system

Abstract

The system according to the embodiment aims to analyze complex error codes and assist users in solving the problem themselves. [Solution] A system according to an embodiment includes an analysis unit, a cause identification unit, a guide provision unit, a solution provision unit, a feedback collection unit, and a learning unit. The analysis unit analyzes error codes. The cause identification unit identifies the cause of the problem based on the error code analyzed by the analysis unit. The guide provision unit provides clear guidance based on the cause identified by the cause identification unit. The solution provision unit provides detailed solutions based on the guide provided by the guide provision unit. The feedback collection unit collects user feedback. The learning unit learns based on the feedback collected by the feedback collection unit.

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has the problem that it is difficult to analyze complex error codes and identify the cause of problems, and there is a lack of support for users to solve problems themselves.

[0005] The system according to the embodiment aims to analyze complex error codes and assist users in solving the problem themselves. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a cause identification unit, a guide provision unit, a solution provision unit, a feedback collection unit, and a learning unit. The analysis unit analyzes an error code. The cause identification unit identifies the cause of the problem based on the error code analyzed by the analysis unit. The guide provision unit provides clear guidance based on the cause identified by the cause identification unit. The solution provision unit provides detailed solutions based on the guide provided by the guide provision unit. The feedback collection unit collects user feedback. The learning unit performs learning based on the feedback collected by the feedback collection unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze complex error codes and assist users in solving the problem themselves. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

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

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) A troubleshooting system according to an embodiment of the present invention uses a generation AI to understand complex error codes and quickly resolve computer problems. In this troubleshooting system, a user inputs an error code encountered by the user into the generation AI, which then analyzes the error code and identifies the cause of the problem. The generation AI then provides easy-to-understand guidance and solutions to help the user resolve the problem themselves. Furthermore, the generation AI utilizes user feedback to learn and improves its ability to provide accurate solutions. This allows users to resolve problems without stress and improves the efficiency of computer troubleshooting. For example, even when a system administrator deals with a large number of error codes, the generation AI can quickly identify the cause and provide appropriate solutions, improving work efficiency. First, a user inputs the error code encountered by the user into the generation AI. Next, the generation AI analyzes the error code and identifies the cause of the problem. For example, when a specific error code is input, the generation AI analyzes the error code and identifies the cause of the problem. Furthermore, the generation AI provides easy-to-understand guidance and solutions to help the user resolve the problem themselves. For example, the generation AI identifies the cause of the error code "Access Denied" and suggests appropriate solutions. Furthermore, the generative AI uses user feedback to learn and improve its ability to provide accurate solutions. For example, when a user provides feedback such as "This solution solved the problem," the generative AI learns from that information and becomes able to provide faster and more accurate solutions when the same error code occurs in the future. This mechanism allows users to solve problems without stress and makes computer troubleshooting more efficient. For example, when a system administrator deals with a large number of error codes, the generative AI can quickly identify the cause and provide appropriate solutions, improving work efficiency. This allows the troubleshooting system to quickly and accurately solve problems based on the user's error code.

[0029] A troubleshooting system according to an embodiment includes an analysis unit, a cause identification unit, a guide provision unit, a solution provision unit, a feedback collection unit, and a learning unit. The analysis unit analyzes an error code. For example, the analysis unit analyzes a specific error code. The analysis unit can perform syntax analysis and semantic analysis of the error code. For example, the analysis unit analyzes the syntax of the error code to identify the type of error. The analysis unit can also analyze the meaning of the error code to infer the cause of the error. The cause identification unit identifies the cause of the problem based on the error code analyzed by the analysis unit. For example, the cause identification unit identifies the cause using root cause analysis or pattern matching. For example, the cause identification unit analyzes the pattern of the error code and identifies the cause by referring to a database of past similar errors. The cause identification unit can also identify the root cause of the problem based on the detailed analysis results of the error code. The guide provision unit provides an easy-to-understand guide based on the cause identified by the cause identification unit. For example, the guide provision unit provides step-by-step procedures or visual guides. For example, the guide providing unit indicates specific steps for the user to resolve the error. The guide providing unit can also provide a solution depending on the cause of the error. The solution providing unit provides the specific solution based on the guide provided by the guide providing unit. The solution providing unit provides a specific solution, such as reinstalling software or changing settings. For example, the solution providing unit indicates specific steps for the user to resolve the error. The solution providing unit can also provide a correction patch depending on the cause of the error. The feedback collecting unit collects feedback from the user. The feedback collecting unit, for example, conducts a user survey or collects log data. For example, the feedback collecting unit collects feedback after the user has resolved the error. The feedback collecting unit can also collect feedback on the circumstances under which the error occurred and the effectiveness of the solution. The learning unit performs learning based on the feedback collected by the feedback collecting unit. The learning unit performs learning using, for example, a machine learning algorithm or data mining technology.For example, the learning unit learns the causes of errors and the effectiveness of countermeasures based on the collected feedback. The learning unit can also analyze the content of the feedback and perform learning to improve the accuracy of the system. As a result, the troubleshooting system according to the embodiment performs a consistent process from analyzing error codes to providing countermeasures, and collecting and learning feedback, allowing users to solve problems without stress.

[0030] The analysis unit can analyze specific error codes. Examples of specific error codes include, but are not limited to, HTTP status codes and system error messages. The analysis unit analyzes, for example, specific HTTP status codes. For example, the analysis unit analyzes an HTTP 404 error code to identify the cause of a resource not being found. The analysis unit can also analyze specific system error messages. For example, the analysis unit analyzes a system error message such as "Access Denied" to identify an access permission issue. This allows the cause of the problem to be quickly identified by analyzing the specific error code. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may analyze the error code using an AI model that inputs the specific error code and outputs an analysis result.

[0031] The cause identification unit can identify the cause of the problem based on the analyzed error code. The analyzed error code includes, for example, the format of the analysis result and details of the error message, but is not limited to these examples. For example, the cause identification unit analyzes the pattern of the analyzed error code and identifies the cause by referring to a database of similar past errors. For example, the cause identification unit analyzes the pattern of the error code and identifies the cause by referring to similar error codes that have occurred in the past. The cause identification unit can also identify the root cause of the problem based on the detailed analysis results of the error code. For example, the cause identification unit identifies a specific setting error or software bug based on the detailed analysis results of the error code. In this way, by identifying the cause of the problem based on the analyzed error code, an appropriate solution can be provided. Some or all of the above-mentioned processing in the cause identification unit may be performed using, for example, AI, or may be performed without AI. For example, the cause identification unit can input the analyzed error code and use an AI model that identifies the cause to identify the cause.

[0032] The guide providing unit can provide an easy-to-understand guide based on the identified cause. Examples of easy-to-understand guides include, but are not limited to, a user-friendly interface and concise explanations. For example, the guide providing unit can provide step-by-step procedures based on the identified cause. For example, the guide providing unit can show specific procedures for the user to resolve the error. The guide providing unit can also provide a visual guide based on the identified cause. For example, the guide providing unit can illustrate a solution depending on the cause of the error. This allows the user to resolve the problem themselves by providing an easy-to-understand guide based on the identified cause. Some or all of the above-described processing by the guide providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the guide providing unit can provide a guide using an AI model that inputs the identified cause and outputs an easy-to-understand guide.

[0033] The solution providing unit can provide a specific solution based on the provided guide. Specific solutions include, but are not limited to, providing a procedure manual or a patch. For example, the solution providing unit instructs the user to reinstall software based on the provided guide. For example, the solution providing unit indicates specific steps for the user to resolve the error. The solution providing unit can also instruct the user to change settings based on the provided guide. For example, the solution providing unit indicates setting change procedures depending on the cause of the error. This allows the user to quickly solve the problem by providing a specific solution based on the provided guide. Some or all of the above-mentioned processing by the solution providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the solution providing unit can provide a solution using an AI model that inputs the provided guide and outputs a specific solution.

[0034] The feedback collection unit can collect feedback from users. Examples of user feedback include, but are not limited to, questionnaires and usage logs. For example, the feedback collection unit collects feedback by conducting a user questionnaire. For example, the feedback collection unit collects feedback after a user resolves an error. The feedback collection unit can also obtain feedback by collecting usage logs. For example, the feedback collection unit collects log data on the occurrence of an error and the effectiveness of a solution. By collecting feedback from users, the collected feedback can be used to improve the system. Some or all of the above-described processing in the feedback collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback collection unit can collect feedback using an AI model that inputs the results of a user questionnaire and analyzes the feedback.

[0035] The learning unit can perform learning based on the collected feedback. The collected feedback includes, but is not limited to, text data and numerical data. The learning unit, for example, performs learning using a machine learning algorithm based on the collected feedback. For example, the learning unit analyzes the collected feedback and learns the causes of errors and the effectiveness of countermeasures. The learning unit can also analyze the content of the feedback and perform learning to improve the accuracy of the system. As a result, learning based on the collected feedback improves the accuracy of the system. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can perform learning using an AI model that uses the collected feedback as input and outputs learning results.

