difficulty and details of the test patterns.

[0734] 5. Test pattern generation: The server receives the test patterns generated by the AI ​​engine and converts them into a format that is easy for humans to understand. The converted data is temporarily stored in storage.

[0735] 6. Result notification: The server reconverts the converted test pattern into JSON format and sends it to the terminal as an HTTP response, including supplementary explanations and links to reference materials as needed.

[0736] 7. User confirmation and correction: The device displays the received test pattern on the screen. The user confirms the displayed test pattern and inputs correction requests as necessary. The emotion engine continues to monitor the user's emotions and updates the emotion data as necessary.

[0737] 8. Re-analysis: The server receives the correction request and passes the data to the AI ​​engine again to generate a new test pattern, taking into account the newly collected emotion data. The generated test pattern is then sent back to the device.

[0738] 9. Final confirmation: The user checks the regenerated test pattern on the terminal one last time, and if there are no problems, presses the "Confirm" button to confirm the test pattern.

[0739] 10. Data saving: The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[0740] Specific examples

[0741] As a concrete example, consider the case of verifying the operation of a temperature sensor device. If a user inputs the specifications and operational requirements of the temperature sensor and the emotion engine determines that the user is expressing "anxiety," the AI ​​engine generates a test pattern with more details or additional explanations.

[0742] Example of generated test pattern

[0743] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[0744] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[0745] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[0746] Prompt Sentence Examples

[0747] "To verify the operation of a temperature sensor device, please generate test patterns for normal, quasi-normal, and abnormal conditions. The specifications and requirements are as follows."

[0748] "Generate highly accurate test patterns based on user input and emotion data."

[0749] The present invention enables highly accurate test pattern generation that takes user feelings into consideration, thereby realizing a user-friendly and efficient development process.

[0750] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0751] Step 1: User Input

[0752] Users access the system using a terminal and enter the specifications and requirements to be verified into the displayed form. This involves entering detailed information using text areas and drop-down lists. At the same time, the terminal's built-in camera and microphone capture the user's facial expressions and voice, which are then analyzed by the emotion engine to generate emotion data in real time.

[0753] Input: The user inputs specifications and requirements, and the device captures facial expressions and voice

[0754] Output: Input specifications, requirements, and sentiment data

[0755] Step 2: Sending data

[0756] The device converts the specifications and requirements data entered by the user into JSON format, and simultaneously collects the emotion data recognized by the emotion engine, consolidates them into a single data packet, and sends the data packet to the server as an HTTP POST request.

[0757] Input: Input specifications, requirements, and sentiment data

[0758] Output: JSON formatted data packet

[0759] Step 3: Verify data integrity

[0760] The server analyzes the received data packet and checks the integrity of the data. Specifically, it checks the JSON format, confirms the existence of required fields, and detects invalid data. If invalid data is included, the server generates an error message and returns it to the terminal. If the data is normal, it proceeds to the next step.

[0761] Input: JSON formatted data packet

[0762] Output: Data that has been verified to be consistent, or an error message

[0763] Step 4: Analysis by AI engine

[0764] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and knowledge. Emotional data is also taken into account, and the difficulty and details of the test patterns are adjusted based on the user's emotional state.

[0765] Input: Integrity checked data

[0766] Output: Generated quasi-normal and abnormal test patterns

[0767] Step 5: Formatting and temporarily saving the test pattern

[0768] The server converts the test patterns received from the AI ​​engine into a format that is easy for humans to understand, such as a list format or tree structure. The converted data is temporarily stored in storage.

[0769] Input: Generated test pattern

[0770] Output: Formatted test pattern

[0771] Step 6: Notification of results

[0772] The server then converts the formatted test pattern back into JSON format and sends it to the device as an HTTP response, adding any necessary supplementary explanations or links to reference material.

[0773] Input: Formatted test pattern

[0774] Output: Test pattern in JSON format sent to the terminal

[0775] Step 7: User review and correction

[0776] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. At the same time, the emotion engine continues to monitor the user's emotions and updates the data as necessary.

[0777] Input: Test pattern in JSON format sent to the terminal

[0778] Output: User-entered correction requests

[0779] Step 8: Reprocessing

[0780] The server receives the correction request and passes the data back to the AI ​​engine to generate a new test pattern, taking into account the corrections and the newly collected emotion data. The generated test pattern is then sent back to the device.

[0781] Input: The correction request entered by the user

[0782] Output: Regenerated test pattern

[0783] Step 9: Final check

[0784] The user makes a final check of the regenerated test pattern on the terminal, and if there are no problems, presses the "Confirm" button to confirm the test pattern.

[0785] Input: Regenerated test pattern

[0786] Output: User-defined test pattern

[0787] Step 10: Save Data

[0788] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[0789] Input: User-defined test pattern

[0790] Output: Test pattern stored in the database, end message sent to the terminal

[0791] (Application example 2)

[0792] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0793] In the development of autonomous vehicles, it is necessary to create highly accurate test patterns based on specifications and requirements so that drivers can use the vehicle with confidence. However, current test pattern generation systems generate test patterns with insufficient accuracy that takes into account the driver's emotions, making it impossible to alleviate driver anxiety. Another issue is the lack of systems that can flexibly respond to the driver's emotions when checking and modifying test patterns.

[0794] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to input specifications and requirements for the verification target via a terminal, means for the terminal to transmit the input data to the server, means for the server to verify the consistency of the received data and pass the data to the AI ​​engine, means for the AI ​​engine to generate quasi-normal and abnormal test patterns by referring to a past database and an expert knowledge base, means for the AI ​​engine to adjust the difficulty and details of the test patterns based on the user's emotional data using an emotion engine that recognizes the user's emotions in real time, means for converting the test patterns into a format that is easy for humans to understand and transmitting them to the terminal, means for the terminal to display the received test patterns and for the user to send a correction request, and means for the server to re-pass the data to the AI ​​engine based on the correction request and regenerate the test patterns. This enables the generation of highly accurate test patterns based on the driver's emotions, making it possible to provide a system that reduces driver anxiety and allows for flexible response.

[0795] A "terminal" is an electronic device that allows a user to input specifications and requirements, and is a device that communicates with a server.

[0796] The "server" is a central device that receives input data and generates and transmits test patterns using an AI engine and emotion engine.

[0797] An "AI engine" is an artificial intelligence system that references a database and expert knowledge base to generate test patterns for quasi-normal and abnormal conditions.

[0798] The "emotion engine" is a system that analyzes the user's facial expressions and voice in real time to recognize the user's emotions.

[0799] "Specifications and requirements" are data that indicate the detailed conditions and required performance of the product or system being verified.

[0800] A "test pattern" is a test pattern used to check the operation and performance of the object to be verified based on specifications and requirements.

[0801] A "database" is a repository of information that stores past data and specialized knowledge.

[0802] An "expertise base" is information that systematically compiles knowledge in a particular field.

[0803] "Real-time" refers to the time characteristic of being able to respond immediately to user operations and emotional changes.

[0804] "Integrity" means making sure that data is accurate and consistent.

[0805] An "anomaly detection algorithm" is a computational method for detecting abnormal behavior or situations.

[0806] This invention relates to a test pattern generation system for autonomous vehicles. Users input specifications and requirements via a terminal, and an AI engine is used to generate test patterns for quasi-normal and abnormal conditions. By combining this with an emotion engine, it is possible to generate test patterns with even greater accuracy. This system is composed of the following elements: a server, a terminal, a user, and an emotion engine.

[0807] Basic program structure

[0808] Data collection

[0809] Users access the system using a terminal and input their specifications and requirements, which can include specifications such as maximum speed, minimum speed, braking distance, etc. These data are finally converted into JSON format.

[0810] emotion recognition

[0811] In parallel, the emotion engine analyzes the user's facial expressions and voice in real time to obtain emotion data. The emotion engine uses an image analysis module (e.g., OpenCV) and an audio analysis module (e.g., Pyaudio).

[0812] From data transmission to analysis preparation

[0813] The device collects specifications, requirements, and emotion data and sends them to the server as an HTTP POST request. The server checks the integrity of the received data and, if invalid data is included, generates an error message and returns it to the device. If the integrity is confirmed, the device proceeds to the next step.

[0814] AI-based test pattern generation

[0815] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge. The user's emotional data provided by the emotion engine is also used for analysis; for example, if the user expresses "anxiety," a detailed test pattern is generated.

[0816] Test pattern conversion and transmission

[0817] The server receives the test patterns generated by the AI ​​engine and converts them into a format that is easy for humans to understand. This is often expressed in list format or tree structure. The converted data is temporarily stored in storage, then converted back into JSON format and sent to the device as an HTTP response.

[0818] Verify and correct users

[0819] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If there are correction requests, the user presses the "correct" button and the data is sent to the server again. The server again passes the data to the AI ​​engine and generates a new test pattern. During this time, the emotion engine continues to monitor the user's emotions.

[0820] Final confirmation and data storage

[0821] The user performs a final check, and if there are no problems, presses the "Confirm" button to confirm the test pattern. The server saves the finalized test pattern in the database. Once saving is complete, the server notifies the terminal and sends a completion message.

[0822] Examples and prompts

[0823] For example, suppose the emotion engine recognizes that the user appears anxious when the maximum speed of an autonomous vehicle is set to 120 km / h, the minimum speed to 0 km / h, and the braking distance to 3.5 m. In this case, the AI ​​engine generates a detailed test pattern. An example of a prompt sentence could be, "Please generate a vehicle operation test pattern with a maximum speed of 120 km / h, a minimum speed of 0 km / h, and a braking distance of 3.5 m. The driver appears anxious."

[0824] In this way, the system of the present invention enables the generation of highly accurate test patterns that take user emotions into consideration, thereby supporting the development of safer self-driving vehicles.

[0825] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0826] Step 1:

[0827] The user uses the terminal to input the specifications and requirements of the vehicle to be verified. The terminal screen displays a form for inputting maximum speed, minimum speed, braking distance, etc. When the user inputs this data and presses the submit button, the data is converted into JSON format. For example, the input data could be specification information such as "maximum speed: 120 km / h, minimum speed: 0 km / h, braking distance: 3.5 m."

[0828] Step 2:

[0829] The emotion engine analyzes the user's facial expressions and voice in real time and generates emotion data. The emotion engine captures the user's facial expressions and voice using the device's built-in camera and microphone. Images are processed using an image analysis library such as OpenCV, and audio is analyzed using an audio analysis library such as Pyaudio. An example of the generated emotion data is "Emotion: Anxiety."

[0830] Step 3:

[0831] The device converts the input specification and requirement data and the emotion data generated by the emotion engine into JSON format and sends it to the server as an HTTP POST request. An example of the data sent is as follows:

[0832] json

[0833] {

[0834] "specs": {

[0835] "max_speed": 120,

[0836] "min_speed": 0,

[0837] "braking_distance": 3.5

[0838] },

[0839] "emotion": "anxiety"

[0840] }

[0841] Step 4:

[0842] The server checks the integrity of the received data. It verifies that the JSON formatted data is correctly formed and that all required fields are included. If the data is inconsistent, the server generates an error message and returns it to the terminal. If the integrity is confirmed, it proceeds to the next step.

[0843] Step 5:

[0844] The server passes the consistent data to the AI ​​engine. The AI ​​engine refers to the database and expert knowledge base and generates quasi-normal and abnormal test patterns based on the user's input data. The emotion data provided by the emotion engine is also taken into consideration; for example, if the user expresses "anxiety," a detailed test pattern is generated. The AI ​​engine uses the generative AI model to generate test patterns based on the prompt sentence.

[0845] Step 6:

[0846] The server converts the test patterns received from the AI ​​engine into a format that is easy for humans to understand. The converted test patterns are temporarily stored in a list format or tree structure format. As a specific example, the following test patterns are generated:

[0847] Normal pattern: The vehicle is driven normally between 0km / h and 120km / h.

[0848] Quasi-normal pattern: The vehicle briefly exceeds 120 km / h but quickly returns to the normal range.

[0849] Abnormal pattern: When the vehicle exceeds 150 km / h, the brake system exhibits abnormal operation.

[0850] Step 7:

[0851] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any reference materials or supplementary explanations as needed.

[0852] Step 8:

[0853] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If there are correction requests, the user presses the "correct" button and the data including the corrections is sent again to the server. A specific example would be a correction such as "Maximum speed: 130 km / h."

