system

Abstract

We provide the system. [Solution] A means for automatically generating communication error scenarios between multiple services using a generative model, A means for simulating failures in a virtual environment based on the aforementioned scenario, A means for collecting and analyzing data obtained from the aforementioned simulation, Based on the aforementioned analysis results, a means of proposing a solution to the problem, A system that includes this.

Description

Technical Field

[0004] , ,

[0005] , , ,

[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 performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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 modern system development, an architecture that constructs by coordinating a plurality of small-scale services has become common. In such an architecture, the possibility of occurrence of obstacles due to communication problems and resource constraints increases, and it becomes difficult to grasp the behavior during an obstacle. On the other hand, the introduction of chaos engineering involves a high technical burden, and there are problems that require a great deal of man-hours for creating an exhaustive obstacle scenario and conducting tests. Furthermore, it is difficult to cover all unexpected obstacles in conventional tests performed manually. As a result, system vulnerabilities remain, and there is a risk of causing unexpected downtime.

Means for Solving the Problems

[0005] To solve these problems, the present invention provides a system that automatically generates failure scenarios using a generative model. This system includes means for automatically generating communication error scenarios between multiple services and means for simulating failures in a virtual environment based on the generated scenarios. It also includes means for collecting and analyzing test data obtained from the simulation, and can propose solutions to problems based on the results of this analysis. In this way, it is possible to increase the robustness of the system while reducing the technical burden.

[0006] A "generative model" is a machine learning algorithm used to analyze data and generate results based on predetermined conditions.

[0007] A "communication error scenario between services" is a hypothetical situation that describes patterns and behaviors of communication failures that may occur between multiple software components.

[0008] A "virtual environment" is a computer simulation space that replicates the operation of software and hardware by mimicking the actual system configuration.

[0009] "Simulation" is a method of studying or verifying the behavior of real-world processes and systems by imitating them.

[0010] "Means of collecting and analyzing data" refer to the technologies and processes used to capture information generated during tests and simulations and to evaluate that information.

[0011] "Being able to propose solutions" means having the ability to identify the root cause of a problem and to present effective methods or improvement plans to address it. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] 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.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention aims to enhance systems in a microservices architecture by automatically generating failure scenarios using a generative model. To implement this system, the program processes as follows:

[0034] First, the server collects information from each service within the system and, based on that information, utilizes a generative model to automatically generate communication error scenarios. These generated scenarios include anticipated communication outages and overload conditions and are used to anticipate risks in actual service integration.

[0035] Next, the server builds a virtual environment and simulates actual failures based on the generated scenarios. The virtual environment is a replica of the actual production environment and is configured to observe how each service operates and how it behaves when a failure occurs.

[0036] Subsequently, the server collects data during the test execution, such as system response time, error logs, and resource usage, and analyzes this data to identify the root cause of problems and potential weaknesses. This analysis utilizes AI models to detect unusual behavior and changes in patterns.

[0037] Based on the collected and analyzed data, the server suggests solutions and improvements to the user. This allows the user to reduce system vulnerabilities and prevent unexpected failures.

[0038] For example, if a scenario is generated in which communication between services A and B is interrupted, the server will reproduce this communication failure in a virtual environment and observe how many retries service A can perform and how service B responds to the results. If it is found that service A is retrying more than expected and consequently depleting resources, the server will suggest to the user that they review their retry policy and re-evaluate their load balancing strategy.

[0039] In this way, the present invention makes it possible to efficiently promote improvements in system reliability.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server collects metadata and log data from each service to understand all services within the system and their interdependencies. This data includes API endpoint information, uptime, and call frequency.

[0043] Step 2:

[0044] The server uses a generative model based on the collected information to automatically generate failure scenarios. These scenarios include multiple behaviors such as communication interruptions and delays between services, and resource overload.

[0045] Step 3:

[0046] The server creates a virtual environment and places a simulated system environment within it. Here, service containers are started, and a state is created that can mimic the actual service operation.

[0047] Step 4:

[0048] The server will intentionally cause failures according to the generated scenario. For example, it might block network access to a specific service and observe the system's response when communication is interrupted.

[0049] Step 5:

[0050] During testing, the server collects data such as system response time, error messages, and the number of calls between services. This data is used for later analysis.

[0051] Step 6:

[0052] The server analyzes the collected data using an AI model to detect behavior and abnormal patterns during failures. This identifies the root cause of the problem and potential system weaknesses.

[0053] Step 7:

[0054] The server reports the analysis results to the user and suggests system improvements and specific solutions. This allows the user to take steps to reduce system vulnerabilities.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In systems employing a microservices architecture, communication failures between services can have a significant impact on the overall reliability of the system. While effectively preventing such communication failures and stabilizing system operation is crucial, previous methods have faced challenges in predicting failures and developing countermeasures.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for utilizing generation technology to generate communication failure scenarios between multiple activity units, means for reproducing the failures in a virtualized environment based on the scenarios, and means for collecting and analyzing information obtained through the reproduction. This makes it possible to predict communication failures within the system in advance and take effective countermeasures.

[0060] "Generative technology" refers to technologies that use artificial intelligence and machine learning to automatically create new information and scenarios based on data and patterns.

[0061] An "activity unit" is a unit of individual services or components in a microservices architecture, and is an independent system element with a specific function or role.

[0062] A "communication failure scenario" is a preliminary plan created based on anticipated communication errors and connection problems that may occur between different activity units.

[0063] A "virtualized environment" is a computer-based simulation environment designed to mimic an actual production environment and test the behavior of a system.

[0064] "Reproduction" is the process of artificially constructing a specific scenario or condition and then experiencing it in a simulation to see how the system reacts.

[0065] "Information" refers to all data to be analyzed, including data and logs obtained from communication and failure simulations, and system performance indicators.

[0066] "Analysis" is a procedure performed to thoroughly examine collected data in order to identify the causes and characteristics of a problem and clarify areas for improvement.

[0067] The system for implementing this invention is built for systems employing a microservices architecture. The server utilizes a generative AI model to automatically generate communication failure scenarios and enables their reproduction within a virtualized environment.

[0068] The server first collects detailed information from each activity unit within the system. This includes the latency, error rate, and interdependencies of each activity unit. The collected information is used as prompts by the generative AI model to create communication failure scenarios. A specific example of a prompt statement is, "Evaluate the impact of a communication timeout between service A and service B."

[0069] Based on the generated scenarios, the server uses virtual environment management software such as Docker or Kubernetes to build a virtualized environment that closely resembles the actual production environment. In this environment, failure scenarios are reproduced, and the responses of each activity unit and the behavior of the system are observed and recorded.

[0070] The server then collects information obtained from this virtual environment and analyzes it using an AI model. Specifically, it analyzes data such as re-entry data, error logs, and resource usage to identify potential problems and areas for improvement in the system.

[0071] Based on the analysis results, the server will present the user with a solution. This solution may include revising the retry policy or improving the load balancing strategy. This will allow the user to improve system reliability and prevent unexpected communication failures in advance.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The server collects information from the activity units within the system. This information includes dependencies between activity units, communication delays, and error logs. Based on this information, it creates prompt statements to be input into the generated AI model. For example, data to understand the response time of service A and its dependencies with service B may be input, and based on this, a prompt statement such as "Evaluate the impact of a communication timeout between service A and service B" may be output.

[0075] Step 2:

[0076] The server inputs the generated prompt message into the AI ​​model to generate communication failure scenarios. The AI ​​model outputs various communication failure patterns based on the prompt message. These output scenarios include communication outages and overload conditions, illustrating the types of failures the system may face.

[0077] Step 3:

[0078] The server builds a virtualized environment based on the generated communication failure scenario. This environment mimics a real production environment using Docker or Kubernetes. The inputs are failure scenarios and virtual environment templates, and the output is a configuration within the virtual environment that reflects the scenario.

[0079] Step 4:

[0080] The server simulates communication failure scenarios in a virtual environment. Specifically, it intentionally introduces network delays and disconnections and observes how each activity unit reacts. The input is the scenario and the configured virtual environment, and the output is simulation data, such as the number of re-entries and network response time.

[0081] Step 5:

[0082] The server collects data obtained from simulations and analyzes it using an AI model. The input includes simulation data, with particular attention paid to the number of re-entries, error logs, and resource consumption. The output provides analysis results regarding areas where system improvement is needed and potential problems.

[0083] Step 6:

[0084] The server proposes solutions to the user based on the analysis results. Specifically, it suggests improvement methods such as modifying the retry policy or optimizing load balancing settings. The input is the analysis results, and the output is a proposal report for the user. This proposal allows the user to improve system reliability and take measures to prevent future failures.

[0085] (Application Example 1)

[0086] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0087] In modern information processing systems, it is common for multiple information processing units to work together in coordination. However, this complex interaction increases the likelihood of communication errors and malfunctions, which can lead to a decline in or complete shutdown of the entire system, ultimately causing safety and reliability issues. Furthermore, existing systems make it difficult to predict and prevent these failures before they occur.

[0088] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0089] In this invention, the server includes means for automatically generating communication error scenarios between multiple information processing units using a generative model, means for simulating failures in a virtual work area based on the scenarios, means for collecting and interpreting information obtained from the simulation, and means for providing the interpretation results as visual information in real time on a visual display device. This makes it possible to detect potential communication errors and functional failures in the information processing system in advance and propose solutions quickly and effectively.

[0090] A "generative model" is an artificial intelligence technology that has the ability to learn patterns from data and generate new data.

[0091] An "information processing unit" is a fundamental component of a computer that performs information input, processing, and output.

[0092] A "communication error scenario" is a scenario that illustrates specific situations of communication failures that may occur within an information processing system.

[0093] A "virtual workspace" is a virtual work environment that functions within software, but does not have a physical presence.

[0094] "Interpretation" is the act of reading and understanding meaning from collected data.

[0095] A "visual display device" is a hardware device used to present information visually.

[0096] To realize this invention, a system is provided in which a server and a visual display device work in coordination. The server uses a generative model to automatically generate communication error scenarios between information processing units. Specifically, it uses a natural language processing model such as OpenAI's GPT as the generative model to analyze communication data obtained from multiple information processing units and generate patterns of potential communication errors.

[0097] The server constructs a virtual workspace and simulates communication error scenarios that occur within it. This virtual workspace mimics a real-world environment using a real-time data processing framework such as Apache® Kafka. As a result of the simulation, the server collects various data, including system response times and error logs, and interprets this data to identify potential communication failures and propose solutions.

[0098] Users can visually confirm the interpretation results provided by the server using a visual display device. This device features a visually intuitive interface to present collected data to the user in real time. Users can take swift action based on the system's suggestions.

[0099] For example, if the system detects a communication failure in a security camera, the generating AI model uses prompts to perform a specific simulation. An example of a prompt might be, "Generate a failure scenario for camera A in the security camera system and propose the optimal strategy for load balancing to other cameras." This allows the system to quickly provide the user with an appropriate solution, thereby improving system reliability.

[0100] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0101] Step 1:

[0102] The server collects communication data from information processing units in real time. The input is log data from each unit, and the output is a dataset for analysis. This data collection is performed using a data stream platform such as Apache Kafka.

[0103] Step 2:

[0104] The server uses a generative AI model based on the collected dataset to generate potential communication error scenarios. The input is the dataset obtained in step 1, and the output is the generated error scenario. In this process, the generative model utilizes prompt statements to automatically generate scenarios.

[0105] Step 3:

[0106] The server sets up a virtual workspace based on the generated communication error scenario and starts the simulation. The input is the scenario and virtual environment configuration data generated in step 2, and the output is detailed data associated with the simulation execution. Specifically, the communication behavior between units in the event of an anomaly is simulated.

[0107] Step 4:

[0108] The server analyzes the data obtained from the simulation to evaluate the system's response characteristics and error patterns. The input is the simulation data obtained in step 3, and the output is the analysis results that lead to the proposal of specific solutions. Anomaly behavior is detected using an AI algorithm.

