system

Abstract

An object of a system according to an embodiment is to automatically correct an error caused by RPA.SOLUTION: A system includes a collection unit, an analysis unit, and a generation unit. The collection unit collects error information. The analysis unit analyzes the error information collected by the collection unit. The generation unit generates a corrected code based on the analysis result obtained by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, errors generated by RPA had to be corrected manually, which was a problem that made it inefficient.

[0005] The system according to the embodiment aims to automatically correct errors made by RPA. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, and a generation unit. The collection unit collects error information. The analysis unit analyzes the error information collected by the collection unit. The generation unit generates a correction code based on the analysis result obtained by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can automatically correct errors made by the RPA. [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) An error correction system according to an embodiment of the present invention automatically analyzes errors made by an RPA and generates correction codes. The error correction system collects error information, analyzes it using AI, and immediately generates correction codes for known errors. It also learns a correction process for unknown errors, aiming to automatically correct those error codes in the future. For example, the error correction system collects error information when an RPA makes an error. Then, AI analyzes the collected error information and immediately generates correction codes for known errors. For example, if a specific input format is incorrect, the AI ​​generates code to correct it to the correct format. For unknown errors, the AI ​​learns a correction process and can automatically generate correction codes the next time the same error occurs. This improves the efficiency of RPA error response and improves system stability. The error correction system automatically corrects errors made by an RPA and improves system stability. For example, the error correction system quickly and accurately collects error information, analyzes it using AI, and immediately generates correction codes for known errors. It also learns a correction process for unknown errors and can automatically generate correction codes in the future. This will enable the error correction system to respond more efficiently to RPA errors and improve system stability.

[0029] An error correction system according to an embodiment includes a collection unit, an analysis unit, and a generation unit. The collection unit collects error information generated by the RPA. Examples of the error information include, but are not limited to, log files, system error messages, and user reports. The collection unit collects the error information from, for example, log files. The collection unit can also collect system error messages in real time. The collection unit can also analyze user reports to collect the error information. For example, the collection unit analyzes log files and extracts the error information. System error messages are collected in real time and analyzed immediately. User reports are analyzed using natural language processing technology to extract the error information. The analysis unit uses AI to analyze the error information collected by the collection unit. The analysis can be performed using, for example, error cause analysis, pattern recognition, statistical analysis, or other methods, but is not limited to these examples. For example, the analysis unit identifies the cause of the error and proposes a correction method. The analysis unit can also recognize error patterns and propose correction methods for similar errors. The analysis unit can also use statistical analysis to evaluate the frequency and impact of errors. For example, the analysis unit analyzes the error log to identify the cause of the error. Error pattern recognition is performed using a machine learning algorithm. Statistical analysis is used to evaluate the frequency and impact of the error. The generation unit uses AI to generate correction code based on the analysis results obtained by the analysis unit. The correction code may be generated by, for example, automatic code generation, template-based correction, or other methods, but is not limited to these examples. For example, the generation unit generates code to correct a specific input format to a correct format when the input format is incorrect. The generation unit can also perform template-based correction to quickly generate correction code for known errors. The generation unit can also use a machine learning algorithm to learn the correction process for unknown errors and automatically generate correction code the next time the same error occurs. For example, the generation unit generates code to correct a specific input format to a correct format when the input format is incorrect.Template-based correction is used to quickly generate correction code for known errors, while machine learning algorithms are used to learn the correction process for unknown errors and automatically generate correction code the next time the same error occurs. This allows the error correction system according to the embodiment to efficiently collect, analyze, and generate correction code for error information.

[0030] The generation unit includes an instant correction unit that instantly generates correction code for known errors. The instant correction unit quickly generates correction code for known errors. For example, if a specific input format is incorrect, the instant correction unit generates code that corrects the input to a correct format. The instant correction unit can also perform template-based correction to quickly generate correction code for known errors. The instant correction unit can also recognize error patterns and suggest correction methods for similar errors. For example, if a specific input format is incorrect, the instant correction unit generates code that corrects the input to a correct format. Template-based correction is used to quickly generate correction code for known errors. Error pattern recognition is performed using a machine learning algorithm. This makes it possible to quickly generate correction code for known errors.

[0031] The generation unit includes a learning unit that learns a correction process for unknown errors. The learning unit learns the correction process for unknown errors. For example, when a new error occurs, the learning unit analyzes the cause of the error and learns a correction method. The learning unit can also learn the correction process using a machine learning algorithm and automatically generate correction code the next time the same error occurs. The learning unit can also recognize error patterns and suggest correction methods for similar errors. For example, when a new error occurs, the learning unit analyzes the cause of the error and learns a correction method. The machine learning algorithm is used to learn a correction process for unknown errors and automatically generate correction code the next time the same error occurs. Error pattern recognition is performed using a machine learning algorithm. This makes it possible to automatically correct unknown errors in the future.

[0032] The collection unit can collect error information from log files. Examples of log files include, but are not limited to, text files, system logs, and application logs. The collection unit collects error information from log files, for example. For example, the collection unit analyzes log files in text file format to extract error information. The collection unit can also collect system logs in real time and analyze them immediately. The collection unit can also analyze application logs to collect error information. For example, the collection unit analyzes log files in text file format to extract error information. System logs are collected in real time and analyzed immediately. Application logs are analyzed to collect error information related to a specific application. This allows error information to be collected efficiently from log files.

[0033] The learning unit can learn the correction process using a machine learning algorithm. Examples of machine learning algorithms include, but are not limited to, neural networks and support vector machines. The learning unit learns the correction process using, for example, a neural network. For example, the learning unit recognizes error patterns using a neural network and learns a correction method. The learning unit can also learn the correction process using a support vector machine. The learning unit can also analyze the cause of an error and learn a correction method using a machine learning algorithm. For example, the learning unit recognizes error patterns using a neural network and learns a correction method. A support vector machine is used to analyze the cause of an error and learn a correction method. The machine learning algorithm is used to learn the correction process based on error pattern recognition and cause analysis. As a result, using the machine learning algorithm improves the learning accuracy of the correction process.

[0034] The collection unit can determine the collection priority based on the frequency of error occurrence. For example, the collection unit prioritizes collecting information about errors that occur frequently in order to respond quickly. For example, the collection unit measures the frequency of error occurrence and prioritizes collecting information about errors that occur frequently. The collection unit can also postpone error information that occurs less frequently and prioritize error information that is more important. The collection unit can also adjust the timing of collection based on the frequency of error occurrence to efficiently collect information. For example, the collection unit determines the collection priority based on the frequency of error occurrence. The frequency of error occurrence is measured by the number of errors per hour or the number of errors that occur within a specific period. This makes it possible to efficiently collect error information based on the frequency of error occurrence.