[0854] Step 9:

[0855] The server then passes the data back to the AI ​​engine based on the requested corrections, generating a new test pattern. This takes into account the newly acquired emotion data. The new test pattern is then sent back to the device, where the user can view it on the screen.

[0856] Step 10:

[0857] The user performs a final check, and if there are no problems, presses the "Confirm" button to confirm the test pattern. The server saves the confirmed test pattern in the database. Once saving is complete, the server notifies the user and sends a completion message to the terminal. This completes processing for the entire system, and the terminal is ready for verification.

[0858] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0859] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0860] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0861] [Third embodiment]

[0862] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0863] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0864] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0865] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0866] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0867] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0868] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0869] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0870] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0871] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0872] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0873] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0874] The present invention is a system in which a user inputs the specifications and requirements of a verification target via a terminal and generates test patterns for quasi-normal and abnormal conditions using an AI engine. This system is composed of elements including a server, a terminal, and a user, and a detailed embodiment of the system is described below.

[0875] User Interaction

[0876] The user accesses the system using a terminal. A form is displayed on the terminal screen for entering the specifications and requirements of the tool and development equipment to be verified. The user enters the necessary information into this form and presses the "Submit" button.

[0877] Data transmission

[0878] The terminal converts the specifications and requirements data entered by the user into JSON format and sends it to the server as an HTTP POST request.

[0879] Data reception and preparation for analysis

[0880] The server processes the received JSON data, checks the data integrity, and detects invalid data. If invalid data is included, the server generates an error message and returns it to the terminal. If the integrity is confirmed, the data proceeds to the next step.

[0881] AI-based analysis

[0882] The server passes the data whose integrity has been confirmed to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge.

[0883] Test Pattern Generation

[0884] The server converts the test patterns generated by the AI ​​engine into a format that is easy for humans to understand, such as a list or tree structure. This data is then stored in temporary storage.

[0885] Send results

[0886] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any necessary supplementary explanations or links to reference materials.

[0887] User verification and correction

[0888] The terminal displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If correction requests are required, the user presses the "correct" button and resends the corrections to the server.

[0889] reanalysis

[0890] The server receives the correction request, passes the data to the AI ​​engine again, and regenerates the test pattern. The regenerated test pattern is then sent back to the device.

[0891] Final confirmation

[0892] The user makes a final check of the regenerated test pattern on the terminal, and if there are no problems, presses the "Confirm" button.

[0893] Data storage

[0894] The server permanently saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives this message and is ready to begin verification.

[0895] As a concrete example, consider the case of verifying the operation of a temperature sensor device. When the user inputs the specifications and operational requirements of the temperature sensor, the AI ​​engine generates the following test pattern.

[0896] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[0897] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[0898] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[0899] According to the present invention, regardless of the user's level of experience, high-quality test patterns can be generated efficiently, thereby improving the quality and efficiency of the development process.

[0900] The processing flow will be explained below.

[0901] Step 1:

[0902] The user accesses the system using a terminal. A form for entering the specifications and requirements of the tool and development equipment to be verified is displayed on the terminal screen. The user enters the necessary information into this form and presses the "Submit" button.

[0903] Step 2:

[0904] The terminal converts the specifications and requirements data entered by the user into JSON format and sends the converted JSON data to the server as an HTTP POST request.

[0905] Step 3:

[0906] The server processes the received JSON data. Specifically, it checks the data for consistency and detects invalid data. If invalid data is included, it generates an error message and returns it to the terminal. If consistency is confirmed, it proceeds to the next step.

[0907] Step 4:

[0908] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge.

[0909] Step 5:

[0910] The server receives the test patterns generated by the AI ​​engine, converts them into a format that is easy for humans to understand, and temporarily stores this data in storage.

[0911] Step 6:

[0912] The server then converts the converted test pattern back into JSON format and sends it to the terminal as an HTTP response, along with supplementary explanations and links to reference materials, if necessary.

[0913] Step 7:

[0914] The terminal displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If the user wants to submit a correction request, he or she presses the "Edit" button and resends the data including the corrections to the server.

[0915] Step 8:

[0916] Based on the received correction request, the server passes the data to the AI ​​engine again, generates a new test pattern, and sends the generated test pattern back to the device.

[0917] Step 9:

[0918] The terminal displays the received test pattern again, and the user performs a final check. If there are no problems, the user presses the "Confirm" button to confirm the test pattern.

[0919] Step 10:

[0920] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[0921] Example 1

[0922] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0923] Conventional test pattern generation methods require users to manually design test cases, which is time-consuming, labor-intensive, and prone to errors. Furthermore, because they rely on the user's experience and knowledge, it is difficult to generate test patterns of consistent quality. In particular, designing test patterns for quasi-normal and abnormal conditions requires advanced expertise. The present invention aims to solve these problems and provide an efficient, high-quality test pattern generation system.

[0924] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0925] In this invention, the server includes a means for a user to input specifications and requirements for the verification target via a terminal, a means for the terminal to convert the input data into JSON format and send it to the server as an HTTP POST request, and a means for the server to check the integrity of the received JSON data and pass the data to the AI ​​engine. This enables users to easily generate high-quality test patterns and improve the quality and efficiency of the development process.

[0926] "Terminal" means a computing device used by a User to input specifications and requirements.

[0927] The term "server" refers to a computer system that receives and processes data sent from a terminal.

[0928] "JSON format" is a standard for describing data in text format and is an abbreviation for JavaScript Object Notation.

[0929] "HTTP POST request" refers to the part of the HTTP protocol that allows a client to send data to a server.

[0930] "Integrity" refers to the property of ensuring that data is accurate and consistent.

[0931] "AI engine" refers to an artificial intelligence system that performs data analysis and test pattern generation.

[0932] A "database" refers to a system for efficiently storing and managing data.

[0933] "Expertise base" refers to a dataset that aggregates knowledge in a particular field of expertise.

[0934] "Test patterns" refer to scenarios or cases used to verify systems or equipment.

[0935] "Quasi-normal" refers to operating conditions that deviate slightly from normal conditions but do not pose a serious problem.

[0936] "Abnormal" refers to a situation in which a system or device malfunctions beyond its expected range.

[0937] "Temporary storage" refers to memory or disk space used to temporarily store data.

[0938] "Finish message" refers to a message that notifies the user that a process has been successfully completed.

[0939] MODE FOR CARRYING OUT THE INVENTION

[0940] This system allows users to input specifications and requirements for the verification target via a terminal, and the server processes the data and passes it to an AI engine, which then generates test patterns for quasi-normal and abnormal conditions. The system is composed of the following elements: a terminal, a server, and a user.

[0941] The user enters the specifications and operational requirements of a temperature sensor or other device into a form on the terminal. For example, for a temperature sensor, the user enters information such as the measurement range and response time. Once the input is complete, the user presses the "Submit" button.

[0942] The terminal converts this input data into JSON format. For example, if you enter "measurement range -20°C to 100°C" and "response time 1 second" as the specifications for a temperature sensor, this data will be converted as {"measurement range": "-20°C to 100°C", "response time": "1 second"}. This converted data is sent to the server as an HTTP POST request.

[0943] The server checks the integrity of the received JSON data. For example, it checks whether the data is invalid or missing. If it contains error data, the server generates an error message and returns it to the terminal. If the data is correct, it saves the data to proceed to the next step.

[0944] The server then passes the data, whose integrity has been confirmed, to the AI ​​engine, which then references the database and expert knowledge base. For example, the expert knowledge base contains past test data and existing technical literature. Based on this data, the AI ​​engine generates test patterns for quasi-normal and abnormal conditions.

[0945] The generated test patterns are converted by the server into a format that is easy for humans to understand, such as a list format or a tree structure, and this converted data is stored in temporary storage.

[0946] The server converts this data back into JSON format and sends it to the terminal as an HTTP response. The terminal displays the received test pattern on the screen. The user checks the displayed test pattern. If necessary, they can enter a correction request and press the "Edit" button, and the terminal will resend the corrections to the server.

[0947] The server receives the correction request and passes the data to the AI ​​engine again to regenerate the test pattern. This regenerated test pattern is also sent to the device again, and the user checks it. If there are no final problems, the user presses the "Confirm" button, and the final confirmed information is sent to the server.

[0948] The server permanently saves the confirmed data in the database and notifies the terminal that the saving is complete. The user receives this completion message and ends their use of the system.

[0949] As a concrete example, the following prompt sentences are input to the generative AI model to verify the operation of a temperature sensor device:

[0950] "The specifications and operating requirements for the temperature sensor device have been entered as follows:

[0951] Measurement range: -20°C to 100°C

[0952] Response time: 1 second

[0953] Based on this, generate a test pattern like this:

[0954] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[0955] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[0956] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[0957] The present invention enables users to efficiently generate high-quality test patterns, thereby improving the quality and efficiency of the development process.

[0958] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0959] Step 1:

[0960] The user uses the terminal to input the specifications and requirements of the object to be verified. The user enters the temperature sensor specifications (e.g., measurement range -20°C to 100°C, response time 1 second) into the form and presses the "Submit" button. The input data is collected by the terminal.

[0961] Input: User-entered specification and requirements data

[0962] Output: Input data collected on the terminal

[0963] Step 2:

[0964] The terminal converts the collected input data into JSON format, for example, {'Measurement range': '-20°C to 100°C', 'Response time': '1 second'}, and then sends it to the server as an HTTP POST request.

[0965] Input: Data entered by the user into the terminal

[0966] Output: Data converted to JSON format

[0967] Step 3:

[0968] The server receives the JSON data sent from the terminal and checks the integrity of the data. If invalid data is included, the server generates an error message and returns it to the terminal. If the data is confirmed to be valid, it proceeds to the next processing step.

[0969] Input: JSON data sent from the terminal

[0970] Output: Consistency checked data or error message

[0971] Step 4:

[0972] The server passes the data whose integrity has been confirmed to the AI ​​engine. For example, it provides measurement range and response time data as input to the AI ​​engine.

[0973] Input: Integrity checked data

[0974] Output: Data passed to the AI ​​engine

[0975] Step 5:

[0976] The AI ​​engine references a database and expert knowledge base to generate test patterns for quasi-normal and abnormal conditions, such as normal operation between 25°C and 30°C, and abnormal operation above 40°C.

[0977] Input: Data passed to the AI ​​engine

[0978] Output: Generated quasi-normal and abnormal test patterns

[0979] Step 6:

[0980] The server receives the test patterns generated by the AI ​​engine and converts them into a format that is easy for humans to understand (e.g., list format or tree structure). This data is stored in temporary storage.

[0981] Input: Test patterns generated by the AI ​​engine

[0982] Output: Test patterns converted into a human-readable format

[0983] Step 7:

[0984] The server converts the converted test pattern back into JSON format and sends it to the terminal as an HTTP response.

[0985] Input: Test patterns converted to a human-readable format

[0986] Output: Test patterns converted to JSON format

[0987] Step 8:

[0988] The terminal displays the received test pattern on the screen. The user checks the test pattern and inputs correction requests as necessary. Then, by pressing the "Correction" button, the terminal resends the correction request to the server.

[0989] Input: Test pattern sent to the terminal

[0990] Output: User correction request

[0991] Step 9:

[0992] The server receives the correction request, passes the data to the AI ​​engine again, and regenerates the test pattern. The regenerated test pattern is then sent back to the device.

[0993] Input: User requested correction

[0994] Output: Regenerated test pattern

[0995] Step 10:

[0996] The user checks the regenerated test pattern on the terminal and, if there are no problems, presses the "Confirm" button, which sends the confirmed test pattern to the server.

[0997] Input: Regenerated test pattern

[0998] Output: Final confirmation by user

[0999] Step 11:

[1000] The server permanently saves the finalized data in the database and notifies the terminal that the saving is complete. The user receives a completion message and ends their use of the system.

[1001] Input: Test pattern confirmed by the user

[1002] Output: Test patterns stored in the database and an end message

[1003] (Application example 1)

[1004] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1005] Conventional methods for verifying the operation of industrial robots require users to manually create numerous test patterns, which often leads to errors. Furthermore, generating abnormal test patterns is difficult, making it difficult to effectively perform abnormality testing for specific operational scenarios. This reduces the efficiency of ensuring the reliability and safety of industrial robots.