[0109] Step 5:

[0110] The user views the analysis results provided by the server through a visual display device. The input is the analysis results obtained in step 4, and the output is the visual information displayed on the screen. For example, a dashboard showing which communication paths are likely to experience failures is displayed.

[0111] Step 6:

[0112] The user monitors the entire system and takes immediate action based on the information displayed on the screen. The input is the interpretation result visually presented in step 5, and the output is the user's instructions for operations and configuration changes. An example prompt used by the generated AI model is, "Please suggest countermeasures for the inter-service failure scenario."

[0113] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0114] This invention combines a generative model and an emotion engine to achieve more effective system operation and user support. The embodiments for carrying out this invention are described below.

[0115] First, the server collects the necessary data from each service within the system and automatically generates communication error scenarios using a generative model. The scenarios generated in this process are deployed in a virtual environment to simulate various failure conditions, taking into account the dependencies within the system.

[0116] Next, the server simulates failures in this virtual environment based on the generated scenario. This allows it to reproduce situations such as disruptions to communication between services or intentional increases in system load.

[0117] As the test progresses, the server uses an emotion engine to analyze the emotions of the user performing the test operations in real time. If a change in emotional state is detected, the system adjusts the suggested solutions and the feedback provided to better respond to the user.

[0118] Specifically, when providing reports based on test results, if the server determines that the user's emotions are negative, it will provide information in a more detailed format, highlighting proactive solutions and success stories. Conversely, if positive emotions are detected, it will focus on providing concise and efficient information.

[0119] Furthermore, the emotion engine receives user feedback and analyzes it to improve the usability of the system itself. For example, if feedback indicates that a user is experiencing stress with a particular operation, it generates suggestions for interface improvements to simplify that operation.

[0120] In this way, the present invention can demonstrate high effectiveness in both technical troubleshooting and user experience.

[0121] The following describes the processing flow.

[0122] Step 1:

[0123] The server collects necessary data from all related services and analyzes system dependencies. This data collection process includes information such as the operational status and communication patterns of each service, and the frequency of API calls.

[0124] Step 2:

[0125] The server uses the collected data to run a generative model and automatically generate communication error scenarios. This generative model considers a variety of failure conditions and outputs scenarios that include potential vulnerabilities that would not normally be noticed.

[0126] Step 3:

[0127] The server builds a virtual environment and deploys the generated failure scenarios within it. This virtual environment is built to simulate the actual system environment and serves as a testbed for evaluating how each service responds.

[0128] Step 4:

[0129] The server runs simulations within a virtual environment, intentionally generating failures such as communication outages and increased load based on failure scenarios. This verifies the fault tolerance and automatic recovery capabilities of each service.

[0130] Step 5:

[0131] During the failure simulation, the server collects test data in real time and simultaneously analyzes the user's emotional state using an emotion engine. Based on user interactions, it determines whether the emotion is positive, negative, or neutral.

[0132] Step 6:

[0133] The server analyzes the simulation results in conjunction with the user's emotional state to identify the root cause of the problem and generate the optimal solution tailored to the user's emotions. For example, if the user is feeling anxious, it will add detailed explanations to reassure them.

[0134] Step 7:

[0135] The server generates a report for the user based on the test results and presents solutions tailored based on sentiment analysis. This ensures that system improvement suggestions take into account not only the technical aspects but also the user experience.

[0136] Step 8:

[0137] Through feedback sessions, users drive further improvements to the interface and procedures based on analysis results obtained using the emotion engine. This feedback allows the system to continuously evolve in a direction that enhances usability.

[0138] (Example 2)

[0139] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0140] In conventional systems, handling communication errors was reactive, making it difficult to comprehensively test all failure conditions in advance. Furthermore, system error information was highly specialized for engineers, preventing the provision of appropriate information by leveraging user feedback and emotional states. Therefore, there is a need for a method that simultaneously improves both fault response and user experience.

[0141] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0142] In this invention, the server includes means for automatically generating communication error scenarios using a generative model, means for simulating failures in a virtual environment, and means for analyzing the user's emotional state in real time and adjusting the information provided. This makes it possible to simulate various failure conditions in advance and consider appropriate countermeasures, and also enables the provision of information according to the user's emotional state.

[0143] A "generative model" is an artificial intelligence technology that learns patterns from data and automatically generates new data and scenarios.

[0144] A "virtual environment" is a simulation environment created on a computer without physical constraints, and is used to test operation under various conditions.

[0145] The "emotion analysis mechanism" is a technological system that analyzes the user's facial expressions and voice data to recognize and classify their emotional state in real time.

[0146] "User's emotional state" refers to the emotional response of a person operating the system, and includes psychological states such as stress, joy, and surprise.

[0147] A "communication error scenario" is a hypothetical scenario created to simulate the specific circumstances and progression of communication failures that may occur between multiple systems.

[0148] "Adjusting information" refers to the act of optimizing the content, format, or timing of data and messages provided in accordance with the user's emotional state or the system's status.

[0149] This invention is a system that uses generative models and emotion analysis mechanisms to improve the user experience and enable preventative and adaptive responses to communication errors.

[0150] The server first collects the necessary data from various services within the system (e.g., databases, APIs). This utilizes industry-standard messaging systems to achieve real-time data streaming. Next, the server automatically generates communication error scenarios by inputting prompts into a generation AI model. An example of such a prompt is, "Generate a scenario that considers the impact of communication errors."

[0151] The generated scenarios are deployed in a virtual environment, and the servers run the simulations. This virtual environment utilizes container technology and an orchestration platform to create a flexible and large-scale test environment. This allows for the reproduction of diverse failure conditions without disrupting the normal operation of the system.

[0152] The terminal monitors the user's actions while the simulation is running. The emotion analysis mechanism receives this data and analyzes the user's emotional state in real time from their facial expressions and voice. Specifically, the emotion analysis outputs the user's psychological state, such as stress and satisfaction, as numerical values ​​or categories.

[0153] Based on this emotional data, the server adjusts the information and feedback it provides to the user. For example, if a user expresses negative emotions due to a communication problem, the server will provide more detailed, step-by-step guidance to facilitate communication. Conversely, if positive emotions are detected, the focus will be on providing concise and easy-to-understand information.

[0154] Ultimately, based on feedback, we will propose further interface optimizations to improve the system and enhance its usability. This will allow users to use the system more intuitively and comfortably.

[0155] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0156] Step 1:

[0157] The server collects the necessary data from each service within the system. This input data includes communication logs and performance metrics. The server streams the data through the messaging system and aggregates it in real time. The output is an integrated dataset in a format suitable for analysis.

[0158] Step 2:

[0159] The server uses the collected data to input a prompt message into the generated AI model. The prompt message used is "Create a scenario that includes communication errors." In this process, the server receives the communication error scenario generated by the AI ​​model. The output is detailed scenario data used for simulation in a virtual environment.

[0160] Step 3:

[0161] The server deploys the generated scenarios into a virtual environment. The input is the scenario data generated in the previous step, and the virtual environment is built using container technology. The server then starts simulating communication failures within this environment. The output is the execution result data for each scenario.

[0162] Step 4:

[0163] The terminal monitors user actions during simulation and analyzes that data using an emotion analysis mechanism. Inputs include user action data and environmental sensor data. The emotion analysis mechanism analyzes the monitored data in real time to determine the user's emotional state. Outputs include metrics representing the user's emotional state.

[0164] Step 5:

[0165] The server adjusts feedback information based on the user's emotional state metrics. Inputs include emotional state metrics and notification data from various services. The server optimizes the information provided to the user accordingly. Specifically, if negative emotions are present, it generates detailed and positive feedback; if positive emotions are present, it provides summarized information. Outputs are the adjusted feedback messages and suggestions.

[0166] Step 6:

[0167] The user receives adjusted feedback from the server and performs actions based on that feedback. After receiving the feedback, the user provides new input regarding their actions, and this data is sent back to the system as the basis for further improvement suggestions. The output is the result of the user's improved actions.

[0168] (Application Example 2)

[0169] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0170] In modern information systems, communication errors and failures can impair the user experience and lead to decreased customer satisfaction. Furthermore, the lack of adequate mechanisms for accurately understanding and responding to users' emotional states in real time can negatively impact the quality of customer service. To efficiently resolve these issues, a system is needed that can respond quickly and flexibly to communication errors and provide appropriate feedback tailored to the user's emotional state.

[0171] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0172] In this invention, the server includes means for automatically generating communication error scenarios between multiple services using a generative model, means for simulating failures in a virtual environment based on the scenarios, and means for analyzing the user's emotions using an emotion engine and dynamically providing information based on the analysis results. This makes it possible to provide appropriate feedback and solutions that correspond to the user's emotions even in the event of a communication error.

[0173] A "generative model" refers to algorithms and methods for automatically generating communication error scenarios.

[0174] A "communication error scenario" refers to a hypothetical configuration of possible communication failure patterns that may occur between multiple services.

[0175] A "virtual environment" refers to a simulation space built on a computer that is different from the actual system.

[0176] An "emotion engine" refers to software or algorithms used to analyze a user's emotional state.

[0177] "User emotion analysis" refers to the process of inferring a user's emotional state at a given time based on their actions and behavior.

[0178] A "solution" refers to specific countermeasures or methods to be taken in response to a particular problem or obstacle.

[0179] The system for implementing this invention has a server-centric configuration. The server uses a generative AI model to automatically generate scenarios between multiple services where communication errors may occur. The generated scenarios are reproduced in a virtual environment, and user interactions are simulated.

[0180] The server uses an emotion engine to analyze in real time what emotions the user experiences within the simulation. This emotion analysis information is used to provide feedback and solutions for communication errors. For example, if a transaction fails while a user is in the process of purchasing a particular product, the server will take that emotion into consideration and offer proactive solutions or suggestions for similar products.

[0181] The analysis utilizes the OpenAI API, and when providing information based on real-time sentiment analysis results, real-time data processing is performed using the Django framework. The frontend is built using React Native to provide interactive information to the user.

[0182] As a concrete example, consider a scenario where a user is searching for a smartphone on an e-commerce site. If the user shows signs of hesitation in making a purchase, the server immediately presents alternative product recommendations and relevant success stories. This can increase the user's willingness to buy and reduce stress caused by communication errors.

[0183] The generative AI model creates optimal prompts based on the situation, helping the server provide appropriate feedback. A concrete example of a prompt might be, "If the user experiences frustration on product page B, suggest alternative products."

[0184] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0185] Step 1:

[0186] The server automatically generates communication error scenarios using a generative AI model. In this process, it takes dependency information for each service within the system as input and outputs scenarios that reflect a variety of failure conditions. This scenario generation utilizes past error data as training data and performs data calculations to generate new error scenarios.

[0187] Step 2:

[0188] The server deploys the generated communication error scenario into a virtual environment and starts the simulation. The virtual environment simulates the actual operating environment and artificially generates failures, such as blocking communication between services, based on the generated scenario. The input is the generated error scenario, and the resulting service responses and state changes are collected as output.

[0189] Step 3:

[0190] The user's terminal interacts with the virtual environment during the simulation, and the server uses an emotion engine to analyze the user's emotional state in real time. Using user operation logs and eye-tracking data as input, the emotion engine infers the user's emotions and sends the inferred result to the server as output. This process employs non-invasive emotion recognition technology.

[0191] Step 4:

[0192] The server combines the sentiment analysis results with the simulation results of communication error scenarios to build an AI model that generates appropriate solutions and feedback. It receives the user's emotional state as input, generates the most appropriate prompt based on that, and outputs information showing alternative solutions and success stories.

[0193] Step 5:

[0194] The user's device displays solutions and feedback sent from the server on its interface. React Native is used to present the data in an intuitive and easy-to-understand format for the user. Input is feedback from the server, and this feedback is output in a way that encourages user action.