[0035] The collection unit can apply different collection methods depending on the type of error. For example, for an input format error, the collection unit collects detailed log information. For example, when an input format error occurs, the collection unit collects detailed log information and identifies the cause of the error. The collection unit can also collect connection status and communication logs for network errors. The collection unit can also collect memory dumps and system logs for system crashes. For example, when a network error occurs, the collection unit collects connection status and communication logs and identifies the cause of the error. When a system crash occurs, the collection unit collects memory dumps and system logs and identifies the cause of the error. This makes it possible to apply an appropriate collection method depending on the type of error.

[0036] The collection unit can adjust the level of detail of the collection based on the impact of the error. For example, the collection unit collects detailed information for serious errors to enable a prompt response. For example, when a serious error occurs, the collection unit collects detailed information to identify the cause of the error. The collection unit can also collect simplified information for minor errors to enable an efficient response. The collection unit can also adjust the scope and level of detail of the information to be collected based on the impact of the error. For example, the collection unit evaluates the impact of the error and collects detailed information for serious errors and simplified information for minor errors. The impact of an error is evaluated based on the impact on the entire system, the impact on users, the impact on business, etc. This makes it possible to adjust the level of detail of the collection according to the impact of the error.

[0037] The collection unit can adjust the timing of collection taking into account the operating status of the system. For example, the collection unit delays the collection of error information when the system is in a high-load state. For example, the collection unit monitors the CPU usage and memory usage of the system, and delays the collection of error information when the system is in a high-load state. The collection unit can also collect error information immediately when the system is in a low-load state. The collection unit can also dynamically adjust the timing of collection according to the operating status of the system. For example, the collection unit monitors the network traffic of the system, and collects error information immediately when the system is in a low-load state. The operating status of the system is evaluated based on the CPU usage, memory usage, network traffic, etc. This makes it possible to adjust the timing of collection according to the operating status of the system.

[0038] The collection unit can customize the collection method based on the location of the error. For example, for an error that occurs in a specific module, the collection unit collects detailed information related to the module. For example, if an error occurs in a specific module, the collection unit collects detailed information related to the module and identifies the cause of the error. Furthermore, for an error that occurs in a specific function, the collection unit can also collect log information related to the function. Furthermore, the collection unit can customize the range and level of detail of the information to be collected based on the location of the error. For example, for an error that occurs in a specific module, the collection unit collects detailed information related to the module. For an error that occurs in a specific function, the collection unit collects log information related to the function. The location of the error is identified as a specific module, server, user terminal, etc. This makes it possible to apply an appropriate collection method depending on the location of the error.

[0039] The collection unit can preferentially collect relevant error information by referring to the user's operation history. The collection unit, for example, preferentially collects error information related to the operation performed most recently by the user. For example, the collection unit analyzes the user's click log and operation log, and preferentially collects error information related to the operation performed most recently. The collection unit can also preferentially collect frequently occurring error information from the user's operation history. The collection unit can also analyze the user's operation history and preferentially collect highly relevant error information. For example, the collection unit analyzes the user's click log and operation log, and preferentially collects error information related to the operation performed most recently. Frequently occurring error information is identified from the user's operation history and collected preferentially. The user's operation history is collected using click logs, operation logs, session data, etc. This makes it possible to preferentially collect relevant error information based on the user's operation history.

[0040] The analysis unit can determine the priority of analysis based on the frequency of error occurrence. For example, the analysis unit prioritizes analysis of frequently occurring error information to enable prompt response. For example, the analysis unit measures the frequency of error occurrence and prioritizes analysis of frequently occurring error information. The analysis unit can also postpone error information that occurs less frequently and prioritize error information that is more important. The analysis unit can also adjust the timing of analysis based on the frequency of error occurrence to perform efficient information analysis. For example, the analysis unit determines the priority of analysis based on the frequency of error occurrence. The frequency of error occurrence is measured by the number of errors per hour or the number of errors occurring within a specific period. This allows error information to be analyzed efficiently based on the frequency of error occurrence.

[0041] The analysis unit can apply different analysis algorithms depending on the type of error. For example, the analysis unit applies a format check algorithm to an input format error. For example, when an input format error occurs, the analysis unit applies a format check algorithm to identify the cause of the error. The analysis unit can also apply an algorithm that analyzes connection status and communication logs to identify a network error. The analysis unit can also apply an algorithm that analyzes memory dumps and system logs to identify a system crash. For example, when a network error occurs, the analysis unit analyzes connection status and communication logs to identify the cause of the error. When a system crash occurs, the analysis unit analyzes memory dumps and system logs to identify the cause of the error. This makes it possible to apply an appropriate analysis algorithm depending on the type of error.

[0042] The analysis unit can adjust the level of detail of the analysis based on the impact of the error. For example, the analysis unit performs a detailed analysis of a serious error to ensure a prompt response. For example, when a serious error occurs, the analysis unit performs a detailed analysis to identify the cause of the error. The analysis unit can also perform a simplified analysis of a minor error to ensure an efficient response. The analysis unit can also adjust the scope and level of detail of the analysis based on the impact of the error. For example, the analysis unit evaluates the impact of the error and performs a detailed analysis of a serious error and a simplified analysis of a minor error. The impact of an error is evaluated based on the impact on the entire system, the impact on users, the impact on business, etc. This makes it possible to adjust the level of detail of the analysis according to the impact of the error.

[0043] The analysis unit can adjust the timing of the analysis taking into account the operating status of the system. For example, the analysis unit delays the analysis when the system is in a high load state. For example, the analysis unit monitors the CPU usage and memory usage of the system, and delays the analysis when the system is in a high load state. The analysis unit can also perform analysis immediately when the system is in a low load state. The analysis unit can also dynamically adjust the timing of the analysis according to the operating status of the system. For example, the analysis unit monitors the network traffic of the system, and performs analysis immediately when the system is in a low load state. The operating status of the system is evaluated based on the CPU usage, memory usage, network traffic, etc. This makes it possible to adjust the timing of the analysis according to the operating status of the system.

[0044] The analysis unit can customize the analysis method based on the location of the error. For example, for an error that occurs in a specific module, the analysis unit performs a detailed analysis related to that module. For example, if an error occurs in a specific module, the analysis unit performs a detailed analysis related to that module to identify the cause of the error. Furthermore, for an error that occurs in a specific function, the analysis unit can analyze log information related to that function. Furthermore, the analysis unit can customize the analysis method based on the location of the error. For example, for an error that occurs in a specific module, the analysis unit performs a detailed analysis related to that module. For an error that occurs in a specific function, the analysis unit analyzes log information related to that function. The location of the error is identified as a specific module, server, user terminal, etc. This makes it possible to apply an appropriate analysis method depending on the location of the error.