[1006] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1007] In this invention, the server includes: a means for a user to input specifications and requirements for the verification target via a terminal; a means for the terminal to transmit the input data to the server; a means for the server to verify the consistency of the received data and pass the data to the AI ​​engine; a means for the AI ​​engine to generate quasi-normal and abnormal test patterns by referring to a past database and an expert knowledge base; a means for converting the test patterns into a human-understandable format and transmitting the converted test patterns to the terminal; a means for the terminal to display the received test patterns and for the user to send a correction request; a means for the server to re-pass the data to the AI ​​engine based on the correction request and re-generate the test patterns; a means for inputting operational specifications and requirements for the industrial robot and generating test patterns; a means for displaying the generated test patterns and performing a final check; a means for saving the finalized test patterns to the server; a means for inputting prompt statements to a generative AI model and generating test patterns based on specific operational scenarios; a means for generating prompt statements for identifying operational scenarios of the industrial robot; a means for generating abnormal test patterns for the industrial robot using the generative AI model; and a means for evaluating the generated test patterns. This eliminates the need for users to manually create numerous test patterns, enabling accurate and efficient operational verification of industrial robots.

[1008] "User" refers to a user who uses the system to input specifications and requirements to be verified.

[1009] "Terminal" means a device used by a user to input specifications and requirements and communicate with a server.

[1010] A "server" is a device that receives data sent from a user via a terminal, processes the data, and checks the consistency of the data.

[1011] An "AI engine" is an algorithm that generates quasi-normal and abnormal test patterns by referencing a past database and expert knowledge base.

[1012] A "database" is a collection of information that stores past data and is used as a reference by an AI engine.

[1013] An "expertise base" is information that accumulates specialized knowledge in a specific field, and is used by the AI ​​engine as a reference when generating test patterns.

[1014] A "test pattern" is a specific scenario for verifying the behavior of the target system.

[1015] "Quasi-normal" refers to a situation or scenario that is nearly normal but contains some abnormalities.

[1016] An "abnormal situation" is a situation or scenario in which the subject of verification does not operate normally.

[1017] "Behavioral specifications" are requirements that define how the object to be verified should behave.

[1018] "Requirements" are conditions or standards that the object of verification must meet.

[1019] A "prompt" is an instruction sentence to be input to a generative AI model and is used to identify a specific behavior scenario.

[1020] A "generative AI model" is a trained algorithm that allows an AI engine to generate test patterns based on prompt sentences.

[1021] An "anomaly detection algorithm" is a specific computational method or program for detecting abnormal patterns.

[1022] This invention is a system that streamlines operational verification of industrial robots by allowing users to input specifications and requirements for the object to be verified via a terminal, and generating test patterns for quasi-normal and abnormal conditions using a server and an AI engine.

[1023] Users use devices such as smartphones and tablets to enter the operational specifications and requirements of the industrial robot to be verified into a form. The entered data is converted to JSON format by the device and sent to the server as an HTTP POST request.

[1024] The server checks the integrity of the received JSON data and verifies that it does not contain any invalid data. Once the integrity is confirmed, the server passes the data to the AI ​​engine, which then references its past database and expert knowledge base to generate quasi-normal and abnormal test patterns.

[1025] The generated test patterns are converted by the server into a human-readable format, usually expressed as a list or tree structure, and the converted data is stored in temporary storage.

[1026] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response. The user can check the received test pattern on the device and enter correction requests as necessary. If corrections are required, the user enters the corrections and sends it back to the server.

[1027] The server receives the correction request and passes the data to the AI ​​engine again to regenerate the test pattern. The regenerated test pattern is then sent back to the device for final confirmation by the user. When the user presses the "Confirm" button, the confirmed test pattern is permanently saved in the database by the server.

[1028] For example, consider the case of verifying an industrial robot's operational scenario. The user inputs the robot's operational specifications and requirements, such as temperature range, load capacity, and operational pattern. In this case, the AI ​​engine generates the following test patterns:

[1029] Normal condition: The robot operates normally within a temperature range of 20°C-30°C and moves the specified object accurately.

[1030] Quasi-normal pattern: Operation is not affected even if the ambient temperature temporarily exceeds 30°C.

[1031] Abnormal pattern: The robot begins to malfunction when the environmental temperature exceeds 50°C.

[1032] Examples of prompt sentences to be input to the generative AI model include the following:

[1033] "Generate test patterns to identify operating scenarios for industrial robot model XYZ-123. Specifications are temperature 0-50°C, humidity 20-80%, and load capacity up to 50kg."

[1034] "Please tell me the abnormality test pattern for the model XYZ-123 robot that includes a temperature sensor function."

[1035] The software used is Python and its libraries (requests, json), and the hardware is a smartphone or tablet connected to the internet.The AI ​​engine utilizes a generative AI model to efficiently generate test patterns.

[1036] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1037] Step 1:

[1038] The user inputs the specifications and requirements to be verified into the terminal, including the operating scenario of the industrial robot and environmental conditions (e.g., temperature range, humidity, load capacity). The input data is saved on the terminal.

[1039] Step 2:

[1040] The terminal converts the input data into JSON format. Specifically, it converts the specifications and requirements entered by the user into a JSON object and sends it to the server as an HTTP POST request. Here, the input data is serialized and sent.

[1041] Step 3:

[1042] The server receives the received JSON data and checks its integrity. The server parses the JSON data and checks for invalid data or defects. The result of the integrity check becomes the output data. If integrity is confirmed, proceed to the next step.

[1043] Step 4:

[1044] The server passes the data whose integrity has been confirmed to the AI ​​engine, which then references the database and expert knowledge base to generate test patterns for quasi-normal and abnormal conditions. In this process, the AI ​​engine analyzes the input data and makes predictions and generates patterns. The output is the generated test patterns.

[1045] Step 5:

[1046] The server converts the test patterns generated by the AI ​​engine into a format that is easy for humans to understand, including formats such as lists and tree structures. Specifically, it converts the data structure of the test patterns and saves them as output data.

[1047] Step 6:

[1048] The server reconverts the converted test pattern into JSON format and sends it to the terminal as an HTTP response. The server serializes the parsed data and prepares it for transmission. The terminal displays the received data on the screen.

[1049] Step 7:

[1050] The user checks the received test pattern on the terminal and inputs correction requests as necessary. The user evaluates the test pattern and inputs corrections if they find any errors or deficiencies. The correction requests are sent from the terminal to the server.

[1051] Step 8:

[1052] The server receives the correction request and passes the data to the AI ​​engine again to regenerate the test pattern. Reanalysis is performed based on the new input data, and new test patterns are generated. During this process, the AI ​​engine again refers to the database and expert knowledge base.

[1053] Step 9:

[1054] The user checks the regenerated test pattern on the terminal and presses the "Confirm" button if there are no problems. The final checked test pattern is sent to the server. The output is the final checked test pattern.

[1055] Step 10:

[1056] The server permanently saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user confirms the received message and is ready for verification.

[1057] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1058] The present invention enables the generation of more accurate test patterns by combining an emotion engine that recognizes the user's emotions with a system in which a user inputs the specifications and requirements of the object to be verified via a terminal and generates quasi-normal and abnormal test patterns using an AI engine. This system is composed of the elements of a server, a terminal, a user, and an emotion engine, and detailed embodiments are described below.

[1059] User Interaction

[1060] The user accesses the system using a terminal. A form is displayed on the terminal screen for entering the specifications and requirements of the tool to be verified and the development equipment. The user enters the necessary information into this form and presses the "Submit" button. In parallel, the emotion engine analyzes the user's facial expressions and voice, recognizing emotions in real time.

[1061] Data transmission

[1062] The device converts the specifications and requirements data entered by the user into JSON format, simultaneously collecting the emotion data recognized by the emotion engine, and sends this data to the server as an HTTP POST request.

[1063] Data reception and preparation for analysis

[1064] The server processes the received JSON data. Specifically, it checks the data for consistency and detects invalid data. If invalid data is included, it generates an error message and returns it to the terminal. If consistency is confirmed, it proceeds to the next step.

[1065] AI-based analysis

[1066] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge. The user's emotional data provided by the emotion engine is also used for analysis, and the difficulty and details of the test patterns are adjusted.

[1067] Test Pattern Generation

[1068] The server receives the test patterns generated by the AI ​​engine. The server converts the test patterns into a format that is easy for humans to understand. Specifically, they are often expressed in list format or tree structure. This data is temporarily stored in storage.

[1069] Send results

[1070] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any necessary supplementary explanations or links to reference materials.

[1071] User verification and correction

[1072] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. In parallel, the emotion engine continues to monitor the user's emotions. If the user wishes to send a correction request, they press the "Edit" button and the data including the corrections is resent to the server.

[1073] reanalysis

[1074] The server receives the correction request and passes the data to the AI ​​engine again to generate a new test pattern, taking into account the newly collected emotion data. The generated test pattern is then sent back to the device.

[1075] Final confirmation

[1076] The user makes a final check of the regenerated test pattern on the terminal, and if there are no problems, presses the "Confirm" button to confirm the test pattern.

[1077] Data storage

[1078] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[1079] As a concrete example, consider the case of verifying the operation of a temperature sensor device. If a user inputs the specifications and operational requirements of a temperature sensor and the emotion engine determines that the user is expressing "anxiety," the AI ​​engine generates a test pattern with more details or additional explanations. For example, it generates the following test pattern:

[1080] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[1081] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[1082] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[1083] According to the present invention, by utilizing the emotion engine, the user can generate more accurate test patterns, thereby realizing a more user-friendly and efficient development process.

[1084] The processing flow will be explained below.

[1085] Step 1:

[1086] The user accesses the system using a terminal. A form for entering the specifications and requirements of the tool and development equipment to be verified is displayed on the terminal screen. The user enters the necessary information into this form and presses the "Submit" button.

[1087] Step 2:

[1088] The device converts the specifications and requirements data entered by the user into JSON format. At the same time, the emotion engine analyzes the user's facial expressions and voice to recognize emotions in real time. The recognized emotion data is also included in the JSON format.

[1089] Step 3:

[1090] The device sends the converted JSON data of specifications and requirements and emotion data to the server as an HTTP POST request.

[1091] Step 4:

[1092] The server processes the received JSON data. Specifically, it first checks the data for consistency and detects invalid data. If invalid data is included, it generates an error message and returns it to the terminal.

[1093] Step 5:

[1094] The server passes the data whose integrity has been confirmed to the AI ​​engine, which then references the received database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge.

[1095] Step 6:

[1096] When generating test patterns, the AI ​​engine takes into account the user's emotional data provided by the emotion engine. For example, if the user is feeling "anxious" or "stressed," the AI ​​engine will adjust the explanation of the test pattern to be more detailed or simpler.

[1097] Step 7:

[1098] The server receives the test patterns generated by the AI ​​engine, converts them into a format that is easy for humans to understand, and temporarily stores the test patterns in storage.

[1099] Step 8:

[1100] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any supplementary explanations or links to reference materials, if necessary.

[1101] Step 9:

[1102] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. In parallel, the emotion engine continues to monitor the user's emotions.

[1103] Step 10:

[1104] When the user wishes to send a correction request, the data including the corrections is resent to the server by pressing the "correct" button.

[1105] Step 11:

[1106] The server receives the correction request and passes the data to the AI ​​engine again to generate a new test pattern, taking into account the recollected emotion data. The generated test pattern is then sent back to the device.

[1107] Step 12:

[1108] The terminal displays the received test pattern again, and the user performs a final check. If there are no problems, the user presses the "Confirm" button to confirm the test pattern.

[1109] Step 13:

[1110] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the terminal and sends a completion message.

[1111] Step 14:

[1112] The user receives a completion message, and the emotion engine also collects and saves the final emotion data. Verification preparation is complete, and the user is ready to proceed to the next step.

[1113] As a concrete example, consider the case of verifying the operation of a temperature sensor device. If the user inputs the specifications and operational requirements of the temperature sensor and the emotion engine detects "anxiety," the AI ​​engine generates a test pattern with a more detailed explanation. On the other hand, if the emotion is recognized as "calm," it generates a standard test pattern. For example, the following test pattern may be generated:

[1114] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[1115] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[1116] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[1117] This specific flow provides optimal test patterns according to the user's emotions, realizing more efficient and high-quality verification.