[0195] 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.

[0196] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0197] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0198] [Second Embodiment]

[0199] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0200] 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.

[0201] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0202] 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.

[0203] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0204] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0205] 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.

[0206] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0207] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0208] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0209] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0210] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0211] This invention aims to enhance systems in a microservices architecture by automatically generating failure scenarios using a generative model. To implement this system, the program processes as follows:

[0212] First, the server collects information from each service within the system and, based on that information, utilizes a generative model to automatically generate communication error scenarios. These generated scenarios include anticipated communication outages and overload conditions and are used to anticipate risks in actual service integration.

[0213] Next, the server builds a virtual environment and simulates actual failures based on the generated scenarios. The virtual environment is a replica of the actual production environment and is configured to observe how each service operates and how it behaves when a failure occurs.

[0214] Subsequently, the server collects data during the test execution, such as system response time, error logs, and resource usage, and analyzes this data to identify the root cause of problems and potential weaknesses. This analysis utilizes AI models to detect unusual behavior and changes in patterns.

[0215] Based on the collected and analyzed data, the server suggests solutions and improvements to the user. This allows the user to reduce system vulnerabilities and prevent unexpected failures.

[0216] For example, if a scenario is generated in which communication between services A and B is interrupted, the server will reproduce this communication failure in a virtual environment and observe how many retries service A can perform and how service B responds to the results. If it is found that service A is retrying more than expected and consequently depleting resources, the server will suggest to the user that they review their retry policy and re-evaluate their load balancing strategy.

[0217] In this way, the present invention makes it possible to efficiently promote improvements in system reliability.

[0218] The following describes the processing flow.

[0219] Step 1:

[0220] The server collects metadata and log data from each service to understand all services within the system and their interdependencies. This data includes API endpoint information, uptime, and call frequency.

[0221] Step 2:

[0222] The server uses a generative model based on the collected information to automatically generate failure scenarios. These scenarios include multiple behaviors such as communication interruptions and delays between services, and resource overload.

[0223] Step 3:

[0224] The server creates a virtual environment and places a simulated system environment within it. Here, service containers are started, and a state is created that can mimic the actual service operation.

[0225] Step 4:

[0226] The server will intentionally cause failures according to the generated scenario. For example, it might block network access to a specific service and observe the system's response when communication is interrupted.

[0227] Step 5:

[0228] During testing, the server collects data such as system response time, error messages, and the number of calls between services. This data is used for later analysis.

[0229] Step 6:

[0230] The server analyzes the collected data using an AI model to detect behavior and abnormal patterns during failures. This identifies the root cause of the problem and potential system weaknesses.

[0231] Step 7:

[0232] The server reports the analysis results to the user and suggests system improvements and specific solutions. This allows the user to take steps to reduce system vulnerabilities.

[0233] (Example 1)

[0234] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0235] In systems employing a microservices architecture, communication failures between services can have a significant impact on the overall reliability of the system. While effectively preventing such communication failures and stabilizing system operation is crucial, previous methods have faced challenges in predicting failures and developing countermeasures.

[0236] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0237] In this invention, the server includes means for utilizing generation technology to generate communication failure scenarios between multiple activity units, means for reproducing the failures in a virtualized environment based on the scenarios, and means for collecting and analyzing information obtained through the reproduction. This makes it possible to predict communication failures within the system in advance and take effective countermeasures.

[0238] "Generative technology" refers to technologies that use artificial intelligence and machine learning to automatically create new information and scenarios based on data and patterns.

[0239] An "activity unit" is a unit of individual services or components in a microservices architecture, and is an independent system element with a specific function or role.

[0240] A "communication failure scenario" is a preliminary plan created based on anticipated communication errors and connection problems that may occur between different activity units.

[0241] A "virtualized environment" is a computer-based simulation environment designed to mimic an actual production environment and test the behavior of a system.

[0242] "Reproduction" is the process of artificially constructing a specific scenario or condition and then experiencing it in a simulation to see how the system reacts.

[0243] "Information" refers to all data to be analyzed, including data and logs obtained from communication and failure simulations, and system performance indicators.

[0244] "Analysis" is a procedure performed to thoroughly examine collected data in order to identify the causes and characteristics of a problem and clarify areas for improvement.

[0245] The system for implementing this invention is built for systems employing a microservices architecture. The server utilizes a generative AI model to automatically generate communication failure scenarios and enables their reproduction within a virtualized environment.

[0246] The server first collects detailed information from each activity unit within the system. This includes the latency, error rate, and interdependencies of each activity unit. The collected information is used as prompts by the generative AI model to create communication failure scenarios. A specific example of a prompt statement is, "Evaluate the impact of a communication timeout between service A and service B."

[0247] Based on the generated scenarios, the server uses virtual environment management software such as Docker or Kubernetes to build a virtualized environment that closely resembles the actual production environment. In this environment, failure scenarios are reproduced, and the responses of each activity unit and the behavior of the system are observed and recorded.

[0248] The server then collects information obtained from this virtual environment and analyzes it using an AI model. Specifically, it analyzes data such as re-entry data, error logs, and resource usage to identify potential problems and areas for improvement in the system.

[0249] Based on the analysis results, the server will present the user with a solution. This solution may include revising the retry policy or improving the load balancing strategy. This will allow the user to improve system reliability and prevent unexpected communication failures in advance.

[0250] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0251] Step 1:

[0252] The server collects information from the activity units within the system. This information includes dependencies between activity units, communication delays, and error logs. Based on this information, it creates prompt statements to be input into the generated AI model. For example, data to understand the response time of service A and its dependencies with service B may be input, and based on this, a prompt statement such as "Evaluate the impact of a communication timeout between service A and service B" may be output.

[0253] Step 2:

[0254] The server inputs the generated prompt message into the AI ​​model to generate communication failure scenarios. The AI ​​model outputs various communication failure patterns based on the prompt message. These output scenarios include communication outages and overload conditions, illustrating the types of failures the system may face.

[0255] Step 3:

[0256] The server builds a virtualized environment based on the generated communication failure scenario. This environment mimics a real production environment using Docker or Kubernetes. The inputs are failure scenarios and virtual environment templates, and the output is a configuration within the virtual environment that reflects the scenario.

[0257] Step 4:

[0258] The server simulates communication failure scenarios in a virtual environment. Specifically, it intentionally introduces network delays and disconnections and observes how each activity unit reacts. The input is the scenario and the configured virtual environment, and the output is simulation data, such as the number of re-entries and network response time.

[0259] Step 5:

[0260] The server collects data obtained from simulations and analyzes it using an AI model. The input includes simulation data, with particular attention paid to the number of re-entries, error logs, and resource consumption. The output provides analysis results regarding areas where system improvement is needed and potential problems.

[0261] Step 6:

[0262] The server proposes solutions to the user based on the analysis results. Specifically, it suggests improvement methods such as modifying the retry policy or optimizing load balancing settings. The input is the analysis results, and the output is a proposal report for the user. This proposal allows the user to improve system reliability and take measures to prevent future failures.

[0263] (Application Example 1)

[0264] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0265] In modern information processing systems, it is common for multiple information processing units to work together in coordination. However, this complex interaction increases the likelihood of communication errors and malfunctions, which can lead to a decline in or complete shutdown of the entire system, ultimately causing safety and reliability issues. Furthermore, existing systems make it difficult to predict and prevent these failures before they occur.

[0266] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0267] In this invention, the server includes means for automatically generating communication error scenarios between multiple information processing units using a generative model, means for simulating failures in a virtual work area based on the scenarios, means for collecting and interpreting information obtained from the simulation, and means for providing the interpretation results as visual information in real time on a visual display device. This makes it possible to detect potential communication errors and functional failures in the information processing system in advance and propose solutions quickly and effectively.

[0268] A "generative model" is an artificial intelligence technology that has the ability to learn patterns from data and generate new data.

[0269] An "information processing unit" is a fundamental component of a computer that performs information input, processing, and output.

[0270] A "communication error scenario" is a scenario that illustrates specific situations of communication failures that may occur within an information processing system.

[0271] A "virtual workspace" is a virtual work environment that functions within software, but does not have a physical presence.

[0272] "Interpretation" is the act of reading and understanding meaning from collected data.

[0273] A "visual display device" is a hardware device used to present information visually.

[0274] To realize this invention, a system is provided in which a server and a visual display device work in coordination. The server uses a generative model to automatically generate communication error scenarios between information processing units. Specifically, it uses a natural language processing model such as OpenAI's GPT as the generative model to analyze communication data obtained from multiple information processing units and generate patterns of potential communication errors.

[0275] The server constructs a virtual workspace and simulates communication error scenarios that occur within it. This virtual workspace mimics a real-world environment using a real-time data processing framework such as Apache Kafka. As a result of the simulation, the server collects various data, including system response times and error logs, and interprets this data to identify potential communication failures and propose solutions.

[0276] Users can visually confirm the interpretation results provided by the server using a visual display device. This device features a visually intuitive interface to present collected data to the user in real time. Users can take swift action based on the system's suggestions.

[0277] For example, if the system detects a communication failure in a security camera, the generating AI model uses prompts to perform a specific simulation. An example of a prompt might be, "Generate a failure scenario for camera A in the security camera system and propose the optimal strategy for load balancing to other cameras." This allows the system to quickly provide the user with an appropriate solution, thereby improving system reliability.

[0278] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0279] Step 1:

[0280] The server collects communication data from the information processing unit in real time. The input is the log data of each unit, and the output is a dataset for analyzing this data. This data collection is implemented using a data stream platform such as Apache Kafka.

[0281] Step 2:

[0282] The server generates potential communication error scenarios using an AI model based on the collected dataset. The input is the dataset obtained in Step 1, and the output is the generated error scenarios. At this time, in the generation model, prompt sentences are utilized to automatically generate scenarios.

[0283] Step 3:

[0284] The server sets up a virtual working area based on the generated communication error scenarios and starts the simulation. The input is the scenarios generated in Step 2 and the virtual environment setting data, and the output is the detailed data associated with the simulation execution. As a specific operation, the communication behavior between units when an abnormality occurs is simulated.

[0285] Step 4:

[0286] The server analyzes the data obtained from the simulation and evaluates the response characteristics and error patterns of the system. The input is the simulation data obtained in Step 3, and the output is the analysis results leading to the proposal of specific solutions. AI algorithms are used to detect abnormal operations.

[0287] Step 5:

[0288] The user checks the analysis results provided by the server through the visual display device. The input is the analysis results obtained in Step 4, and the output is the visual information displayed on the screen. As a specific example, a dashboard indicating which communication paths are likely to experience failures is displayed.

[0289] Step 6:

[0290] The user monitors the entire system and takes immediate action based on the information displayed on the screen. The input is the interpretation result visually presented in step 5, and the output is the user's instructions for operations and configuration changes. An example prompt used by the generated AI model is, "Please suggest countermeasures for the inter-service failure scenario."

[0291] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0292] This invention combines a generative model and an emotion engine to achieve more effective system operation and user support. The embodiments for carrying out this invention are described below.

[0293] First, the server collects the necessary data from each service within the system and automatically generates communication error scenarios using a generative model. The scenarios generated in this process are deployed in a virtual environment to simulate various failure conditions, taking into account the dependencies within the system.

[0294] Next, the server simulates failures in this virtual environment based on the generated scenario. This allows it to reproduce situations such as disruptions to communication between services or intentional increases in system load.

[0295] As the test progresses, the server uses an emotion engine to analyze the emotions of the user performing the test operations in real time. If a change in emotional state is detected, the system adjusts the suggested solutions and the feedback provided to better respond to the user.

[0296] Specifically, when providing reports based on test results, if the server determines that the user's emotions are negative, it will provide information in a more detailed format, highlighting proactive solutions and success stories. Conversely, if positive emotions are detected, it will focus on providing concise and efficient information.