[0045] The analysis unit can prioritize analyzing related error information by referring to the user's operation history. The analysis unit, for example, prioritizes analyzing error information related to the operation performed most recently by the user. For example, the analysis unit analyzes the user's click log and operation log, and prioritizes analyzing error information related to the operation performed most recently. The analysis unit can also prioritize analyzing frequently occurring error information from the user's operation history. The analysis unit can also analyze the user's operation history and prioritize analyzing highly relevant error information. For example, the analysis unit analyzes the user's click log and operation log, and prioritizes analyzing error information related to the operation performed most recently. Frequently occurring error information is identified from the user's operation history and analyzed preferentially. The user's operation history is collected using click logs, operation logs, session data, etc. This makes it possible to prioritize analyzing related error information based on the user's operation history.

[0046] The generation unit can apply different generation algorithms depending on the type of error. For example, for an input format error, the generation unit applies a format check algorithm to generate a correction code. For example, when an input format error occurs, the generation unit applies a format check algorithm to generate a correction code. Furthermore, for a network error, the generation unit can analyze the connection status and communication log to generate a correction code. Furthermore, for a system crash, the generation unit can analyze a memory dump and system log to generate a correction code. For example, when a network error occurs, the generation unit analyzes the connection status and communication log to generate a correction code. When a system crash occurs, the generation unit analyzes the memory dump and system log to generate a correction code. This makes it possible to apply an appropriate generation algorithm depending on the type of error.

[0047] The generation unit can adjust the level of detail of the generation based on the impact of the error. For example, the generation unit generates detailed correction code for a serious error. For example, when a serious error occurs, the generation unit generates detailed correction code and identifies the cause of the error. The generation unit can also generate simplified correction code for a minor error. The generation unit can also adjust the scope and level of detail of the correction code to be generated based on the impact of the error. For example, the generation unit evaluates the impact of the error and generates detailed correction code for a serious error and generates simplified correction code for a minor error. The impact of the error is evaluated based on the impact on the entire system, the impact on users, the impact on business, etc. This makes it possible to adjust the level of detail of the generation according to the impact of the error.

[0048] The generation unit can adjust the timing of generation taking into account the operating status of the system. For example, the generation unit delays the generation of the correction code when the system is in a high-load state. For example, the generation unit monitors the CPU usage and memory usage of the system, and delays the generation of the correction code when the system is in a high-load state. The generation unit can also generate the correction code immediately when the system is in a low-load state. The generation unit can also dynamically adjust the timing of generation of the correction code according to the operating status of the system. For example, the generation unit monitors the network traffic of the system, and generates the correction code immediately when the system is in a low-load state. The operating status of the system is evaluated based on the CPU usage, memory usage, network traffic, etc. This makes it possible to adjust the timing of generation according to the operating status of the system.

[0049] The generation unit can customize the generation method based on the location of the error. For example, for an error that occurs in a specific module, the generation unit generates a correction code related to the module. For example, for an error that occurs in a specific module, the generation unit generates a correction code related to the module. Furthermore, for an error that occurs in a specific function, the generation unit can generate a correction code related to the function. Furthermore, the generation unit can customize the generation method of the correction code based on the location of the error. For example, for an error that occurs in a specific module, the generation unit generates a correction code related to the module. For an error that occurs in a specific function, the generation unit generates a correction code related to the function. The location of the error is identified as a specific module, a server, a user terminal, etc. This makes it possible to apply an appropriate generation method depending on the location of the error.

[0050] The generation unit can refer to the user's operation history and prioritize correcting related error information. The generation unit, for example, prioritizes correcting error information related to the operation performed most recently by the user. For example, the generation unit analyzes the user's click log and operation log, and prioritizes correcting error information related to the operation performed most recently. The generation unit can also prioritize correcting frequently occurring error information from the user's operation history. The generation unit can also analyze the user's operation history and prioritize correcting highly relevant error information. For example, the generation unit analyzes the user's click log and operation log, and prioritizes correcting error information related to the operation performed most recently. Frequently occurring error information is identified from the user's operation history and prioritizes correcting it. The user's operation history is collected using click logs, operation logs, session data, etc. This makes it possible to prioritize correcting related error information based on the user's operation history.

[0051] The immediate correction unit can determine the priority of correction based on the frequency of error occurrence. For example, the immediate correction unit prioritizes correction of errors that occur frequently. For example, the immediate correction unit measures the frequency of error occurrence and prioritizes correction of frequently occurring errors. The immediate correction unit can also postpone errors that occur less frequently and prioritize errors that are more important. The immediate correction unit can also adjust the timing of correction based on the frequency of error occurrence. For example, the immediate correction unit determines the priority of correction based on the frequency of error occurrence. The frequency of error occurrence is measured by the number of errors per hour or the number of errors occurring within a specific period. This allows efficient correction based on the frequency of error occurrence.

[0052] The real-time correction unit can apply different correction algorithms depending on the type of error. For example, for input format errors, the real-time correction unit applies a format check algorithm to make corrections. For example, when an input format error occurs, the real-time correction unit applies a format check algorithm to make corrections. Furthermore, for network errors, the real-time correction unit can analyze connection status and communication logs to make corrections. Furthermore, for system crashes, the real-time correction unit can analyze memory dumps and system logs to make corrections. For example, when a network error occurs, the real-time correction unit analyzes connection status and communication logs to make corrections. When a system crash occurs, the real-time correction unit analyzes memory dumps and system logs to make corrections. This makes it possible to apply an appropriate correction algorithm depending on the type of error.

[0053] The immediate correction unit can adjust the level of detail of the correction based on the impact of the error. For example, the immediate correction unit performs detailed correction for serious errors. For example, when a serious error occurs, the immediate correction unit performs detailed correction and identifies the cause of the error. The immediate correction unit can also perform simplified correction for minor errors. The immediate correction unit can also adjust the scope and level of detail of the correction based on the impact of the error. For example, the immediate correction unit evaluates the impact of the error and performs detailed correction for serious errors and simplified correction for minor errors. The impact of an error is evaluated based on the impact on the entire system, the impact on users, the impact on business, etc. This makes it possible to adjust the level of detail of the correction according to the impact of the error.

[0054] The immediate correction unit can adjust the timing of correction taking into account the operating status of the system. For example, the immediate correction unit delays correction when the system is in a high-load state. For example, the immediate correction unit monitors the system's CPU usage and memory usage, and delays correction when the system is in a high-load state. The immediate correction unit can also perform correction immediately when the system is in a low-load state. The immediate correction unit can also dynamically adjust the timing of correction according to the operating status of the system. For example, the immediate correction unit monitors the system's network traffic, and performs correction immediately when the system is in a low-load state. The operating status of the system is evaluated based on CPU usage, memory usage, network traffic, etc. This makes it possible to adjust the timing of correction according to the operating status of the system.