[1118] Example 2

[1119] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1120] Conventional test pattern generation systems generate test patterns based on specifications and requirements entered by the user, but the generated test patterns do not always reflect the user's intentions or emotions. Furthermore, particularly for abnormality test patterns, flexible adjustments that take into account the user's emotions and level of understanding are required. However, conventional systems were unable to achieve this, making it difficult to achieve a user-friendly and efficient development process.

[1121] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1122] In this invention, the server includes means for converting data input by the terminal into JSON format and sending it to the server, means for checking the consistency of the received data and, if invalid data is detected, generating an error message and sending it to the terminal, and means for passing the consistent data to the AI ​​engine. This enables the AI ​​engine to refer to the past database and expert knowledge base and generate quasi-normal and abnormal test patterns that take user emotion data into consideration.

[1123] A "terminal" is an electronic device used by a user to input specifications and requirements for a verification target, and is used to input, send, receive, and display data.

[1124] A "server" is a computer system that receives data sent from a terminal, checks the integrity of the data, detects fraudulent data, and provides the data to the AI ​​engine.

[1125] An "AI engine" is a program that incorporates artificial intelligence technology to generate quasi-normal and abnormal test patterns by referencing past databases and expert knowledge bases.

[1126] The "emotion engine" is a program that incorporates technology that analyzes the user's facial expressions and voice input and recognizes emotions in real time.

[1127] A "specification" is a document or data that describes in detail the functions and characteristics of the object to be verified.

[1128] "Requirements" are documents or data that describe the conditions and constraints that the verification target must satisfy.

[1129] "JSON format" is an abbreviation for JavaScript Object Notation, and is a data exchange format that represents structured text data in a format that is easy for humans to read and computers to analyze.

[1130] An "HTTP POST request" is a request format for sending data from a client (terminal) to a server using the POST method of the Hypertext Transfer Protocol.

[1131] "Integrity check" is the process of verifying whether the received data is formally correct and contains all required fields.

[1132] "Invalid data" refers to data that cannot be processed normally, such as data that has an incorrect data format or is missing required fields.

[1133] A "test pattern" refers to a scenario or case for verifying the behavior of a system under specific conditions.

[1134] A "quasi-normal" situation refers to a situation in which the system is temporarily placed in an unstable state, but is expected to return to a normal state.

[1135] "Abnormal situation" refers to a situation in which the system is placed in an abnormal condition and is expected to not function normally.

[1136] "Emotion data" is data that indicates the user's emotional state and is obtained through facial expression and voice analysis.

[1137] "Storage" refers to a storage device for temporarily or permanently storing data or information.

[1138] The "list format" is a format in which data is arranged in bullet points.

[1139] A "tree structure" is a format in which data is arranged hierarchically, and is a structure of nodes (data elements) that have parent-child relationships.

[1140] An "HTTP response" is a response message sent by a server in response to a request from a client.

[1141] This invention enables the generation of more accurate test patterns by combining an emotion engine that recognizes the user's emotions with a system in which a user inputs the specifications and requirements of the object to be verified via a terminal and generates test patterns for quasi-normal and abnormal conditions using an AI engine. This system is composed of the following elements: a server, a terminal, a user, and an emotion engine.

[1142] Hardware and software used

[1143] Terminal: An electronic device used by a user to input specifications and requirements, such as a personal computer or smartphone.

[1144] Server: A computer system that processes data reception, integrity checks, AI analysis, data storage, etc.

[1145] AI engine: A program that implements machine learning algorithms and runs on a high-performance GPU (Graphics Processing Unit) server.

[1146] Emotion engine: A software component that analyzes the user's facial expressions and voice to generate emotion data.

[1147] Natural language description of the program

[1148] 1. User input: The user accesses the system using a terminal and enters the specifications and requirements to be verified into the displayed form. Once the input is complete, the emotion engine captures the user's facial expressions and voice to recognize their emotions.

[1149] 2. Data transmission: The device converts the input specifications and requirements data into JSON format and sends it to the server as an HTTP POST request along with the emotion data obtained from the emotion engine.

[1150] 3. Data integrity check: The server checks the integrity of the received data. If invalid data is included, it generates an error message and returns it to the terminal. If the data is confirmed to be valid, it proceeds to the next step.

[1151] 4. AI analysis: The server passes the consistent data to the AI ​​engine, which then refers to the database and expert knowledge base to generate quasi-normal and abnormal test patterns. The AI ​​engine also takes into account the emotional data provided by the emotion engine to adjust the difficulty and details of the test patterns.

[1152] 5. Test pattern generation: The server receives the test patterns generated by the AI ​​engine and converts them into a format that is easy for humans to understand. The converted data is temporarily stored in storage.

[1153] 6. Result notification: The server reconverts the converted test pattern into JSON format and sends it to the terminal as an HTTP response, including supplementary explanations and links to reference materials as needed.

[1154] 7. User confirmation and correction: The device displays the received test pattern on the screen. The user confirms the displayed test pattern and inputs correction requests as necessary. The emotion engine continues to monitor the user's emotions and updates the emotion data as necessary.

[1155] 8. Re-analysis: The server receives the correction request and passes the data to the AI ​​engine again to generate a new test pattern, taking into account the newly collected emotion data. The generated test pattern is then sent back to the device.

[1156] 9. Final confirmation: The user checks the regenerated test pattern on the terminal one last time, and if there are no problems, presses the "Confirm" button to confirm the test pattern.

[1157] 10. Data saving: The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[1158] Specific examples

[1159] As a concrete example, consider the case of verifying the operation of a temperature sensor device. If a user inputs the specifications and operational requirements of the temperature sensor and the emotion engine determines that the user is expressing "anxiety," the AI ​​engine generates a test pattern with more details or additional explanations.

[1160] Example of generated test pattern

[1161] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[1162] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[1163] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[1164] Prompt Sentence Examples

[1165] "To verify the operation of a temperature sensor device, please generate test patterns for normal, quasi-normal, and abnormal conditions. The specifications and requirements are as follows."

[1166] "Generate highly accurate test patterns based on user input and emotion data."

[1167] The present invention enables highly accurate test pattern generation that takes user feelings into consideration, thereby realizing a user-friendly and efficient development process.

[1168] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1169] Step 1: User Input

[1170] Users access the system using a terminal and enter the specifications and requirements to be verified into the displayed form. This involves entering detailed information using text areas and drop-down lists. At the same time, the terminal's built-in camera and microphone capture the user's facial expressions and voice, which are then analyzed by the emotion engine to generate emotion data in real time.

[1171] Input: The user inputs specifications and requirements, and the device captures facial expressions and voice

[1172] Output: Input specifications, requirements, and sentiment data

[1173] Step 2: Sending data

[1174] The device converts the specifications and requirements data entered by the user into JSON format, and simultaneously collects the emotion data recognized by the emotion engine, consolidates them into a single data packet, and sends the data packet to the server as an HTTP POST request.

[1175] Input: Input specifications, requirements, and sentiment data

[1176] Output: JSON formatted data packet

[1177] Step 3: Verify data integrity

[1178] The server analyzes the received data packet and checks the integrity of the data. Specifically, it checks the JSON format, confirms the existence of required fields, and detects invalid data. If invalid data is included, the server generates an error message and returns it to the terminal. If the data is normal, it proceeds to the next step.

[1179] Input: JSON formatted data packet

[1180] Output: Data that has been verified to be consistent, or an error message

[1181] Step 4: Analysis by AI engine

[1182] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and knowledge. Emotional data is also taken into account, and the difficulty and details of the test patterns are adjusted based on the user's emotional state.

[1183] Input: Integrity checked data

[1184] Output: Generated quasi-normal and abnormal test patterns

[1185] Step 5: Formatting and temporarily saving the test pattern

[1186] The server converts the test patterns received from the AI ​​engine into a format that is easy for humans to understand, such as a list format or tree structure. The converted data is temporarily stored in storage.

[1187] Input: Generated test pattern

[1188] Output: Formatted test pattern

[1189] Step 6: Notification of results

[1190] The server then converts the formatted test pattern back into JSON format and sends it to the device as an HTTP response, adding any necessary supplementary explanations or links to reference material.

[1191] Input: Formatted test pattern

[1192] Output: Test pattern in JSON format sent to the terminal

[1193] Step 7: User review and correction

[1194] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. At the same time, the emotion engine continues to monitor the user's emotions and updates the data as necessary.

[1195] Input: Test pattern in JSON format sent to the terminal

[1196] Output: User-entered correction requests

[1197] Step 8: Reprocessing

[1198] The server receives the correction request and passes the data back to the AI ​​engine to generate a new test pattern, taking into account the corrections and the newly collected emotion data. The generated test pattern is then sent back to the device.

[1199] Input: The correction request entered by the user

[1200] Output: Regenerated test pattern

[1201] Step 9: Final check

[1202] The user makes a final check of the regenerated test pattern on the terminal, and if there are no problems, presses the "Confirm" button to confirm the test pattern.

[1203] Input: Regenerated test pattern

[1204] Output: User-defined test pattern

[1205] Step 10: Save Data

[1206] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[1207] Input: User-defined test pattern

[1208] Output: Test pattern stored in the database, end message sent to the terminal

[1209] (Application example 2)

[1210] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1211] In the development of autonomous vehicles, it is necessary to create highly accurate test patterns based on specifications and requirements so that drivers can use the vehicle with confidence. However, current test pattern generation systems generate test patterns with insufficient accuracy that takes into account the driver's emotions, making it impossible to alleviate driver anxiety. Another issue is the lack of systems that can flexibly respond to the driver's emotions when checking and modifying test patterns.

[1212] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to input specifications and requirements for the verification target via a terminal, means for the terminal to transmit the input data to the server, means for the server to verify the consistency of the received data and pass the data to the AI ​​engine, means for the AI ​​engine to generate quasi-normal and abnormal test patterns by referring to a past database and an expert knowledge base, means for the AI ​​engine to adjust the difficulty and details of the test patterns based on the user's emotional data using an emotion engine that recognizes the user's emotions in real time, means for converting the test patterns into a format that is easy for humans to understand and transmitting them to the terminal, means for the terminal to display the received test patterns and for the user to send a correction request, and means for the server to re-pass the data to the AI ​​engine based on the correction request and regenerate the test patterns. This enables the generation of highly accurate test patterns based on the driver's emotions, making it possible to provide a system that reduces driver anxiety and allows for flexible response.

[1213] A "terminal" is an electronic device that allows a user to input specifications and requirements, and is a device that communicates with a server.

[1214] The "server" is a central device that receives input data and generates and transmits test patterns using an AI engine and emotion engine.

[1215] An "AI engine" is an artificial intelligence system that references a database and expert knowledge base to generate test patterns for quasi-normal and abnormal conditions.

[1216] The "emotion engine" is a system that analyzes the user's facial expressions and voice in real time to recognize the user's emotions.

[1217] "Specifications and requirements" are data that indicate the detailed conditions and required performance of the product or system being verified.

[1218] A "test pattern" is a test pattern used to check the operation and performance of the object to be verified based on specifications and requirements.

[1219] A "database" is a repository of information that stores past data and specialized knowledge.

[1220] An "expertise base" is information that systematically compiles knowledge in a particular field.

[1221] "Real-time" refers to the time characteristic of being able to respond immediately to user operations and emotional changes.

[1222] "Integrity" means making sure that data is accurate and consistent.

[1223] An "anomaly detection algorithm" is a computational method for detecting abnormal behavior or situations.

[1224] This invention relates to a test pattern generation system for autonomous vehicles. Users input specifications and requirements via a terminal, and an AI engine is used to generate test patterns for quasi-normal and abnormal conditions. By combining this with an emotion engine, it is possible to generate test patterns with even greater accuracy. This system is composed of the following elements: a server, a terminal, a user, and an emotion engine.

[1225] Basic program structure

[1226] Data collection

[1227] Users access the system using a terminal and input their specifications and requirements, which can include specifications such as maximum speed, minimum speed, braking distance, etc. These data are finally converted into JSON format.

[1228] emotion recognition

[1229] In parallel, the emotion engine analyzes the user's facial expressions and voice in real time to obtain emotion data. The emotion engine uses an image analysis module (e.g., OpenCV) and an audio analysis module (e.g., Pyaudio).

[1230] From data transmission to analysis preparation

[1231] The device collects specifications, requirements, and emotion data and sends them to the server as an HTTP POST request. The server checks the integrity of the received data and, if invalid data is included, generates an error message and returns it to the device. If the integrity is confirmed, the device proceeds to the next step.