[0036] When analyzing an error code, the analysis unit can improve the accuracy of the analysis by referring to a database of similar error codes from the past. The database of similar error codes from the past includes, but is not limited to, the database structure and the type of data stored therein. For example, the analysis unit can quickly identify the cause by referring to similar error codes that have occurred in the past. For example, the analysis unit can search a database of past error codes to find similar error codes. The analysis unit can also select the optimal analysis method by referring to countermeasures for similar error codes. For example, the analysis unit can select the optimal analysis method based on the countermeasures for past error codes. Furthermore, the analysis unit can analyze the frequency of occurrence of past error codes and determine the analysis priority. For example, the analysis unit can prioritize the analysis of frequently occurring error codes. By referring to the database of similar error codes from the past, the analysis accuracy can be improved. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input past error code data and perform analysis using an AI model that improves analysis accuracy.

[0037] When analyzing an error code, the analysis unit can perform analysis based on the system's operating status and load status. Examples of the system's operating status and load status include, but are not limited to, CPU usage and memory usage. For example, the analysis unit checks the current system load status and distributes the analysis if the load is high. For example, when the system load is high, the analysis unit distributes analysis tasks to multiple processors. The analysis unit can also refer to the system's operating status and perform analysis without affecting running processes. For example, the analysis unit monitors running processes of the system and performs analysis to minimize the impact. Furthermore, the analysis unit can select the optimal analysis timing based on past system operation data. For example, the analysis unit analyzes past system operation data and performs analysis during times of low load. This improves analysis efficiency by taking the system's operating status and load status into consideration. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can perform analysis using an AI model that inputs system operation data and adjusts the analysis method.

[0038] When analyzing an error code, the analysis unit can refer to the user's operation history and prioritize analyzing related error codes. The user's operation history includes, but is not limited to, click logs and operation sequences. For example, the analysis unit prioritizes analyzing error codes that the user frequently encountered in the past. For example, the analysis unit analyzes the user's operation history and prioritizes analyzing frequently occurring error codes. The analysis unit can also identify past errors related to the current error code from the user's operation history and analyze them. For example, the analysis unit identifies related error codes based on the user's operation history and prioritizes analyzing them. Furthermore, the analysis unit can analyze the user's operation patterns and prioritize analyzing the most relevant error codes. For example, the analysis unit analyzes the user's operation patterns and prioritizes analyzing the most relevant error codes. This allows related error codes to be prioritized by referring to the user's operation history. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may perform analysis using an AI model that inputs user operation history data and determines analysis priorities.

[0039] When analyzing an error code, the analysis unit can integrate system log data and perform analysis. System log data includes, but is not limited to, error logs and access logs. For example, the analysis unit collects system log data in real time and uses it for analysis. For example, the analysis unit collects system log data in real time and uses it for error code analysis. The analysis unit can also identify the cause of an error code by referring to past log data. For example, the analysis unit identifies the cause of an error code based on past log data. Furthermore, the analysis unit can integrate system log data and analyze the correlation between multiple error codes. For example, the analysis unit integrates system log data and analyzes the correlation between multiple error codes. Integrating the system log data improves the accuracy of the analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may perform analysis using an AI model that inputs system log data and outputs analysis results.

[0040] The cause identification unit can improve the identification accuracy by referring to past cause identification results when identifying a cause. Examples of past cause identification results include, but are not limited to, the database structure and the type of stored data. For example, the cause identification unit can quickly identify a cause by referring to previously identified causes. For example, the cause identification unit can quickly identify similar causes based on past cause identification results. The cause identification unit can also refer to similar cause identification results and select an optimal identification method. For example, the cause identification unit selects an optimal identification method based on past cause identification results. Furthermore, the cause identification unit can analyze past cause identification results to improve the identification accuracy. For example, the cause identification unit can analyze past cause identification results and improve the method for improving the identification accuracy. As a result, the identification accuracy is improved by referring to past cause identification results. Some or all of the above-described processing in the cause identification unit may be performed using, for example, AI, or may be performed without AI. For example, the cause identification unit can input past cause identification data and perform cause identification using an AI model that improves the identification accuracy.

[0041] The cause identification unit can identify the cause by taking into account system configuration information. System configuration information includes, but is not limited to, hardware configuration and software version information. For example, the cause identification unit can identify the cause by referring to the system's hardware configuration information. For example, the cause identification unit can identify a specific hardware problem based on the system's hardware configuration information. The cause identification unit can also identify the cause by referring to the system's software configuration information. For example, the cause identification unit can identify a specific software problem based on the system's software version information. The cause identification unit can also identify the cause by referring to the system's network configuration information. For example, the cause identification unit can identify a network-related problem based on the system's network configuration information. Taking the system configuration information into consideration improves the accuracy of the identification. Some or all of the above-described processing in the cause identification unit may be performed using, for example, AI, or may be performed without AI. For example, the cause identification unit can input the system's configuration information and use an AI model that identifies the cause.

[0042] When identifying the cause, the cause identification unit can refer to the user's system usage pattern to identify the cause. The user's system usage pattern includes, but is not limited to, for example, usage frequency and operation sequence. For example, the cause identification unit analyzes the user's system usage pattern to identify the most likely cause. For example, the cause identification unit identifies an error caused by a specific operation based on the user's system usage pattern. The cause identification unit can also refer to the user's operation history to identify the cause. For example, the cause identification unit identifies related errors based on the user's operation history. Furthermore, the cause identification unit can also identify causes that occur during specific time periods based on the user's system usage pattern. For example, the cause identification unit analyzes the user's system usage pattern to identify errors that occur during specific time periods. In this way, referring to the user's system usage pattern improves the accuracy of identification. Some or all of the above-described processing in the cause identification unit may be performed using, for example, AI, or may be performed without AI. For example, the cause identification unit can input the user's system usage pattern data and use an AI model that identifies causes to identify the cause.

[0043] The cause identification unit can identify the cause by referring to real-time system data. Examples of real-time system data include, but are not limited to, current CPU usage and memory usage. For example, the cause identification unit collects real-time system data and identifies the cause. For example, the cause identification unit analyzes the current system status based on the real-time system data and identifies the cause. The cause identification unit can also identify the cause by referring to real-time system performance data. For example, the cause identification unit identifies a specific performance problem based on the real-time system performance data. Furthermore, the cause identification unit can also identify the cause by referring to real-time network data. For example, the cause identification unit identifies a network-related problem based on the real-time network data. By referring to the real-time system data, the accuracy of the identification is improved. Some or all of the above-described processing in the cause identification unit may be performed using, for example, AI, or may be performed without AI. For example, the cause identification unit can input real-time system data and use an AI model that identifies the cause to identify the cause.

[0044] When providing a guide, the guide providing unit can adjust the level of detail of the guide according to the user's skill level. Examples of user skill levels include, but are not limited to, beginner, intermediate, and advanced. For example, the guide providing unit can provide a guide including basic procedures to a beginner user. For example, the guide providing unit can provide a guide using simple procedures and illustrations to a beginner user. The guide providing unit can also provide a guide including detailed procedures and additional information to an intermediate user. For example, the guide providing unit can provide detailed procedures and troubleshooting tips to an intermediate user. Furthermore, the guide providing unit can provide a guide including specialized information to an advanced user. For example, the guide providing unit can provide detailed technical information and advanced setting procedures to an advanced user. This allows the level of detail of the guide to be adjusted according to the user's skill level, thereby providing an optimal guide for the user. Some or all of the above-described processing by the guide providing unit can be performed using, for example, AI, or without AI. For example, the guide providing unit can provide a guide using an AI model that inputs the user's skill level data and adjusts the level of detail of the guide.

[0045] When providing a guide, the guide providing unit can determine the priority of the guide according to the severity of the error. The severity of the error includes, but is not limited to, the impact on the entire system and the impact on the user. For example, in the case of a serious error, the guide providing unit provides the guide with the highest priority. For example, the guide providing unit quickly provides a guide for a serious error that affects the entire system. Furthermore, in the case of a moderate error, the guide providing unit can also provide a guide at an appropriate time. For example, the guide providing unit provides a guide for an error that is important to the user at an appropriate time. Furthermore, in the case of a minor error, the guide providing unit can provide the guide after providing guides for other errors. For example, the guide providing unit provides a guide for an error that has a small impact on the user after providing guides for other errors. Thus, by determining the priority of the guide according to the severity of the error, it is possible to quickly respond to an important error. Some or all of the above-described processing in the guide providing unit may be performed using, for example, AI, or may be performed without AI. For example, the guide providing unit can provide the guide using an AI model that inputs error severity data and determines the priority of the guide.

[0046] When providing a guide, the guide providing unit can provide an optimal guide by referring to the user's past solution history. The user's past solution history includes, for example, past support tickets and resolved problems, but is not limited to these examples. The guide providing unit can provide an optimal guide, for example, based on solutions that the user has used successfully in the past. For example, the guide providing unit can provide an optimal guide for a similar problem based on the user's past solution history. The guide providing unit can also select the most effective guide from the user's past solution history. For example, the guide providing unit can analyze the user's past solution history and select the most effective guide. Furthermore, the guide providing unit can analyze the user's past solution history and provide an optimal guide. For example, the guide providing unit can provide an optimal guide based on the user's past solution history. In this way, the optimal guide can be provided by referring to the user's past solution history. Some or all of the above-described processing in the guide providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the guide providing unit can provide a guide using an AI model that inputs the user's past solution history data and provides an optimal guide.

