system

Abstract

The system according to this embodiment aims to efficiently detect potential bugs and implementation omissions by mimicking the actions of service users. [Solution] The system according to the embodiment comprises a user characteristic instruction unit, a test case generation unit, an operation verification unit, and an evidence recording unit. The user characteristic instruction unit instructs the characteristics of a user to be imitated. The test case generation unit generates test cases based on the characteristics instructed by the user characteristic instruction unit. The operation verification unit performs operation verification based on the test cases generated by the test case generation unit. The evidence recording unit records the results obtained by the operation verification unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to efficiently detect potential bugs and implementation leaks by mimicking the movements of service users.

[0005] The system according to the embodiment aims to efficiently detect potential bugs and implementation leaks by mimicking the movements of service users.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a user characteristic instruction unit, a test case generation unit, an operation verification unit, and an evidence recording unit. The user characteristic instruction unit specifies the characteristics of a user to be imitated. The test case generation unit generates test cases based on the characteristics specified by the user characteristic instruction unit. The operation verification unit performs operation verification based on the test cases generated by the test case generation unit. The evidence recording unit records the results obtained by the operation verification unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently detect potential bugs and implementation omissions by mimicking the actions of service users. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The user simulation agent system according to an embodiment of the present invention is a system for reducing the costs that web service providers have to ensure service quality and for automating user-centric testing. This system provides an agent that mimics the behavior of a service user to detect potential bugs and implementation omissions. This agent uses the service on behalf of a user by specifying the characteristics of the user to be mimicked. There are two types of users: users who understand the specifications (E2E testing) and users who do not understand the specifications (monkey testing). For example, in E2E testing, the procedure involves reading the specifications, considering test patterns, launching a browser to verify that the behavior matches the specifications, and leaving evidence (screenshots or videos). In monkey testing, the procedure involves launching a browser without reading the specifications, checking screen items, performing possible actions, and reporting any unexpected behavior. This agent utilizes generative AI to automate the creation of test cases and operational verification. It also performs random actions with only screen items as input and detects unexpected behavior. This reduces the cost of ensuring service quality and improves service quality by detecting potential bugs before they reach the user. This allows the user simulation agent system to improve the quality of service.

[0029] The user simulation agent system according to this embodiment includes a user characteristic instruction unit, a test case generation unit, an operation verification unit, and an evidence recording unit. The user characteristic instruction unit specifies the characteristics of a user to be imitated. For example, the user characteristic instruction unit can specify user characteristics such as age, gender, and usage history. The test case generation unit generates test cases based on the characteristics specified by the user characteristic instruction unit. For example, the test case generation unit can generate scenario-based test cases or functional test cases. Some or all of the above-described processes in the test case generation unit may be performed using a generation AI, or not. For example, the test case generation unit can generate test cases using a generation AI model that takes the characteristics specified by the user characteristic instruction unit as input and outputs test cases. The operation verification unit performs operation verification based on the test cases generated by the test case generation unit. For example, the operation verification unit can perform operation verification based on test success criteria and error detection methods. Some or all of the above-described processes in the operation verification unit may be performed using AI, or not. For example, the operation verification unit can perform operation verification using an AI model that takes test cases generated by the test case generation unit as input and outputs the results of operation verification. The evidence recording unit records the results obtained by the operation verification unit. For example, the evidence recording unit can record the results in the form of log files, screenshots, error reports, etc. Some or all of the above processing in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can record evidence using an AI model that takes the results obtained by the operation verification unit as input and outputs evidence. As a result, the user simulation agent system according to the embodiment can improve the quality of service.

[0030] The user characteristic directive specifies the characteristics of the user to be imitated. For example, the user characteristic directive can specify user characteristics such as age, gender, and usage history. Specifically, the user characteristic directive can specify the user's age within a range such as teens, twenties, or thirties, and select gender from options such as male, female, or other. Furthermore, detailed data such as past purchase history, access history, and usage frequency can be specified for usage history. This allows the user characteristic directive to create a concrete profile of the user to be imitated, thereby improving the accuracy of the simulation. In addition, the user characteristic directive can also specify psychological characteristics such as the user's interests, concerns, and behavioral patterns. For example, by specifying purchasing tendencies for specific products or access tendencies at specific times of day, a more realistic user simulation can be achieved. In this way, the user characteristic directive can cover a wide range of user characteristics and provide a foundation for generating test cases that correspond to various scenarios.

[0031] The test case generation unit generates test cases based on the features specified by the user feature specification unit. For example, the test case generation unit can generate scenario-based test cases and functional test cases. Specifically, as a scenario-based test case, it generates cases that simulate a series of steps in which a user performs a specific operation. For example, it can generate a test case that includes a series of operations from when a user searches for a product, adds it to their cart, and completes the purchase process. As a functional test case, it generates cases to verify whether a specific function works correctly. For example, it can generate test cases for individual functions such as login, search, and payment. Some or all of the above processing in the test case generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the test case generation unit can generate test cases using a generation AI model that takes features specified by the user feature specification unit as input and outputs test cases. The generation AI model can learn from past test case data and user behavior data and generate optimal test cases based on the specified features. As a result, the test case generation unit can achieve efficient and highly accurate test case generation and contribute to improving the overall quality of the system.

[0032] The operation verification unit performs operation verification based on test cases generated by the test case generation unit. For example, the operation verification unit can perform operation verification based on test success criteria and error detection methods. Specifically, the operation verification unit executes each function of the system according to the test cases and compares the expected results with the actual results. For example, in the login function test case, it verifies whether login is successful when the correct username and password are entered, and whether an appropriate error message is displayed when an incorrect username or password is entered. In addition, as an error detection method, the operation verification unit can analyze system log files and error messages to detect abnormal operation or the occurrence of errors. Some or all of the above processing in the operation verification unit may be performed using AI or not. For example, the operation verification unit can perform operation verification using an AI model that takes test cases generated by the test case generation unit as input and outputs the results of operation verification. The AI ​​model can learn past test results and error patterns and evaluate the system's operation based on the test cases. This enables the operation verification unit to achieve efficient and highly accurate operation verification, contributing to the improvement of system quality.

[0033] The evidence recording unit records the results obtained by the operation verification unit. For example, the evidence recording unit can record results in the form of log files, screenshots, and error reports. Specifically, the evidence recording unit saves log files obtained at each step of the operation verification, and records the test execution status and error occurrences in detail. In addition, by saving screenshots, the screen state during test execution can be visually confirmed. Furthermore, it can generate error reports that describe the error content, conditions under which it occurred, and steps to reproduce it in detail. Some or all of the above processing in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can record evidence using an AI model that takes the results obtained by the operation verification unit as input and outputs evidence. The AI ​​model can learn from past evidence data and propose the optimal recording method and error report generation method. As a result, the evidence recording unit can achieve efficient and highly accurate evidence recording and contribute to improving the quality of the system.

[0034] The operation verification unit includes an action execution unit that performs random actions. The action execution unit performs random actions. For example, the action execution unit can perform random actions such as random clicks or random inputs. Some or all of the above-described processing in the action execution unit may be performed using AI or not. For example, the action execution unit can perform random actions using an AI model that takes screen items as input and outputs random actions. This makes it possible to detect unexpected behavior by performing random actions.

[0035] The action execution unit can perform random actions using only screen items as input. For example, the action execution unit can perform random actions such as random clicks or random inputs using only screen items as input. This allows it to mimic user operations by performing random actions using only screen items as input. Some or all of the above processing in the action execution unit may be performed using AI or not. For example, the action execution unit can perform random actions using an AI model that takes screen items as input and outputs random actions.

[0036] The operation verification unit includes a reporting unit that reports unexpected behavior. The reporting unit reports unexpected behavior. For example, the reporting unit can report unexpected behavior such as error messages, crashes, or unforeseen actions. Some or all of the above processing in the reporting unit may be performed using AI or not. For example, the reporting unit can report unexpected behavior using an AI model that takes the unexpected behavior detected by the operation verification unit as input and outputs the report content. This makes it possible to detect potential bugs or implementation omissions by reporting unexpected behavior.