[0297] Furthermore, the emotion engine receives user feedback and analyzes it to improve the usability of the system itself. For example, if feedback indicates that a user is experiencing stress with a particular operation, it generates suggestions for interface improvements to simplify that operation.

[0298] In this way, the present invention can demonstrate high effectiveness in both technical troubleshooting and user experience.

[0299] The following describes the processing flow.

[0300] Step 1:

[0301] The server collects necessary data from all related services and analyzes system dependencies. This data collection process includes information such as the operational status and communication patterns of each service, and the frequency of API calls.

[0302] Step 2:

[0303] The server uses the collected data to run a generative model and automatically generate communication error scenarios. This generative model considers a variety of failure conditions and outputs scenarios that include potential vulnerabilities that would not normally be noticed.

[0304] Step 3:

[0305] The server builds a virtual environment and deploys the generated failure scenarios within it. This virtual environment is built to simulate the actual system environment and serves as a testbed for evaluating how each service responds.

[0306] Step 4:

[0307] The server executes simulations within a virtual environment and intentionally generates faults such as communication interruptions and increased load based on the fault scenario. This verifies the fault tolerance and self - recovery ability of each service.

[0308] Step 5:

[0309] During the execution of the fault simulation, the server collects test data in real - time and simultaneously analyzes the user's emotional state using the emotion engine. Based on user interactions, it discriminates positive, negative, and neutral emotions.

[0310] Step 6:

[0311] The server analyzes the simulation results in combination with the user's emotional state, identifies the root cause of the problem, and generates an optimal solution according to the emotion. For example, if the user feels anxious, detailed explanations for providing a sense of security are added.

[0312] Step 7:

[0313] The server generates a report based on the test results for the user and presents a solution adjusted based on the emotion analysis results. This proposes improvement plans for the system in a form that takes into account not only the technical aspects but also the user experience.

[0314] Step 8:

[0315] Through the feedback session, the user promotes further improvement of the interface and procedures based on the analysis results obtained by utilizing the emotion engine. This feedback enables the system to continuously evolve in the direction of enhancing usability.

[0316] (Example 2)

[0317] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0318] In conventional systems, handling communication errors was reactive, making it difficult to comprehensively test all failure conditions in advance. Furthermore, system error information was highly specialized for engineers, preventing the provision of appropriate information by leveraging user feedback and emotional states. Therefore, there is a need for a method that simultaneously improves both fault response and user experience.

[0319] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0320] In this invention, the server includes means for automatically generating communication error scenarios using a generative model, means for simulating failures in a virtual environment, and means for analyzing the user's emotional state in real time and adjusting the information provided. This makes it possible to simulate various failure conditions in advance and consider appropriate countermeasures, and also enables the provision of information according to the user's emotional state.

[0321] A "generative model" is an artificial intelligence technology that learns patterns from data and automatically generates new data and scenarios.

[0322] A "virtual environment" is a simulation environment created on a computer without physical constraints, and is used to test operation under various conditions.

[0323] The "emotion analysis mechanism" is a technological system that analyzes the user's facial expressions and voice data to recognize and classify their emotional state in real time.

[0324] "User's emotional state" refers to the emotional response of a person operating the system, and includes psychological states such as stress, joy, and surprise.

[0325] A "communication error scenario" is a hypothetical scenario created to simulate the specific circumstances and progression of communication failures that may occur between multiple systems.

[0326] "Adjusting information" refers to the act of optimizing the content, format, or timing of data and messages provided in accordance with the user's emotional state or the system's status.

[0327] This invention is a system that uses a generative model and an emotion analysis mechanism to improve the user experience and enable preventative and adaptive responses to communication errors.

[0328] The server first collects the necessary data from various services within the system (e.g., databases, APIs). This utilizes industry-standard messaging systems to achieve real-time data streaming. Next, the server automatically generates communication error scenarios by inputting prompts into a generation AI model. An example of such a prompt is, "Generate a scenario that considers the impact of communication errors."

[0329] The generated scenarios are deployed in a virtual environment, and the servers run the simulations. This virtual environment utilizes container technology and an orchestration platform to create a flexible and large-scale test environment. This allows for the reproduction of diverse failure conditions without disrupting the normal operation of the system.

[0330] The terminal monitors the user's actions while the simulation is running. The emotion analysis mechanism receives this data and analyzes the user's emotional state in real time from their facial expressions and voice. Specifically, the emotion analysis outputs the user's psychological state, such as stress and satisfaction, as numerical values ​​or categories.

[0331] Based on this emotional data, the server adjusts the information and feedback it provides to the user. For example, if a user expresses negative emotions due to a communication problem, the server will provide more detailed, step-by-step guidance to facilitate communication. Conversely, if positive emotions are detected, the focus will be on providing concise and easy-to-understand information.

[0332] Ultimately, based on feedback, we will propose further interface optimizations to improve the system and enhance its usability. This will allow users to use the system more intuitively and comfortably.

[0333] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0334] Step 1:

[0335] The server collects the necessary data from each service within the system. This input data includes communication logs and performance metrics. The server streams the data through the messaging system and aggregates it in real time. The output is an integrated dataset in a format suitable for analysis.

[0336] Step 2:

[0337] The server uses the collected data to input a prompt message into the generated AI model. The prompt message used is "Create a scenario that includes communication errors." In this process, the server receives the communication error scenario generated by the AI ​​model. The output is detailed scenario data used for simulation in a virtual environment.

[0338] Step 3:

[0339] The server deploys the generated scenarios into a virtual environment. The input is the scenario data generated in the previous step, and the virtual environment is built using container technology. The server then starts simulating communication failures within this environment. The output is the execution result data for each scenario.

[0340] Step 4:

[0341] The terminal monitors user actions during simulation and analyzes that data using an emotion analysis mechanism. Inputs include user action data and environmental sensor data. The emotion analysis mechanism analyzes the monitored data in real time to determine the user's emotional state. Outputs include metrics representing the user's emotional state.

[0342] Step 5:

[0343] The server adjusts feedback information based on the user's emotional state metrics. Inputs include emotional state metrics and notification data from various services. The server optimizes the information provided to the user accordingly. Specifically, if negative emotions are present, it generates detailed and positive feedback; if positive emotions are present, it provides summarized information. Outputs are the adjusted feedback messages and suggestions.

[0344] Step 6:

[0345] The user receives adjusted feedback from the server and performs actions based on that feedback. After receiving the feedback, the user provides new input regarding their actions, and this data is sent back to the system as the basis for further improvement suggestions. The output is the result of the user's improved actions.

[0346] (Application Example 2)

[0347] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0348] In modern information systems, communication errors and failures can impair the user experience and lead to decreased customer satisfaction. Furthermore, the lack of adequate mechanisms for accurately understanding and responding to users' emotional states in real time can negatively impact the quality of customer service. To efficiently resolve these issues, a system is needed that can respond quickly and flexibly to communication errors and provide appropriate feedback tailored to the user's emotional state.

[0349] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0350] In this invention, the server includes means for automatically generating communication error scenarios between multiple services using a generative model, means for simulating failures in a virtual environment based on the scenarios, and means for analyzing the user's emotions using an emotion engine and dynamically providing information based on the analysis results. This makes it possible to provide appropriate feedback and solutions that correspond to the user's emotions even in the event of a communication error.

[0351] A "generative model" refers to algorithms and methods for automatically generating communication error scenarios.

[0352] A "communication error scenario" refers to a hypothetical configuration of possible communication failure patterns that may occur between multiple services.

[0353] A "virtual environment" refers to a simulation space built on a computer that is different from the actual system.

[0354] An "emotion engine" refers to software or algorithms used to analyze a user's emotional state.

[0355] "User emotion analysis" refers to the process of inferring a user's emotional state at a given time based on their actions and behavior.

[0356] A "solution" refers to specific countermeasures or methods to be taken in response to a particular problem or obstacle.

[0357] The system for implementing this invention has a server-centric configuration. The server uses a generative AI model to automatically generate scenarios between multiple services where communication errors may occur. The generated scenarios are reproduced in a virtual environment, and user interactions are simulated.

[0358] The server uses an emotion engine to analyze in real time what emotions the user experiences within the simulation. This emotion analysis information is used to provide feedback and solutions for communication errors. For example, if a transaction fails while a user is in the process of purchasing a particular product, the server will take that emotion into consideration and offer proactive solutions or suggestions for similar products.

[0359] The analysis utilizes the OpenAI API, and when providing information based on real-time sentiment analysis results, real-time data processing is performed using the Django framework. The frontend is built using React Native to provide interactive information to the user.

[0360] As a concrete example, consider a scenario where a user is searching for a smartphone on an e-commerce site. If the user shows signs of hesitation in making a purchase, the server immediately presents alternative product recommendations and relevant success stories. This can increase the user's willingness to buy and reduce stress caused by communication errors.

[0361] The generative AI model creates optimal prompts based on the situation, helping the server provide appropriate feedback. A concrete example of a prompt might be, "If the user experiences frustration on product page B, suggest alternative products."

[0362] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0363] Step 1:

[0364] The server automatically generates communication error scenarios using a generative AI model. In this process, it takes dependency information for each service within the system as input and outputs scenarios that reflect a variety of failure conditions. This scenario generation utilizes past error data as training data and performs data calculations to generate new error scenarios.

[0365] Step 2:

[0366] The server deploys the generated communication error scenario into a virtual environment and starts the simulation. The virtual environment simulates the actual operating environment and artificially generates failures, such as blocking communication between services, based on the generated scenario. The input is the generated error scenario, and the resulting service responses and state changes are collected as output.

[0367] Step 3:

[0368] The user's terminal interacts with the virtual environment during the simulation, and the server uses an emotion engine to analyze the user's emotional state in real time. Using user operation logs and eye-tracking data as input, the emotion engine infers the user's emotions and sends the inferred result to the server as output. This process employs non-invasive emotion recognition technology.

[0369] Step 4:

[0370] The server combines the sentiment analysis results with the simulation results of communication error scenarios to build an AI model that generates appropriate solutions and feedback. It receives the user's emotional state as input, generates the most appropriate prompt based on that, and outputs information showing alternative solutions and success stories.

[0371] Step 5:

[0372] The user's device displays solutions and feedback sent from the server on its interface. React Native is used to present the data in an intuitive and easy-to-understand format for the user. Input is feedback from the server, and this feedback is output in a way that encourages user action.

[0373] 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.

[0374] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0375] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0376] [Third Embodiment]

[0377] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0378] 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.

[0379] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0380] 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.

[0381] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0382] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0383] 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.

[0384] 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.

[0385] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0386] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0387] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0388] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0389] This invention aims to enhance systems in a microservices architecture by automatically generating failure scenarios using a generative model. To implement this system, the program processes as follows:

[0390] First, the server collects information from each service within the system and, based on that information, utilizes a generative model to automatically generate communication error scenarios. These generated scenarios include anticipated communication outages and overload conditions and are used to anticipate risks in actual service integration.

[0391] Next, the server builds a virtual environment and simulates actual failures based on the generated scenarios. The virtual environment is a replica of the actual production environment and is configured to observe how each service operates and how it behaves when a failure occurs.

[0392] Subsequently, the server collects data during the test execution, such as system response time, error logs, and resource usage, and analyzes this data to identify the root cause of problems and potential weaknesses. This analysis utilizes AI models to detect unusual behavior and changes in patterns.

[0393] Based on the collected and analyzed data, the server suggests solutions and improvements to the user. This allows the user to reduce system vulnerabilities and prevent unexpected failures.

[0394] For example, if a scenario is generated in which communication between services A and B is interrupted, the server will reproduce this communication failure in a virtual environment and observe how many retries service A can perform and how service B responds to the results. If it is found that service A is retrying more than expected and consequently depleting resources, the server will suggest to the user that they review their retry policy and re-evaluate their load balancing strategy.