[0047] When providing a guide, the guide providing unit can provide an optimal guide by taking into account the user's device information. The user's device information includes, for example, the device type and the OS version, but is not limited to these examples. The guide providing unit can provide an optimal guide, for example, depending on the type of device used by the user. For example, the guide providing unit provides a guide depending on the device used by the user. The guide providing unit can also provide an optimal guide by referring to the setting information of the user's device. For example, the guide providing unit provides an optimal guide based on the setting information of the user's device. Furthermore, the guide providing unit can also provide an optimal guide by taking into account the performance of the user's device. For example, the guide providing unit provides an optimal guide based on the performance of the user's device. In this way, the optimal guide can be provided by taking the user's device information into consideration. Some or all of the above-described processing in the guide providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the guide providing unit can provide a guide using an AI model that inputs the user's device information and provides an optimal guide.

[0048] When providing a solution, the solution providing unit can select the optimal solution by referring to the success rates of past solutions. The success rates of past solutions include, but are not limited to, methods for calculating the success rates and methods for storing the data. The solution providing unit selects the optimal solution based on solutions that have been successful in the past. For example, the solution providing unit selects the optimal solution for a similar problem based on the success rates of past solutions. The solution providing unit can also select a solution with a high success rate for a similar error. For example, the solution providing unit selects the optimal solution based on the success rates of past solutions. Furthermore, the solution providing unit can analyze the success rates of past solutions and select the optimal solution. For example, the solution providing unit analyzes the success rates of past solutions and selects the optimal solution. This allows the optimal solution to be selected by referring to the success rates of past solutions. Some or all of the above-described processing in the solution providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the solution providing unit can provide solutions using an AI model that inputs data on the success rate of past solutions and selects the optimal solution.

[0049] When providing a countermeasure, the solution providing unit can determine the priority of the countermeasures according to the frequency of error occurrence. The frequency of error occurrence includes, but is not limited to, the number of occurrences and the period of occurrence. For example, the solution providing unit provides a countermeasure with the highest priority for a frequently occurring error. For example, the solution providing unit quickly provides a countermeasure for a frequently occurring error. The solution providing unit can also provide a countermeasure at an appropriate time for an error with a medium frequency of occurrence. For example, the solution providing unit provides a countermeasure at an appropriate time for an error with a medium frequency of occurrence. Furthermore, the solution providing unit can also provide a countermeasure for an error that occurs infrequently after providing a countermeasure for another error. For example, the solution providing unit provides a countermeasure for an error that occurs infrequently after providing a countermeasure for another error. In this way, by determining the priority of the countermeasures according to the frequency of error occurrence, frequently occurring errors can be quickly addressed. Some or all of the above-described processing by the solution providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the solution providing unit can provide solutions using an AI model that inputs error occurrence frequency data and determines the priority order of solutions.

[0050] When providing a solution, the solution providing unit can provide an optimal solution by referring to the user's system configuration information. The user's system configuration information includes, but is not limited to, a configuration file and a user profile. The solution providing unit, for example, refers to the user's system configuration information and provides an optimal solution. For example, the solution providing unit provides an optimal solution based on the user's system configuration information. The solution providing unit can also provide a customized solution based on the user's system configuration. For example, the solution providing unit provides a customized solution based on the user's system configuration information. Furthermore, the solution providing unit can analyze the user's system configuration information and select an optimal solution. For example, the solution providing unit selects an optimal solution based on the user's system configuration information. In this way, the optimal solution can be provided by referring to the user's system configuration information. Some or all of the above-described processing in the solution providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the solution providing unit can provide a solution using an AI model that takes the user's system setting information as input and provides the optimal solution.

[0051] When providing a countermeasure, the solution providing unit can provide an optimal solution by taking into account the user's operating environment. The user's operating environment includes, but is not limited to, the device being used and the network environment. For example, the solution providing unit references the user's operating environment and provides the optimal solution. For example, the solution providing unit provides the optimal solution based on the user's operating environment. The solution providing unit can also provide a customized solution based on the user's operating environment. For example, the solution providing unit provides the customized solution based on the user's operating environment. Furthermore, the solution providing unit can analyze the user's operating environment and select the optimal solution. For example, the solution providing unit selects the optimal solution based on the user's operating environment. This allows the optimal solution to be provided by taking the user's operating environment into consideration. Some or all of the above-described processing in the solution providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the solution providing unit can input data about the user's operating environment and provide a countermeasure using an AI model that provides the optimal solution.

[0052] When collecting feedback, the feedback collection unit can improve the collection accuracy by referring to the user's past feedback history. The user's past feedback history includes, for example, past survey results and feedback content, but is not limited to these examples. For example, the feedback collection unit selects an optimal feedback collection method by referring to the user's past feedback history. For example, the feedback collection unit selects an optimal feedback collection method based on the user's past feedback history. The feedback collection unit can also request detailed feedback from the user's past feedback history. For example, the feedback collection unit requests detailed feedback based on the user's past feedback history. Furthermore, the feedback collection unit can analyze the user's past feedback history to improve the collection accuracy. For example, the feedback collection unit improves a method for improving the collection accuracy based on the user's past feedback history. As a result, the collection accuracy is improved by referring to the user's past feedback history. Some or all of the above-described processing in the feedback collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback collection unit can collect feedback using an AI model that uses the user's past feedback history data as input and improves the collection accuracy.

[0053] When collecting feedback, the feedback collection unit can select an optimal collection method by referring to the user's system usage status. The user's system usage status includes, but is not limited to, for example, frequency of use and operation sequence. The feedback collection unit, for example, refers to the user's system usage status to select an optimal feedback collection method. For example, the feedback collection unit selects an optimal feedback collection method based on the user's system usage status. The feedback collection unit can also provide a customized feedback collection method based on the user's system usage status. For example, the feedback collection unit provides a customized feedback collection method based on the user's system usage status. Furthermore, the feedback collection unit can analyze the user's system usage status and select an optimal feedback collection method. For example, the feedback collection unit selects an optimal feedback collection method based on the user's system usage status. In this way, the optimal feedback collection method can be selected by referring to the user's system usage status. Some or all of the above-described processing in the feedback collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback collection unit can collect feedback using an AI model that takes user system usage data as input and selects the optimal feedback collection method.

[0054] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. Past learning data includes, for example, the structure of a database and the type of data stored, but is not limited to these examples. For example, the learning unit selects an optimal learning algorithm by referring to past learning data. For example, the learning unit selects an optimal learning algorithm based on the past learning data. The learning unit can also analyze the past learning data and optimize the learning algorithm. For example, the learning unit optimizes the learning algorithm based on the past learning data. Furthermore, the learning unit can adjust parameters of the learning algorithm based on the past learning data. For example, the learning unit adjusts parameters of the learning algorithm based on the past learning data. As a result, the accuracy of the learning algorithm is improved by referring to the past learning data. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can perform learning using an AI model that uses past learning data as input and optimizes the learning algorithm.

[0055] During learning, the learning unit can weight the learning data based on the time of feedback submission. The time of feedback submission includes, but is not limited to, for example, the submission date and time and the frequency of submission. For example, the learning unit sets a high weight for the learning data if the feedback submission time is recent. For example, the learning unit sets a high weight for the learning data based on recently submitted feedback. Furthermore, the learning unit can also set a low weight for the learning data if the feedback submission time is old. For example, the learning unit sets a low weight for the learning data based on old feedback. Furthermore, the learning unit can also appropriately adjust the weight for the learning data based on the time of feedback submission. For example, the learning unit appropriately adjusts the weight for the learning data based on the time of feedback submission. Thus, weighting the learning data based on the time of feedback submission improves the accuracy of learning. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit can perform learning using an AI model that uses feedback submission time data as input and weights the learning data.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] When analyzing error codes, the analysis unit can take the user's operating environment into consideration. For example, the analysis unit can select the optimal analysis method by referring to the type of device and network environment used by the user. For example, when using a mobile device, the analysis unit can use a lightweight analysis algorithm to provide results quickly. In addition, when the network environment is unstable, the analysis unit can perform offline analysis and synchronize the results later. This allows for flexible analysis that suits the user's operating environment.

[0058] Based on the analysis results of the error code, the cause identification unit can refer to the user's past operation history and identify the most relevant cause. For example, the cause identification unit can analyze the operation sequence performed by the user in the past and identify the cause when a similar error occurs. The cause identification unit can also extract specific patterns from the user's operation history and identify the root cause of the error. Furthermore, the cause identification unit can analyze the frequency of error occurrence based on the user's operation history and identify the most likely cause. This makes it possible to identify the cause with greater accuracy by utilizing the user's operation history.

[0059] The guide providing unit can customize the content of the guide according to the user's skill level. For example, it can provide a guide including basic procedures for beginner users and detailed procedures and additional information for intermediate users. It can also provide a guide including specialized information for advanced users. Furthermore, the guide providing unit can automatically estimate the user's skill level and provide the most appropriate guide. This provides an appropriate guide according to the user's skill level, deepening the user's understanding.