[1232] AI-based test pattern generation

[1233] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge. The user's emotional data provided by the emotion engine is also used for analysis; for example, if the user expresses "anxiety," a detailed test pattern is generated.

[1234] Test pattern conversion and transmission

[1235] The server receives the test patterns generated by the AI ​​engine and converts them into a format that is easy for humans to understand. This is often expressed in list format or tree structure. The converted data is temporarily stored in storage, then converted back into JSON format and sent to the device as an HTTP response.

[1236] Verify and correct users

[1237] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If there are correction requests, the user presses the "correct" button and the data is sent to the server again. The server again passes the data to the AI ​​engine and generates a new test pattern. During this time, the emotion engine continues to monitor the user's emotions.

[1238] Final confirmation and data storage

[1239] The user performs a final check, and if there are no problems, presses the "Confirm" button to confirm the test pattern. The server saves the finalized test pattern in the database. Once saving is complete, the server notifies the terminal and sends a completion message.

[1240] Examples and prompts

[1241] For example, suppose the emotion engine recognizes that the user appears anxious when the maximum speed of an autonomous vehicle is set to 120 km / h, the minimum speed to 0 km / h, and the braking distance to 3.5 m. In this case, the AI ​​engine generates a detailed test pattern. An example of a prompt sentence could be, "Please generate a vehicle operation test pattern with a maximum speed of 120 km / h, a minimum speed of 0 km / h, and a braking distance of 3.5 m. The driver appears anxious."

[1242] In this way, the system of the present invention enables the generation of highly accurate test patterns that take user emotions into consideration, thereby supporting the development of safer self-driving vehicles.

[1243] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1244] Step 1:

[1245] The user uses the terminal to input the specifications and requirements of the vehicle to be verified. The terminal screen displays a form for inputting maximum speed, minimum speed, braking distance, etc. When the user inputs this data and presses the submit button, the data is converted into JSON format. For example, the input data could be specification information such as "maximum speed: 120 km / h, minimum speed: 0 km / h, braking distance: 3.5 m."

[1246] Step 2:

[1247] The emotion engine analyzes the user's facial expressions and voice in real time and generates emotion data. The emotion engine captures the user's facial expressions and voice using the device's built-in camera and microphone. Images are processed using an image analysis library such as OpenCV, and audio is analyzed using an audio analysis library such as Pyaudio. An example of the generated emotion data is "Emotion: Anxiety."

[1248] Step 3:

[1249] The device converts the input specification and requirement data and the emotion data generated by the emotion engine into JSON format and sends it to the server as an HTTP POST request. An example of the data sent is as follows:

[1250] json

[1251] {

[1252] "specs": {

[1253] "max_speed": 120,

[1254] "min_speed": 0,

[1255] "braking_distance": 3.5

[1256] },

[1257] "emotion": "anxiety"

[1258] }

[1259] Step 4:

[1260] The server checks the integrity of the received data. It verifies that the JSON formatted data is correctly formed and that all required fields are included. If the data is inconsistent, the server generates an error message and returns it to the terminal. If the integrity is confirmed, it proceeds to the next step.

[1261] Step 5:

[1262] The server passes the consistent data to the AI ​​engine. The AI ​​engine refers to the database and expert knowledge base and generates quasi-normal and abnormal test patterns based on the user's input data. The emotion data provided by the emotion engine is also taken into consideration; for example, if the user expresses "anxiety," a detailed test pattern is generated. The AI ​​engine uses the generative AI model to generate test patterns based on the prompt sentence.

[1263] Step 6:

[1264] The server converts the test patterns received from the AI ​​engine into a format that is easy for humans to understand. The converted test patterns are temporarily stored in a list format or tree structure format. As a specific example, the following test patterns are generated:

[1265] Normal pattern: The vehicle is driven normally between 0km / h and 120km / h.

[1266] Quasi-normal pattern: The vehicle briefly exceeds 120 km / h but quickly returns to the normal range.

[1267] Abnormal pattern: When the vehicle exceeds 150 km / h, the brake system exhibits abnormal operation.

[1268] Step 7:

[1269] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any reference materials or supplementary explanations as needed.

[1270] Step 8:

[1271] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If there are correction requests, the user presses the "correct" button and the data including the corrections is sent again to the server. A specific example would be a correction such as "Maximum speed: 130 km / h."

[1272] Step 9:

[1273] The server then passes the data back to the AI ​​engine based on the requested corrections, generating a new test pattern. This takes into account the newly acquired emotion data. The new test pattern is then sent back to the device, where the user can view it on the screen.

[1274] Step 10:

[1275] The user performs a final check, and if there are no problems, presses the "Confirm" button to confirm the test pattern. The server saves the confirmed test pattern in the database. Once saving is complete, the server notifies the user and sends a completion message to the terminal. This completes processing for the entire system, and the terminal is ready for verification.

[1276] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1277] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1278] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1279] [Fourth embodiment]

[1280] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1281] 7, a 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.

[1282] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1283] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1284] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1285] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1286] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1287] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1288] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1289] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1290] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1291] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1292] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1293] The present invention is a system in which a user inputs the specifications and requirements of a verification target via a terminal and generates test patterns for quasi-normal and abnormal conditions using an AI engine. This system is composed of elements including a server, a terminal, and a user, and a detailed embodiment of the system is described below.

[1294] User Interaction

[1295] The user accesses the system using a terminal. A form is displayed on the terminal screen for entering the specifications and requirements of the tool and development equipment to be verified. The user enters the necessary information into this form and presses the "Submit" button.

[1296] Data transmission

[1297] The terminal converts the specifications and requirements data entered by the user into JSON format and sends it to the server as an HTTP POST request.

[1298] Data reception and preparation for analysis

[1299] The server processes the received JSON data, checks the data integrity, and detects invalid data. If invalid data is included, the server generates an error message and returns it to the terminal. If the integrity is confirmed, the data proceeds to the next step.

[1300] AI-based analysis

[1301] The server passes the data whose integrity has been confirmed to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge.

[1302] Test Pattern Generation

[1303] The server converts the test patterns generated by the AI ​​engine into a format that is easy for humans to understand, such as a list or tree structure. This data is then stored in temporary storage.

[1304] Send results

[1305] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any necessary supplementary explanations or links to reference materials.

[1306] User verification and correction

[1307] The terminal displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If correction requests are required, the user presses the "correct" button and resends the corrections to the server.

[1308] reanalysis

[1309] The server receives the correction request, passes the data to the AI ​​engine again, and regenerates the test pattern. The regenerated test pattern is then sent back to the device.

[1310] Final confirmation

[1311] The user makes a final check of the regenerated test pattern on the terminal, and if there are no problems, presses the "Confirm" button.

[1312] Data storage

[1313] The server permanently saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives this message and is ready to begin verification.

[1314] As a concrete example, consider the case of verifying the operation of a temperature sensor device. When the user inputs the specifications and operational requirements of the temperature sensor, the AI ​​engine generates the following test pattern.

[1315] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[1316] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[1317] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[1318] According to the present invention, regardless of the user's level of experience, high-quality test patterns can be generated efficiently, thereby improving the quality and efficiency of the development process.

[1319] The processing flow will be explained below.

[1320] Step 1:

[1321] The user accesses the system using a terminal. A form for entering the specifications and requirements of the tool and development equipment to be verified is displayed on the terminal screen. The user enters the necessary information into this form and presses the "Submit" button.

[1322] Step 2:

[1323] The terminal converts the specifications and requirements data entered by the user into JSON format and sends the converted JSON data to the server as an HTTP POST request.

[1324] Step 3:

[1325] The server processes the received JSON data. Specifically, it checks the data for consistency and detects invalid data. If invalid data is included, it generates an error message and returns it to the terminal. If consistency is confirmed, it proceeds to the next step.

[1326] Step 4:

[1327] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge.

[1328] Step 5:

[1329] The server receives the test patterns generated by the AI ​​engine, converts them into a format that is easy for humans to understand, and temporarily stores this data in storage.

[1330] Step 6:

[1331] The server then converts the converted test pattern back into JSON format and sends it to the terminal as an HTTP response, along with supplementary explanations and links to reference materials, if necessary.

[1332] Step 7:

[1333] The terminal displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If the user wants to submit a correction request, he or she presses the "Edit" button and resends the data including the corrections to the server.

[1334] Step 8:

[1335] Based on the received correction request, the server passes the data to the AI ​​engine again, generates a new test pattern, and sends the generated test pattern back to the device.

[1336] Step 9:

[1337] The terminal displays the received test pattern again, and the user performs a final check. If there are no problems, the user presses the "Confirm" button to confirm the test pattern.

[1338] Step 10:

[1339] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[1340] Example 1

[1341] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1342] Conventional test pattern generation methods require users to manually design test cases, which is time-consuming, labor-intensive, and prone to errors. Furthermore, because they rely on the user's experience and knowledge, it is difficult to generate test patterns of consistent quality. In particular, designing test patterns for quasi-normal and abnormal conditions requires advanced expertise. The present invention aims to solve these problems and provide an efficient, high-quality test pattern generation system.

[1343] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1344] In this invention, the server includes a means for a user to input specifications and requirements for the verification target via a terminal, a means for the terminal to convert the input data into JSON format and send it to the server as an HTTP POST request, and a means for the server to check the integrity of the received JSON data and pass the data to the AI ​​engine. This enables users to easily generate high-quality test patterns and improve the quality and efficiency of the development process.

[1345] "Terminal" means a computing device used by a User to input specifications and requirements.

[1346] The term "server" refers to a computer system that receives and processes data sent from a terminal.

[1347] "JSON format" is a standard for describing data in text format and is an abbreviation for JavaScript Object Notation.

[1348] "HTTP POST request" refers to the part of the HTTP protocol that allows a client to send data to a server.

[1349] "Integrity" refers to the property of ensuring that data is accurate and consistent.

[1350] "AI engine" refers to an artificial intelligence system that performs data analysis and test pattern generation.

[1351] A "database" refers to a system for efficiently storing and managing data.

[1352] "Expertise base" refers to a dataset that aggregates knowledge in a particular field of expertise.

[1353] "Test patterns" refer to scenarios or cases used to verify systems or equipment.

[1354] "Quasi-normal" refers to operating conditions that deviate slightly from normal conditions but do not pose a serious problem.

[1355] "Abnormal" refers to a situation in which a system or device malfunctions beyond its expected range.

[1356] "Temporary storage" refers to memory or disk space used to temporarily store data.

[1357] "Finish message" refers to a message that notifies the user that a process has been successfully completed.

[1358] MODE FOR CARRYING OUT THE INVENTION

[1359] This system allows users to input specifications and requirements for the verification target via a terminal, and the server processes the data and passes it to an AI engine, which then generates test patterns for quasi-normal and abnormal conditions. The system is composed of the following elements: a terminal, a server, and a user.

[1360] The user enters the specifications and operational requirements of a temperature sensor or other device into a form on the terminal. For example, for a temperature sensor, the user enters information such as the measurement range and response time. Once the input is complete, the user presses the "Submit" button.

[1361] The terminal converts this input data into JSON format. For example, if you enter "measurement range -20°C to 100°C" and "response time 1 second" as the specifications for a temperature sensor, this data will be converted as {"measurement range": "-20°C to 100°C", "response time": "1 second"}. This converted data is sent to the server as an HTTP POST request.

[1362] The server checks the integrity of the received JSON data. For example, it checks whether the data is invalid or missing. If it contains error data, the server generates an error message and returns it to the terminal. If the data is correct, it saves the data to proceed to the next step.

[1363] The server then passes the data, whose integrity has been confirmed, to the AI ​​engine, which then references the database and expert knowledge base. For example, the expert knowledge base contains past test data and existing technical literature. Based on this data, the AI ​​engine generates test patterns for quasi-normal and abnormal conditions.

[1364] The generated test patterns are converted by the server into a format that is easy for humans to understand, such as a list format or a tree structure, and this converted data is stored in temporary storage.

[1365] The server converts this data back into JSON format and sends it to the terminal as an HTTP response. The terminal displays the received test pattern on the screen. The user checks the displayed test pattern. If necessary, they can enter a correction request and press the "Edit" button, and the terminal will resend the corrections to the server.