[0395] In this way, the present invention makes it possible to efficiently promote improvements in system reliability.

[0396] The following describes the processing flow.

[0397] Step 1:

[0398] The server collects metadata and log data from each service to understand all services within the system and their interdependencies. This data includes API endpoint information, uptime, and call frequency.

[0399] Step 2:

[0400] The server uses a generative model based on the collected information to automatically generate failure scenarios. These scenarios include multiple behaviors such as communication interruptions and delays between services, and resource overload.

[0401] Step 3:

[0402] The server creates a virtual environment and places a simulated system environment within it. Here, service containers are started, and a state is created that can mimic the actual service operation.

[0403] Step 4:

[0404] The server will intentionally cause failures according to the generated scenario. For example, it might block network access to a specific service and observe the system's response when communication is interrupted.

[0405] Step 5:

[0406] During testing, the server collects data such as system response time, error messages, and the number of calls between services. This data is used for later analysis.

[0407] Step 6:

[0408] The server analyzes the collected data using an AI model to detect behavior and abnormal patterns during failures. This identifies the root cause of the problem and potential system weaknesses.

[0409] Step 7:

[0410] The server reports the analysis results to the user and suggests system improvements and specific solutions. This allows the user to take steps to reduce system vulnerabilities.

[0411] (Example 1)

[0412] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0413] In systems employing a microservices architecture, communication failures between services can have a significant impact on the overall reliability of the system. While effectively preventing such communication failures and stabilizing system operation is crucial, previous methods have faced challenges in predicting failures and developing countermeasures.

[0414] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0415] In this invention, the server includes means for utilizing generation technology to generate communication failure scenarios between multiple activity units, means for reproducing the failures in a virtualized environment based on the scenarios, and means for collecting and analyzing information obtained through the reproduction. This makes it possible to predict communication failures within the system in advance and take effective countermeasures.

[0416] "Generative technology" refers to technologies that use artificial intelligence and machine learning to automatically create new information and scenarios based on data and patterns.

[0417] An "activity unit" is a unit of individual services or components in a microservices architecture, and is an independent system element with a specific function or role.

[0418] A "communication failure scenario" is a preliminary plan created based on anticipated communication errors and connection problems that may occur between different activity units.

[0419] A "virtualized environment" is a computer-based simulation environment designed to mimic an actual production environment and test the behavior of a system.

[0420] "Reproduction" is the process of artificially constructing a specific scenario or condition and then experiencing it in a simulation to see how the system reacts.

[0421] "Information" refers to all data to be analyzed, including data and logs obtained from communication and failure simulations, and system performance indicators.

[0422] "Analysis" is a procedure performed to thoroughly examine collected data in order to identify the causes and characteristics of a problem and clarify areas for improvement.

[0423] The system for implementing this invention is built for systems employing a microservices architecture. The server utilizes a generative AI model to automatically generate communication failure scenarios and enables their reproduction within a virtualized environment.

[0424] The server first collects detailed information from each activity unit within the system. This includes the latency, error rate, and interdependencies of each activity unit. The collected information is used as prompts by the generative AI model to create communication failure scenarios. A specific example of a prompt statement is, "Evaluate the impact of a communication timeout between service A and service B."

[0425] Based on the generated scenarios, the server uses virtual environment management software such as Docker or Kubernetes to build a virtualized environment that closely resembles the actual production environment. In this environment, failure scenarios are reproduced, and the responses of each activity unit and the behavior of the system are observed and recorded.

[0426] The server then collects information obtained from this virtual environment and analyzes it using an AI model. Specifically, it analyzes data such as re-entry data, error logs, and resource usage to identify potential problems and areas for improvement in the system.

[0427] Based on the analysis results, the server will present the user with a solution. This solution may include revising the retry policy or improving the load balancing strategy. This will allow the user to improve system reliability and prevent unexpected communication failures in advance.

[0428] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0429] Step 1:

[0430] The server collects information from the activity units within the system. This information includes dependencies between activity units, communication delays, and error logs. Based on this information, it creates prompt statements to be input into the generated AI model. For example, data to understand the response time of service A and its dependencies with service B may be input, and based on this, a prompt statement such as "Evaluate the impact of a communication timeout between service A and service B" may be output.

[0431] Step 2:

[0432] The server inputs the generated prompt message into the AI ​​model to generate communication failure scenarios. The AI ​​model outputs various communication failure patterns based on the prompt message. These output scenarios include communication outages and overload conditions, illustrating the types of failures the system may face.

[0433] Step 3:

[0434] The server builds a virtualized environment based on the generated communication failure scenario. This environment mimics a real production environment using Docker or Kubernetes. The inputs are failure scenarios and virtual environment templates, and the output is a configuration within the virtual environment that reflects the scenario.

[0435] Step 4:

[0436] The server simulates communication failure scenarios in a virtual environment. Specifically, it intentionally introduces network delays and disconnections and observes how each activity unit reacts. The input is the scenario and the configured virtual environment, and the output is simulation data, such as the number of re-entries and network response time.

[0437] Step 5:

[0438] The server collects data obtained from simulations and analyzes it using an AI model. The input includes simulation data, with particular attention paid to the number of re-entries, error logs, and resource consumption. The output provides analysis results regarding areas where system improvement is needed and potential problems.

[0439] Step 6:

[0440] The server proposes solutions to the user based on the analysis results. Specifically, it suggests improvement methods such as modifying the retry policy or optimizing load balancing settings. The input is the analysis results, and the output is a proposal report for the user. This proposal allows the user to improve system reliability and take measures to prevent future failures.

[0441] (Application Example 1)

[0442] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0443] In modern information processing systems, it is common for multiple information processing units to work together in coordination. However, this complex interaction increases the likelihood of communication errors and malfunctions, which can lead to a decline in or complete shutdown of the entire system, ultimately causing safety and reliability issues. Furthermore, existing systems make it difficult to predict and prevent these failures before they occur.

[0444] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0445] In this invention, the server includes means for automatically generating communication error scenarios between multiple information processing units using a generative model, means for simulating failures in a virtual work area based on the scenarios, means for collecting and interpreting information obtained from the simulation, and means for providing the interpretation results as visual information in real time on a visual display device. This makes it possible to detect potential communication errors and functional failures in the information processing system in advance and propose solutions quickly and effectively.

[0446] A "generative model" is an artificial intelligence technology that has the ability to learn patterns from data and generate new data.

[0447] An "information processing unit" is a fundamental component of a computer that performs information input, processing, and output.

[0448] A "communication error scenario" is a scenario that illustrates specific situations of communication failures that may occur within an information processing system.

[0449] A "virtual workspace" is a virtual work environment that functions within software, but does not have a physical presence.

[0450] "Interpretation" is the act of reading and understanding meaning from collected data.

[0451] A "visual display device" is a hardware device used to present information visually.

[0452] To realize this invention, a system is provided in which a server and a visual display device work in coordination. The server uses a generative model to automatically generate communication error scenarios between information processing units. Specifically, it uses a natural language processing model such as OpenAI's GPT as the generative model to analyze communication data obtained from multiple information processing units and generate patterns of potential communication errors.

[0453] The server constructs a virtual workspace and simulates communication error scenarios that occur within it. This virtual workspace mimics a real-world environment using a real-time data processing framework such as Apache Kafka. As a result of the simulation, the server collects various data, including system response times and error logs, and interprets this data to identify potential communication failures and propose solutions.

[0454] Users can visually confirm the interpretation results provided by the server using a visual display device. This device features a visually intuitive interface to present collected data to the user in real time. Users can take swift action based on the system's suggestions.

[0455] For example, if the system detects a communication failure in a security camera, the generating AI model uses prompts to perform a specific simulation. An example of a prompt might be, "Generate a failure scenario for camera A in the security camera system and propose the optimal strategy for load balancing to other cameras." This allows the system to quickly provide the user with an appropriate solution, thereby improving system reliability.

[0456] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0457] Step 1:

[0458] The server collects communication data from information processing units in real time. The input is log data from each unit, and the output is a dataset for analysis. This data collection is performed using a data stream platform such as Apache Kafka.

[0459] Step 2:

[0460] The server uses a generative AI model based on the collected dataset to generate potential communication error scenarios. The input is the dataset obtained in step 1, and the output is the generated error scenario. In this process, the generative model utilizes prompt statements to automatically generate scenarios.

[0461] Step 3:

[0462] The server sets up a virtual workspace based on the generated communication error scenario and starts the simulation. The input is the scenario and virtual environment configuration data generated in step 2, and the output is detailed data associated with the simulation execution. Specifically, the communication behavior between units in the event of an anomaly is simulated.

[0463] Step 4:

[0464] The server analyzes the data obtained from the simulation to evaluate the system's response characteristics and error patterns. The input is the simulation data obtained in step 3, and the output is the analysis results that lead to the proposal of specific solutions. Anomaly behavior is detected using an AI algorithm.

[0465] Step 5:

[0466] The user views the analysis results provided by the server through a visual display device. The input is the analysis results obtained in step 4, and the output is the visual information displayed on the screen. For example, a dashboard showing which communication paths are likely to experience failures is displayed.

[0467] Step 6:

[0468] The user monitors the entire system and takes immediate action based on the information displayed on the screen. The input is the interpretation result visually presented in step 5, and the output is the user's instructions for operations and configuration changes. An example prompt used by the generated AI model is, "Please suggest countermeasures for the inter-service failure scenario."

[0469] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0470] This invention combines a generative model and an emotion engine to achieve more effective system operation and user support. The embodiments for carrying out this invention are described below.

[0471] First, the server collects the necessary data from each service within the system and automatically generates communication error scenarios using a generative model. The scenarios generated in this process are deployed in a virtual environment to simulate various failure conditions, taking into account the dependencies within the system.

[0472] Next, the server simulates failures in this virtual environment based on the generated scenario. This allows it to reproduce situations such as disruptions to communication between services or intentional increases in system load.

[0473] As the test progresses, the server uses an emotion engine to analyze the emotions of the user performing the test operations in real time. If a change in emotional state is detected, the system adjusts the suggested solutions and the feedback provided to better respond to the user.

[0474] Specifically, when providing reports based on test results, if the server determines that the user's emotions are negative, it will provide information in a more detailed format, highlighting proactive solutions and success stories. Conversely, if positive emotions are detected, it will focus on providing concise and efficient information.

[0475] Furthermore, the emotion engine receives user feedback and analyzes it to improve the usability of the system itself. For example, if feedback indicates that a user is experiencing stress with a particular operation, it generates suggestions for interface improvements to simplify that operation.

[0476] In this way, the present invention can demonstrate high effectiveness in both technical troubleshooting and user experience.

[0477] The following describes the processing flow.

[0478] Step 1:

[0479] The server collects necessary data from all related services and analyzes system dependencies. This data collection process includes information such as the operational status and communication patterns of each service, and the frequency of API calls.

[0480] Step 2:

[0481] The server uses the collected data to run a generative model and automatically generate communication error scenarios. This generative model considers a variety of failure conditions and outputs scenarios that include potential vulnerabilities that would not normally be noticed.

[0482] Step 3:

[0483] The server builds a virtual environment and deploys the generated failure scenarios within it. This virtual environment is built to simulate the actual system environment and serves as a testbed for evaluating how each service responds.

[0484] Step 4:

[0485] The server runs simulations within a virtual environment, intentionally generating failures such as communication outages and increased load based on failure scenarios. This verifies the fault tolerance and automatic recovery capabilities of each service.

[0486] Step 5:

[0487] During the failure simulation, the server collects test data in real time and simultaneously analyzes the user's emotional state using an emotion engine. Based on user interactions, it determines whether the emotion is positive, negative, or neutral.