[0037] The reporting unit can detect and report unexpected behavior. For example, the reporting unit can detect and report unexpected behavior using log analysis or anomaly detection algorithms. This allows for improvement of service quality by detecting and reporting unexpected behavior. Some or all of the above-described processes in the reporting unit may be performed using AI or not. For example, the reporting unit can report unexpected behavior using an AI model that takes unexpected behavior detected by the operation verification unit as input and outputs the report content.

[0038] The user feature instruction unit can analyze the user's past usage history and select the optimal user features. For example, the user feature instruction unit can select features to mimic based on functions that the user has frequently used in the past. It can also analyze the user's past operation patterns and select the optimal features. Furthermore, the user feature instruction unit can select features to avoid errors by referring to the user's past error history. In this way, the optimal user features can be selected by analyzing the user's past usage history. Some or all of the above processing in the user feature instruction unit may be performed using AI or not. For example, the user feature instruction unit can select the optimal user features using an AI model that takes the user's past usage history data as input and outputs the optimal user features.

[0039] The user feature indicator can filter user features based on the user's current usage and areas of interest. For example, the user feature indicator can filter features to mimic based on the functions the user is currently using. It can also filter relevant features based on the user's areas of interest. Furthermore, it can filter the most appropriate features according to the user's current operation status. This allows for the selection of more appropriate user features by filtering features based on the user's current usage and areas of interest. Some or all of the above processing in the user feature indicator may be performed using AI or not. For example, the user feature indicator can filter user features using an AI model that takes the user's current usage data and areas of interest data as input and outputs filtered user features.

[0040] The user feature indicator can prioritize highly relevant user features by considering the user's geographical location information. For example, if the user is in a specific region, the user feature indicator can prioritize features related to that region. Furthermore, if the user is traveling, the user feature indicator can prioritize features related to travel. Also, if the user is at home, the user feature indicator can prioritize features suitable for use at home. This allows for the selection of highly relevant user features by considering the user's geographical location information. Some or all of the above processing in the user feature indicator may be performed using AI or not. For example, the user feature indicator can use an AI model that takes the user's geographical location information as input and outputs highly relevant user features to indicate user features.

[0041] The user feature indicator can analyze a user's social media activity and indicate relevant user features. For example, the user feature indicator can indicate features based on the content a user frequently posts on social media. It can also indicate features based on a user's interests on social media. Furthermore, it can indicate features based on a user's friendships on social media. This allows for the selection of relevant user features by analyzing a user's social media activity. Some or all of the above processing in the user feature indicator may be performed using AI or not. For example, the user feature indicator can indicate user features using an AI model that takes a user's social media activity data as input and outputs relevant user features.

[0042] The test case generation unit can adjust the level of detail of test cases based on the importance of the service during test case generation. For example, the test case generation unit can generate detailed test cases for important services. Conversely, it can generate concise test cases for less important services. Furthermore, the test case generation unit can adjust the level of detail of test cases in stages according to their importance. This allows for more effective testing by adjusting the level of detail of test cases based on the importance of the service. Some or all of the above processing in the test case generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the test case generation unit can adjust the level of detail of test cases using a generation AI model that takes service importance data as input and outputs the level of detail of test cases.

[0043] The test case generation unit can apply different test algorithms depending on the service category when generating test cases. For example, for e-commerce services, the test case generation unit can apply a test algorithm specialized in the purchase flow. For social networking services, it can apply a test algorithm specialized in posting and commenting functions. For financial services, it can apply a test algorithm specialized in security checks. By applying different test algorithms depending on the service category, more effective testing becomes possible. Some or all of the above processing in the test case generation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the test case generation unit can apply a test algorithm using a generative AI model that takes service category data as input and outputs the test algorithm to be applied.

[0044] The test case generation unit can determine the priority of test cases based on the service release date when generating test cases. For example, the test case generation unit will prioritize generating test cases for services scheduled for release soon. Conversely, it can postpone generating test cases for services whose release is far off. Furthermore, the test case generation unit can adjust the priority of test cases in stages according to the release date. This allows for more effective testing by determining the priority of test cases based on the service release date. Some or all of the above processing in the test case generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the test case generation unit can determine the priority of test cases using a generation AI model that takes service release date data as input and outputs the priority of test cases.

[0045] The test case generation unit can adjust the order of test cases based on the relationships between services during the test case generation process. For example, the test case generation unit can prioritize generating test cases for highly relevant services. It can also postpone generating test cases for less relevant services. Furthermore, the test case generation unit can adjust the order of test cases in stages according to the relationships between services. This allows for more effective testing by adjusting the order of test cases based on the relationships between services. Some or all of the above-described processes in the test case generation unit may be performed using a generative AI, or they may not. For example, the test case generation unit can adjust the order of test cases using a generative AI model that takes service relationship data as input and outputs the order of test cases.

[0046] The operation verification unit can improve the accuracy of operation verification by considering the interrelationships between services during the verification process. For example, the operation verification unit can verify data exchange between services. Furthermore, the operation verification unit can perform operation verification while considering the dependencies between services. In addition, the operation verification unit can verify the interactions between services. As a result, the accuracy of operation verification is improved by considering the interrelationships between services. Some or all of the above processing in the operation verification unit may be performed using AI or not. For example, the operation verification unit can take interrelationship data between services as input and perform operation verification using an AI model that improves the accuracy of operation verification.

[0047] The operation verification unit can perform operation verification while considering the attribute information of the service provider. For example, the operation verification unit can perform operation verification while considering the reliability of the service provider. It can also perform operation verification while considering the past performance of the service provider. Furthermore, it can perform operation verification while considering the technical capabilities of the service provider. As a result, the accuracy of operation verification is improved by considering the attribute information of the service provider. Some or all of the above processing in the operation verification unit may be performed using AI or not. For example, the operation verification unit can take the attribute information of the service provider as input and perform operation verification using an AI model that improves the accuracy of operation verification.

[0048] The operation verification unit can perform operation verification while considering the geographical distribution of the service. For example, the operation verification unit can perform operation verification for each region where the service is provided. Furthermore, the operation verification unit can perform operation verification in geographically different environments. In addition, the operation verification unit can perform operation verification while considering the user characteristics of each region. As a result, the accuracy of operation verification is improved by considering the geographical distribution of the service. Some or all of the above processing in the operation verification unit may be performed using AI or not. For example, the operation verification unit can take geographical distribution data of the service as input and perform operation verification using an AI model that improves the accuracy of operation verification.

[0049] The operation verification unit can improve the accuracy of operation verification by referring to relevant service literature during operation verification. For example, the operation verification unit performs operation verification by referring to technical literature related to the service. The operation verification unit can also perform operation verification by referring to patent documents related to the service. Furthermore, the operation verification unit can perform operation verification by referring to research papers related to the service. As a result, the accuracy of operation verification is improved by referring to relevant service literature. Some or all of the above processing in the operation verification unit may be performed using AI or not. For example, the operation verification unit can take relevant service literature data as input and perform operation verification using an AI model that improves the accuracy of operation verification.

[0050] The evidence recording unit can optimize its recording algorithm by referring to past evidence data when recording evidence. For example, the evidence recording unit can select the optimal recording method based on past evidence data. Furthermore, the evidence recording unit can analyze past evidence data and optimize its recording algorithm. It can also improve the method of recording evidence by referring to past evidence data. This allows for the optimization of the recording algorithm by referring to past evidence data. Some or all of the above processes in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can record evidence using an AI model that optimizes the recording algorithm based on past evidence data as input.

[0051] The evidence recording unit can apply different recording methods to each service category when recording evidence. For example, for e-commerce services, the evidence recording unit can apply an evidence recording method specialized for the purchase flow. For social networking services, the evidence recording unit can apply an evidence recording method specialized for posting and commenting functions. For financial services, the evidence recording unit can apply an evidence recording method specialized for security checks. By applying different recording methods to each service category, more appropriate evidence recording becomes possible. Some or all of the above processing in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can record evidence using an AI model that takes service category data as input and outputs a recording method.

[0052] The evidence recording unit can determine the priority of evidence based on the service release date when recording evidence. For example, the evidence recording unit will prioritize recording evidence for services scheduled for release in the near future. Conversely, it can postpone recording evidence for services with a distant release date. Furthermore, the evidence recording unit can adjust the priority of evidence in stages according to the release date. This enables more effective evidence recording by determining the priority of evidence based on the service release date. Some or all of the above processing in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can record evidence using an AI model that takes service release date data as input and outputs the priority of evidence.