[0055] The real-time correction unit can customize a correction method based on the location of the error. For example, for an error that occurs in a specific module, the real-time correction unit applies a correction method related to that module. For example, for an error that occurs in a specific module, the real-time correction unit applies a correction method related to that module. Furthermore, for an error that occurs in a specific function, the real-time correction unit can apply a correction method related to that function. Furthermore, the real-time correction unit can customize a correction method based on the location of the error. For example, for an error that occurs in a specific module, the real-time correction unit applies a correction method related to that module. For an error that occurs in a specific function, the real-time correction unit applies a correction method related to that function. The location of the error is identified as a specific module, server, user terminal, etc. This makes it possible to apply an appropriate correction method depending on the location of the error.

[0056] The immediate correction unit can refer to the user's operation history and prioritize correcting related error information. The immediate correction unit, for example, prioritizes correcting error information related to the operation performed most recently by the user. For example, the immediate correction unit analyzes the user's click log and operation log, and prioritizes correcting error information related to the operation performed most recently. The immediate correction unit can also prioritize correcting frequently occurring error information from the user's operation history. The immediate correction unit can also analyze the user's operation history and prioritize correcting highly relevant error information. For example, the immediate correction unit analyzes the user's click log and operation log, and prioritizes correcting error information related to the operation performed most recently. Frequently occurring error information is identified from the user's operation history and prioritized for correction. The user's operation history is collected using click logs, operation logs, session data, etc. This makes it possible to prioritize correcting related error information based on the user's operation history.

[0057] The learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on the past learning data. For example, the learning unit analyzes the past learning data, extracts effective learning patterns, and optimizes the algorithm. The learning unit can also adjust parameters of the learning algorithm by referring to the past learning data. The learning unit can also select and optimize a learning algorithm based on the past learning data. For example, the learning unit analyzes the past learning data and selects an optimal learning algorithm. Effective learning patterns are extracted from the past learning data and used to optimize the algorithm. The parameters of the learning algorithm are adjusted based on the past learning data. In this way, the learning algorithm can be optimized based on the past learning data.

[0058] The learning unit can weight the learning data based on the frequency of error occurrence. For example, the learning unit sets a high weight for error information that occurs frequently. For example, the learning unit measures the frequency of error occurrence and sets a high weight for error information that occurs frequently. The learning unit can also set a low weight for error information that occurs infrequently. The learning unit can also dynamically adjust the weighting of the learning data based on the frequency of error occurrence. For example, the learning unit determines the weighting of the learning data based on the frequency of error occurrence. The frequency of error occurrence is measured using the number of errors per hour or the number of errors occurring within a specific period. This makes it possible to weight the learning data based on the frequency of error occurrence.

[0059] The learning unit can customize the learning data based on the location of the error. For example, when an error occurs in a specific module, the learning unit preferentially uses learning data related to that module. For example, when an error occurs in a specific module, the learning unit preferentially uses learning data related to that module. Furthermore, when an error occurs in a specific function, the learning unit can preferentially use learning data related to that function. Furthermore, the learning unit can customize the learning data based on the location of the error. For example, when an error occurs in a specific module, the learning unit preferentially uses learning data related to that module. For example, when an error occurs in a specific function, the learning unit preferentially uses learning data related to that function. The location of the error is identified as a specific module, server, user terminal, etc. This allows appropriate learning data to be used depending on the location of the error.

[0060] The learning unit can refer to the user's operation history and prioritize learning related error information. The learning unit, for example, prioritizes learning error information related to the operation performed most recently by the user. For example, the learning unit analyzes the user's click log and operation log, and prioritizes learning error information related to the operation performed most recently. The learning unit can also prioritize learning frequently occurring error information from the user's operation history. The learning unit can also analyze the user's operation history and prioritize learning highly relevant error information. For example, the learning unit analyzes the user's click log and operation log, and prioritizes learning error information related to the operation performed most recently. Frequently occurring error information is identified from the user's operation history and learned with priority. The user's operation history is collected using click logs, operation logs, session data, etc. This makes it possible to prioritize learning related error information based on the user's operation history.

[0061] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0062] The analysis unit can customize the analysis method based on the location of the error. For example, if an error occurs in a specific module, it can perform a detailed analysis related to that module. If an error occurs in a specific function, it can also analyze log information related to that function. The location of the error can be identified as a specific module, server, user terminal, etc. This allows the appropriate analysis method to be applied depending on the location of the error.

[0063] The generator can adjust the level of detail of the generated code based on the impact of the error. For example, for a serious error, detailed correction code is generated. For a minor error, simplified correction code can be generated. The impact of the error is evaluated based on the impact on the entire system, the impact on users, the impact on business operations, etc. This allows the level of detail of the generated code to be adjusted according to the impact of the error.

[0064] The learning unit can weight the learning data based on the frequency of error occurrence. For example, a high weight can be set for error information that occurs frequently. A low weight can also be set for error information that occurs infrequently. This allows the learning data to be weighted based on the frequency of error occurrence.

[0065] The collection unit can determine the collection priority based on the frequency of error occurrence. For example, it can prioritize collection of information about errors that occur frequently and respond quickly. It can also prioritize error information that occurs less frequently and prioritize error information that is more important. This makes it possible to efficiently collect error information based on the frequency of error occurrence.

[0066] The analysis unit can apply different analysis algorithms depending on the type of error. For example, for input format errors, it applies a format check algorithm. For network errors, it can also apply an algorithm that analyzes connection status and communication logs. This makes it possible to apply an appropriate analysis algorithm depending on the type of error.

[0067] The processing flow of the first embodiment will be briefly explained below.

[0068] Step 1: The collection unit collects error information generated by the RPA. This information includes log files, system error messages, and user reports. The collection unit collects error information from log files, collects system error messages in real time, and analyzes user reports to collect error information. For example, the collection unit analyzes log files to extract error information, immediately analyzes system error messages, and analyzes user reports using natural language processing technology. Step 2: The analysis unit uses AI to analyze the error information collected by the collection unit. The analysis is performed using methods such as error cause analysis, pattern recognition, and statistical analysis. For example, it identifies the cause of the error and proposes a correction method, recognizes error patterns and proposes correction methods for similar errors, and evaluates the frequency and impact of errors using statistical analysis. Step 3: The generator uses AI to generate correction code based on the analysis results obtained by the analyzer. The correction code can be generated using methods such as automatic code generation or template-based correction. For example, if a specific input format is incorrect, it can generate code to correct it to the correct format, perform template-based correction, quickly generate correction code for known errors, and use machine learning algorithms to learn the correction process for unknown errors, automatically generating correction code the next time the same error occurs.