[0488] Step 6:

[0489] The server analyzes the simulation results along with the user's emotional state to identify the root cause of the problem and generate the optimal solution tailored to the user's emotions. For example, if the user is feeling anxious, it will add detailed explanations to reassure them.

[0490] Step 7:

[0491] The server generates a report for the user based on the test results and presents solutions tailored based on sentiment analysis. This ensures that system improvement suggestions take into account not only the technical aspects but also the user experience.

[0492] Step 8:

[0493] Through feedback sessions, users drive further improvements to the interface and procedures based on analysis results obtained using the emotion engine. This feedback allows the system to continuously evolve in a direction that enhances usability.

[0494] (Example 2)

[0495] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0496] In conventional systems, handling communication errors was reactive, making it difficult to comprehensively test all failure conditions in advance. Furthermore, system error information was highly specialized for engineers, preventing the provision of appropriate information by leveraging user feedback and emotional states. Therefore, there is a need for a method that simultaneously improves both fault response and user experience.

[0497] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0498] In this invention, the server includes means for automatically generating communication error scenarios using a generative model, means for simulating failures in a virtual environment, and means for analyzing the user's emotional state in real time and adjusting the information provided. This makes it possible to simulate various failure conditions in advance and consider appropriate countermeasures, and also enables the provision of information according to the user's emotional state.

[0499] A "generative model" is an artificial intelligence technology that learns patterns from data and automatically generates new data and scenarios.

[0500] A "virtual environment" is a simulation environment created on a computer without physical constraints, and is used to test operation under various conditions.

[0501] The "emotion analysis mechanism" is a technological system that analyzes the user's facial expressions and voice data to recognize and classify their emotional state in real time.

[0502] "User's emotional state" refers to the emotional response of a person operating the system, and includes psychological states such as stress, joy, and surprise.

[0503] A "communication error scenario" is a hypothetical scenario created to simulate the specific circumstances and progression of communication failures that may occur between multiple systems.

[0504] "Adjusting information" refers to the act of optimizing the content, format, or timing of data and messages provided in accordance with the user's emotional state or the system's status.

[0505] This invention is a system that uses a generative model and an emotion analysis mechanism to improve the user experience and enable preventative and adaptive responses to communication errors.

[0506] The server first collects the necessary data from various services within the system (e.g., databases, APIs). This utilizes industry-standard messaging systems to achieve real-time data streaming. Next, the server automatically generates communication error scenarios by inputting prompts into a generation AI model. An example of such a prompt is, "Generate a scenario that considers the impact of communication errors."

[0507] The generated scenarios are deployed in a virtual environment, and the servers run the simulations. This virtual environment utilizes container technology and an orchestration platform to create a flexible and large-scale test environment. This allows for the reproduction of diverse failure conditions without disrupting the normal operation of the system.

[0508] The terminal monitors the user's actions while the simulation is running. The emotion analysis mechanism receives this data and analyzes the user's emotional state in real time from their facial expressions and voice. Specifically, the emotion analysis outputs the user's psychological state, such as stress and satisfaction, as numerical values ​​or categories.

[0509] Based on this emotional data, the server adjusts the information and feedback it provides to the user. For example, if a user expresses negative emotions due to a communication problem, the server will provide more detailed, step-by-step guidance to facilitate communication. Conversely, if positive emotions are detected, the focus will be on providing concise and easy-to-understand information.

[0510] Ultimately, based on feedback, we will propose further interface optimizations to improve the system and enhance its usability. This will allow users to use the system more intuitively and comfortably.

[0511] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0512] Step 1:

[0513] The server collects the necessary data from each service within the system. This input data includes communication logs and performance metrics. The server streams the data through the messaging system and aggregates it in real time. The output is an integrated dataset in a format suitable for analysis.

[0514] Step 2:

[0515] The server uses the collected data to input a prompt message into the generated AI model. The prompt message used is "Create a scenario that includes communication errors." In this process, the server receives the communication error scenario generated by the AI ​​model. The output is detailed scenario data used for simulation in a virtual environment.

[0516] Step 3:

[0517] The server deploys the generated scenarios into a virtual environment. The input is the scenario data generated in the previous step, and the virtual environment is built using container technology. The server then starts simulating communication failures within this environment. The output is the execution result data for each scenario.

[0518] Step 4:

[0519] The terminal monitors user actions during simulation and analyzes that data using an emotion analysis mechanism. Inputs include user action data and environmental sensor data. The emotion analysis mechanism analyzes the monitored data in real time to determine the user's emotional state. Outputs include metrics representing the user's emotional state.

[0520] Step 5:

[0521] The server adjusts feedback information based on the user's emotional state metrics. Inputs include emotional state metrics and notification data from various services. The server optimizes the information provided to the user accordingly. Specifically, if negative emotions are present, it generates detailed and positive feedback; if positive emotions are present, it provides summarized information. Outputs are the adjusted feedback messages and suggestions.

[0522] Step 6:

[0523] The user receives adjusted feedback from the server and performs actions based on that feedback. After receiving the feedback, the user provides new input regarding their actions, and this data is sent back to the system as the basis for further improvement suggestions. The output is the result of the user's improved actions.

[0524] (Application Example 2)

[0525] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0526] In modern information systems, communication errors and failures can impair the user experience and lead to decreased customer satisfaction. Furthermore, the lack of adequate mechanisms for accurately understanding and responding to users' emotional states in real time can negatively impact the quality of customer service. To efficiently resolve these issues, a system is needed that can respond quickly and flexibly to communication errors and provide appropriate feedback tailored to the user's emotional state.

[0527] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0528] In this invention, the server includes means for automatically generating communication error scenarios between multiple services using a generative model, means for simulating failures in a virtual environment based on the scenarios, and means for analyzing the user's emotions using an emotion engine and dynamically providing information based on the analysis results. This makes it possible to provide appropriate feedback and solutions that correspond to the user's emotions even in the event of a communication error.

[0529] A "generative model" refers to algorithms and methods for automatically generating communication error scenarios.

[0530] A "communication error scenario" refers to a hypothetical configuration of possible communication failure patterns that may occur between multiple services.

[0531] A "virtual environment" refers to a simulation space built on a computer that is different from the actual system.

[0532] An "emotion engine" refers to software or algorithms used to analyze a user's emotional state.

[0533] "User emotion analysis" refers to the process of inferring a user's emotional state at a given time based on their actions and behavior.

[0534] A "solution" refers to specific countermeasures or methods to be taken in response to a particular problem or obstacle.

[0535] The system for implementing this invention has a server-centric configuration. The server uses a generative AI model to automatically generate scenarios between multiple services where communication errors may occur. The generated scenarios are reproduced in a virtual environment, and user interactions are simulated.

[0536] The server uses an emotion engine to analyze in real time what emotions the user experiences within the simulation. This emotion analysis information is used to provide feedback and solutions for communication errors. For example, if a transaction fails while a user is in the process of purchasing a particular product, the server will take that emotion into consideration and offer proactive solutions or suggestions for similar products.

[0537] The analysis utilizes the OpenAI API, and when providing information based on real-time sentiment analysis results, real-time data processing is performed using the Django framework. The frontend is built using React Native to provide interactive information to the user.

[0538] As a concrete example, consider a scenario where a user is searching for a smartphone on an e-commerce site. If the user shows signs of hesitation in making a purchase, the server immediately presents alternative product recommendations and relevant success stories. This can increase the user's willingness to buy and reduce stress caused by communication errors.

[0539] The generative AI model creates optimal prompts based on the situation, helping the server provide appropriate feedback. A concrete example of a prompt might be, "If the user experiences frustration on product page B, suggest alternative products."

[0540] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0541] Step 1:

[0542] The server automatically generates communication error scenarios using a generative AI model. In this process, it takes dependency information for each service within the system as input and outputs scenarios that reflect a variety of failure conditions. This scenario generation utilizes past error data as training data and performs data calculations to generate new error scenarios.

[0543] Step 2:

[0544] The server deploys the generated communication error scenario into a virtual environment and starts the simulation. The virtual environment simulates the actual operating environment and artificially generates failures, such as blocking communication between services, based on the generated scenario. The input is the generated error scenario, and the resulting service responses and state changes are collected as output.

[0545] Step 3:

[0546] The user's terminal interacts with the virtual environment during the simulation, and the server uses an emotion engine to analyze the user's emotional state in real time. Using user operation logs and eye-tracking data as input, the emotion engine infers the user's emotions and sends the inferred result to the server as output. This process employs non-invasive emotion recognition technology.

[0547] Step 4:

[0548] The server combines the sentiment analysis results with the simulation results of communication error scenarios to build an AI model that generates appropriate solutions and feedback. It receives the user's emotional state as input, generates the most appropriate prompt based on that, and outputs information showing alternative solutions and success stories.

[0549] Step 5:

[0550] The user's device displays solutions and feedback sent from the server on its interface. React Native is used to present the data in an intuitive and easy-to-understand format for the user. Input is feedback from the server, and this feedback is output in a way that encourages user action.

[0551] 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.

[0552] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0553] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0554] [Fourth Embodiment]

[0555] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0556] 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.

[0557] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0558] 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.

[0559] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0560] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0561] 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.

[0562] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0563] 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.

[0564] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0565] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0566] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0567] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0568] This invention aims to enhance systems in a microservices architecture by automatically generating failure scenarios using a generative model. To implement this system, the program processes as follows:

[0569] First, the server collects information from each service within the system and, based on that information, utilizes a generative model to automatically generate communication error scenarios. These generated scenarios include anticipated communication outages and overload conditions and are used to anticipate risks in actual service integration.

[0570] Next, the server builds a virtual environment and simulates actual failures based on the generated scenarios. The virtual environment is a replica of the actual production environment and is configured to observe how each service operates and how it behaves when a failure occurs.

[0571] Subsequently, the server collects data during the test execution, such as system response time, error logs, and resource usage, and analyzes this data to identify the root cause of problems and potential weaknesses. This analysis utilizes AI models to detect unusual behavior and changes in patterns.

[0572] Based on the collected and analyzed data, the server suggests solutions and improvements to the user. This allows the user to reduce system vulnerabilities and prevent unexpected failures.

[0573] For example, if a scenario is generated in which communication between services A and B is interrupted, the server will reproduce this communication failure in a virtual environment and observe how many retries service A can perform and how service B responds to the results. If it is found that service A is retrying more than expected and consequently depleting resources, the server will suggest to the user that they review their retry policy and re-evaluate their load balancing strategy.

[0574] In this way, the present invention makes it possible to efficiently promote improvements in system reliability.

[0575] The following describes the processing flow.

[0576] Step 1:

[0577] The server collects metadata and log data from each service to understand all services within the system and their interdependencies. This data includes API endpoint information, uptime, and call frequency.

[0578] Step 2:

[0579] The server uses a generative model based on the collected information to automatically generate failure scenarios. These scenarios include multiple behaviors such as communication interruptions and delays between services, and resource overload.

[0580] Step 3:

[0581] The server creates a virtual environment and places a simulated system environment within it. Here, service containers are started, and a state is created that can mimic the actual service operation.

[0582] Step 4:

[0583] The server will intentionally cause failures according to the generated scenario. For example, it might block network access to a specific service and observe the system's response when communication is interrupted.

[0584] Step 5:

[0585] During testing, the server collects data such as system response time, error messages, and the number of calls between services. This data is used for later analysis.

[0586] Step 6:

[0587] The server analyzes the collected data using an AI model to detect behavior and abnormal patterns during failures. This identifies the root cause of the problem and potential system weaknesses.

[0588] Step 7:

[0589] The server reports the analysis results to the user and suggests system improvements and specific solutions. This allows the user to take steps to reduce system vulnerabilities.

[0590] (Example 1)

[0591] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0592] In systems employing a microservices architecture, communication failures between services can have a significant impact on the overall reliability of the system. While effectively preventing such communication failures and stabilizing system operation is crucial, previous methods have faced challenges in predicting failures and developing countermeasures.