[0060] The solution provider can prioritize solutions according to the severity of the error. For example, solutions are provided with the highest priority for serious errors that affect the entire system, allowing for rapid resolution. Solutions can also be provided at an appropriate time for errors that are important to the user. Furthermore, solutions can be provided for minor errors after solutions for other errors have been provided. This allows for the provision of appropriate solutions according to the severity of the error, improving the stability of the system.

[0061] When performing learning based on collected feedback, the learning unit can weight the learning data based on the time of submission of the feedback. For example, the weight of learning data can be set high based on recently submitted feedback, and the weight of learning data can be set low based on older feedback. The weight of learning data can also be appropriately adjusted based on the frequency of feedback submission. This allows learning to emphasize the most recent information, improving the accuracy of the system.

[0062] When analyzing error codes, the analysis unit can perform analysis based on the system's operating status and load status. For example, it checks the current system load status and distributes the analysis if the load is high. It can also refer to the system's operating status and perform analysis without affecting running processes. It can also select the optimal timing for analysis based on the system's past operating data. This enables efficient analysis that takes into account the system's operating status and load status.

[0063] The processing flow of the first embodiment will be briefly explained below.

[0064] Step 1: The analysis unit analyzes the error code. The analysis unit performs syntactic and semantic analysis of the error code to identify the type and cause of the error. Step 2: The cause identification unit identifies the cause of the problem based on the error code analyzed by the analysis unit. The cause identification unit identifies the cause using root cause analysis and pattern matching, and identifies the root cause by referring to a database of past similar errors. Step 3: The guide provider provides an easy-to-understand guide based on the cause identified by the cause identifyr. The guide provider provides step-by-step instructions and visual guides to show the user specific steps to resolve the error. Step 4: The solution providing unit provides specific solutions based on the guide provided by the guide providing unit. The solution providing unit provides specific solutions such as reinstalling software or changing settings, and can also provide a patch to fix the cause of the error. Step 5: The feedback collection unit collects feedback from users. The feedback collection unit collects user surveys and log data, and gathers feedback on the occurrence of errors and the effectiveness of countermeasures. Step 6: The learning unit performs learning based on the feedback collected by the feedback collection unit. Using machine learning algorithms and data mining techniques, the learning unit learns the causes of errors and the effectiveness of countermeasures, thereby improving the accuracy of the system.

[0065] (Example 2) A troubleshooting system according to an embodiment of the present invention uses a generation AI to understand complex error codes and quickly resolve computer problems. In this troubleshooting system, a user inputs an error code encountered by the user into the generation AI, which then analyzes the error code and identifies the cause of the problem. The generation AI then provides easy-to-understand guidance and solutions to help the user resolve the problem themselves. Furthermore, the generation AI utilizes user feedback to learn and improves its ability to provide accurate solutions. This allows users to resolve problems without stress and improves the efficiency of computer troubleshooting. For example, even when a system administrator deals with a large number of error codes, the generation AI can quickly identify the cause and provide appropriate solutions, improving work efficiency. First, a user inputs the error code encountered by the user into the generation AI. Next, the generation AI analyzes the error code and identifies the cause of the problem. For example, when a specific error code is input, the generation AI analyzes the error code and identifies the cause of the problem. Furthermore, the generation AI provides easy-to-understand guidance and solutions to help the user resolve the problem themselves. For example, the generation AI identifies the cause of the error code "Access Denied" and suggests appropriate solutions. Furthermore, the generative AI uses user feedback to learn and improve its ability to provide accurate solutions. For example, when a user provides feedback such as "This solution solved the problem," the generative AI learns from that information and becomes able to provide faster and more accurate solutions when the same error code occurs in the future. This mechanism allows users to solve problems without stress and makes computer troubleshooting more efficient. For example, when a system administrator deals with a large number of error codes, the generative AI can quickly identify the cause and provide appropriate solutions, improving work efficiency. This allows the troubleshooting system to quickly and accurately solve problems based on the user's error code.

[0066] A troubleshooting system according to an embodiment includes an analysis unit, a cause identification unit, a guide provision unit, a solution provision unit, a feedback collection unit, and a learning unit. The analysis unit analyzes an error code. For example, the analysis unit analyzes a specific error code. The analysis unit can perform syntax analysis and semantic analysis of the error code. For example, the analysis unit analyzes the syntax of the error code to identify the type of error. The analysis unit can also analyze the meaning of the error code to infer the cause of the error. The cause identification unit identifies the cause of the problem based on the error code analyzed by the analysis unit. For example, the cause identification unit identifies the cause using root cause analysis or pattern matching. For example, the cause identification unit analyzes the pattern of the error code and identifies the cause by referring to a database of past similar errors. The cause identification unit can also identify the root cause of the problem based on the detailed analysis results of the error code. The guide provision unit provides an easy-to-understand guide based on the cause identified by the cause identification unit. For example, the guide provision unit provides step-by-step procedures or visual guides. For example, the guide providing unit indicates specific steps for the user to resolve the error. The guide providing unit can also provide a solution depending on the cause of the error. The solution providing unit provides the specific solution based on the guide provided by the guide providing unit. The solution providing unit provides a specific solution, such as reinstalling software or changing settings. For example, the solution providing unit indicates specific steps for the user to resolve the error. The solution providing unit can also provide a correction patch depending on the cause of the error. The feedback collecting unit collects feedback from the user. The feedback collecting unit, for example, conducts a user survey or collects log data. For example, the feedback collecting unit collects feedback after the user has resolved the error. The feedback collecting unit can also collect feedback on the circumstances under which the error occurred and the effectiveness of the solution. The learning unit performs learning based on the feedback collected by the feedback collecting unit. The learning unit performs learning using, for example, a machine learning algorithm or data mining technology.For example, the learning unit learns the causes of errors and the effectiveness of countermeasures based on the collected feedback. The learning unit can also analyze the content of the feedback and perform learning to improve the accuracy of the system. As a result, the troubleshooting system according to the embodiment performs a consistent process from analyzing error codes to providing countermeasures, and collecting and learning feedback, allowing users to solve problems without stress.

[0067] The analysis unit can analyze specific error codes. Examples of specific error codes include, but are not limited to, HTTP status codes and system error messages. The analysis unit analyzes, for example, specific HTTP status codes. For example, the analysis unit analyzes an HTTP 404 error code to identify the cause of a resource not being found. The analysis unit can also analyze specific system error messages. For example, the analysis unit analyzes a system error message such as "Access Denied" to identify an access permission issue. This allows the cause of the problem to be quickly identified by analyzing the specific error code. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may analyze the error code using an AI model that inputs the specific error code and outputs an analysis result.

[0068] The cause identification unit can identify the cause of the problem based on the analyzed error code. The analyzed error code includes, for example, the format of the analysis result and details of the error message, but is not limited to these examples. For example, the cause identification unit analyzes the pattern of the analyzed error code and identifies the cause by referring to a database of similar past errors. For example, the cause identification unit analyzes the pattern of the error code and identifies the cause by referring to similar error codes that have occurred in the past. The cause identification unit can also identify the root cause of the problem based on the detailed analysis results of the error code. For example, the cause identification unit identifies a specific setting error or software bug based on the detailed analysis results of the error code. In this way, by identifying the cause of the problem based on the analyzed error code, an appropriate solution can be provided. Some or all of the above-mentioned processing in the cause identification unit may be performed using, for example, AI, or may be performed without AI. For example, the cause identification unit can input the analyzed error code and use an AI model that identifies the cause to identify the cause.

[0069] The guide providing unit can provide an easy-to-understand guide based on the identified cause. Examples of easy-to-understand guides include, but are not limited to, a user-friendly interface and concise explanations. For example, the guide providing unit can provide step-by-step procedures based on the identified cause. For example, the guide providing unit can show specific procedures for the user to resolve the error. The guide providing unit can also provide a visual guide based on the identified cause. For example, the guide providing unit can illustrate a solution depending on the cause of the error. This allows the user to resolve the problem themselves by providing an easy-to-understand guide based on the identified cause. Some or all of the above-described processing by the guide providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the guide providing unit can provide a guide using an AI model that inputs the identified cause and outputs an easy-to-understand guide.

[0070] The solution providing unit can provide a specific solution based on the provided guide. Specific solutions include, but are not limited to, providing a procedure manual or a patch. For example, the solution providing unit instructs the user to reinstall software based on the provided guide. For example, the solution providing unit indicates specific steps for the user to resolve the error. The solution providing unit can also instruct the user to change settings based on the provided guide. For example, the solution providing unit indicates setting change procedures depending on the cause of the error. This allows the user to quickly solve the problem by providing a specific solution based on the provided guide. Some or all of the above-mentioned processing by the solution providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the solution providing unit can provide a solution using an AI model that inputs the provided guide and outputs a specific solution.

[0071] The feedback collection unit can collect feedback from users. Examples of user feedback include, but are not limited to, questionnaires and usage logs. For example, the feedback collection unit collects feedback by conducting a user questionnaire. For example, the feedback collection unit collects feedback after a user resolves an error. The feedback collection unit can also obtain feedback by collecting usage logs. For example, the feedback collection unit collects log data on the occurrence of an error and the effectiveness of a solution. By collecting feedback from users, the collected feedback can be used to improve the system. Some or all of the above-described processing in the feedback collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback collection unit can collect feedback using an AI model that inputs the results of a user questionnaire and analyzes the feedback.