[0053] The evidence recording unit can record evidence by referring to relevant market data for the service at the time of evidence recording. For example, the evidence recording unit can record evidence based on the service's market share. The evidence recording unit can also record evidence by referring to data of the service's competitors. Furthermore, the evidence recording unit can record evidence by considering the service's market trends. This makes it possible to record more appropriate evidence by referring to relevant market data for the service. Some or all of the above processing in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can record evidence using an AI model that takes relevant market data for the service as input and records evidence.

[0054] The action execution unit can improve the accuracy of actions by considering the interrelationships between services when executing an action. For example, the action execution unit can execute actions while considering data linkages between services. It can also execute actions while considering dependencies between services. Furthermore, it can execute actions while considering interactions between services. As a result, the accuracy of actions is improved by considering the interrelationships between services. Some or all of the above processing in the action execution unit may be performed using AI or not. For example, the action execution unit can take interrelationship data between services as input and execute actions using an AI model that improves the accuracy of actions.

[0055] The action execution unit can perform actions while considering the attribute information of the service provider. For example, the action execution unit can perform actions while considering the reliability of the service provider. It can also perform actions while considering the past performance of the service provider. Furthermore, it can perform actions while considering the technical capabilities of the service provider. This improves the accuracy of actions by considering the attribute information of the service provider. Some or all of the above processing in the action execution unit may be performed using AI or not. For example, the action execution unit can take the attribute information of the service provider as input and perform actions using an AI model that improves the accuracy of actions.

[0056] The action execution unit can perform actions while considering the geographical distribution of services. For example, the action execution unit can perform actions for each region where the service is provided. Furthermore, the action execution unit can perform actions in geographically different environments. It can also perform actions while considering the user characteristics of each region. This improves the accuracy of actions by considering the geographical distribution of services. Some or all of the above processing in the action execution unit may be performed using AI, or not. For example, the action execution unit can take geographical distribution data of services as input and perform actions using an AI model that improves the accuracy of the actions.

[0057] The action execution unit can improve the accuracy of its actions by referring to relevant service literature during action execution. For example, the action execution unit can perform actions by referring to technical literature related to the service. It can also perform actions by referring to patent documents related to the service. Furthermore, it can perform actions by referring to research papers related to the service. As a result, the accuracy of the actions is improved by referring to relevant service literature. Some or all of the above processing in the action execution unit may be performed using AI or not. For example, the action execution unit can take relevant service literature data as input and perform actions using an AI model that improves the accuracy of the actions.

[0058] The reporting unit can optimize its reporting algorithm by referring to past reporting data when submitting a report. For example, the reporting unit can select the optimal reporting method based on past reporting data. Furthermore, the reporting unit can analyze past reporting data and optimize its reporting algorithm. It can also improve its reporting method by referring to past reporting data. This allows for the optimization of the reporting algorithm by referring to past reporting data. Some or all of the above processes in the reporting unit may be performed using AI, or not. For example, the reporting unit can use past reporting data as input and perform reporting using an AI model that optimizes the reporting algorithm.

[0059] The reporting unit can apply different reporting methods to each service category when submitting reports. For example, the reporting unit can apply a reporting method specialized for the purchase flow to e-commerce services. It can also apply a reporting method specialized for posting and commenting functions to social networking services. Furthermore, it can apply a reporting method specialized for security checks to financial services. By applying different reporting methods to each service category, more appropriate reporting becomes possible. Some or all of the above processing in the reporting unit may be performed using AI, or not. For example, the reporting unit can perform reporting using an AI model that takes service category data as input and outputs a reporting method.

[0060] The reporting unit can determine the priority of reports based on the service release date. For example, it can prioritize reporting on services scheduled for release soon, and postpone reporting on services with a later release date. Furthermore, the reporting unit can adjust the reporting priority in stages according to the release date. This allows for more effective reporting by prioritizing reports based on the service release date. Some or all of the above processing in the reporting unit may be performed using AI, or not. For example, the reporting unit can use an AI model that takes service release date data as input and outputs reporting priorities to perform the reporting.

[0061] The reporting unit can refer to relevant market data for the service when making reports. For example, the reporting unit can make reports based on the service's market share. It can also refer to data on the service's competitors when making reports. Furthermore, it can consider market trends for the service when making reports. This allows for more appropriate reporting by referring to relevant market data for the service. Some or all of the above processing in the reporting unit may be performed using AI or not. For example, the reporting unit can use an AI model that takes relevant market data for the service as input and makes reports.

[0062] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0063] The user simulation agent system can analyze a user's past usage history and generate optimal test cases. For example, it can generate test cases based on functions that the user has frequently used in the past. It can also analyze a user's past operation patterns and generate optimal test cases. Furthermore, it can generate test cases that avoid errors by referring to the user's past error history. In this way, optimal test cases can be generated by analyzing a user's past usage history. Some or all of the above processing in the test case generation unit may be performed using AI, or it may be performed without using AI.

[0064] The user simulation agent system can filter test cases based on the user's current usage and areas of interest. For example, it can filter test cases based on the functions the user is currently using. It can also filter relevant test cases based on the user's areas of interest. Furthermore, it can filter the most suitable test cases according to the user's current operation status. This allows for the generation of more appropriate test cases by filtering test cases based on the user's current usage and areas of interest. Some or all of the above processing in the test case generation unit may be performed using AI or not.

[0065] The user simulation agent system can prioritize the generation of highly relevant test cases by considering the user's geographical location. For example, if the user is in a specific region, test cases related to that region can be prioritized. Similarly, if the user is traveling, test cases related to travel can be prioritized. Furthermore, if the user is at home, test cases suitable for use at home can be prioritized. In this way, highly relevant test cases can be generated by considering the user's geographical location. Some or all of the above processing in the test case generation unit may be performed using AI or not.

[0066] The user simulation agent system can analyze a user's social media activity and generate relevant test cases. For example, it can generate test cases based on the content a user frequently posts on social media. It can also generate test cases based on a user's interests on social media. Furthermore, it can generate test cases based on a user's social media friendships. In this way, relevant test cases can be generated by analyzing a user's social media activity. Some or all of the above processing in the test case generation unit may be performed using AI or not.

[0067] The user simulation agent system can adjust the level of detail of test cases based on the importance of the service during test case generation. For example, it can generate detailed test cases for important services and concise test cases for less important services. Furthermore, it can adjust the level of detail of test cases in stages according to their importance. This allows for more effective testing by adjusting the level of detail of test cases based on the importance of the service. Some or all of the above processing in the test case generation unit may be performed using a generation AI, or it may be performed without using a generation AI.

[0068] The user simulation agent system can apply different test algorithms depending on the service category when generating test cases. For example, a test algorithm specialized for the purchase flow can be applied to e-commerce services. Similarly, a test algorithm specialized for posting and commenting functions can be applied to social networking services. Furthermore, a test algorithm specialized for security checks can be applied to financial services. By applying different test algorithms depending on the service category, more effective testing becomes possible. Some or all of the above-described processes in the test case generation unit may be performed using a generation AI, or they may be performed without using a generation AI.

[0069] The user simulation agent system can prioritize test cases based on the service release date when generating them. For example, it can prioritize generating test cases for services scheduled for release soon, and postpone generating test cases for services with a later release date. Furthermore, it can adjust the priority of test cases in stages according to the release date. This allows for more effective testing by prioritizing test cases based on the service release date. Some or all of the above processing in the test case generation unit may be performed using a generation AI, or it may be performed without using a generation AI.

[0070] The following briefly describes the processing flow for example form 1.

[0071] Step 1: The user feature indicator specifies the user characteristics to be imitated. For example, the user feature indicator can specify user characteristics such as age, gender, and usage history. Step 2: The test case generation unit generates test cases based on the features specified by the user feature specification unit. For example, the test case generation unit can generate scenario-based test cases or functional test cases. Some or all of the above-described processes in the test case generation unit may be performed using a generation AI, or they may not be performed using a generation AI. Step 3: The operation verification unit performs operation verification based on the test cases generated by the test case generation unit. For example, the operation verification unit can perform operation verification based on the success criteria for the test and the error detection method. Some or all of the above processes in the operation verification unit may be performed using AI or not. Step 4: The evidence recording unit records the results obtained by the operation verification unit. For example, the evidence recording unit can record the results in the form of log files, screenshots, error reports, etc. Some or all of the above processing in the evidence recording unit may be performed using AI or not.