[0593] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0594] In this invention, the server includes means for utilizing generation technology to generate communication failure scenarios between multiple activity units, means for reproducing the failures in a virtualized environment based on the scenarios, and means for collecting and analyzing information obtained through the reproduction. This makes it possible to predict communication failures within the system in advance and take effective countermeasures.

[0595] "Generative technology" refers to technologies that use artificial intelligence and machine learning to automatically create new information and scenarios based on data and patterns.

[0596] An "activity unit" is a unit of individual services or components in a microservices architecture, and is an independent system element with a specific function or role.

[0597] A "communication failure scenario" is a preliminary plan created based on anticipated communication errors and connection problems that may occur between different activity units.

[0598] A "virtualized environment" is a computer-based simulation environment designed to mimic an actual production environment and test the behavior of a system.

[0599] "Reproduction" is the process of artificially constructing a specific scenario or condition and then experiencing it in a simulation to see how the system reacts.

[0600] "Information" refers to all data to be analyzed, including data and logs obtained from communication and failure simulations, and system performance indicators.

[0601] "Analysis" is a procedure performed to thoroughly examine collected data in order to identify the causes and characteristics of a problem and clarify areas for improvement.

[0602] The system for implementing this invention is built for systems employing a microservices architecture. The server utilizes a generative AI model to automatically generate communication failure scenarios and enables their reproduction within a virtualized environment.

[0603] The server first collects detailed information from each activity unit within the system. This includes the latency, error rate, and interdependencies of each activity unit. The collected information is used as prompts by a generative AI model to create communication failure scenarios. A specific example of a prompt statement is, "Evaluate the impact of a communication timeout between service A and service B."

[0604] Based on the generated scenarios, the server uses virtual environment management software such as Docker or Kubernetes to build a virtualized environment that closely resembles the actual production environment. In this environment, failure scenarios are reproduced, and the responses of each activity unit and the behavior of the system are observed and recorded.

[0605] The server then collects information obtained from this virtual environment and analyzes it using an AI model. Specifically, it analyzes data such as re-entry data, error logs, and resource usage to identify potential problems and areas for improvement in the system.

[0606] Based on the analysis results, the server will present the user with a solution. This solution may include revising the retry policy or improving the load balancing strategy. This will allow the user to improve system reliability and prevent unexpected communication failures in advance.

[0607] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0608] Step 1:

[0609] The server collects information from the activity units within the system. This information includes dependencies between activity units, communication delays, and error logs. Based on this information, it creates prompt statements to be input into the generated AI model. For example, data to understand the response time of service A and its dependencies with service B may be input, and based on this, a prompt statement such as "Evaluate the impact of a communication timeout between service A and service B" may be output.

[0610] Step 2:

[0611] The server inputs the generated prompt message into the AI ​​model to generate communication failure scenarios. The AI ​​model outputs various communication failure patterns based on the prompt message. These output scenarios include communication outages and overload conditions, illustrating the types of failures the system may face.

[0612] Step 3:

[0613] The server builds a virtualized environment based on the generated communication failure scenario. This environment mimics a real production environment using Docker or Kubernetes. The inputs are failure scenarios and virtual environment templates, and the output is a configuration within the virtual environment that reflects the scenario.

[0614] Step 4:

[0615] The server simulates communication failure scenarios in a virtual environment. Specifically, it intentionally introduces network delays and disconnections and observes how each activity unit reacts. The input is the scenario and the configured virtual environment, and the output is simulation data, such as the number of re-entries and network response time.

[0616] Step 5:

[0617] The server collects data obtained from simulations and analyzes it using an AI model. The input includes simulation data, with particular attention paid to the number of re-entries, error logs, and resource consumption. The output provides analysis results regarding areas where system improvement is needed and potential problems.

[0618] Step 6:

[0619] The server proposes solutions to the user based on the analysis results. Specifically, it suggests improvement methods such as modifying the retry policy or optimizing load balancing settings. The input is the analysis results, and the output is a proposal report for the user. This proposal allows the user to improve system reliability and take measures to prevent future failures.

[0620] (Application Example 1)

[0621] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0622] In modern information processing systems, it is common for multiple information processing units to work together in coordination. However, this complex interaction increases the likelihood of communication errors and malfunctions, which can lead to a decline in or complete shutdown of the entire system, ultimately causing safety and reliability issues. Furthermore, existing systems make it difficult to predict and prevent these failures before they occur.

[0623] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0624] In this invention, the server includes means for automatically generating communication error scenarios between multiple information processing units using a generative model, means for simulating failures in a virtual work area based on the scenarios, means for collecting and interpreting information obtained from the simulation, and means for providing the interpretation results as visual information in real time on a visual display device. This makes it possible to detect potential communication errors and functional failures in the information processing system in advance and propose solutions quickly and effectively.

[0625] A "generative model" is an artificial intelligence technology that has the ability to learn patterns from data and generate new data.

[0626] An "information processing unit" is a fundamental component of a computer that performs information input, processing, and output.

[0627] A "communication error scenario" is a scenario that illustrates specific situations of communication failures that may occur within an information processing system.

[0628] A "virtual workspace" is a virtual work environment that functions within software, but does not have a physical presence.

[0629] "Interpretation" is the act of reading and understanding meaning from collected data.

[0630] A "visual display device" is a hardware device used to present information visually.

[0631] To realize this invention, a system is provided in which a server and a visual display device work in coordination. The server uses a generative model to automatically generate communication error scenarios between information processing units. Specifically, it uses a natural language processing model such as OpenAI's GPT as the generative model to analyze communication data obtained from multiple information processing units and generate patterns of potential communication errors.

[0632] The server constructs a virtual workspace and simulates communication error scenarios that occur within it. This virtual workspace mimics a real-world environment using a real-time data processing framework such as Apache Kafka. As a result of the simulation, the server collects various data, including system response times and error logs, and interprets this data to identify potential communication failures and propose solutions.

[0633] Users can visually confirm the interpretation results provided by the server using a visual display device. This device features a visually intuitive interface to present collected data to the user in real time. Users can take swift action based on the system's suggestions.

[0634] For example, if the system detects a communication failure in a security camera, the generating AI model uses prompts to perform a specific simulation. An example of a prompt might be, "Generate a failure scenario for camera A in the security camera system and propose the optimal strategy for load balancing to other cameras." This allows the system to quickly provide the user with an appropriate solution, thereby improving system reliability.

[0635] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0636] Step 1:

[0637] The server collects communication data from information processing units in real time. The input is log data from each unit, and the output is a dataset for analysis. This data collection is performed using a data stream platform such as Apache Kafka.

[0638] Step 2:

[0639] The server uses a generative AI model based on the collected dataset to generate potential communication error scenarios. The input is the dataset obtained in step 1, and the output is the generated error scenario. In this process, the generative model utilizes prompt statements to automatically generate scenarios.

[0640] Step 3:

[0641] The server sets up a virtual workspace based on the generated communication error scenario and starts the simulation. The input is the scenario and virtual environment configuration data generated in step 2, and the output is detailed data associated with the simulation execution. Specifically, the communication behavior between units in the event of an anomaly is simulated.

[0642] Step 4:

[0643] The server analyzes the data obtained from the simulation to evaluate the system's response characteristics and error patterns. The input is the simulation data obtained in step 3, and the output is the analysis results that lead to the proposal of specific solutions. Anomaly behavior is detected using an AI algorithm.

[0644] Step 5:

[0645] The user views the analysis results provided by the server through a visual display device. The input is the analysis results obtained in step 4, and the output is the visual information displayed on the screen. For example, a dashboard showing which communication paths are likely to experience failures is displayed.

[0646] Step 6:

[0647] The user monitors the entire system and takes immediate action based on the information displayed on the screen. The input is the interpretation result visually presented in step 5, and the output is the user's instructions for operations and configuration changes. An example prompt used by the generated AI model is, "Please suggest countermeasures for the inter-service failure scenario."

[0648] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0649] This invention combines a generative model and an emotion engine to achieve more effective system operation and user support. The embodiments for carrying out this invention are described below.

[0650] First, the server collects the necessary data from each service within the system and automatically generates communication error scenarios using a generative model. The scenarios generated in this process are deployed in a virtual environment to simulate various failure conditions, taking into account the dependencies within the system.

[0651] Next, the server simulates failures in this virtual environment based on the generated scenario. This allows it to reproduce situations such as disruptions to communication between services or intentional increases in system load.

[0652] As the test progresses, the server uses an emotion engine to analyze the emotions of the user performing the test operations in real time. If a change in emotional state is detected, the system adjusts the suggested solutions and the feedback provided to better respond to the user.

[0653] Specifically, when providing reports based on test results, if the server determines that the user's emotions are negative, it will provide information in a more detailed format, highlighting proactive solutions and success stories. Conversely, if positive emotions are detected, it will focus on providing concise and efficient information.

[0654] Furthermore, the emotion engine receives user feedback and analyzes it to improve the usability of the system itself. For example, if feedback indicates that a user is experiencing stress with a particular operation, it generates suggestions for interface improvements to simplify that operation.

[0655] In this way, the present invention can demonstrate high effectiveness in both technical troubleshooting and user experience.

[0656] The following describes the processing flow.

[0657] Step 1:

[0658] The server collects necessary data from all related services and analyzes system dependencies. This data collection process includes information such as the operational status and communication patterns of each service, and the frequency of API calls.

[0659] Step 2:

[0660] The server uses the collected data to run a generative model and automatically generate communication error scenarios. This generative model considers a variety of failure conditions and outputs scenarios that include potential vulnerabilities that would not normally be noticed.

[0661] Step 3:

[0662] The server builds a virtual environment and deploys the generated failure scenarios within it. This virtual environment is built to simulate the actual system environment and serves as a testbed for evaluating how each service responds.

[0663] Step 4:

[0664] The server runs simulations within a virtual environment, intentionally generating failures such as communication outages and increased load based on failure scenarios. This verifies the fault tolerance and automatic recovery capabilities of each service.

[0665] Step 5:

[0666] During the failure simulation, the server collects test data in real time and simultaneously analyzes the user's emotional state using an emotion engine. Based on user interactions, it determines whether the emotion is positive, negative, or neutral.

[0667] Step 6:

[0668] The server analyzes the simulation results along with the user's emotional state to identify the root cause of the problem and generate the optimal solution tailored to the user's emotions. For example, if the user is feeling anxious, it will add detailed explanations to reassure them.

[0669] Step 7:

[0670] The server generates a report for the user based on the test results and presents solutions tailored based on sentiment analysis. This ensures that system improvement suggestions take into account not only the technical aspects but also the user experience.

[0671] Step 8:

[0672] Through feedback sessions, users drive further improvements to the interface and procedures based on analysis results obtained using the emotion engine. This feedback allows the system to continuously evolve in a direction that enhances usability.

[0673] (Example 2)

[0674] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0675] In conventional systems, handling communication errors was reactive, making it difficult to comprehensively test all failure conditions in advance. Furthermore, system error information was highly specialized for engineers, preventing the provision of appropriate information by leveraging user feedback and emotional states. Therefore, there is a need for a method that simultaneously improves both fault response and user experience.

[0676] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0677] In this invention, the server includes means for automatically generating communication error scenarios using a generative model, means for simulating failures in a virtual environment, and means for analyzing the user's emotional state in real time and adjusting the information provided. This makes it possible to simulate various failure conditions in advance and consider appropriate countermeasures, and also enables the provision of information according to the user's emotional state.

[0678] A "generative model" is an artificial intelligence technology that learns patterns from data and automatically generates new data and scenarios.

[0679] A "virtual environment" is a simulation environment created on a computer without physical constraints, and is used to test operation under various conditions.

[0680] The "emotion analysis mechanism" is a technological system that analyzes the user's facial expressions and voice data to recognize and classify their emotional state in real time.