[1366] The server receives the correction request and passes the data to the AI ​​engine again to regenerate the test pattern. This regenerated test pattern is also sent to the device again, and the user checks it. If there are no final problems, the user presses the "Confirm" button, and the final confirmed information is sent to the server.

[1367] The server permanently saves the confirmed data in the database and notifies the terminal that the saving is complete. The user receives this completion message and ends their use of the system.

[1368] As a concrete example, the following prompt sentences are input to the generative AI model to verify the operation of a temperature sensor device:

[1369] "The specifications and operating requirements for the temperature sensor device have been entered as follows:

[1370] Measurement range: -20°C to 100°C

[1371] Response time: 1 second

[1372] Based on this, generate a test pattern like this:

[1373] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[1374] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[1375] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[1376] The present invention enables users to efficiently generate high-quality test patterns, thereby improving the quality and efficiency of the development process.

[1377] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1378] Step 1:

[1379] The user uses the terminal to input the specifications and requirements of the object to be verified. The user enters the temperature sensor specifications (e.g., measurement range -20°C to 100°C, response time 1 second) into the form and presses the "Submit" button. The input data is collected by the terminal.

[1380] Input: User-entered specification and requirements data

[1381] Output: Input data collected on the terminal

[1382] Step 2:

[1383] The terminal converts the collected input data into JSON format, for example, {'Measurement range': '-20°C to 100°C', 'Response time': '1 second'}, and then sends it to the server as an HTTP POST request.

[1384] Input: Data entered by the user into the terminal

[1385] Output: Data converted to JSON format

[1386] Step 3:

[1387] The server receives the JSON data sent from the terminal and checks the integrity of the data. If invalid data is included, the server generates an error message and returns it to the terminal. If the data is confirmed to be valid, it proceeds to the next processing step.

[1388] Input: JSON data sent from the terminal

[1389] Output: Consistency checked data or error message

[1390] Step 4:

[1391] The server passes the data whose integrity has been confirmed to the AI ​​engine. For example, it provides measurement range and response time data as input to the AI ​​engine.

[1392] Input: Integrity checked data

[1393] Output: Data passed to the AI ​​engine

[1394] Step 5:

[1395] The AI ​​engine references a database and expert knowledge base to generate test patterns for quasi-normal and abnormal conditions, such as normal operation between 25°C and 30°C, and abnormal operation above 40°C.

[1396] Input: Data passed to the AI ​​engine

[1397] Output: Generated quasi-normal and abnormal test patterns

[1398] Step 6:

[1399] The server receives the test patterns generated by the AI ​​engine and converts them into a format that is easy for humans to understand (e.g., list format or tree structure). This data is stored in temporary storage.

[1400] Input: Test patterns generated by the AI ​​engine

[1401] Output: Test patterns converted into a human-readable format

[1402] Step 7:

[1403] The server converts the converted test pattern back into JSON format and sends it to the terminal as an HTTP response.

[1404] Input: Test patterns converted to a human-readable format

[1405] Output: Test patterns converted to JSON format

[1406] Step 8:

[1407] The terminal displays the received test pattern on the screen. The user checks the test pattern and inputs correction requests as necessary. Then, by pressing the "Correction" button, the terminal resends the correction request to the server.

[1408] Input: Test pattern sent to the terminal

[1409] Output: User correction request

[1410] Step 9:

[1411] The server receives the correction request, passes the data to the AI ​​engine again, and regenerates the test pattern. The regenerated test pattern is then sent back to the device.

[1412] Input: User requested correction

[1413] Output: Regenerated test pattern

[1414] Step 10:

[1415] The user checks the regenerated test pattern on the terminal and, if there are no problems, presses the "Confirm" button, which sends the confirmed test pattern to the server.

[1416] Input: Regenerated test pattern

[1417] Output: Final confirmation by user

[1418] Step 11:

[1419] The server permanently saves the finalized data in the database and notifies the terminal that the saving is complete. The user receives a completion message and ends their use of the system.

[1420] Input: Test pattern confirmed by the user

[1421] Output: Test patterns stored in the database and an end message

[1422] (Application example 1)

[1423] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1424] Conventional methods for verifying the operation of industrial robots require users to manually create numerous test patterns, which often leads to errors. Furthermore, generating abnormal test patterns is difficult, making it difficult to effectively perform abnormality testing for specific operational scenarios. This reduces the efficiency of ensuring the reliability and safety of industrial robots.

[1425] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1426] In this invention, the server includes: a means for a user to input specifications and requirements for the verification target via a terminal; a means for the terminal to transmit the input data to the server; a means for the server to verify the consistency of the received data and pass the data to the AI ​​engine; a means for the AI ​​engine to generate quasi-normal and abnormal test patterns by referring to a past database and an expert knowledge base; a means for converting the test patterns into a human-understandable format and transmitting the converted test patterns to the terminal; a means for the terminal to display the received test patterns and for the user to send a correction request; a means for the server to re-pass the data to the AI ​​engine based on the correction request and re-generate the test patterns; a means for inputting operational specifications and requirements for the industrial robot and generating test patterns; a means for displaying the generated test patterns and performing a final check; a means for saving the finalized test patterns to the server; a means for inputting prompt statements to a generative AI model and generating test patterns based on specific operational scenarios; a means for generating prompt statements for identifying operational scenarios of the industrial robot; a means for generating abnormal test patterns for the industrial robot using the generative AI model; and a means for evaluating the generated test patterns. This eliminates the need for users to manually create numerous test patterns, enabling accurate and efficient operational verification of industrial robots.

[1427] "User" refers to a user who uses the system to input specifications and requirements to be verified.

[1428] "Terminal" means a device used by a user to input specifications and requirements and communicate with a server.

[1429] A "server" is a device that receives data sent from a user via a terminal, processes the data, and checks the consistency of the data.

[1430] An "AI engine" is an algorithm that generates quasi-normal and abnormal test patterns by referencing a past database and expert knowledge base.

[1431] A "database" is a collection of information that stores past data and is used as a reference by an AI engine.

[1432] An "expertise base" is information that accumulates specialized knowledge in a specific field, and is used by the AI ​​engine as a reference when generating test patterns.

[1433] A "test pattern" is a specific scenario for verifying the behavior of the target system.

[1434] "Quasi-normal" refers to a situation or scenario that is nearly normal but contains some abnormalities.

[1435] An "abnormal situation" is a situation or scenario in which the subject of verification does not operate normally.

[1436] "Behavioral specifications" are requirements that define how the object to be verified should behave.

[1437] "Requirements" are conditions or standards that the object of verification must meet.

[1438] A "prompt" is an instruction sentence to be input to a generative AI model and is used to identify a specific behavior scenario.

[1439] A "generative AI model" is a trained algorithm that allows an AI engine to generate test patterns based on prompt sentences.

[1440] An "anomaly detection algorithm" is a specific computational method or program for detecting abnormal patterns.

[1441] This invention is a system that streamlines operational verification of industrial robots by allowing users to input specifications and requirements for the object to be verified via a terminal, and generating test patterns for quasi-normal and abnormal conditions using a server and an AI engine.

[1442] Users use devices such as smartphones and tablets to enter the operational specifications and requirements of the industrial robot to be verified into a form. The entered data is converted to JSON format by the device and sent to the server as an HTTP POST request.

[1443] The server checks the integrity of the received JSON data and verifies that it does not contain any invalid data. Once the integrity is confirmed, the server passes the data to the AI ​​engine, which then references its past database and expert knowledge base to generate quasi-normal and abnormal test patterns.

[1444] The generated test patterns are converted by the server into a human-readable format, usually expressed as a list or tree structure, and the converted data is stored in temporary storage.

[1445] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response. The user can check the received test pattern on the device and enter correction requests as necessary. If corrections are required, the user enters the corrections and sends it back to the server.

[1446] The server receives the correction request and passes the data to the AI ​​engine again to regenerate the test pattern. The regenerated test pattern is then sent back to the device for final confirmation by the user. When the user presses the "Confirm" button, the confirmed test pattern is permanently saved in the database by the server.

[1447] For example, consider the case of verifying an industrial robot's operational scenario. The user inputs the robot's operational specifications and requirements, such as temperature range, load capacity, and operational pattern. In this case, the AI ​​engine generates the following test patterns:

[1448] Normal condition: The robot operates normally within a temperature range of 20°C-30°C and moves the specified object accurately.

[1449] Quasi-normal pattern: Operation is not affected even if the ambient temperature temporarily exceeds 30°C.

[1450] Abnormal pattern: The robot begins to malfunction when the environmental temperature exceeds 50°C.

[1451] Examples of prompt sentences to be input to the generative AI model include the following:

[1452] "Generate test patterns to identify operating scenarios for industrial robot model XYZ-123. Specifications are temperature 0-50°C, humidity 20-80%, and load capacity up to 50kg."

[1453] "Please tell me the abnormality test pattern for the model XYZ-123 robot that includes a temperature sensor function."

[1454] The software used is Python and its libraries (requests, json), and the hardware is a smartphone or tablet connected to the internet.The AI ​​engine utilizes a generative AI model to efficiently generate test patterns.

[1455] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1456] Step 1:

[1457] The user inputs the specifications and requirements to be verified into the terminal, including the operating scenario of the industrial robot and environmental conditions (e.g., temperature range, humidity, load capacity). The input data is saved on the terminal.

[1458] Step 2:

[1459] The terminal converts the input data into JSON format. Specifically, it converts the specifications and requirements entered by the user into a JSON object and sends it to the server as an HTTP POST request. Here, the input data is serialized and sent.

[1460] Step 3:

[1461] The server receives the received JSON data and checks its integrity. The server parses the JSON data and checks for invalid data or defects. The result of the integrity check becomes the output data. If integrity is confirmed, proceed to the next step.

[1462] Step 4:

[1463] The server passes the data whose integrity has been confirmed to the AI ​​engine, which then references the database and expert knowledge base to generate test patterns for quasi-normal and abnormal conditions. In this process, the AI ​​engine analyzes the input data and makes predictions and generates patterns. The output is the generated test patterns.

[1464] Step 5:

[1465] The server converts the test patterns generated by the AI ​​engine into a format that is easy for humans to understand, including formats such as lists and tree structures. Specifically, it converts the data structure of the test patterns and saves them as output data.

[1466] Step 6:

[1467] The server reconverts the converted test pattern into JSON format and sends it to the terminal as an HTTP response. The server serializes the parsed data and prepares it for transmission. The terminal displays the received data on the screen.

[1468] Step 7:

[1469] The user checks the received test pattern on the terminal and inputs correction requests as necessary. The user evaluates the test pattern and inputs corrections if they find any errors or deficiencies. The correction requests are sent from the terminal to the server.

[1470] Step 8:

[1471] The server receives the correction request and passes the data to the AI ​​engine again to regenerate the test pattern. Reanalysis is performed based on the new input data, and new test patterns are generated. During this process, the AI ​​engine again refers to the database and expert knowledge base.

[1472] Step 9:

[1473] The user checks the regenerated test pattern on the terminal and presses the "Confirm" button if there are no problems. The final checked test pattern is sent to the server. The output is the final checked test pattern.

[1474] Step 10:

[1475] The server permanently saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user confirms the received message and is ready for verification.

[1476] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1477] The present invention enables the generation of more accurate test patterns by combining an emotion engine that recognizes the user's emotions with a system in which a user inputs the specifications and requirements of the object to be verified via a terminal and generates quasi-normal and abnormal test patterns using an AI engine. This system is composed of the elements of a server, a terminal, a user, and an emotion engine, and detailed embodiments are described below.

[1478] User Interaction

[1479] The user accesses the system using a terminal. A form is displayed on the terminal screen for entering the specifications and requirements of the tool to be verified and the development equipment. The user enters the necessary information into this form and presses the "Submit" button. In parallel, the emotion engine analyzes the user's facial expressions and voice, recognizing emotions in real time.

[1480] Data transmission

[1481] The device converts the specifications and requirements data entered by the user into JSON format, simultaneously collecting the emotion data recognized by the emotion engine, and sends this data to the server as an HTTP POST request.

[1482] Data reception and preparation for analysis

[1483] The server processes the received JSON data. Specifically, it checks the data for consistency and detects invalid data. If invalid data is included, it generates an error message and returns it to the terminal. If consistency is confirmed, it proceeds to the next step.

[1484] AI-based analysis

[1485] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge. The user's emotional data provided by the emotion engine is also used for analysis, and the difficulty and details of the test patterns are adjusted.