[0072] (Example of form 2) The user simulation agent system according to an embodiment of the present invention is a system for reducing the costs that web service providers have to ensure service quality and for automating user-centric testing. This system provides an agent that mimics the behavior of a service user to detect potential bugs and implementation omissions. This agent uses the service on behalf of a user by specifying the characteristics of the user to be mimicked. There are two types of users: users who understand the specifications (E2E testing) and users who do not understand the specifications (monkey testing). For example, in E2E testing, the procedure involves reading the specifications, considering test patterns, launching a browser to verify that the behavior matches the specifications, and leaving evidence (screenshots or videos). In monkey testing, the procedure involves launching a browser without reading the specifications, checking screen items, performing possible actions, and reporting any unexpected behavior. This agent utilizes generative AI to automate the creation of test cases and operational verification. It also performs random actions with only screen items as input and detects unexpected behavior. This reduces the cost of ensuring service quality and improves service quality by detecting potential bugs before they reach the user. This allows the user simulation agent system to improve the quality of service.

[0073] The user simulation agent system according to this embodiment includes a user characteristic instruction unit, a test case generation unit, an operation verification unit, and an evidence recording unit. The user characteristic instruction unit specifies the characteristics of a user to be imitated. For example, the user characteristic instruction unit can specify user characteristics such as age, gender, and usage history. The test case generation unit generates test cases based on the characteristics specified by the user characteristic instruction unit. For example, the test case generation unit can generate scenario-based test cases or functional test cases. Some or all of the above-described processes in the test case generation unit may be performed using a generation AI, or not. For example, the test case generation unit can generate test cases using a generation AI model that takes the characteristics specified by the user characteristic instruction unit as input and outputs test cases. The operation verification unit performs operation verification based on the test cases generated by the test case generation unit. For example, the operation verification unit can perform operation verification based on test success criteria and error detection methods. Some or all of the above-described processes in the operation verification unit may be performed using AI, or not. For example, the operation verification unit can perform operation verification using an AI model that takes test cases generated by the test case generation unit as input and outputs the results of operation verification. The evidence recording unit records the results obtained by the operation verification unit. For example, the evidence recording unit can record the results in the form of log files, screenshots, error reports, etc. Some or all of the above processing in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can record evidence using an AI model that takes the results obtained by the operation verification unit as input and outputs evidence. As a result, the user simulation agent system according to the embodiment can improve the quality of service.

[0074] The user characteristic directive specifies the characteristics of the user to be imitated. For example, the user characteristic directive can specify user characteristics such as age, gender, and usage history. Specifically, the user characteristic directive can specify the user's age within a range such as teens, twenties, or thirties, and select gender from options such as male, female, or other. Furthermore, detailed data such as past purchase history, access history, and usage frequency can be specified for usage history. This allows the user characteristic directive to create a concrete profile of the user to be imitated, thereby improving the accuracy of the simulation. In addition, the user characteristic directive can also specify psychological characteristics such as the user's interests, concerns, and behavioral patterns. For example, by specifying purchasing tendencies for specific products or access tendencies at specific times of day, a more realistic user simulation can be achieved. In this way, the user characteristic directive can cover a wide range of user characteristics and provide a foundation for generating test cases that correspond to various scenarios.

[0075] The test case generation unit generates test cases based on the features specified by the user feature specification unit. For example, the test case generation unit can generate scenario-based test cases and functional test cases. Specifically, as a scenario-based test case, it generates cases that simulate a series of steps in which a user performs a specific operation. For example, it can generate a test case that includes a series of operations from when a user searches for a product, adds it to their cart, and completes the purchase process. As a functional test case, it generates cases to verify whether a specific function works correctly. For example, it can generate test cases for individual functions such as login, search, and payment. Some or all of the above processing in the test case generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the test case generation unit can generate test cases using a generation AI model that takes features specified by the user feature specification unit as input and outputs test cases. The generation AI model can learn from past test case data and user behavior data and generate optimal test cases based on the specified features. As a result, the test case generation unit can achieve efficient and highly accurate test case generation and contribute to improving the overall quality of the system.

[0076] The operation verification unit performs operation verification based on test cases generated by the test case generation unit. For example, the operation verification unit can perform operation verification based on test success criteria and error detection methods. Specifically, the operation verification unit executes each function of the system according to the test cases and compares the expected results with the actual results. For example, in the login function test case, it verifies whether login is successful when the correct username and password are entered, and whether an appropriate error message is displayed when an incorrect username or password is entered. In addition, as an error detection method, the operation verification unit can analyze system log files and error messages to detect abnormal operation or the occurrence of errors. Some or all of the above processing in the operation verification unit may be performed using AI or not. For example, the operation verification unit can perform operation verification using an AI model that takes test cases generated by the test case generation unit as input and outputs the results of operation verification. The AI ​​model can learn past test results and error patterns and evaluate the system's operation based on the test cases. This enables the operation verification unit to achieve efficient and highly accurate operation verification, contributing to the improvement of system quality.

[0077] The evidence recording unit records the results obtained by the operation verification unit. For example, the evidence recording unit can record results in the form of log files, screenshots, and error reports. Specifically, the evidence recording unit saves log files obtained at each step of the operation verification, and records the test execution status and error occurrences in detail. In addition, by saving screenshots, the screen state during test execution can be visually confirmed. Furthermore, it can generate error reports that describe the error content, conditions under which it occurred, and steps to reproduce it in detail. Some or all of the above processing in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can record evidence using an AI model that takes the results obtained by the operation verification unit as input and outputs evidence. The AI ​​model can learn from past evidence data and propose the optimal recording method and error report generation method. As a result, the evidence recording unit can achieve efficient and highly accurate evidence recording and contribute to improving the quality of the system.

[0078] The operation verification unit includes an action execution unit that performs random actions. The action execution unit performs random actions. For example, the action execution unit can perform random actions such as random clicks or random inputs. Some or all of the above-described processing in the action execution unit may be performed using AI or not. For example, the action execution unit can perform random actions using an AI model that takes screen items as input and outputs random actions. This makes it possible to detect unexpected behavior by performing random actions.

[0079] The action execution unit can perform random actions using only screen items as input. For example, the action execution unit can perform random actions such as random clicks or random inputs using only screen items as input. This allows it to mimic user operations by performing random actions using only screen items as input. Some or all of the above processing in the action execution unit may be performed using AI or not. For example, the action execution unit can perform random actions using an AI model that takes screen items as input and outputs random actions.

[0080] The operation verification unit includes a reporting unit that reports unexpected behavior. The reporting unit reports unexpected behavior. For example, the reporting unit can report unexpected behavior such as error messages, crashes, or unforeseen actions. Some or all of the above processing in the reporting unit may be performed using AI or not. For example, the reporting unit can report unexpected behavior using an AI model that takes the unexpected behavior detected by the operation verification unit as input and outputs the report content. This makes it possible to detect potential bugs or implementation omissions by reporting unexpected behavior.

[0081] The reporting unit can detect and report unexpected behavior. For example, the reporting unit can detect and report unexpected behavior using log analysis or anomaly detection algorithms. This allows for improvement of service quality by detecting and reporting unexpected behavior. Some or all of the above-described processes in the reporting unit may be performed using AI or not. For example, the reporting unit can report unexpected behavior using an AI model that takes unexpected behavior detected by the operation verification unit as input and outputs the report content.

[0082] The user feature indicator can estimate the user's emotions and adjust the user characteristics to be mimicked based on the estimated emotions. For example, if the user is stressed, the user feature indicator can mimic the preference for simple operations. If the user is relaxed, it can mimic the willingness to perform complex operations. If the user is in a hurry, it can mimic the preference for quick operations. By adjusting the mimicked characteristics based on the user's emotions, a more realistic representation of the user's behavior can be achieved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the user feature indicator may be performed using AI or not. For example, the user feature indicator can adjust the user characteristics to be mimicked using an AI model that takes user emotion data as input and outputs the user characteristics to be mimicked.