[0072] The learning unit can perform learning based on the collected feedback. The collected feedback includes, but is not limited to, text data and numerical data. The learning unit, for example, performs learning using a machine learning algorithm based on the collected feedback. For example, the learning unit analyzes the collected feedback and learns the causes of errors and the effectiveness of countermeasures. The learning unit can also analyze the content of the feedback and perform learning to improve the accuracy of the system. As a result, learning based on the collected feedback improves the accuracy of the system. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can perform learning using an AI model that uses the collected feedback as input and outputs learning results.

[0073] The analysis unit can estimate the user's emotions and adjust the error code analysis method based on the estimated user emotions. The analysis unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the analysis unit captures the user's facial expression data using a camera and estimates the emotion using an emotion estimation algorithm. The analysis unit can also estimate the user's emotions using voice analysis technology. For example, the analysis unit captures the user's voice data using a microphone and estimates the emotion using a voice analysis algorithm. The analysis unit then adjusts the error code analysis method based on the user's emotions. For example, if the user is stressed, the analysis unit performs a quick analysis and provides a concise result. On the other hand, if the user is relaxed, the analysis unit provides a detailed analysis result for a deeper understanding. This allows the analysis method to be adjusted according to the user's emotions, thereby providing the optimal analysis result for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may perform analysis using an AI model that inputs user emotion data and adjusts the analysis method.

[0074] When analyzing an error code, the analysis unit can improve the accuracy of the analysis by referring to a database of similar error codes from the past. The database of similar error codes from the past includes, but is not limited to, the database structure and the type of data stored therein. For example, the analysis unit can quickly identify the cause by referring to similar error codes that have occurred in the past. For example, the analysis unit can search a database of past error codes to find similar error codes. The analysis unit can also select the optimal analysis method by referring to countermeasures for similar error codes. For example, the analysis unit can select the optimal analysis method based on the countermeasures for past error codes. Furthermore, the analysis unit can analyze the frequency of occurrence of past error codes and determine the analysis priority. For example, the analysis unit can prioritize the analysis of frequently occurring error codes. By referring to the database of similar error codes from the past, the analysis accuracy can be improved. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input past error code data and perform analysis using an AI model that improves analysis accuracy.

[0075] When analyzing an error code, the analysis unit can perform analysis based on the system's operating status and load status. Examples of the system's operating status and load status include, but are not limited to, CPU usage and memory usage. For example, the analysis unit checks the current system load status and distributes the analysis if the load is high. For example, when the system load is high, the analysis unit distributes analysis tasks to multiple processors. The analysis unit can also refer to the system's operating status and perform analysis without affecting running processes. For example, the analysis unit monitors running processes of the system and performs analysis to minimize the impact. Furthermore, the analysis unit can select the optimal analysis timing based on past system operation data. For example, the analysis unit analyzes past system operation data and performs analysis during times of low load. This improves analysis efficiency by taking the system's operating status and load status into consideration. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can perform analysis using an AI model that inputs system operation data and adjusts the analysis method.

[0076] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. The analysis unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the analysis unit acquires the user's facial expression data using a camera and estimates the emotion using an emotion estimation algorithm. The analysis unit can also estimate the user's emotions using voice analysis technology. For example, the analysis unit acquires the user's voice data using a microphone and estimates the emotion using a voice analysis algorithm. The analysis unit also adjusts the display method of the analysis results based on the user's emotions. For example, if the user is nervous, the analysis unit can provide a simple, highly visible display method. On the other hand, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. This allows the display method of the analysis results to be optimized for the user by adjusting the display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input user emotion data and display the analysis results using an AI model that adjusts the display method.

[0077] When analyzing an error code, the analysis unit can refer to the user's operation history and prioritize analyzing related error codes. The user's operation history includes, but is not limited to, click logs and operation sequences. For example, the analysis unit prioritizes analyzing error codes that the user frequently encountered in the past. For example, the analysis unit analyzes the user's operation history and prioritizes analyzing frequently occurring error codes. The analysis unit can also identify past errors related to the current error code from the user's operation history and analyze them. For example, the analysis unit identifies related error codes based on the user's operation history and prioritizes analyzing them. Furthermore, the analysis unit can analyze the user's operation patterns and prioritize analyzing the most relevant error codes. For example, the analysis unit analyzes the user's operation patterns and prioritizes analyzing the most relevant error codes. This allows related error codes to be prioritized by referring to the user's operation history. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may perform analysis using an AI model that inputs user operation history data and determines analysis priorities.

[0078] When analyzing an error code, the analysis unit can integrate system log data and perform analysis. System log data includes, but is not limited to, error logs and access logs. For example, the analysis unit collects system log data in real time and uses it for analysis. For example, the analysis unit collects system log data in real time and uses it for error code analysis. The analysis unit can also identify the cause of an error code by referring to past log data. For example, the analysis unit identifies the cause of an error code based on past log data. Furthermore, the analysis unit can integrate system log data and analyze the correlation between multiple error codes. For example, the analysis unit integrates system log data and analyzes the correlation between multiple error codes. Integrating the system log data improves the accuracy of the analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may perform analysis using an AI model that inputs system log data and outputs analysis results.

[0079] The cause identification unit can estimate the user's emotion and adjust the cause identification method based on the estimated user's emotion. The cause identification unit, for example, uses facial expression recognition technology to estimate the user's emotion. For example, the cause identification unit acquires the user's facial expression data using a camera and estimates the emotion using an emotion estimation algorithm. The cause identification unit can also estimate the user's emotion using voice analysis technology. For example, the cause identification unit acquires the user's voice data using a microphone and estimates the emotion using a voice analysis algorithm. The cause identification unit further adjusts the cause identification method based on the user's emotion. For example, if the user is feeling stressed, the cause identification unit can quickly identify the cause and provide a concise explanation. On the other hand, if the user is relaxed, the cause identification unit can provide a detailed explanation using a cause identification method. This allows the cause identification method to be optimized for the user by adjusting the cause identification method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the cause identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the cause identification unit may input user emotion data and identify the cause using an AI model that adjusts the cause identification method.

[0080] The cause identification unit can improve the identification accuracy by referring to past cause identification results when identifying a cause. Examples of past cause identification results include, but are not limited to, the database structure and the type of stored data. For example, the cause identification unit can quickly identify a cause by referring to previously identified causes. For example, the cause identification unit can quickly identify similar causes based on past cause identification results. The cause identification unit can also refer to similar cause identification results and select an optimal identification method. For example, the cause identification unit selects an optimal identification method based on past cause identification results. Furthermore, the cause identification unit can analyze past cause identification results to improve the identification accuracy. For example, the cause identification unit can analyze past cause identification results and improve the method for improving the identification accuracy. As a result, the identification accuracy is improved by referring to past cause identification results. Some or all of the above-described processing in the cause identification unit may be performed using, for example, AI, or may be performed without AI. For example, the cause identification unit can input past cause identification data and perform cause identification using an AI model that improves the identification accuracy.

[0081] The cause identification unit can identify the cause by taking into account system configuration information. System configuration information includes, but is not limited to, hardware configuration and software version information. For example, the cause identification unit can identify the cause by referring to the system's hardware configuration information. For example, the cause identification unit can identify a specific hardware problem based on the system's hardware configuration information. The cause identification unit can also identify the cause by referring to the system's software configuration information. For example, the cause identification unit can identify a specific software problem based on the system's software version information. The cause identification unit can also identify the cause by referring to the system's network configuration information. For example, the cause identification unit can identify a network-related problem based on the system's network configuration information. Taking the system configuration information into consideration improves the accuracy of the identification. Some or all of the above-described processing in the cause identification unit may be performed using, for example, AI, or may be performed without AI. For example, the cause identification unit can input the system's configuration information and use an AI model that identifies the cause.

[0082] The cause identification unit can estimate the user's emotion and adjust the display method of the cause identification result based on the estimated user's emotion. The cause identification unit, for example, uses facial expression recognition technology to estimate the user's emotion. For example, the cause identification unit acquires the user's facial expression data using a camera and estimates the emotion using an emotion estimation algorithm. The cause identification unit can also estimate the user's emotion using voice analysis technology. For example, the cause identification unit acquires the user's voice data using a microphone and estimates the emotion using a voice analysis algorithm. The cause identification unit also adjusts the display method of the cause identification result based on the user's emotion. For example, if the user is nervous, the cause identification unit can provide a simple, highly visible display method. On the other hand, if the user is relaxed, the cause identification unit can provide a display method that includes detailed information. This allows the display method of the cause identification result to be optimized for the user by adjusting the display method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the cause identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the cause identification unit may input user emotion data and display the cause identification results using an AI model that adjusts the display method.

[0083] When identifying the cause, the cause identification unit can refer to the user's system usage pattern to identify the cause. The user's system usage pattern includes, but is not limited to, for example, usage frequency and operation sequence. For example, the cause identification unit analyzes the user's system usage pattern to identify the most likely cause. For example, the cause identification unit identifies an error caused by a specific operation based on the user's system usage pattern. The cause identification unit can also refer to the user's operation history to identify the cause. For example, the cause identification unit identifies related errors based on the user's operation history. Furthermore, the cause identification unit can also identify causes that occur during specific time periods based on the user's system usage pattern. For example, the cause identification unit analyzes the user's system usage pattern to identify errors that occur during specific time periods. In this way, referring to the user's system usage pattern improves the accuracy of identification. Some or all of the above-described processing in the cause identification unit may be performed using, for example, AI, or may be performed without AI. For example, the cause identification unit can input the user's system usage pattern data and use an AI model that identifies causes to identify the cause.