[1486] Test Pattern Generation

[1487] The server receives the test patterns generated by the AI ​​engine. The server converts the test patterns into a format that is easy for humans to understand. Specifically, they are often expressed in list format or tree structure. This data is temporarily stored in storage.

[1488] Send results

[1489] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any necessary supplementary explanations or links to reference materials.

[1490] User verification and correction

[1491] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. In parallel, the emotion engine continues to monitor the user's emotions. If the user wishes to send a correction request, they press the "Edit" button and the data including the corrections is resent to the server.

[1492] reanalysis

[1493] The server receives the correction request and passes the data to the AI ​​engine again to generate a new test pattern, taking into account the newly collected emotion data. The generated test pattern is then sent back to the device.

[1494] Final confirmation

[1495] The user makes a final check of the regenerated test pattern on the terminal, and if there are no problems, presses the "Confirm" button to confirm the test pattern.

[1496] Data storage

[1497] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[1498] As a concrete example, consider the case of verifying the operation of a temperature sensor device. If a user inputs the specifications and operational requirements of a temperature sensor and the emotion engine determines that the user is expressing "anxiety," the AI ​​engine generates a test pattern with more details or additional explanations. For example, it generates the following test pattern:

[1499] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[1500] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[1501] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[1502] According to the present invention, by utilizing the emotion engine, the user can generate more accurate test patterns, thereby realizing a more user-friendly and efficient development process.

[1503] The processing flow will be explained below.

[1504] Step 1:

[1505] The user accesses the system using a terminal. A form for entering the specifications and requirements of the tool and development equipment to be verified is displayed on the terminal screen. The user enters the necessary information into this form and presses the "Submit" button.

[1506] Step 2:

[1507] The device converts the specifications and requirements data entered by the user into JSON format. At the same time, the emotion engine analyzes the user's facial expressions and voice to recognize emotions in real time. The recognized emotion data is also included in the JSON format.

[1508] Step 3:

[1509] The device sends the converted JSON data of specifications and requirements and emotion data to the server as an HTTP POST request.

[1510] Step 4:

[1511] The server processes the received JSON data. Specifically, it first checks the data for consistency and detects invalid data. If invalid data is included, it generates an error message and returns it to the terminal.

[1512] Step 5:

[1513] The server passes the data whose integrity has been confirmed to the AI ​​engine, which then references the received database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge.

[1514] Step 6:

[1515] When generating test patterns, the AI ​​engine takes into account the user's emotional data provided by the emotion engine. For example, if the user is feeling "anxious" or "stressed," the AI ​​engine will adjust the explanation of the test pattern to be more detailed or simpler.

[1516] Step 7:

[1517] The server receives the test patterns generated by the AI ​​engine, converts them into a format that is easy for humans to understand, and temporarily stores the test patterns in storage.

[1518] Step 8:

[1519] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any supplementary explanations or links to reference materials, if necessary.

[1520] Step 9:

[1521] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. In parallel, the emotion engine continues to monitor the user's emotions.

[1522] Step 10:

[1523] When the user wishes to send a correction request, the data including the corrections is resent to the server by pressing the "correct" button.

[1524] Step 11:

[1525] The server receives the correction request and passes the data to the AI ​​engine again to generate a new test pattern, taking into account the recollected emotion data. The generated test pattern is then sent back to the device.

[1526] Step 12:

[1527] The terminal displays the received test pattern again, and the user performs a final check. If there are no problems, the user presses the "Confirm" button to confirm the test pattern.

[1528] Step 13:

[1529] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the terminal and sends a completion message.

[1530] Step 14:

[1531] The user receives a completion message, and the emotion engine also collects and saves the final emotion data. Verification preparation is complete, and the user is ready to proceed to the next step.

[1532] As a concrete example, consider the case of verifying the operation of a temperature sensor device. If the user inputs the specifications and operational requirements of the temperature sensor and the emotion engine detects "anxiety," the AI ​​engine generates a test pattern with a more detailed explanation. On the other hand, if the emotion is recognized as "calm," it generates a standard test pattern. For example, the following test pattern may be generated:

[1533] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[1534] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[1535] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[1536] This specific flow provides optimal test patterns according to the user's emotions, realizing more efficient and high-quality verification.

[1537] Example 2

[1538] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1539] Conventional test pattern generation systems generate test patterns based on specifications and requirements entered by the user, but the generated test patterns do not always reflect the user's intentions or emotions. Furthermore, particularly for abnormality test patterns, flexible adjustments that take into account the user's emotions and level of understanding are required. However, conventional systems were unable to achieve this, making it difficult to achieve a user-friendly and efficient development process.

[1540] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1541] In this invention, the server includes means for converting data input by the terminal into JSON format and sending it to the server, means for checking the consistency of the received data and, if invalid data is detected, generating an error message and sending it to the terminal, and means for passing the consistent data to the AI ​​engine. This enables the AI ​​engine to refer to the past database and expert knowledge base and generate quasi-normal and abnormal test patterns that take user emotion data into consideration.

[1542] A "terminal" is an electronic device used by a user to input specifications and requirements for a verification target, and is used to input, send, receive, and display data.

[1543] A "server" is a computer system that receives data sent from a terminal, checks the integrity of the data, detects fraudulent data, and provides the data to the AI ​​engine.

[1544] An "AI engine" is a program that incorporates artificial intelligence technology to generate quasi-normal and abnormal test patterns by referencing past databases and expert knowledge bases.

[1545] The "emotion engine" is a program that incorporates technology that analyzes the user's facial expressions and voice input and recognizes emotions in real time.

[1546] A "specification" is a document or data that describes in detail the functions and characteristics of the object to be verified.

[1547] "Requirements" are documents or data that describe the conditions and constraints that the verification target must satisfy.

[1548] "JSON format" is an abbreviation for JavaScript Object Notation, and is a data exchange format that represents structured text data in a format that is easy for humans to read and computers to analyze.

[1549] An "HTTP POST request" is a request format for sending data from a client (terminal) to a server using the POST method of the Hypertext Transfer Protocol.

[1550] "Integrity check" is the process of verifying whether the received data is formally correct and contains all required fields.

[1551] "Invalid data" refers to data that cannot be processed normally, such as data that has an incorrect data format or is missing required fields.

[1552] A "test pattern" refers to a scenario or case for verifying the behavior of a system under specific conditions.

[1553] A "quasi-normal" situation refers to a situation in which the system is temporarily placed in an unstable state, but is expected to return to a normal state.

[1554] "Abnormal situation" refers to a situation in which the system is placed in an abnormal condition and is expected to not function normally.

[1555] "Emotion data" is data that indicates the user's emotional state and is obtained through facial expression and voice analysis.

[1556] "Storage" refers to a storage device for temporarily or permanently storing data or information.

[1557] The "list format" is a format in which data is arranged in bullet points.

[1558] A "tree structure" is a format in which data is arranged hierarchically, and is a structure of nodes (data elements) that have parent-child relationships.

[1559] An "HTTP response" is a response message sent by a server in response to a request from a client.

[1560] This invention enables the generation of more accurate test patterns by combining an emotion engine that recognizes the user's emotions with a system in which a user inputs the specifications and requirements of the object to be verified via a terminal and generates test patterns for quasi-normal and abnormal conditions using an AI engine. This system is composed of the following elements: a server, a terminal, a user, and an emotion engine.

[1561] Hardware and software used

[1562] Terminal: An electronic device used by a user to input specifications and requirements, such as a personal computer or smartphone.

[1563] Server: A computer system that processes data reception, integrity checks, AI analysis, data storage, etc.

[1564] AI engine: A program that implements machine learning algorithms and runs on a high-performance GPU (Graphics Processing Unit) server.

[1565] Emotion engine: A software component that analyzes the user's facial expressions and voice to generate emotion data.

[1566] Natural language description of the program

[1567] 1. User input: The user accesses the system using a terminal and enters the specifications and requirements to be verified into the displayed form. Once the input is complete, the emotion engine captures the user's facial expressions and voice to recognize their emotions.

[1568] 2. Data transmission: The device converts the input specifications and requirements data into JSON format and sends it to the server as an HTTP POST request along with the emotion data obtained from the emotion engine.

[1569] 3. Data integrity check: The server checks the integrity of the received data. If invalid data is included, it generates an error message and returns it to the terminal. If the data is confirmed to be valid, it proceeds to the next step.

[1570] 4. AI analysis: The server passes the consistent data to the AI ​​engine, which then refers to the database and expert knowledge base to generate quasi-normal and abnormal test patterns. The AI ​​engine also takes into account the emotional data provided by the emotion engine to adjust the difficulty and details of the test patterns.

[1571] 5. Test pattern generation: The server receives the test patterns generated by the AI ​​engine and converts them into a format that is easy for humans to understand. The converted data is temporarily stored in storage.

[1572] 6. Result notification: The server reconverts the converted test pattern into JSON format and sends it to the terminal as an HTTP response, including supplementary explanations and links to reference materials as needed.

[1573] 7. User confirmation and correction: The device displays the received test pattern on the screen. The user confirms the displayed test pattern and inputs correction requests as necessary. The emotion engine continues to monitor the user's emotions and updates the emotion data as necessary.

[1574] 8. Re-analysis: The server receives the correction request and passes the data to the AI ​​engine again to generate a new test pattern, taking into account the newly collected emotion data. The generated test pattern is then sent back to the device.

[1575] 9. Final confirmation: The user checks the regenerated test pattern on the terminal one last time, and if there are no problems, presses the "Confirm" button to confirm the test pattern.

[1576] 10. Data saving: The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[1577] Specific examples

[1578] As a concrete example, consider the case of verifying the operation of a temperature sensor device. If a user inputs the specifications and operational requirements of the temperature sensor and the emotion engine determines that the user is expressing "anxiety," the AI ​​engine generates a test pattern with more details or additional explanations.

[1579] Example of generated test pattern

[1580] Normal pattern: When the temperature sensor accurately measures between 25°C and 30°C.

[1581] Quasi-normal pattern: When the temperature sensor temporarily exceeds 30°C but returns to the normal range again.

[1582] Abnormal pattern: The system malfunctions when the temperature sensor exceeds 40°C.

[1583] Prompt Sentence Examples

[1584] "To verify the operation of a temperature sensor device, please generate test patterns for normal, quasi-normal, and abnormal conditions. The specifications and requirements are as follows."

[1585] "Generate highly accurate test patterns based on user input and emotion data."

[1586] The present invention enables highly accurate test pattern generation that takes user feelings into consideration, thereby realizing a user-friendly and efficient development process.

[1587] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1588] Step 1: User Input

[1589] Users access the system using a terminal and enter the specifications and requirements to be verified into the displayed form. This involves entering detailed information using text areas and drop-down lists. At the same time, the terminal's built-in camera and microphone capture the user's facial expressions and voice, which are then analyzed by the emotion engine to generate emotion data in real time.

[1590] Input: The user inputs specifications and requirements, and the device captures facial expressions and voice

[1591] Output: Input specifications, requirements, and sentiment data

[1592] Step 2: Sending data

[1593] The device converts the specifications and requirements data entered by the user into JSON format, and simultaneously collects the emotion data recognized by the emotion engine, consolidates them into a single data packet, and sends the data packet to the server as an HTTP POST request.

[1594] Input: Input specifications, requirements, and sentiment data

[1595] Output: JSON formatted data packet

[1596] Step 3: Verify data integrity

[1597] The server analyzes the received data packet and checks the integrity of the data. Specifically, it checks the JSON format, confirms the existence of required fields, and detects invalid data. If invalid data is included, the server generates an error message and returns it to the terminal. If the data is normal, it proceeds to the next step.

[1598] Input: JSON formatted data packet

[1599] Output: Data that has been verified to be consistent, or an error message

[1600] Step 4: Analysis by AI engine

[1601] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and knowledge. Emotional data is also taken into account, and the difficulty and details of the test patterns are adjusted based on the user's emotional state.

[1602] Input: Integrity checked data

[1603] Output: Generated quasi-normal and abnormal test patterns

[1604] Step 5: Formatting and temporarily saving the test pattern

[1605] The server converts the test patterns received from the AI ​​engine into a format that is easy for humans to understand, such as a list format or tree structure. The converted data is temporarily stored in storage.