[0083] The user feature instruction unit can analyze the user's past usage history and select the optimal user features. For example, the user feature instruction unit can select features to mimic based on functions that the user has frequently used in the past. It can also analyze the user's past operation patterns and select the optimal features. Furthermore, the user feature instruction unit can select features to avoid errors by referring to the user's past error history. In this way, the optimal user features can be selected by analyzing the user's past usage history. Some or all of the above processing in the user feature instruction unit may be performed using AI or not. For example, the user feature instruction unit can select the optimal user features using an AI model that takes the user's past usage history data as input and outputs the optimal user features.

[0084] The user feature indicator can filter user features based on the user's current usage and areas of interest. For example, the user feature indicator can filter features to mimic based on the functions the user is currently using. It can also filter relevant features based on the user's areas of interest. Furthermore, it can filter the most appropriate features according to the user's current operation status. This allows for the selection of more appropriate user features by filtering features based on the user's current usage and areas of interest. Some or all of the above processing in the user feature indicator may be performed using AI or not. For example, the user feature indicator can filter user features using an AI model that takes the user's current usage data and areas of interest data as input and outputs filtered user features.

[0085] The user feature indicator can estimate the user's emotions and determine the priority of users to emulate based on the estimated emotions. For example, if the user is stressed, the user feature indicator may prioritize operations that reduce stress. If the user is relaxed, the user feature indicator may prioritize complex operations. If the user is in a hurry, the user feature indicator may prioritize quick operations. This allows for the reproduction of more realistic user behavior by determining priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the user feature indicator may be performed using AI or not. For example, the user feature indicator can determine the priority of users to emulate using an AI model that takes user emotion data as input and outputs the priority of users to emulate.

[0086] The user feature indicator can prioritize highly relevant user features by considering the user's geographical location information. For example, if the user is in a specific region, the user feature indicator can prioritize features related to that region. Furthermore, if the user is traveling, the user feature indicator can prioritize features related to travel. Also, if the user is at home, the user feature indicator can prioritize features suitable for use at home. This allows for the selection of highly relevant user features by considering the user's geographical location information. Some or all of the above processing in the user feature indicator may be performed using AI or not. For example, the user feature indicator can use an AI model that takes the user's geographical location information as input and outputs highly relevant user features to indicate user features.

[0087] The user feature indicator can analyze a user's social media activity and indicate relevant user features. For example, the user feature indicator can indicate features based on the content a user frequently posts on social media. It can also indicate features based on a user's interests on social media. Furthermore, it can indicate features based on a user's friendships on social media. This allows for the selection of relevant user features by analyzing a user's social media activity. Some or all of the above processing in the user feature indicator may be performed using AI or not. For example, the user feature indicator can indicate user features using an AI model that takes a user's social media activity data as input and outputs relevant user features.

[0088] The test case generation unit can estimate the user's emotions and adjust the way the test cases are presented based on the estimated emotions. For example, if the user is relaxed, the test case generation unit can generate test cases with detailed explanations. If the user is in a hurry, the test case generation unit can generate concise test cases. If the user is excited, the test case generation unit can generate visually stimulating test cases. By adjusting the way the test cases are presented based on the user's emotions, more appropriate test cases can be generated. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the test case generation unit may be performed using generative AI or not. For example, the test case generation unit can adjust the way the test cases are presented using a generative AI model that takes user emotion data as input and outputs the way the test cases are presented.

[0089] The test case generation unit can adjust the level of detail of test cases based on the importance of the service during test case generation. For example, the test case generation unit can generate detailed test cases for important services. Conversely, it can generate concise test cases for less important services. Furthermore, the test case generation unit can adjust the level of detail of test cases in stages according to their importance. This allows for more effective testing by adjusting the level of detail of test cases based on the importance of the service. Some or all of the above processing in the test case generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the test case generation unit can adjust the level of detail of test cases using a generation AI model that takes service importance data as input and outputs the level of detail of test cases.

[0090] The test case generation unit can apply different test algorithms depending on the service category when generating test cases. For example, for e-commerce services, the test case generation unit can apply a test algorithm specialized in the purchase flow. For social networking services, it can apply a test algorithm specialized in posting and commenting functions. For financial services, it can apply a test algorithm specialized in security checks. By applying different test algorithms depending on the service category, more effective testing becomes possible. Some or all of the above processing in the test case generation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the test case generation unit can apply a test algorithm using a generative AI model that takes service category data as input and outputs the test algorithm to be applied.

[0091] The test case generation unit can estimate the user's emotions and adjust the length of the test cases based on the estimated emotions. For example, if the user is in a hurry, the test case generation unit can generate short test cases. If the user is relaxed, the test case generation unit can generate detailed test cases. If the user is excited, the test case generation unit can generate visually stimulating test cases. By adjusting the length of the test cases based on the user's emotions, more appropriate test cases can be generated. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the test case generation unit may be performed using generative AI or not. For example, the test case generation unit can adjust the length of the test cases using a generative AI model that takes user emotion data as input and outputs the length of the test cases.

[0092] The test case generation unit can determine the priority of test cases based on the service release date when generating test cases. For example, the test case generation unit will prioritize generating test cases for services scheduled for release soon. Conversely, it can postpone generating test cases for services whose release is far off. Furthermore, the test case generation unit can adjust the priority of test cases in stages according to the release date. This allows for more effective testing by determining the priority of test cases based on the service release date. Some or all of the above processing in the test case generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the test case generation unit can determine the priority of test cases using a generation AI model that takes service release date data as input and outputs the priority of test cases.

[0093] The test case generation unit can adjust the order of test cases based on the relationships between services during the test case generation process. For example, the test case generation unit can prioritize generating test cases for highly relevant services. It can also postpone generating test cases for less relevant services. Furthermore, the test case generation unit can adjust the order of test cases in stages according to the relationships between services. This allows for more effective testing by adjusting the order of test cases based on the relationships between services. Some or all of the above-described processes in the test case generation unit may be performed using a generative AI, or they may not. For example, the test case generation unit can adjust the order of test cases using a generative AI model that takes service relationship data as input and outputs the order of test cases.

[0094] The operation verification unit can estimate the user's emotions and adjust the operation verification criteria based on the estimated user emotions. For example, if the user is relaxed, the operation verification unit can perform a detailed operation verification. If the user is in a hurry, the operation verification unit can perform a concise operation verification. If the user is excited, the operation verification unit can perform a visually stimulating operation verification. By adjusting the operation verification criteria based on the user's emotions, more appropriate operation verification becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the operation verification unit may be performed using AI or not. For example, the operation verification unit can adjust the operation verification criteria using an AI model that takes user emotion data as input and outputs operation verification criteria.

[0095] The operation verification unit can improve the accuracy of operation verification by considering the interrelationships between services during the verification process. For example, the operation verification unit can verify data exchange between services. Furthermore, the operation verification unit can perform operation verification while considering the dependencies between services. In addition, the operation verification unit can verify the interactions between services. As a result, the accuracy of operation verification is improved by considering the interrelationships between services. Some or all of the above processing in the operation verification unit may be performed using AI or not. For example, the operation verification unit can take interrelationship data between services as input and perform operation verification using an AI model that improves the accuracy of operation verification.

[0096] The operation verification unit can perform operation verification while considering the attribute information of the service provider. For example, the operation verification unit can perform operation verification while considering the reliability of the service provider. It can also perform operation verification while considering the past performance of the service provider. Furthermore, it can perform operation verification while considering the technical capabilities of the service provider. As a result, the accuracy of operation verification is improved by considering the attribute information of the service provider. Some or all of the above processing in the operation verification unit may be performed using AI or not. For example, the operation verification unit can take the attribute information of the service provider as input and perform operation verification using an AI model that improves the accuracy of operation verification.

[0097] The operation verification unit can estimate the user's emotions and adjust the order in which the operation verification results are displayed based on the estimated user emotions. For example, if the user is relaxed, the operation verification unit can prioritize displaying detailed results. If the user is in a hurry, the operation verification unit can prioritize displaying results that summarize the key points. If the user is excited, the operation verification unit can prioritize displaying visually stimulating results. By adjusting the order in which the operation verification results are displayed based on the user's emotions, more appropriate results can be displayed. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the operation verification unit may be performed using AI or not. For example, the operation verification unit can adjust the order in which the operation verification results are displayed using an AI model that takes user emotion data as input and outputs the order in which the operation verification results are displayed.