[0084] The cause identification unit can identify the cause by referring to real-time system data. Examples of real-time system data include, but are not limited to, current CPU usage and memory usage. For example, the cause identification unit collects real-time system data and identifies the cause. For example, the cause identification unit analyzes the current system status based on the real-time system data and identifies the cause. The cause identification unit can also identify the cause by referring to real-time system performance data. For example, the cause identification unit identifies a specific performance problem based on the real-time system performance data. Furthermore, the cause identification unit can also identify the cause by referring to real-time network data. For example, the cause identification unit identifies a network-related problem based on the real-time network data. By referring to the real-time system data, the accuracy of the identification is improved. Some or all of the above-described processing in the cause identification unit may be performed using, for example, AI, or may be performed without AI. For example, the cause identification unit can input real-time system data and use an AI model that identifies the cause to identify the cause.

[0085] The guidance providing unit can estimate the user's emotions and adjust the way the guidance is presented based on the estimated user's emotions. The guidance providing unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the guidance providing unit acquires the user's facial expression data using a camera and estimates the emotion using an emotion estimation algorithm. The guidance providing unit can also estimate the user's emotions using voice analysis technology. For example, the guidance providing unit acquires the user's voice data using a microphone and estimates the emotion using a voice analysis algorithm. The guidance providing unit further adjusts the way the guidance is presented based on the user's emotions. For example, if the user is feeling stressed, the guidance providing unit can provide a concise and easy-to-understand guide. On the other hand, if the user is relaxed, the guidance providing unit can provide a guide including detailed explanations. This allows the guidance to be optimally presented for the user by adjusting the way the guidance is presented based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the guidance providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the guidance providing unit may provide guidance using an AI model that receives user emotion data as input and adjusts the way the guidance is presented.

[0086] When providing a guide, the guide providing unit can adjust the level of detail of the guide according to the user's skill level. Examples of user skill levels include, but are not limited to, beginner, intermediate, and advanced. For example, the guide providing unit can provide a guide including basic procedures to a beginner user. For example, the guide providing unit can provide a guide using simple procedures and illustrations to a beginner user. The guide providing unit can also provide a guide including detailed procedures and additional information to an intermediate user. For example, the guide providing unit can provide detailed procedures and troubleshooting tips to an intermediate user. Furthermore, the guide providing unit can provide a guide including specialized information to an advanced user. For example, the guide providing unit can provide detailed technical information and advanced setting procedures to an advanced user. This allows the level of detail of the guide to be adjusted according to the user's skill level, thereby providing an optimal guide for the user. Some or all of the above-described processing by the guide providing unit can be performed using, for example, AI, or without AI. For example, the guide providing unit can provide a guide using an AI model that inputs the user's skill level data and adjusts the level of detail of the guide.

[0087] When providing a guide, the guide providing unit can determine the priority of the guide according to the severity of the error. The severity of the error includes, but is not limited to, the impact on the entire system and the impact on the user. For example, in the case of a serious error, the guide providing unit provides the guide with the highest priority. For example, the guide providing unit quickly provides a guide for a serious error that affects the entire system. Furthermore, in the case of a moderate error, the guide providing unit can also provide a guide at an appropriate time. For example, the guide providing unit provides a guide for an error that is important to the user at an appropriate time. Furthermore, in the case of a minor error, the guide providing unit can provide the guide after providing guides for other errors. For example, the guide providing unit provides a guide for an error that has a small impact on the user after providing guides for other errors. Thus, by determining the priority of the guide according to the severity of the error, it is possible to quickly respond to an important error. Some or all of the above-described processing in the guide providing unit may be performed using, for example, AI, or may be performed without AI. For example, the guide providing unit can provide the guide using an AI model that inputs error severity data and determines the priority of the guide.

[0088] The guidance providing unit can estimate the user's emotions and adjust the length of the guidance based on the estimated user emotions. The guidance providing unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the guidance providing unit acquires the user's facial expression data using a camera and estimates the emotion using an emotion estimation algorithm. The guidance providing unit can also estimate the user's emotions using voice analysis technology. For example, the guidance providing unit acquires the user's voice data using a microphone and estimates the emotion using an emotion analysis algorithm. The guidance providing unit also adjusts the length of the guidance based on the user's emotions. For example, if the user is feeling stressed, the guidance providing unit can provide a short, concise guide. On the other hand, if the user is relaxed, the guidance providing unit can provide a longer guide with detailed explanations. This allows the guidance to be optimally tailored to the user by adjusting the length of the guidance according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the guidance providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the guidance providing unit may provide guidance using an AI model that inputs user emotion data and adjusts the length of the guidance.

[0089] When providing a guide, the guide providing unit can provide an optimal guide by referring to the user's past solution history. The user's past solution history includes, for example, past support tickets and resolved problems, but is not limited to these examples. The guide providing unit can provide an optimal guide, for example, based on solutions that the user has used successfully in the past. For example, the guide providing unit can provide an optimal guide for a similar problem based on the user's past solution history. The guide providing unit can also select the most effective guide from the user's past solution history. For example, the guide providing unit can analyze the user's past solution history and select the most effective guide. Furthermore, the guide providing unit can analyze the user's past solution history and provide an optimal guide. For example, the guide providing unit can provide an optimal guide based on the user's past solution history. In this way, the optimal guide can be provided by referring to the user's past solution history. Some or all of the above-described processing in the guide providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the guide providing unit can provide a guide using an AI model that inputs the user's past solution history data and provides an optimal guide.

[0090] When providing a guide, the guide providing unit can provide an optimal guide by taking into account the user's device information. The user's device information includes, for example, the device type and the OS version, but is not limited to these examples. The guide providing unit can provide an optimal guide, for example, depending on the type of device used by the user. For example, the guide providing unit provides a guide depending on the device used by the user. The guide providing unit can also provide an optimal guide by referring to the setting information of the user's device. For example, the guide providing unit provides an optimal guide based on the setting information of the user's device. Furthermore, the guide providing unit can also provide an optimal guide by taking into account the performance of the user's device. For example, the guide providing unit provides an optimal guide based on the performance of the user's device. In this way, the optimal guide can be provided by taking the user's device information into consideration. Some or all of the above-described processing in the guide providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the guide providing unit can provide a guide using an AI model that inputs the user's device information and provides an optimal guide.

[0091] The solution providing unit can estimate the user's emotions and adjust the way in which the solution is expressed based on the estimated user's emotions. The solution providing unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the solution providing unit acquires the user's facial expression data using a camera and estimates the emotion using an emotion estimation algorithm. The solution providing unit can also estimate the user's emotions using voice analysis technology. For example, the solution providing unit acquires the user's voice data using a microphone and estimates the emotion using an emotion analysis algorithm. The solution providing unit further adjusts the way in which the solution is expressed based on the user's emotions. For example, if the user is feeling stressed, the solution providing unit can provide a concise and easy-to-understand solution. On the other hand, if the user is relaxed, the solution providing unit can provide a solution with detailed explanations. This allows the solution to be optimally expressed based on the user's emotions by adjusting the way in which the solution is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the solution providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the solution providing unit may provide solutions using an AI model that receives user emotion data as input and adjusts the way the solutions are expressed.

[0092] When providing a solution, the solution providing unit can select the optimal solution by referring to the success rates of past solutions. The success rates of past solutions include, but are not limited to, methods for calculating the success rates and methods for storing the data. The solution providing unit selects the optimal solution based on solutions that have been successful in the past. For example, the solution providing unit selects the optimal solution for a similar problem based on the success rates of past solutions. The solution providing unit can also select a solution with a high success rate for a similar error. For example, the solution providing unit selects the optimal solution based on the success rates of past solutions. Furthermore, the solution providing unit can analyze the success rates of past solutions and select the optimal solution. For example, the solution providing unit analyzes the success rates of past solutions and selects the optimal solution. This allows the optimal solution to be selected by referring to the success rates of past solutions. Some or all of the above-described processing in the solution providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the solution providing unit can provide solutions using an AI model that inputs data on the success rate of past solutions and selects the optimal solution.

[0093] When providing a countermeasure, the solution providing unit can determine the priority of the countermeasures according to the frequency of error occurrence. The frequency of error occurrence includes, but is not limited to, the number of occurrences and the period of occurrence. For example, the solution providing unit provides a countermeasure with the highest priority for a frequently occurring error. For example, the solution providing unit quickly provides a countermeasure for a frequently occurring error. The solution providing unit can also provide a countermeasure at an appropriate time for an error with a medium frequency of occurrence. For example, the solution providing unit provides a countermeasure at an appropriate time for an error with a medium frequency of occurrence. Furthermore, the solution providing unit can also provide a countermeasure for an error that occurs infrequently after providing a countermeasure for another error. For example, the solution providing unit provides a countermeasure for an error that occurs infrequently after providing a countermeasure for another error. In this way, by determining the priority of the countermeasures according to the frequency of error occurrence, frequently occurring errors can be quickly addressed. Some or all of the above-described processing by the solution providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the solution providing unit can provide solutions using an AI model that inputs error occurrence frequency data and determines the priority order of solutions.