[0069] (Example 2) An error correction system according to an embodiment of the present invention automatically analyzes errors made by an RPA and generates correction codes. The error correction system collects error information, analyzes it using AI, and immediately generates correction codes for known errors. It also learns a correction process for unknown errors, aiming to automatically correct those error codes in the future. For example, the error correction system collects error information when an RPA makes an error. Then, AI analyzes the collected error information and immediately generates correction codes for known errors. For example, if a specific input format is incorrect, the AI ​​generates code to correct it to the correct format. For unknown errors, the AI ​​learns a correction process and can automatically generate correction codes the next time the same error occurs. This improves the efficiency of RPA error response and improves system stability. The error correction system automatically corrects errors made by an RPA and improves system stability. For example, the error correction system quickly and accurately collects error information, analyzes it using AI, and immediately generates correction codes for known errors. It also learns a correction process for unknown errors and can automatically generate correction codes in the future. This will enable the error correction system to respond more efficiently to RPA errors and improve system stability.

[0070] An error correction system according to an embodiment includes a collection unit, an analysis unit, and a generation unit. The collection unit collects error information generated by the RPA. Examples of the error information include, but are not limited to, log files, system error messages, and user reports. The collection unit collects the error information from, for example, log files. The collection unit can also collect system error messages in real time. The collection unit can also analyze user reports to collect the error information. For example, the collection unit analyzes log files and extracts the error information. System error messages are collected in real time and analyzed immediately. User reports are analyzed using natural language processing technology to extract the error information. The analysis unit uses AI to analyze the error information collected by the collection unit. The analysis can be performed using, for example, error cause analysis, pattern recognition, statistical analysis, or other methods, but is not limited to these examples. For example, the analysis unit identifies the cause of the error and proposes a correction method. The analysis unit can also recognize error patterns and propose correction methods for similar errors. The analysis unit can also use statistical analysis to evaluate the frequency and impact of errors. For example, the analysis unit analyzes the error log to identify the cause of the error. Error pattern recognition is performed using a machine learning algorithm. Statistical analysis is used to evaluate the frequency and impact of the error. The generation unit uses AI to generate correction code based on the analysis results obtained by the analysis unit. The correction code may be generated by, for example, automatic code generation, template-based correction, or other methods, but is not limited to these examples. For example, the generation unit generates code to correct a specific input format to a correct format when the input format is incorrect. The generation unit can also perform template-based correction to quickly generate correction code for known errors. The generation unit can also use a machine learning algorithm to learn the correction process for unknown errors and automatically generate correction code the next time the same error occurs. For example, the generation unit generates code to correct a specific input format to a correct format when the input format is incorrect.Template-based correction is used to quickly generate correction code for known errors, while machine learning algorithms are used to learn the correction process for unknown errors and automatically generate correction code the next time the same error occurs. This allows the error correction system according to the embodiment to efficiently collect, analyze, and generate correction code for error information.

[0071] The generation unit includes an instant correction unit that instantly generates correction code for known errors. The instant correction unit quickly generates correction code for known errors. For example, if a specific input format is incorrect, the instant correction unit generates code that corrects the input to a correct format. The instant correction unit can also perform template-based correction to quickly generate correction code for known errors. The instant correction unit can also recognize error patterns and suggest correction methods for similar errors. For example, if a specific input format is incorrect, the instant correction unit generates code that corrects the input to a correct format. Template-based correction is used to quickly generate correction code for known errors. Error pattern recognition is performed using a machine learning algorithm. This makes it possible to quickly generate correction code for known errors.

[0072] The generation unit includes a learning unit that learns a correction process for unknown errors. The learning unit learns the correction process for unknown errors. For example, when a new error occurs, the learning unit analyzes the cause of the error and learns a correction method. The learning unit can also learn the correction process using a machine learning algorithm and automatically generate correction code the next time the same error occurs. The learning unit can also recognize error patterns and suggest correction methods for similar errors. For example, when a new error occurs, the learning unit analyzes the cause of the error and learns a correction method. The machine learning algorithm is used to learn a correction process for unknown errors and automatically generate correction code the next time the same error occurs. Error pattern recognition is performed using a machine learning algorithm. This makes it possible to automatically correct unknown errors in the future.

[0073] The collection unit can collect error information from log files. Examples of log files include, but are not limited to, text files, system logs, and application logs. The collection unit collects error information from log files, for example. For example, the collection unit analyzes log files in text file format to extract error information. The collection unit can also collect system logs in real time and analyze them immediately. The collection unit can also analyze application logs to collect error information. For example, the collection unit analyzes log files in text file format to extract error information. System logs are collected in real time and analyzed immediately. Application logs are analyzed to collect error information related to a specific application. This allows error information to be collected efficiently from log files.

[0074] The learning unit can learn the correction process using a machine learning algorithm. Examples of machine learning algorithms include, but are not limited to, neural networks and support vector machines. The learning unit learns the correction process using, for example, a neural network. For example, the learning unit recognizes error patterns using a neural network and learns a correction method. The learning unit can also learn the correction process using a support vector machine. The learning unit can also analyze the cause of an error and learn a correction method using a machine learning algorithm. For example, the learning unit recognizes error patterns using a neural network and learns a correction method. A support vector machine is used to analyze the cause of an error and learn a correction method. The machine learning algorithm is used to learn the correction process based on error pattern recognition and cause analysis. As a result, using the machine learning algorithm improves the learning accuracy of the correction process.

[0075] The collection unit can estimate the user's emotions and adjust the timing of collecting error information based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit delays collecting error information and prioritizes the user's work. For example, the collection unit captures the user's facial expression with a camera and estimates the user's emotions using an emotion estimation algorithm. Furthermore, if the user is relaxed, the collection unit can immediately collect error information and take prompt action. Furthermore, if the user is in a hurry, the collection unit can minimize the collection of error information so as not to interfere with the user's work. For example, the collection unit records the user's voice and estimates the user's emotions using voice analysis technology. The emotion estimation is achieved using an emotion estimation function, such as 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. This makes it possible to adjust the timing of collecting error information according to the user's emotions.

[0076] The collection unit can determine the collection priority based on the frequency of error occurrence. For example, the collection unit prioritizes collecting information about errors that occur frequently in order to respond quickly. For example, the collection unit measures the frequency of error occurrence and prioritizes collecting information about errors that occur frequently. The collection unit can also postpone error information that occurs less frequently and prioritize error information that is more important. The collection unit can also adjust the timing of collection based on the frequency of error occurrence to efficiently collect information. For example, the collection unit determines the collection priority based on the frequency of error occurrence. The frequency of error occurrence is measured by the number of errors per hour or the number of errors that occur within a specific period. This makes it possible to efficiently collect error information based on the frequency of error occurrence.