[0098] The operation verification unit can perform operation verification while considering the geographical distribution of the service. For example, the operation verification unit can perform operation verification for each region where the service is provided. Furthermore, the operation verification unit can perform operation verification in geographically different environments. In addition, the operation verification unit can perform operation verification while considering the user characteristics of each region. As a result, the accuracy of operation verification is improved by considering the geographical distribution of the service. Some or all of the above processing in the operation verification unit may be performed using AI or not. For example, the operation verification unit can take geographical distribution data of the service as input and perform operation verification using an AI model that improves the accuracy of operation verification.

[0099] The operation verification unit can improve the accuracy of operation verification by referring to relevant service literature during operation verification. For example, the operation verification unit performs operation verification by referring to technical literature related to the service. The operation verification unit can also perform operation verification by referring to patent documents related to the service. Furthermore, the operation verification unit can perform operation verification by referring to research papers related to the service. As a result, the accuracy of operation verification is improved by referring to relevant service literature. Some or all of the above processing in the operation verification unit may be performed using AI or not. For example, the operation verification unit can take relevant service literature data as input and perform operation verification using an AI model that improves the accuracy of operation verification.

[0100] The evidence recording unit can estimate the user's emotions and adjust the method of recording evidence based on the estimated emotions. For example, if the user is relaxed, the evidence recording unit can record detailed evidence. If the user is in a hurry, the evidence recording unit can record concise evidence. If the user is excited, the evidence recording unit can record visually stimulating evidence. By adjusting the method of recording evidence based on the user's emotions, more appropriate evidence recording becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can adjust the method of recording evidence using an AI model that takes user emotion data as input and outputs the method of recording evidence.

[0101] The evidence recording unit can optimize its recording algorithm by referring to past evidence data when recording evidence. For example, the evidence recording unit can select the optimal recording method based on past evidence data. Furthermore, the evidence recording unit can analyze past evidence data and optimize its recording algorithm. It can also improve the method of recording evidence by referring to past evidence data. This allows for the optimization of the recording algorithm by referring to past evidence data. Some or all of the above processes in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can record evidence using an AI model that optimizes the recording algorithm based on past evidence data as input.

[0102] The evidence recording unit can apply different recording methods to each service category when recording evidence. For example, for e-commerce services, the evidence recording unit can apply an evidence recording method specialized for the purchase flow. For social networking services, the evidence recording unit can apply an evidence recording method specialized for posting and commenting functions. For financial services, the evidence recording unit can apply an evidence recording method specialized for security checks. By applying different recording methods to each service category, more appropriate evidence recording becomes possible. Some or all of the above processing in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can record evidence using an AI model that takes service category data as input and outputs a recording method.

[0103] The evidence recording unit can estimate the user's emotions and adjust the importance of the evidence based on the estimated emotions. For example, if the user is relaxed, the evidence recording unit can record detailed evidence. If the user is in a hurry, the evidence recording unit can record concise evidence. If the user is excited, the evidence recording unit can record visually stimulating evidence. This allows for more appropriate evidence recording by adjusting the importance of the evidence based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can adjust the importance of the evidence using an AI model that takes user emotion data as input and outputs the importance of the evidence.

[0104] The evidence recording unit can determine the priority of evidence based on the service release date when recording evidence. For example, the evidence recording unit will prioritize recording evidence for services scheduled for release in the near future. Conversely, it can postpone recording evidence for services with a distant release date. Furthermore, the evidence recording unit can adjust the priority of evidence in stages according to the release date. This enables more effective evidence recording by determining the priority of evidence based on the service release date. Some or all of the above processing in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can record evidence using an AI model that takes service release date data as input and outputs the priority of evidence.

[0105] The evidence recording unit can record evidence by referring to relevant market data for the service at the time of evidence recording. For example, the evidence recording unit can record evidence based on the service's market share. The evidence recording unit can also record evidence by referring to data of the service's competitors. Furthermore, the evidence recording unit can record evidence by considering the service's market trends. This makes it possible to record more appropriate evidence by referring to relevant market data for the service. Some or all of the above processing in the evidence recording unit may be performed using AI or not. For example, the evidence recording unit can record evidence using an AI model that takes relevant market data for the service as input and records evidence.

[0106] The action execution unit can estimate the user's emotions and determine the priority of actions to perform based on the estimated emotions. For example, if the user is relaxed, the action execution unit may prioritize detailed actions. If the user is in a hurry, the action execution unit may prioritize quick actions. If the user is excited, the action execution unit may prioritize visually stimulating actions. By determining the priority of actions to perform based on the user's emotions, more appropriate actions can be performed. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the action execution unit may be performed using AI or not. For example, the action execution unit may determine the priority of actions using an AI model that takes user emotion data as input and outputs the priority of actions to perform.

[0107] The action execution unit can improve the accuracy of actions by considering the interrelationships between services when executing an action. For example, the action execution unit can execute actions while considering data linkages between services. It can also execute actions while considering dependencies between services. Furthermore, it can execute actions while considering interactions between services. As a result, the accuracy of actions is improved by considering the interrelationships between services. Some or all of the above processing in the action execution unit may be performed using AI or not. For example, the action execution unit can take interrelationship data between services as input and execute actions using an AI model that improves the accuracy of actions.

[0108] The action execution unit can perform actions while considering the attribute information of the service provider. For example, the action execution unit can perform actions while considering the reliability of the service provider. It can also perform actions while considering the past performance of the service provider. Furthermore, it can perform actions while considering the technical capabilities of the service provider. This improves the accuracy of actions by considering the attribute information of the service provider. Some or all of the above processing in the action execution unit may be performed using AI or not. For example, the action execution unit can take the attribute information of the service provider as input and perform actions using an AI model that improves the accuracy of actions.

[0109] The action execution unit can estimate the user's emotions and adjust how the actions to be performed are displayed based on the estimated emotions. For example, if the user is relaxed, the action execution unit can provide a detailed display. If the user is in a hurry, the action execution unit can provide a concise display. If the user is excited, the action execution unit can provide a visually stimulating display. By adjusting how the actions to be performed are displayed based on the user's emotions, more appropriate action displays become possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the action execution unit may be performed using AI or not. For example, the action execution unit can adjust how the actions are displayed using an AI model that takes user emotion data as input and outputs how the actions to be performed are displayed.

[0110] The action execution unit can perform actions while considering the geographical distribution of services. For example, the action execution unit can perform actions for each region where the service is provided. Furthermore, the action execution unit can perform actions in geographically different environments. It can also perform actions while considering the user characteristics of each region. This improves the accuracy of actions by considering the geographical distribution of services. Some or all of the above processing in the action execution unit may be performed using AI, or not. For example, the action execution unit can take geographical distribution data of services as input and perform actions using an AI model that improves the accuracy of the actions.

[0111] The action execution unit can improve the accuracy of its actions by referring to relevant service literature during action execution. For example, the action execution unit can perform actions by referring to technical literature related to the service. It can also perform actions by referring to patent documents related to the service. Furthermore, it can perform actions by referring to research papers related to the service. As a result, the accuracy of the actions is improved by referring to relevant service literature. Some or all of the above processing in the action execution unit may be performed using AI or not. For example, the action execution unit can take relevant service literature data as input and perform actions using an AI model that improves the accuracy of the actions.

[0112] The reporting unit can estimate the user's emotions and adjust the report content based on the estimated emotions. For example, if the user is relaxed, the reporting unit can provide a detailed report. If the user is in a hurry, the reporting unit can provide a concise report. If the user is excited, the reporting unit can provide a visually stimulating report. By adjusting the report content based on the user's emotions, more appropriate reports can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reporting unit may be performed using AI or not. For example, the reporting unit can adjust the report content using an AI model that takes user emotion data as input and outputs a report.

[0113] The reporting unit can optimize its reporting algorithm by referring to past reporting data when submitting a report. For example, the reporting unit can select the optimal reporting method based on past reporting data. Furthermore, the reporting unit can analyze past reporting data and optimize its reporting algorithm. It can also improve its reporting method by referring to past reporting data. This allows for the optimization of the reporting algorithm by referring to past reporting data. Some or all of the above processes in the reporting unit may be performed using AI, or not. For example, the reporting unit can use past reporting data as input and perform reporting using an AI model that optimizes the reporting algorithm.