[0681] "User's emotional state" refers to the emotional response of a person operating the system, and includes psychological states such as stress, joy, and surprise.

[0682] A "communication error scenario" is a hypothetical scenario created to simulate the specific circumstances and progression of communication failures that may occur between multiple systems.

[0683] "Adjusting information" refers to the act of optimizing the content, format, or timing of data and messages provided in accordance with the user's emotional state or the system's status.

[0684] This invention is a system that uses a generative model and an emotion analysis mechanism to improve the user experience and enable preventative and adaptive responses to communication errors.

[0685] The server first collects the necessary data from various services within the system (e.g., databases, APIs). This utilizes industry-standard messaging systems to achieve real-time data streaming. Next, the server automatically generates communication error scenarios by inputting prompts into a generation AI model. An example of such a prompt is, "Generate a scenario that considers the impact of communication errors."

[0686] The generated scenarios are deployed in a virtual environment, and the servers run the simulations. This virtual environment utilizes container technology and an orchestration platform to create a flexible and large-scale test environment. This allows for the reproduction of diverse failure conditions without disrupting the normal operation of the system.

[0687] The terminal monitors the user's actions while the simulation is running. The emotion analysis mechanism receives this data and analyzes the user's emotional state in real time from their facial expressions and voice. Specifically, the emotion analysis outputs the user's psychological state, such as stress and satisfaction, as numerical values ​​or categories.

[0688] Based on this emotional data, the server adjusts the information and feedback it provides to the user. For example, if a user expresses negative emotions due to a communication problem, the server will provide more detailed, step-by-step guidance to facilitate communication. Conversely, if positive emotions are detected, the focus will be on providing concise and easy-to-understand information.

[0689] Ultimately, based on feedback, we will propose further interface optimizations to improve the system and enhance its usability. This will allow users to use the system more intuitively and comfortably.

[0690] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0691] Step 1:

[0692] The server collects the necessary data from each service within the system. This input data includes communication logs and performance metrics. The server streams the data through the messaging system and aggregates it in real time. The output is an integrated dataset in a format suitable for analysis.

[0693] Step 2:

[0694] The server uses the collected data to input a prompt message into the generated AI model. The prompt message used is "Create a scenario that includes communication errors." In this process, the server receives the communication error scenario generated by the AI ​​model. The output is detailed scenario data used for simulation in a virtual environment.

[0695] Step 3:

[0696] The server deploys the generated scenarios into a virtual environment. The input is the scenario data generated in the previous step, and the virtual environment is built using container technology. The server then starts simulating communication failures within this environment. The output is the execution result data for each scenario.

[0697] Step 4:

[0698] The terminal monitors user actions during simulation and analyzes that data using an emotion analysis mechanism. Inputs include user action data and environmental sensor data. The emotion analysis mechanism analyzes the monitored data in real time to determine the user's emotional state. Outputs include metrics representing the user's emotional state.

[0699] Step 5:

[0700] The server adjusts feedback information based on the user's emotional state metrics. Inputs include emotional state metrics and notification data from various services. The server optimizes the information provided to the user accordingly. Specifically, if negative emotions are present, it generates detailed and positive feedback; if positive emotions are present, it provides summarized information. Outputs are the adjusted feedback messages and suggestions.

[0701] Step 6:

[0702] The user receives adjusted feedback from the server and performs actions based on that feedback. After receiving the feedback, the user provides new input regarding their actions, and this data is sent back to the system as the basis for further improvement suggestions. The output is the result of the user's improved actions.

[0703] (Application Example 2)

[0704] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0705] In modern information systems, communication errors and failures can impair the user experience and lead to decreased customer satisfaction. Furthermore, the lack of adequate mechanisms for accurately understanding and responding to users' emotional states in real time can negatively impact the quality of customer service. To efficiently resolve these issues, a system is needed that can respond quickly and flexibly to communication errors and provide appropriate feedback tailored to the user's emotional state.

[0706] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0707] In this invention, the server includes means for automatically generating communication error scenarios between multiple services using a generative model, means for simulating failures in a virtual environment based on the scenarios, and means for analyzing the user's emotions using an emotion engine and dynamically providing information based on the analysis results. This makes it possible to provide appropriate feedback and solutions that correspond to the user's emotions even in the event of a communication error.

[0708] A "generative model" refers to algorithms and methods for automatically generating communication error scenarios.

[0709] A "communication error scenario" refers to a hypothetical configuration of possible communication failure patterns that may occur between multiple services.

[0710] A "virtual environment" refers to a simulation space built on a computer that is different from the actual system.

[0711] An "emotion engine" refers to software or algorithms used to analyze a user's emotional state.

[0712] "User emotion analysis" refers to the process of inferring a user's emotional state at a given time based on their actions and behavior.

[0713] A "solution" refers to specific countermeasures or methods to be taken in response to a particular problem or obstacle.

[0714] The system for implementing this invention has a server-centric configuration. The server uses a generative AI model to automatically generate scenarios between multiple services where communication errors may occur. The generated scenarios are reproduced in a virtual environment, and user interactions are simulated.

[0715] The server uses an emotion engine to analyze in real time what emotions the user experiences within the simulation. This emotion analysis information is used to provide feedback and solutions for communication errors. For example, if a transaction fails while a user is in the process of purchasing a particular product, the server will take that emotion into consideration and offer proactive solutions or suggestions for similar products.

[0716] The analysis utilizes the OpenAI API, and when providing information based on real-time sentiment analysis results, real-time data processing is performed using the Django framework. The frontend is built using React Native to provide interactive information to the user.

[0717] As a concrete example, consider a scenario where a user is searching for a smartphone on an e-commerce site. If the user shows signs of hesitation in making a purchase, the server immediately presents alternative product recommendations and relevant success stories. This can increase the user's willingness to buy and reduce stress caused by communication errors.

[0718] The generative AI model creates optimal prompts based on the situation, helping the server provide appropriate feedback. A concrete example of a prompt might be, "If the user experiences frustration on product page B, suggest alternative products."

[0719] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0720] Step 1:

[0721] The server automatically generates communication error scenarios using a generative AI model. In this process, it takes dependency information for each service within the system as input and outputs scenarios that reflect a variety of failure conditions. This scenario generation utilizes past error data as training data and performs data calculations to generate new error scenarios.

[0722] Step 2:

[0723] The server deploys the generated communication error scenario into a virtual environment and starts the simulation. The virtual environment simulates the actual operating environment and artificially generates failures, such as blocking communication between services, based on the generated scenario. The input is the generated error scenario, and the resulting service responses and state changes are collected as output.

[0724] Step 3:

[0725] The user's terminal interacts with the virtual environment during the simulation, and the server uses an emotion engine to analyze the user's emotional state in real time. Using user operation logs and eye-tracking data as input, the emotion engine infers the user's emotions and sends the inferred result to the server as output. This process employs non-invasive emotion recognition technology.

[0726] Step 4:

[0727] The server combines the sentiment analysis results with the simulation results of communication error scenarios to build an AI model that generates appropriate solutions and feedback. It receives the user's emotional state as input, generates the most appropriate prompt based on that, and outputs information showing alternative solutions and success stories.

[0728] Step 5:

[0729] The user's device displays solutions and feedback sent from the server on its interface. React Native is used to present the data in an intuitive and easy-to-understand format for the user. Input is feedback from the server, and this feedback is output in a way that encourages user action.

[0730] 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.

[0731] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0732] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0733] 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.

[0734] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0735] 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.

[0736] 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.

[0737] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0738] 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."

[0739] 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.

[0740] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0741] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0750] 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.

[0751] The following is further disclosed regarding the embodiments described above.

[0752] (Claim 1)

[0753] A means for automatically generating communication error scenarios between multiple services using a generative model,

[0754] A means for simulating failures in a virtual environment based on the aforementioned scenario,

[0755] A means for collecting and analyzing data obtained from the aforementioned simulation,

[0756] Based on the aforementioned analysis results, a means of proposing a solution to the problem,

[0757] A system that includes this.

[0758] (Claim 2)

[0759] The system according to claim 1, wherein the scenario generation means generates a scenario taking into account the dependencies between services within the system.

[0760] (Claim 3)

[0761] The system according to claim 1, wherein the analysis means identifies behavior that is different from normal using an anomaly detection algorithm.

[0762] "Example 1"

[0763] (Claim 1)

[0764] A means of utilizing generation technology to generate communication failure scenarios between multiple activity units,

[0765] A means for reproducing the failure in a virtualized environment based on the aforementioned scenario,

[0766] A means for collecting and analyzing information obtained through the aforementioned reproduction,

[0767] A means for presenting a solution based on the aforementioned analysis results,

[0768] A system that includes this.

[0769] (Claim 2)

[0770] The system according to claim 1, wherein the scenario generation means creates a scenario taking into account the dependency status between activity units within the system.

[0771] (Claim 3)

[0772] The system according to claim 1, wherein the analysis means identifies an abnormal operation using an anomaly detection method.

[0773] "Application Example 1"

[0774] (Claim 1)

[0775] A means for automatically generating communication error scenarios between multiple information processing units using a generative model,

[0776] A means for simulating failures in a virtual work area based on the aforementioned scenario,

[0777] A means for collecting and interpreting information obtained from the aforementioned simulation,

[0778] Based on the aforementioned interpretation, means for presenting solutions to the problem,

[0779] A means for providing the interpretation result as visual information in real time in a visual display device,

[0780] A system that includes this.

[0781] (Claim 2)

[0782] The system according to claim 1, wherein the scenario generation means generates a scenario taking into account the dependencies between units in the information processing system.

[0783] (Claim 3)

[0784] The system according to claim 1, wherein the interpretation means identifies an abnormal operation using an anomaly detection process.

[0785] "Example 2 of combining an emotion engine"

[0786] (Claim 1)

[0787] A means for automatically generating communication error scenarios between multiple services using a generative model,

[0788] A means for simulating failures in a virtual environment based on the aforementioned scenario,

[0789] A means of analyzing a user's emotional state in real time using an emotion analysis mechanism,

[0790] A means of adjusting the information provided based on the user's emotional state,

[0791] Based on the aforementioned analysis results and emotional analysis, a means of proposing a solution to the problem,

[0792] A system that includes this.

[0793] (Claim 2)

[0794] The system according to claim 1, wherein the scenario generation means generates a scenario taking into account the dependencies between services within the system.

[0795] (Claim 3)

[0796] The system according to claim 1, wherein the analysis means identifies behavior that is different from normal using an anomaly detection algorithm.

[0797] "Application example 2 when combining with an emotional engine"

[0798] (Claim 1)

[0799] A means for automatically generating communication error scenarios between multiple services using a generative model,

[0800] A means for simulating failures in a virtual environment based on the aforementioned scenario,

[0801] A means for collecting and analyzing data obtained from the aforementioned simulation,

[0802] A means of analyzing the user's emotions using an emotion engine and dynamically providing information based on the analysis results,

[0803] Based on the aforementioned analysis results and emotional analysis results, a means for proposing solutions to the problem,

[0804] A system that includes this.

[0805] (Claim 2)

[0806] The system according to claim 1, wherein the scenario generation means generates a scenario taking into account the dependencies between services within the system.

[0807] (Claim 3)

[0808] The system according to claim 1, wherein the analysis means identifies behavior that is different from normal using an anomaly detection algorithm. [Explanation of Symbols]

[0809] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for automatically generating communication error scenarios between multiple services using a generative model, A means for simulating failures in a virtual environment based on the aforementioned scenario, A means for collecting and analyzing data obtained from the aforementioned simulation, Based on the aforementioned analysis results, a means of proposing a solution to the problem, A system that includes this.

2. The system according to claim 1, wherein the scenario generation means generates a scenario taking into account the dependencies between services within the system.

3. The system according to claim 1, wherein the analysis means identifies behavior that is different from normal using an anomaly detection algorithm.

Images