[0077] The collection unit can apply different collection methods depending on the type of error. For example, for an input format error, the collection unit collects detailed log information. For example, when an input format error occurs, the collection unit collects detailed log information and identifies the cause of the error. The collection unit can also collect connection status and communication logs for network errors. The collection unit can also collect memory dumps and system logs for system crashes. For example, when a network error occurs, the collection unit collects connection status and communication logs and identifies the cause of the error. When a system crash occurs, the collection unit collects memory dumps and system logs and identifies the cause of the error. This makes it possible to apply an appropriate collection method depending on the type of error.

[0078] The collection unit can adjust the level of detail of the collection based on the impact of the error. For example, the collection unit collects detailed information for serious errors to enable a prompt response. For example, when a serious error occurs, the collection unit collects detailed information to identify the cause of the error. The collection unit can also collect simplified information for minor errors to enable an efficient response. The collection unit can also adjust the scope and level of detail of the information to be collected based on the impact of the error. For example, the collection unit evaluates the impact of the error and collects detailed information for serious errors and simplified information for minor errors. The impact of an error is evaluated based on the impact on the entire system, the impact on users, the impact on business, etc. This makes it possible to adjust the level of detail of the collection according to the impact of the error.

[0079] The collection unit can estimate the user's emotions and determine the priority of the error information to be collected based on the estimated user emotions. For example, when the user is feeling stressed, the collection unit prioritizes collecting error information of high importance. For example, the collection unit captures the user's facial expressions with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, when the user is relaxed, the collection unit can equally collect all error information. Furthermore, when the user is in a hurry, the collection unit can prioritize collecting error information that will affect the user's work. For example, the collection unit records the user's voice and estimates the emotion using voice analysis technology. The emotion estimation is realized using an emotion estimation function, such as 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. This allows the priority of error information to be determined according to the user's emotions.

[0080] The collection unit can adjust the timing of collection taking into account the operating status of the system. For example, the collection unit delays the collection of error information when the system is in a high-load state. For example, the collection unit monitors the CPU usage and memory usage of the system, and delays the collection of error information when the system is in a high-load state. The collection unit can also collect error information immediately when the system is in a low-load state. The collection unit can also dynamically adjust the timing of collection according to the operating status of the system. For example, the collection unit monitors the network traffic of the system, and collects error information immediately when the system is in a low-load state. The operating status of the system is evaluated based on the CPU usage, memory usage, network traffic, etc. This makes it possible to adjust the timing of collection according to the operating status of the system.

[0081] The collection unit can customize the collection method based on the location of the error. For example, for an error that occurs in a specific module, the collection unit collects detailed information related to the module. For example, if an error occurs in a specific module, the collection unit collects detailed information related to the module and identifies the cause of the error. Furthermore, for an error that occurs in a specific function, the collection unit can also collect log information related to the function. Furthermore, the collection unit can customize the range and level of detail of the information to be collected based on the location of the error. For example, for an error that occurs in a specific module, the collection unit collects detailed information related to the module. For an error that occurs in a specific function, the collection unit collects log information related to the function. The location of the error is identified as a specific module, server, user terminal, etc. This makes it possible to apply an appropriate collection method depending on the location of the error.

[0082] The collection unit can preferentially collect relevant error information by referring to the user's operation history. The collection unit, for example, preferentially collects error information related to the operation performed most recently by the user. For example, the collection unit analyzes the user's click log and operation log, and preferentially collects error information related to the operation performed most recently. The collection unit can also preferentially collect frequently occurring error information from the user's operation history. The collection unit can also analyze the user's operation history and preferentially collect highly relevant error information. For example, the collection unit analyzes the user's click log and operation log, and preferentially collects error information related to the operation performed most recently. Frequently occurring error information is identified from the user's operation history and collected preferentially. The user's operation history is collected using click logs, operation logs, session data, etc. This makes it possible to preferentially collect relevant error information based on the user's operation history.

[0083] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit provides a simple, highly visible display method. For example, the analysis unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that focuses on the main points. For example, the analysis unit records the user's voice and estimates the emotion using voice analysis technology. The emotion estimation is realized using an emotion estimation function, such as 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. This allows the display method of the analysis results to be adjusted according to the user's emotions.

[0084] The analysis unit can determine the priority of analysis based on the frequency of error occurrence. For example, the analysis unit prioritizes analysis of frequently occurring error information to enable prompt response. For example, the analysis unit measures the frequency of error occurrence and prioritizes analysis of frequently occurring error information. The analysis unit can also postpone error information that occurs less frequently and prioritize error information that is more important. The analysis unit can also adjust the timing of analysis based on the frequency of error occurrence to perform efficient information analysis. For example, the analysis unit determines the priority of analysis based on the frequency of error occurrence. The frequency of error occurrence is measured by the number of errors per hour or the number of errors occurring within a specific period. This allows error information to be analyzed efficiently based on the frequency of error occurrence.

[0085] The analysis unit can apply different analysis algorithms depending on the type of error. For example, the analysis unit applies a format check algorithm to an input format error. For example, when an input format error occurs, the analysis unit applies a format check algorithm to identify the cause of the error. The analysis unit can also apply an algorithm that analyzes connection status and communication logs to identify a network error. The analysis unit can also apply an algorithm that analyzes memory dumps and system logs to identify a system crash. For example, when a network error occurs, the analysis unit analyzes connection status and communication logs to identify the cause of the error. When a system crash occurs, the analysis unit analyzes memory dumps and system logs to identify the cause of the error. This makes it possible to apply an appropriate analysis algorithm depending on the type of error.

[0086] The analysis unit can adjust the level of detail of the analysis based on the impact of the error. For example, the analysis unit performs a detailed analysis of a serious error to ensure a prompt response. For example, when a serious error occurs, the analysis unit performs a detailed analysis to identify the cause of the error. The analysis unit can also perform a simplified analysis of a minor error to ensure an efficient response. The analysis unit can also adjust the scope and level of detail of the analysis based on the impact of the error. For example, the analysis unit evaluates the impact of the error and performs a detailed analysis of a serious error and a simplified analysis of a minor error. The impact of an error is evaluated based on the impact on the entire system, the impact on users, the impact on business, etc. This makes it possible to adjust the level of detail of the analysis according to the impact of the error.

[0087] The analysis unit can estimate the user's emotions and prioritize analysis results based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit prioritizes displaying analysis results with high importance. For example, the analysis unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the analysis unit can equally display all analysis results. Furthermore, if the user is in a hurry, the analysis unit can prioritize displaying analysis results that will affect the user's work. For example, the analysis unit records the user's voice and estimates the emotion using voice analysis technology. The emotion estimation is realized using an emotion estimation function, such as 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. This allows the priority of analysis results to be determined according to the user's emotions.