[0114] The reporting unit can apply different reporting methods to each service category when submitting reports. For example, the reporting unit can apply a reporting method specialized for the purchase flow to e-commerce services. It can also apply a reporting method specialized for posting and commenting functions to social networking services. Furthermore, it can apply a reporting method specialized for security checks to financial services. By applying different reporting methods to each service category, more appropriate reporting becomes possible. Some or all of the above processing in the reporting unit may be performed using AI, or not. For example, the reporting unit can perform reporting using an AI model that takes service category data as input and outputs a reporting method.

[0115] The reporting unit can estimate the user's emotions and adjust the importance of the report based on the estimated emotions. For example, if the user is relaxed, the reporting unit can provide a detailed report. If the user is in a hurry, the reporting unit can provide a concise report. If the user is excited, the reporting unit can provide a visually stimulating report. By adjusting the importance of the report based on the user's emotions, more appropriate reports can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reporting unit may be performed using AI or not. For example, the reporting unit can adjust the importance of the report using an AI model that takes user emotion data as input and outputs the importance of the report.

[0116] The reporting unit can determine the priority of reports based on the service release date. For example, it can prioritize reporting on services scheduled for release soon, and postpone reporting on services with a later release date. Furthermore, the reporting unit can adjust the reporting priority in stages according to the release date. This allows for more effective reporting by prioritizing reports based on the service release date. Some or all of the above processing in the reporting unit may be performed using AI, or not. For example, the reporting unit can use an AI model that takes service release date data as input and outputs reporting priorities to perform the reporting.

[0117] The reporting unit can refer to relevant market data for the service when making reports. For example, the reporting unit can make reports based on the service's market share. It can also refer to data on the service's competitors when making reports. Furthermore, it can consider market trends for the service when making reports. This allows for more appropriate reporting by referring to relevant market data for the service. Some or all of the above processing in the reporting unit may be performed using AI or not. For example, the reporting unit can use an AI model that takes relevant market data for the service as input and makes reports.

[0118] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0119] The user simulation agent system can estimate the user's emotions and prioritize test cases based on those emotions. For example, if the user is stressed, it can prioritize operations that reduce stress. If the user is relaxed, it can prioritize complex operations. Furthermore, if the user is in a hurry, it can prioritize quick operations. By prioritizing test cases based on the user's emotions, it is possible to reproduce more realistic user behavior. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI or multimodal generation AI. Some or all of the processing described above in the user feature instruction unit may be performed using AI or not.

[0120] The user simulation agent system can analyze a user's past usage history and generate optimal test cases. For example, it can generate test cases based on functions that the user has frequently used in the past. It can also analyze a user's past operation patterns and generate optimal test cases. Furthermore, it can generate test cases that avoid errors by referring to the user's past error history. In this way, optimal test cases can be generated by analyzing a user's past usage history. Some or all of the above processing in the test case generation unit may be performed using AI, or it may be performed without using AI.

[0121] The user simulation agent system can filter test cases based on the user's current usage and areas of interest. For example, it can filter test cases based on the functions the user is currently using. It can also filter relevant test cases based on the user's areas of interest. Furthermore, it can filter the most suitable test cases according to the user's current operation status. This allows for the generation of more appropriate test cases by filtering test cases based on the user's current usage and areas of interest. Some or all of the above processing in the test case generation unit may be performed using AI or not.

[0122] The user simulation agent system can prioritize the generation of highly relevant test cases by considering the user's geographical location. For example, if the user is in a specific region, test cases related to that region can be prioritized. Similarly, if the user is traveling, test cases related to travel can be prioritized. Furthermore, if the user is at home, test cases suitable for use at home can be prioritized. In this way, highly relevant test cases can be generated by considering the user's geographical location. Some or all of the above processing in the test case generation unit may be performed using AI or not.

[0123] The user simulation agent system can analyze a user's social media activity and generate relevant test cases. For example, it can generate test cases based on the content a user frequently posts on social media. It can also generate test cases based on a user's interests on social media. Furthermore, it can generate test cases based on a user's social media friendships. In this way, relevant test cases can be generated by analyzing a user's social media activity. Some or all of the above processing in the test case generation unit may be performed using AI or not.

[0124] The user simulation agent system can estimate the user's emotions and adjust the way test cases are presented based on those emotions. For example, if the user is relaxed, it can generate test cases with detailed explanations. If the user is in a hurry, it can generate concise test cases. Furthermore, if the user is excited, it can generate visually stimulating test cases. By adjusting the presentation of test cases based on the user's emotions, more appropriate test cases can be generated. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI includes, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the test case generation unit may be performed using generative AI or not.

[0125] The user simulation agent system can adjust the level of detail of test cases based on the importance of the service during test case generation. For example, it can generate detailed test cases for important services and concise test cases for less important services. Furthermore, it can adjust the level of detail of test cases in stages according to their importance. This allows for more effective testing by adjusting the level of detail of test cases based on the importance of the service. Some or all of the above processing in the test case generation unit may be performed using a generation AI, or it may be performed without using a generation AI.

[0126] The user simulation agent system can apply different test algorithms depending on the service category when generating test cases. For example, a test algorithm specialized for the purchase flow can be applied to e-commerce services. Similarly, a test algorithm specialized for posting and commenting functions can be applied to social networking services. Furthermore, a test algorithm specialized for security checks can be applied to financial services. By applying different test algorithms depending on the service category, more effective testing becomes possible. Some or all of the above-described processes in the test case generation unit may be performed using a generation AI, or they may be performed without using a generation AI.

[0127] The user simulation agent system can estimate the user's emotions and adjust the length of test cases based on the estimated emotions. For example, if the user is in a hurry, it can generate short test cases. If the user is relaxed, it can generate detailed test cases. Furthermore, if the user is excited, it can generate visually stimulating test cases. By adjusting the length of test cases based on the user's emotions, more appropriate test cases can be generated. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the test case generation unit may be performed using generative AI or not.

[0128] The user simulation agent system can prioritize test cases based on the service release date when generating them. For example, it can prioritize generating test cases for services scheduled for release soon, and postpone generating test cases for services with a later release date. Furthermore, it can adjust the priority of test cases in stages according to the release date. This allows for more effective testing by prioritizing test cases based on the service release date. Some or all of the above processing in the test case generation unit may be performed using a generation AI, or it may be performed without using a generation AI.

[0129] The following briefly describes the processing flow for example form 2.

[0130] Step 1: The user feature indicator specifies the user characteristics to be imitated. For example, the user feature indicator can specify user characteristics such as age, gender, and usage history. Step 2: The test case generation unit generates test cases based on the features specified by the user feature specification unit. For example, the test case generation unit can generate scenario-based test cases or functional test cases. Some or all of the above-described processes in the test case generation unit may be performed using a generation AI, or they may not be performed using a generation AI. Step 3: The operation verification unit performs operation verification based on the test cases generated by the test case generation unit. For example, the operation verification unit can perform operation verification based on the success criteria for the test and the error detection method. Some or all of the above processes in the operation verification unit may be performed using AI or not. Step 4: The evidence recording unit records the results obtained by the operation verification unit. For example, the evidence recording unit can record the results in the form of log files, screenshots, error reports, etc. Some or all of the above processing in the evidence recording unit may be performed using AI or not.