[1606] Input: Generated test pattern

[1607] Output: Formatted test pattern

[1608] Step 6: Notification of results

[1609] The server then converts the formatted test pattern back into JSON format and sends it to the device as an HTTP response, adding any necessary supplementary explanations or links to reference material.

[1610] Input: Formatted test pattern

[1611] Output: Test pattern in JSON format sent to the terminal

[1612] Step 7: User review and correction

[1613] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. At the same time, the emotion engine continues to monitor the user's emotions and updates the data as necessary.

[1614] Input: Test pattern in JSON format sent to the terminal

[1615] Output: User-entered correction requests

[1616] Step 8: Reprocessing

[1617] The server receives the correction request and passes the data back to the AI ​​engine to generate a new test pattern, taking into account the corrections and the newly collected emotion data. The generated test pattern is then sent back to the device.

[1618] Input: The correction request entered by the user

[1619] Output: Regenerated test pattern

[1620] Step 9: Final check

[1621] The user makes a final check of the regenerated test pattern on the terminal, and if there are no problems, presses the "Confirm" button to confirm the test pattern.

[1622] Input: Regenerated test pattern

[1623] Output: User-defined test pattern

[1624] Step 10: Save Data

[1625] The server saves the finalized test pattern in the database. When saving is complete, the server notifies the user and sends a completion message to the terminal. The user receives the completion message and is ready to begin verification.

[1626] Input: User-defined test pattern

[1627] Output: Test pattern stored in the database, end message sent to the terminal

[1628] (Application example 2)

[1629] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1630] In the development of autonomous vehicles, it is necessary to create highly accurate test patterns based on specifications and requirements so that drivers can use the vehicle with confidence. However, current test pattern generation systems generate test patterns with insufficient accuracy that takes into account the driver's emotions, making it impossible to alleviate driver anxiety. Another issue is the lack of systems that can flexibly respond to the driver's emotions when checking and modifying test patterns.

[1631] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for a user to input specifications and requirements for the verification target via a terminal, means for the terminal to transmit the input data to the server, means for the server to verify the consistency of the received data and pass the data to the AI ​​engine, means for the AI ​​engine to generate quasi-normal and abnormal test patterns by referring to a past database and an expert knowledge base, means for the AI ​​engine to adjust the difficulty and details of the test patterns based on the user's emotional data using an emotion engine that recognizes the user's emotions in real time, means for converting the test patterns into a format that is easy for humans to understand and transmitting them to the terminal, means for the terminal to display the received test patterns and for the user to send a correction request, and means for the server to re-pass the data to the AI ​​engine based on the correction request and regenerate the test patterns. This enables the generation of highly accurate test patterns based on the driver's emotions, making it possible to provide a system that reduces driver anxiety and allows for flexible response.

[1632] A "terminal" is an electronic device that allows a user to input specifications and requirements, and is a device that communicates with a server.

[1633] The "server" is a central device that receives input data and generates and transmits test patterns using an AI engine and emotion engine.

[1634] An "AI engine" is an artificial intelligence system that references a database and expert knowledge base to generate test patterns for quasi-normal and abnormal conditions.

[1635] The "emotion engine" is a system that analyzes the user's facial expressions and voice in real time to recognize the user's emotions.

[1636] "Specifications and requirements" are data that indicate the detailed conditions and required performance of the product or system being verified.

[1637] A "test pattern" is a test pattern used to check the operation and performance of the object to be verified based on specifications and requirements.

[1638] A "database" is a repository of information that stores past data and specialized knowledge.

[1639] An "expertise base" is information that systematically compiles knowledge in a particular field.

[1640] "Real-time" refers to the time characteristic of being able to respond immediately to user operations and emotional changes.

[1641] "Integrity" means making sure that data is accurate and consistent.

[1642] An "anomaly detection algorithm" is a computational method for detecting abnormal behavior or situations.

[1643] This invention relates to a test pattern generation system for autonomous vehicles. Users input specifications and requirements via a terminal, and an AI engine is used to generate test patterns for quasi-normal and abnormal conditions. By combining this with an emotion engine, it is possible to generate test patterns with even greater accuracy. This system is composed of the following elements: a server, a terminal, a user, and an emotion engine.

[1644] Basic program structure

[1645] Data collection

[1646] Users access the system using a terminal and input their specifications and requirements, which can include specifications such as maximum speed, minimum speed, braking distance, etc. These data are finally converted into JSON format.

[1647] emotion recognition

[1648] In parallel, the emotion engine analyzes the user's facial expressions and voice in real time to obtain emotion data. The emotion engine uses an image analysis module (e.g., OpenCV) and an audio analysis module (e.g., Pyaudio).

[1649] From data transmission to analysis preparation

[1650] The device collects specifications, requirements, and emotion data and sends them to the server as an HTTP POST request. The server checks the integrity of the received data and, if invalid data is included, generates an error message and returns it to the device. If the integrity is confirmed, the device proceeds to the next step.

[1651] AI-based test pattern generation

[1652] The server passes the consistent data to the AI ​​engine, which then references the database and expert knowledge base to generate quasi-normal and abnormal test patterns based on past data and expert knowledge. The user's emotional data provided by the emotion engine is also used for analysis; for example, if the user expresses "anxiety," a detailed test pattern is generated.

[1653] Test pattern conversion and transmission

[1654] The server receives the test patterns generated by the AI ​​engine and converts them into a format that is easy for humans to understand. This is often expressed in list format or tree structure. The converted data is temporarily stored in storage, then converted back into JSON format and sent to the device as an HTTP response.

[1655] Verify and correct users

[1656] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If there are correction requests, the user presses the "correct" button and the data is sent to the server again. The server again passes the data to the AI ​​engine and generates a new test pattern. During this time, the emotion engine continues to monitor the user's emotions.

[1657] Final confirmation and data storage

[1658] The user performs a final check, and if there are no problems, presses the "Confirm" button to confirm the test pattern. The server saves the finalized test pattern in the database. Once saving is complete, the server notifies the terminal and sends a completion message.

[1659] Examples and prompts

[1660] For example, suppose the emotion engine recognizes that the user appears anxious when the maximum speed of an autonomous vehicle is set to 120 km / h, the minimum speed to 0 km / h, and the braking distance to 3.5 m. In this case, the AI ​​engine generates a detailed test pattern. An example of a prompt sentence could be, "Please generate a vehicle operation test pattern with a maximum speed of 120 km / h, a minimum speed of 0 km / h, and a braking distance of 3.5 m. The driver appears anxious."

[1661] In this way, the system of the present invention enables the generation of highly accurate test patterns that take user emotions into consideration, thereby supporting the development of safer self-driving vehicles.

[1662] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1663] Step 1:

[1664] The user uses the terminal to input the specifications and requirements of the vehicle to be verified. The terminal screen displays a form for inputting maximum speed, minimum speed, braking distance, etc. When the user inputs this data and presses the submit button, the data is converted into JSON format. For example, the input data could be specification information such as "maximum speed: 120 km / h, minimum speed: 0 km / h, braking distance: 3.5 m."

[1665] Step 2:

[1666] The emotion engine analyzes the user's facial expressions and voice in real time and generates emotion data. The emotion engine captures the user's facial expressions and voice using the device's built-in camera and microphone. Images are processed using an image analysis library such as OpenCV, and audio is analyzed using an audio analysis library such as Pyaudio. An example of the generated emotion data is "Emotion: Anxiety."

[1667] Step 3:

[1668] The device converts the input specification and requirement data and the emotion data generated by the emotion engine into JSON format and sends it to the server as an HTTP POST request. An example of the data sent is as follows:

[1669] json

[1670] {

[1671] "specs": {

[1672] "max_speed": 120,

[1673] "min_speed": 0,

[1674] "braking_distance": 3.5

[1675] },

[1676] "emotion": "anxiety"

[1677] }

[1678] Step 4:

[1679] The server checks the integrity of the received data. It verifies that the JSON formatted data is correctly formed and that all required fields are included. If the data is inconsistent, the server generates an error message and returns it to the terminal. If the integrity is confirmed, it proceeds to the next step.

[1680] Step 5:

[1681] The server passes the consistent data to the AI ​​engine. The AI ​​engine refers to the database and expert knowledge base and generates quasi-normal and abnormal test patterns based on the user's input data. The emotion data provided by the emotion engine is also taken into consideration; for example, if the user expresses "anxiety," a detailed test pattern is generated. The AI ​​engine uses the generative AI model to generate test patterns based on the prompt sentence.

[1682] Step 6:

[1683] The server converts the test patterns received from the AI ​​engine into a format that is easy for humans to understand. The converted test patterns are temporarily stored in a list format or tree structure format. As a specific example, the following test patterns are generated:

[1684] Normal pattern: The vehicle is driven normally between 0km / h and 120km / h.

[1685] Quasi-normal pattern: The vehicle briefly exceeds 120 km / h but quickly returns to the normal range.

[1686] Abnormal pattern: When the vehicle exceeds 150 km / h, the brake system exhibits abnormal operation.

[1687] Step 7:

[1688] The server then converts the converted test pattern back into JSON format and sends it to the device as an HTTP response, along with any reference materials or supplementary explanations as needed.

[1689] Step 8:

[1690] The device displays the received test pattern on the screen. The user checks the displayed test pattern and inputs correction requests as necessary. If there are correction requests, the user presses the "correct" button and the data including the corrections is sent again to the server. A specific example would be a correction such as "Maximum speed: 130 km / h."

[1691] Step 9:

[1692] The server then passes the data back to the AI ​​engine based on the requested corrections, generating a new test pattern. This takes into account the newly acquired emotion data. The new test pattern is then sent back to the device, where the user can view it on the screen.

[1693] Step 10:

[1694] The user performs a final check, and if there are no problems, presses the "Confirm" button to confirm the test pattern. The server saves the confirmed test pattern in the database. Once saving is complete, the server notifies the user and sends a completion message to the terminal. This completes processing for the entire system, and the terminal is ready for verification.

[1695] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1696] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1697] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1698] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1699] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1700] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1701] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1702] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1703] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1704] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1705] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1706] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1707] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1708] 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.

[1709] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1710] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1711] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1712] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1713] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1714] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1715] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1716] The following is further disclosed regarding the above embodiment.

[1717] (Claim 1)

[1718] A means for users to input specifications and requirements to be verified via a terminal;

[1719] A means for transmitting input data from the terminal to a server;

[1720] A means for the server to check the integrity of the data it receives and pass it on to the AI ​​engine;

[1721] A means for the AI ​​engine to generate test patterns for quasi-normal and abnormal conditions by referring to a past database and an expert knowledge base;

[1722] a means for converting the test pattern into a human-readable format and transmitting it to the terminal;

[1723] a means for displaying the received test pattern by the terminal and for the user to send a correction request;

[1724] The server passes the data to the AI ​​engine again based on the correction request, and a means is provided to regenerate the test pattern.

[1725] Including system.

[1726] (Claim 2)

[1727] 2. The system of claim 1, wherein the AI ​​engine uses an anomaly detection algorithm when generating test patterns.

[1728] (Claim 3)

[1729] 2. The system according to claim 1, further comprising means for allowing a user to make a final confirmation via a terminal and for storing the confirmed test pattern on a server.

[1730] "Example 1"

[1731] (Claim 1)

[1732] A means for users to input specifications and requirements to be verified via a terminal;

[1733] A means for the terminal to convert the input data into JSON format and send it to the server as an HTTP POST request;

[1734] A means for the server to check the integrity of the JSON data it receives and pass the data to the AI ​​engine.

[1735] A means for the AI ​​engine to generate test patterns for quasi-normal and abnormal...

Claims

1. A means for users to input specifications and requirements to be verified via a terminal; A means for transmitting input data from the terminal to a server; A means for the server to check the integrity of the data it receives and pass it on to the AI ​​engine; A means for the AI ​​engine to generate test patterns for quasi-normal and abnormal conditions by referring to a past database and an expert knowledge base; a means for converting the test pattern into a human-readable format and transmitting it to the terminal; a means for displaying the received test pattern by the terminal and for the user to send a correction request; The server passes the data to the AI ​​engine again based on the correction request, and a means is provided to regenerate the test pattern. Including system.

2. 2. The system of claim 1, wherein the AI ​​engine uses an anomaly detection algorithm when generating test patterns.

3. 2. The system according to claim 1, further comprising means for allowing a user to make a final confirmation via a terminal and for storing the confirmed test pattern in a server.

Images