[0094] The solution providing unit can estimate the user's emotions and adjust the level of detail of the solution based on the estimated user's emotions. The solution providing unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the solution providing unit acquires the user's facial expression data using a camera and estimates the emotion using an emotion estimation algorithm. The solution providing unit can also estimate the user's emotions using voice analysis technology. For example, the solution providing unit acquires the user's voice data using a microphone and estimates the emotion using an emotion analysis algorithm. Furthermore, the solution providing unit adjusts the level of detail of the solution based on the user's emotions. For example, if the user is feeling stressed, the solution providing unit can provide a concise and to-the-point solution. On the other hand, if the user is relaxed, the solution providing unit can provide a solution that includes detailed explanations. In this way, by adjusting the level of detail of the solution according to the user's emotions, the optimal solution for the user can be provided. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the solution providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the solution providing unit may provide solutions using an AI model that inputs user emotion data and adjusts the level of detail of the solutions.

[0095] When providing a solution, the solution providing unit can provide an optimal solution by referring to the user's system configuration information. The user's system configuration information includes, but is not limited to, a configuration file and a user profile. The solution providing unit, for example, refers to the user's system configuration information and provides an optimal solution. For example, the solution providing unit provides an optimal solution based on the user's system configuration information. The solution providing unit can also provide a customized solution based on the user's system configuration. For example, the solution providing unit provides a customized solution based on the user's system configuration information. Furthermore, the solution providing unit can analyze the user's system configuration information and select an optimal solution. For example, the solution providing unit selects an optimal solution based on the user's system configuration information. In this way, the optimal solution can be provided by referring to the user's system configuration information. Some or all of the above-described processing in the solution providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the solution providing unit can provide a solution using an AI model that takes the user's system setting information as input and provides the optimal solution.

[0096] When providing a countermeasure, the solution providing unit can provide an optimal solution by taking into account the user's operating environment. The user's operating environment includes, but is not limited to, the device being used and the network environment. For example, the solution providing unit references the user's operating environment and provides the optimal solution. For example, the solution providing unit provides the optimal solution based on the user's operating environment. The solution providing unit can also provide a customized solution based on the user's operating environment. For example, the solution providing unit provides the customized solution based on the user's operating environment. Furthermore, the solution providing unit can analyze the user's operating environment and select the optimal solution. For example, the solution providing unit selects the optimal solution based on the user's operating environment. This allows the optimal solution to be provided by taking the user's operating environment into consideration. Some or all of the above-described processing in the solution providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the solution providing unit can input data about the user's operating environment and provide a countermeasure using an AI model that provides the optimal solution.

[0097] The feedback collection unit can estimate the user's emotions and adjust the feedback collection method based on the estimated user's emotions. The feedback collection unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the feedback collection unit acquires the user's facial expression data using a camera and estimates the emotions using an emotion estimation algorithm. The feedback collection unit can also estimate the user's emotions using voice analysis technology. For example, the feedback collection unit acquires the user's voice data using a microphone and estimates the emotions using an emotion analysis algorithm. The feedback collection unit further adjusts the feedback collection method based on the user's emotions. For example, if the user is stressed, the feedback collection unit can provide a brief feedback form. On the other hand, if the user is relaxed, the feedback collection unit can provide a form requesting detailed feedback. This allows the feedback collection method to be adjusted according to the user's emotions, thereby enabling optimal feedback collection for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback collection unit may collect feedback using an AI model that receives user emotion data as input and adjusts the method of feedback collection.

[0098] When collecting feedback, the feedback collection unit can improve the collection accuracy by referring to the user's past feedback history. The user's past feedback history includes, for example, past survey results and feedback content, but is not limited to these examples. For example, the feedback collection unit selects an optimal feedback collection method by referring to the user's past feedback history. For example, the feedback collection unit selects an optimal feedback collection method based on the user's past feedback history. The feedback collection unit can also request detailed feedback from the user's past feedback history. For example, the feedback collection unit requests detailed feedback based on the user's past feedback history. Furthermore, the feedback collection unit can analyze the user's past feedback history to improve the collection accuracy. For example, the feedback collection unit improves a method for improving the collection accuracy based on the user's past feedback history. As a result, the collection accuracy is improved by referring to the user's past feedback history. Some or all of the above-described processing in the feedback collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback collection unit can collect feedback using an AI model that uses the user's past feedback history data as input and improves the collection accuracy.

[0099] The feedback collection unit can estimate the user's emotions and adjust the timing of feedback collection based on the estimated user's emotions. The feedback collection unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the feedback collection unit acquires the user's facial expression data using a camera and estimates the emotions using an emotion estimation algorithm. The feedback collection unit can also estimate the user's emotions using voice analysis technology. For example, the feedback collection unit acquires the user's voice data using a microphone and estimates the emotions using an emotion analysis algorithm. The feedback collection unit further adjusts the timing of feedback collection based on the user's emotions. For example, the feedback collection unit can request feedback when the user is relaxed. Alternatively, the feedback collection unit can request feedback when the user is not feeling stressed. In this way, by adjusting the timing of feedback collection according to the user's emotions, feedback can be collected at the optimal timing for the user. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback collection unit may collect feedback using an AI model that receives user emotion data as input and adjusts the timing of feedback collection.

[0100] When collecting feedback, the feedback collection unit can select an optimal collection method by referring to the user's system usage status. The user's system usage status includes, but is not limited to, for example, frequency of use and operation sequence. The feedback collection unit, for example, refers to the user's system usage status to select an optimal feedback collection method. For example, the feedback collection unit selects an optimal feedback collection method based on the user's system usage status. The feedback collection unit can also provide a customized feedback collection method based on the user's system usage status. For example, the feedback collection unit provides a customized feedback collection method based on the user's system usage status. Furthermore, the feedback collection unit can analyze the user's system usage status and select an optimal feedback collection method. For example, the feedback collection unit selects an optimal feedback collection method based on the user's system usage status. In this way, the optimal feedback collection method can be selected by referring to the user's system usage status. Some or all of the above-described processing in the feedback collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback collection unit can collect feedback using an AI model that takes user system usage data as input and selects the optimal feedback collection method.

[0101] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. The learning unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the learning unit acquires the user's facial expression data using a camera and estimates the emotions using an emotion estimation algorithm. The learning unit can also estimate the user's emotions using voice analysis technology. For example, the learning unit acquires the user's voice data using a microphone and estimates the emotions using a voice analysis algorithm. The learning unit further selects training data based on the user's emotions. For example, if the user is stressed, the learning unit can select concise feedback as training data. On the other hand, if the user is relaxed, the learning unit can select detailed feedback as training data. This improves the accuracy of learning by selecting training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit may perform learning using an AI model that receives user emotion data as input and selects learning data.

[0102] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. Past learning data includes, for example, the structure of a database and the type of data stored, but is not limited to these examples. For example, the learning unit selects an optimal learning algorithm by referring to past learning data. For example, the learning unit selects an optimal learning algorithm based on the past learning data. The learning unit can also analyze the past learning data and optimize the learning algorithm. For example, the learning unit optimizes the learning algorithm based on the past learning data. Furthermore, the learning unit can adjust parameters of the learning algorithm based on the past learning data. For example, the learning unit adjusts parameters of the learning algorithm based on the past learning data. As a result, the accuracy of the learning algorithm is improved by referring to the past learning data. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can perform learning using an AI model that uses past learning data as input and optimizes the learning algorithm.

[0103] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. The learning unit, for example, uses facial expression recognition technology to estimate the user's emotions. For example, the learning unit acquires the user's facial expression data using a camera and estimates the emotions using an emotion estimation algorithm. The learning unit can also estimate the user's emotions using voice analysis technology. For example, the learning unit acquires the user's voice data using a microphone and estimates the emotions using a voice analysis algorithm. The learning unit also adjusts the frequency of learning based on the user's emotions. For example, if the user is stressed, the learning unit can set the frequency of learning low. On the other hand, if the user is relaxed, the learning unit can set the frequency of learning high. This improves learning efficiency by adjusting the frequency of learning according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit may perform learning using an AI model that uses user emotion data as input and adjusts the frequency of learning.