[0088] The analysis unit can adjust the timing of the analysis taking into account the operating status of the system. For example, the analysis unit delays the analysis when the system is in a high load state. For example, the analysis unit monitors the CPU usage and memory usage of the system, and delays the analysis when the system is in a high load state. The analysis unit can also perform analysis immediately when the system is in a low load state. The analysis unit can also dynamically adjust the timing of the analysis according to the operating status of the system. For example, the analysis unit monitors the network traffic of the system, and performs analysis immediately when the system is in a low load state. The operating status of the system is evaluated based on the CPU usage, memory usage, network traffic, etc. This makes it possible to adjust the timing of the analysis according to the operating status of the system.

[0089] The analysis unit can customize the analysis method based on the location of the error. For example, for an error that occurs in a specific module, the analysis unit performs a detailed analysis related to that module. For example, if an error occurs in a specific module, the analysis unit performs a detailed analysis related to that module to identify the cause of the error. Furthermore, for an error that occurs in a specific function, the analysis unit can analyze log information related to that function. Furthermore, the analysis unit can customize the analysis method based on the location of the error. For example, for an error that occurs in a specific module, the analysis unit performs a detailed analysis related to that module. For an error that occurs in a specific function, the analysis unit analyzes log information related to that function. The location of the error is identified as a specific module, server, user terminal, etc. This makes it possible to apply an appropriate analysis method depending on the location of the error.

[0090] The analysis unit can prioritize analyzing related error information by referring to the user's operation history. The analysis unit, for example, prioritizes analyzing error information related to the operation performed most recently by the user. For example, the analysis unit analyzes the user's click log and operation log, and prioritizes analyzing error information related to the operation performed most recently. The analysis unit can also prioritize analyzing frequently occurring error information from the user's operation history. The analysis unit can also analyze the user's operation history and prioritize analyzing highly relevant error information. For example, the analysis unit analyzes the user's click log and operation log, and prioritizes analyzing error information related to the operation performed most recently. Frequently occurring error information is identified from the user's operation history and analyzed preferentially. The user's operation history is collected using click logs, operation logs, session data, etc. This makes it possible to prioritize analyzing related error information based on the user's operation history.

[0091] The generation unit can estimate the user's emotions and adjust the expression method of the generated correction code based on the estimated user emotions. For example, if the user is nervous, the generation unit generates simple, highly visible correction code. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. If the user is relaxed, the generation unit can generate correction code including detailed comments. If the user is in a hurry, the generation unit can generate correction code that focuses on the main points. For example, the generation unit records the user's voice and estimates the emotion using voice analysis technology. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. This makes it possible to adjust the expression method of the correction code according to the user's emotions.

[0092] The generation unit can apply different generation algorithms depending on the type of error. For example, for an input format error, the generation unit applies a format check algorithm to generate a correction code. For example, when an input format error occurs, the generation unit applies a format check algorithm to generate a correction code. Furthermore, for a network error, the generation unit can analyze the connection status and communication log to generate a correction code. Furthermore, for a system crash, the generation unit can analyze a memory dump and system log to generate a correction code. For example, when a network error occurs, the generation unit analyzes the connection status and communication log to generate a correction code. When a system crash occurs, the generation unit analyzes the memory dump and system log to generate a correction code. This makes it possible to apply an appropriate generation algorithm depending on the type of error.

[0093] The generation unit can adjust the level of detail of the generation based on the impact of the error. For example, the generation unit generates detailed correction code for a serious error. For example, when a serious error occurs, the generation unit generates detailed correction code and identifies the cause of the error. The generation unit can also generate simplified correction code for a minor error. The generation unit can also adjust the scope and level of detail of the correction code to be generated based on the impact of the error. For example, the generation unit evaluates the impact of the error and generates detailed correction code for a serious error and generates simplified correction code for a minor error. The impact of the error is evaluated based on the impact on the entire system, the impact on users, the impact on business, etc. This makes it possible to adjust the level of detail of the generation according to the impact of the error.

[0094] The generation unit can estimate the user's emotions and determine the priority of the correction codes to be generated based on the estimated user emotions. For example, if the user is feeling stressed, the generation unit prioritizes generating correction codes with high importance. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the generation unit can generate all correction codes equally. Furthermore, if the user is in a hurry, the generation unit can prioritize generating correction codes that will affect the work. For example, the generation unit records the user's voice and estimates the emotion using voice analysis technology. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. This allows the priority of correction codes to be determined according to the user's emotions.

[0095] The generation unit can adjust the timing of generation taking into account the operating status of the system. For example, the generation unit delays the generation of the correction code when the system is in a high-load state. For example, the generation unit monitors the CPU usage and memory usage of the system, and delays the generation of the correction code when the system is in a high-load state. The generation unit can also generate the correction code immediately when the system is in a low-load state. The generation unit can also dynamically adjust the timing of generation of the correction code according to the operating status of the system. For example, the generation unit monitors the network traffic of the system, and generates the correction code immediately when the system is in a low-load state. The operating status of the system is evaluated based on the CPU usage, memory usage, network traffic, etc. This makes it possible to adjust the timing of generation according to the operating status of the system.

[0096] The generation unit can customize the generation method based on the location of the error. For example, for an error that occurs in a specific module, the generation unit generates a correction code related to the module. For example, for an error that occurs in a specific module, the generation unit generates a correction code related to the module. Furthermore, for an error that occurs in a specific function, the generation unit can generate a correction code related to the function. Furthermore, the generation unit can customize the generation method of the correction code based on the location of the error. For example, for an error that occurs in a specific module, the generation unit generates a correction code related to the module. For an error that occurs in a specific function, the generation unit generates a correction code related to the function. The location of the error is identified as a specific module, a server, a user terminal, etc. This makes it possible to apply an appropriate generation method depending on the location of the error.

[0097] The generation unit can refer to the user's operation history and prioritize correcting related error information. The generation unit, for example, prioritizes correcting error information related to the operation performed most recently by the user. For example, the generation unit analyzes the user's click log and operation log, and prioritizes correcting error information related to the operation performed most recently. The generation unit can also prioritize correcting frequently occurring error information from the user's operation history. The generation unit can also analyze the user's operation history and prioritize correcting highly relevant error information. For example, the generation unit analyzes the user's click log and operation log, and prioritizes correcting error information related to the operation performed most recently. Frequently occurring error information is identified from the user's operation history and prioritizes correcting it. The user's operation history is collected using click logs, operation logs, session data, etc. This makes it possible to prioritize correcting related error information based on the user's operation history.

[0098] The instant correction unit can estimate the user's emotions and adjust the instant correction method based on the estimated user emotions. For example, if the user is nervous, the instant correction unit provides a simple and highly visible correction method. For example, the instant correction unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the instant correction unit can provide a correction method that includes detailed explanations. Furthermore, if the user is in a hurry, the instant correction unit can provide a correction method that focuses on the main points. For example, the instant correction unit records the user's voice and estimates the emotion using voice analysis technology. The emotion estimation is realized using an emotion estimation function, such as 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. This allows the instant correction method to be adjusted according to the user's emotions.