[0131] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0132] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0133] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0134] Each of the multiple elements described above, including the user characteristic instruction unit, test case generation unit, operation verification unit, evidence recording unit, action execution unit, and reporting unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the user characteristic instruction unit is implemented by the control unit 46A of the smart device 14 and specifies the user's characteristics. The test case generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates test cases based on the specified characteristics. The operation verification unit is implemented by the control unit 46A of the smart device 14 and performs operation verification based on the generated test cases. The evidence recording unit is implemented by the specific processing unit 290 of the data processing unit 12 and records the results of the operation verification. The action execution unit is implemented by the control unit 46A of the smart device 14 and executes a random action. The reporting unit is implemented by the specific processing unit 290 of the data processing unit 12 and reports unexpected behavior. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0135] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0136] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0137] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0138] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0139] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0141] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0142] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0143] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0144] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0145] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0146] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0147] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0148] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0149] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0150] Each of the multiple elements described above, including the user characteristic instruction unit, test case generation unit, operation verification unit, evidence recording unit, action execution unit, and reporting unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the user characteristic instruction unit is implemented by the control unit 46A of the smart glasses 214 and specifies the user's characteristics. The test case generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates test cases based on the specified characteristics. The operation verification unit is implemented by the control unit 46A of the smart glasses 214 and performs operation verification based on the generated test cases. The evidence recording unit is implemented by the specific processing unit 290 of the data processing unit 12 and records the results of the operation verification. The action execution unit is implemented by the control unit 46A of the smart glasses 214 and executes a random action. The reporting unit is implemented by the specific processing unit 290 of the data processing unit 12 and reports unexpected behavior. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0151] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0152] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0153] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0154] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0155] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0157] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0158] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0159] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0160] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0161] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0162] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0163] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0164] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0165] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0166] Each of the multiple elements described above, including the user characteristic instruction unit, test case generation unit, operation verification unit, evidence recording unit, action execution unit, and reporting unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the user characteristic instruction unit is implemented by the control unit 46A of the headset terminal 314 and specifies the user's characteristics. The test case generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates test cases based on the specified characteristics. The operation verification unit is implemented by the control unit 46A of the headset terminal 314 and performs operation verification based on the generated test cases. The evidence recording unit is implemented by the specific processing unit 290 of the data processing unit 12 and records the results of the operation verification. The action execution unit is implemented by the control unit 46A of the headset terminal 314 and executes a random action. The reporting unit is implemented by the specific processing unit 290 of the data processing unit 12 and reports unexpected behavior. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0167] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0168] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0169] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0170] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0171] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0172] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0173] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0174] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0175] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0176] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0177] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0178] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0179] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0180] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0181] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0182] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0183] Each of the multiple elements described above, including the user characteristic instruction unit, test case generation unit, operation verification unit, evidence recording unit, action execution unit, and reporting unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the user characteristic instruction unit is implemented by the control unit 46A of the robot 414 and specifies the user's characteristics. The test case generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates test cases based on the specified characteristics. The operation verification unit is implemented by the control unit 46A of the robot 414 and performs operation verification based on the generated test cases. The evidence recording unit is implemented by the specific processing unit 290 of the data processing unit 12 and records the results of the operation verification. The action execution unit is implemented by the control unit 46A of the robot 414 and executes a random action. The reporting unit is implemented by the specific processing unit 290 of the data processing unit 12 and reports unexpected behavior. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0184] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0185] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0186] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0187] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0188] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0189] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0190] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0191] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0192] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0193] 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.

[0194] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0195] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0196] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0197] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0198] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0199] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0200] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0201] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0202] (Note 1) A user feature instruction unit that specifies the characteristics of the user to be imitated, A test case generation unit that generates test cases based on the features specified by the user feature instruction unit, An operation verification unit that performs operation verification based on the test cases generated by the test case generation unit, An evidence recording unit that records the results obtained by the operation verification unit, Equipped with A system characterized by the following features. (Note 2) The aforementioned operation verification unit is It includes an action execution unit that performs random actions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned action execution unit, Perform a random action using only the screen fields as input. The system described in Appendix 2, characterized by the features described herein. (Note 4) The aforementioned operation verification unit is It is equipped with a reporting unit that reports unexpected behavior. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reporting department, Detect and report unexpected behavior. The system described in Appendix 4, characterized by the features described herein. (Note 6) The user characteristic instruction unit is, It estimates the user's emotions and adjusts the characteristics of the user being imitated based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The user characteristic instruction unit is, Analyze the user's past usage history and select the optimal user characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 8) The user characteristic instruction unit is, Filter user characteristics based on the user's current usage patterns and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The user characteristic instruction unit is, It estimates the user's emotions and determines the priority of which users to emulate based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The user characteristic instruction unit is, Prioritize and display highly relevant user features, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The user characteristic instruction unit is, Analyze users' social media activity and identify relevant user characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 12) The test case generation unit, We estimate the user's emotions and adjust the way the test cases are represented based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The test case generation unit, When generating test cases, adjust the level of detail of the test cases based on the importance of the service. The system described in Appendix 1, characterized by the features described herein. (Note 14) The test case generation unit, When generating test cases, different test algorithms are applied depending on the service category. The system described in Appendix 1, characterized by the features described herein. (Note 15) The test case generation unit, The system estimates the user's emotions and adjusts the length of the test cases based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The test case generation unit, When generating test cases, prioritize them based on the service release date. The system described in Appendix 1, characterized by the features described herein. (Note 17) The test case generation unit, When generating test cases, adjust the order of test cases based on the relevance of the services. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned operation verification unit is The system estimates the user's emotions and adjusts the criteria for performance testing based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned operation verification unit is During operational verification, we improve the accuracy of the verification by considering the interrelationships between services. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned operation verification unit is During operational verification, the service provider's attribute information is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned operation verification unit is The system estimates the user's emotions and adjusts the order in which the results of the behavioral check are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned operation verification unit is During operational testing, the geographical distribution of the service should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned operation verification unit is During operational verification, refer to relevant documentation for the service to improve the accuracy of the verification. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned evidence recording unit is We estimate the user's emotions and adjust the method of recording evidence based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned evidence recording unit is When recording evidence, the recording algorithm is optimized by referring to past evidence data. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned evidence recording unit is When recording evidence, different recording methods are applied for each service category. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned evidence recording unit is We estimate the user's emotions and adjust the importance of the evidence based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned evidence recording unit is When recording evidence, prioritize the evidence based on the service release date. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned evidence recording unit is When recording evidence, refer to relevant market data for the service to record the evidence. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned action execution unit, It estimates the user's emotions and determines the priority of actions to take based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned action execution unit, When executing an action, the interrelationships between services are taken into consideration to improve the accuracy of the action. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned action execution unit, When executing an action, the service provider's attribute information should be taken into consideration. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned action execution unit, It estimates the user's emotions and adjusts how actions are displayed based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned action execution unit, When executing an action, consider the geographical distribution of the service. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned action execution unit, When executing an action, refer to relevant service documentation to improve the accuracy of the action. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned reporting department, The system estimates the user's emotions and adjusts the report based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 37) The aforementioned reporting department, When reporting, the reporting algorithm is optimized by referring to past reporting data. The system described in Appendix 4, characterized by the features described herein. (Note 38) The aforementioned reporting department, When reporting, apply different reporting methods for each service category. The system described in Appendix 4, characterized by the features described herein. (Note 39) The aforementioned reporting department, The system estimates the user's sentiment and adjusts the importance of the report based on the estimated user sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned reporting department, When reporting, prioritize reports based on the service release date. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned reporting department, When reporting, refer to relevant market data for the service. The system described in Appendix 4, characterized by the features described herein. [Explanation of symbols]

[0203] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A user feature instruction unit that specifies the characteristics of the user to be imitated, A test case generation unit that generates test cases based on the features specified by the user feature instruction unit, An operation verification unit that performs operation verification based on the test cases generated by the test case generation unit, An evidence recording unit that records the results obtained by the operation verification unit, Equipped with A system characterized by the following features.

2. The aforementioned operation verification unit is It includes an action execution unit that performs random actions. The system according to feature 1.

3. The aforementioned action execution unit, Perform a random action using only the screen fields as input. The system according to feature 2.

4. The aforementioned operation verification unit is It is equipped with a reporting unit that reports unexpected behavior. The system according to feature 1.

5. The aforementioned reporting department, Detect and report unexpected behavior. The system according to feature 4.

6. The user characteristic instruction unit is, It estimates the user's emotions and adjusts the characteristics of the user being imitated based on the estimated user emotions. The system according to feature 1.

7. The user characteristic instruction unit is, Analyze the user's past usage history and select the optimal user characteristics. The system according to feature 1.

8. The user characteristic instruction unit is, Filter user characteristics based on the user's current usage patterns and areas of interest. The system according to feature 1.

9. The user characteristic instruction unit is, It estimates the user's emotions and determines the priority of which users to emulate based on the estimated emotions. The system according to feature 1.

Images