[0104] During learning, the learning unit can weight the learning data based on the time of feedback submission. The time of feedback submission includes, but is not limited to, for example, the submission date and time and the frequency of submission. For example, the learning unit sets a high weight for the learning data if the feedback submission time is recent. For example, the learning unit sets a high weight for the learning data based on recently submitted feedback. Furthermore, the learning unit can also set a low weight for the learning data if the feedback submission time is old. For example, the learning unit sets a low weight for the learning data based on old feedback. Furthermore, the learning unit can also appropriately adjust the weight for the learning data based on the time of feedback submission. For example, the learning unit appropriately adjusts the weight for the learning data based on the time of feedback submission. Thus, weighting the learning data based on the time of feedback submission improves the accuracy of learning. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit can perform learning using an AI model that uses feedback submission time data as input and weights the learning data. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned analysis unit, cause identification unit, guide provision unit, solution provision unit, feedback collection unit, and learning unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit acquires the user's facial expressions and voice using the camera 42 and microphone 38B of the smart device 14, and estimates the user's emotions using the control unit 46A. The cause identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies the cause of the problem based on the analysis results of the error code. The guide provision unit and solution provision unit are realized, for example, by the control unit 46A of the smart device 14, and provide the user with easy-to-understand guides and specific solutions. The feedback collection unit and learning unit are realized, for example, by the identification processing unit 290 of the data processing device 12, and collect feedback from the user and perform learning to improve the accuracy of the system. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned analysis unit, cause identification unit, guide provision unit, solution provision unit, feedback collection unit, and learning unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit acquires the user's facial expressions and voice using the camera 42 and microphone 238 of the smart glasses 214, and estimates the user's emotions using the control unit 46A. The cause identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies the cause of the problem based on the analysis result of the error code. The guide provision unit and solution provision unit are realized, for example, by the control unit 46A of the smart glasses 214, and provide the user with easy-to-understand guides and specific solutions. The feedback collection unit and learning unit are realized, for example, by the identification processing unit 290 of the data processing device 12, and collect feedback from the user and perform learning to improve the accuracy of the system. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned analysis unit, cause identification unit, guide provision unit, solution provision unit, feedback collection unit, and learning unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the analysis unit acquires the user's facial expressions and voice using the camera 42 and microphone 238 of the headset-type terminal 314, and estimates the user's emotions using the control unit 46A. The cause identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies the cause of the problem based on the analysis results of the error code. The guide provision unit and solution provision unit are realized, for example, by the control unit 46A of the headset-type terminal 314, and provide the user with easy-to-understand guides and specific solutions. The feedback collection unit and learning unit are realized, for example, by the identification processing unit 290 of the data processing device 12, and collect feedback from the user and perform learning to improve the accuracy of the system. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned analysis unit, cause identification unit, guide provision unit, solution provision unit, feedback collection unit, and learning unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit acquires the user's facial expressions and voice using the camera 42 and microphone 238 of the robot 414, and estimates the user's emotions using the control unit 46A. The cause identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12, and identifies the cause of the problem based on the analysis results of the error code. The guide provision unit and solution provision unit are realized, for example, by the control unit 46A of the robot 414, and provide the user with easy-to-understand guides and specific solutions. The feedback collection unit and learning unit are realized, for example, by the identification processing unit 290 of the data processing device 12, and collect feedback from the user and perform learning to improve the accuracy of the system.

[0105] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0106] When analyzing error codes, the analysis unit can take the user's operating environment into consideration. For example, the analysis unit can select the optimal analysis method by referring to the type of device and network environment used by the user. For example, when using a mobile device, the analysis unit can use a lightweight analysis algorithm to provide results quickly. In addition, when the network environment is unstable, the analysis unit can perform offline analysis and synchronize the results later. This allows for flexible analysis that suits the user's operating environment.

[0107] Based on the analysis results of the error code, the cause identification unit can refer to the user's past operation history and identify the most relevant cause. For example, the cause identification unit can analyze the operation sequence performed by the user in the past and identify the cause when a similar error occurs. The cause identification unit can also extract specific patterns from the user's operation history and identify the root cause of the error. Furthermore, the cause identification unit can analyze the frequency of error occurrence based on the user's operation history and identify the most likely cause. This makes it possible to identify the cause with greater accuracy by utilizing the user's operation history.

[0108] The guide providing unit can customize the content of the guide according to the user's skill level. For example, it can provide a guide including basic procedures for beginner users and detailed procedures and additional information for intermediate users. It can also provide a guide including specialized information for advanced users. Furthermore, the guide providing unit can automatically estimate the user's skill level and provide the most appropriate guide. This provides an appropriate guide according to the user's skill level, deepening the user's understanding.

[0109] The solution provider can prioritize solutions according to the severity of the error. For example, solutions are provided with the highest priority for serious errors that affect the entire system, allowing for rapid resolution. Solutions can also be provided at an appropriate time for errors that are important to the user. Furthermore, solutions can be provided for minor errors after solutions for other errors have been provided. This allows for the provision of appropriate solutions according to the severity of the error, improving the stability of the system.

[0110] The feedback collection unit can estimate the user's emotions and adjust the feedback collection method based on the estimated user's emotions. For example, if the user is feeling stressed, the feedback collection unit can provide a brief feedback form to reduce the user's burden. Alternatively, if the user is relaxed, the feedback collection unit can provide a form requesting detailed feedback. Furthermore, the feedback collection unit can adjust the timing of feedback collection according to the user's emotions. This enables optimal feedback collection according to the user's emotions, improving collection accuracy.

[0111] When performing learning based on collected feedback, the learning unit can weight the learning data based on the time of submission of the feedback. For example, the weight of learning data can be set high based on recently submitted feedback, and the weight of learning data can be set low based on older feedback. The weight of learning data can also be appropriately adjusted based on the frequency of feedback submission. This allows learning to emphasize the most recent information, improving the accuracy of the system.

[0112] When analyzing error codes, the analysis unit can perform analysis based on the system's operating status and load status. For example, it checks the current system load status and distributes the analysis if the load is high. It can also refer to the system's operating status and perform analysis without affecting running processes. It can also select the optimal timing for analysis based on the system's past operating data. This enables efficient analysis that takes into account the system's operating status and load status.

[0113] The cause identification unit can estimate the user's emotions and adjust the cause identification method based on the estimated user emotions. For example, if the user is feeling stressed, the cause identification unit can quickly identify the cause and provide a concise explanation. On the other hand, if the user is relaxed, the cause identification unit can provide an explanation using a detailed cause identification method. This enables optimal cause identification according to the user's emotions, deepening the user's understanding.

[0114] The guidance providing unit can estimate the user's emotions and adjust the way the guidance is presented based on the estimated user's emotions. For example, if the user is feeling stressed, the guidance providing unit can provide a simple and easy-to-understand guide. On the other hand, if the user is relaxed, the guidance providing unit can provide a guide that includes detailed explanations. This provides the optimal guide according to the user's emotions, deepening the user's understanding.

[0115] The solution providing unit can estimate the user's emotions and adjust the way in which the solution is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the solution providing unit can provide a simple and easy-to-understand solution. On the other hand, if the user is relaxed, the solution providing unit can provide a solution that includes detailed explanations. This provides the optimal solution according to the user's emotions, deepening the user's understanding.

[0116] The processing flow of the second embodiment will be briefly explained below.

[0117] Step 1: The analysis unit analyzes the error code. The analysis unit performs syntactic and semantic analysis of the error code to identify the type and cause of the error. Step 2: The cause identification unit identifies the cause of the problem based on the error code analyzed by the analysis unit. The cause identification unit identifies the cause using root cause analysis and pattern matching, and identifies the root cause by referring to a database of past similar errors. Step 3: The guide provider provides an easy-to-understand guide based on the cause identified by the cause identifyr. The guide provider provides step-by-step instructions and visual guides to show the user specific steps to resolve the error. Step 4: The solution providing unit provides specific solutions based on the guide provided by the guide providing unit. The solution providing unit provides specific solutions such as reinstalling software or changing settings, and can also provide a patch to fix the cause of the error. Step 5: The feedback collection unit collects feedback from users. The feedback collection unit collects user surveys and log data, and gathers feedback on the occurrence of errors and the effectiveness of countermeasures. Step 6: The learning unit performs learning based on the feedback collected by the feedback collection unit. Using machine learning algorithms and data mining techniques, the learning unit learns the causes of errors and the effectiveness of countermeasures, thereby improving the accuracy of the system.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0120] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0121] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0122] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0123] 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.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] 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.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0136] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0139] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0145] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0146] 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.

[0147] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0148] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0149] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0152] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0155] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0156] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0157] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0158] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0159] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0160] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0161] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0162] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0163] 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.

[0164] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0165] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0166] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0167] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0168] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0169] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0170] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0171] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0172] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0173] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0174] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0175] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0176] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0177] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0178] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0179] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0180] 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.

[0181] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0182] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0183] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0184] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0185] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0186] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0187] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0188] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0189] [Explanation of symbols]

[0190] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes the error code; a cause identification unit that identifies the cause of the problem based on the error code analyzed by the analysis unit; a guidance providing unit that provides a clear guidance based on the cause identified by the cause identifying unit; a solution providing unit that provides detailed solutions based on the guide provided by the guide providing unit; a feedback collection unit for collecting user feedback; a learning unit that performs learning based on the feedback collected by the feedback collection unit. A system characterized by:

2. The analysis unit Parsing a specific error code 2. The system of claim 1.

3. The cause identification unit Identify the cause of the problem based on the parsed error code 2. The system of claim 1.

4. The guide providing unit Provides easy-to-follow guidance based on identified causes 2. The system of claim 1.

5. The solution providing unit Provide specific solutions based on the provided guide 2. The system of claim 1.

6. The feedback collection unit: Gather user feedback 2. The system of claim 1.

7. The learning unit Learn from the feedback collected 2. The system of claim 1.

8. The analysis unit Infer user emotions and adjust how error codes are analyzed based on the inferred user emotions.

2. The system of claim 1.

Images