[0099] The immediate correction unit can determine the priority of correction based on the frequency of error occurrence. For example, the immediate correction unit prioritizes correction of errors that occur frequently. For example, the immediate correction unit measures the frequency of error occurrence and prioritizes correction of frequently occurring errors. The immediate correction unit can also postpone errors that occur less frequently and prioritize errors that are more important. The immediate correction unit can also adjust the timing of correction based on the frequency of error occurrence. For example, the immediate correction unit determines the priority of correction based on the frequency of error occurrence. The frequency of error occurrence is measured by the number of errors per hour or the number of errors occurring within a specific period. This allows efficient correction based on the frequency of error occurrence.

[0100] The real-time correction unit can apply different correction algorithms depending on the type of error. For example, for input format errors, the real-time correction unit applies a format check algorithm to make corrections. For example, when an input format error occurs, the real-time correction unit applies a format check algorithm to make corrections. Furthermore, for network errors, the real-time correction unit can analyze connection status and communication logs to make corrections. Furthermore, for system crashes, the real-time correction unit can analyze memory dumps and system logs to make corrections. For example, when a network error occurs, the real-time correction unit analyzes connection status and communication logs to make corrections. When a system crash occurs, the real-time correction unit analyzes memory dumps and system logs to make corrections. This makes it possible to apply an appropriate correction algorithm depending on the type of error.

[0101] The immediate correction unit can adjust the level of detail of the correction based on the impact of the error. For example, the immediate correction unit performs detailed correction for serious errors. For example, when a serious error occurs, the immediate correction unit performs detailed correction and identifies the cause of the error. The immediate correction unit can also perform simplified correction for minor errors. The immediate correction unit can also adjust the scope and level of detail of the correction based on the impact of the error. For example, the immediate correction unit evaluates the impact of the error and performs detailed correction for serious errors and simplified correction for minor errors. The impact of an error is evaluated based on the impact on the entire system, the impact on users, the impact on business, etc. This makes it possible to adjust the level of detail of the correction according to the impact of the error.

[0102] The instant correction unit can estimate the user's emotions and determine the priority of instant corrections based on the estimated user emotions. For example, if the user is feeling stressed, the instant correction unit prioritizes corrections with high importance. For example, the instant correction unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the instant correction unit can perform all corrections equally. Furthermore, if the user is in a hurry, the instant correction unit can prioritize corrections that will affect the work. For example, the instant correction unit records the user's voice and estimates the emotion using voice analysis technology. The emotion estimation is realized using an emotion estimation function, such as 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. This allows the priority of instant corrections to be determined according to the user's emotions.

[0103] The immediate correction unit can adjust the timing of correction taking into account the operating status of the system. For example, the immediate correction unit delays correction when the system is in a high-load state. For example, the immediate correction unit monitors the system's CPU usage and memory usage, and delays correction when the system is in a high-load state. The immediate correction unit can also perform correction immediately when the system is in a low-load state. The immediate correction unit can also dynamically adjust the timing of correction according to the operating status of the system. For example, the immediate correction unit monitors the system's network traffic, and performs correction immediately when the system is in a low-load state. The operating status of the system is evaluated based on CPU usage, memory usage, network traffic, etc. This makes it possible to adjust the timing of correction according to the operating status of the system.

[0104] The real-time correction unit can customize a correction method based on the location of the error. For example, for an error that occurs in a specific module, the real-time correction unit applies a correction method related to that module. For example, for an error that occurs in a specific module, the real-time correction unit applies a correction method related to that module. Furthermore, for an error that occurs in a specific function, the real-time correction unit can apply a correction method related to that function. Furthermore, the real-time correction unit can customize a correction method based on the location of the error. For example, for an error that occurs in a specific module, the real-time correction unit applies a correction method related to that module. For an error that occurs in a specific function, the real-time correction unit applies a correction method related to that function. The location of the error is identified as a specific module, server, user terminal, etc. This makes it possible to apply an appropriate correction method depending on the location of the error.

[0105] The immediate correction unit can refer to the user's operation history and prioritize correcting related error information. The immediate correction unit, for example, prioritizes correcting error information related to the operation performed most recently by the user. For example, the immediate correction unit analyzes the user's click log and operation log, and prioritizes correcting error information related to the operation performed most recently. The immediate correction unit can also prioritize correcting frequently occurring error information from the user's operation history. The immediate correction unit can also analyze the user's operation history and prioritize correcting highly relevant error information. For example, the immediate correction unit analyzes the user's click log and operation log, and prioritizes correcting error information related to the operation performed most recently. Frequently occurring error information is identified from the user's operation history and prioritized for correction. The user's operation history is collected using click logs, operation logs, session data, etc. This makes it possible to prioritize correcting related error information based on the user's operation history.

[0106] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is feeling stressed, the learning unit prioritizes selecting error information with high importance as training data. For example, the learning unit captures the user's facial expressions with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the learning unit can equally select all error information as training data. Furthermore, if the user is in a hurry, the learning unit can prioritize selecting error information that will affect the user's work as training data. For example, the learning unit records the user's voice and estimates the emotion using voice analysis technology. The emotion estimation is realized using an emotion estimation function, such as 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. This allows the selection of training data according to the user's emotions.

[0107] The learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on the past learning data. For example, the learning unit analyzes the past learning data, extracts effective learning patterns, and optimizes the algorithm. The learning unit can also adjust parameters of the learning algorithm by referring to the past learning data. The learning unit can also select and optimize a learning algorithm based on the past learning data. For example, the learning unit analyzes the past learning data and selects an optimal learning algorithm. Effective learning patterns are extracted from the past learning data and used to optimize the algorithm. The parameters of the learning algorithm are adjusted based on the past learning data. In this way, the learning algorithm can be optimized based on the past learning data.

[0108] The learning unit can weight the learning data based on the frequency of error occurrence. For example, the learning unit sets a high weight for error information that occurs frequently. For example, the learning unit measures the frequency of error occurrence and sets a high weight for error information that occurs frequently. The learning unit can also set a low weight for error information that occurs infrequently. The learning unit can also dynamically adjust the weighting of the learning data based on the frequency of error occurrence. For example, the learning unit determines the weighting of the learning data based on the frequency of error occurrence. The frequency of error occurrence is measured using the number of errors per hour or the number of errors occurring within a specific period. This makes it possible to weight the learning data based on the frequency of error occurrence.

[0109] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. For example, if the user is feeling stressed, the learning unit sets the learning frequency low. For example, the learning unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. The learning unit can also set the learning frequency high if the user is relaxed. The learning unit can also set the learning frequency to minimum if the user is in a hurry. For example, the learning unit records the user's voice and estimates the emotions using voice analysis technology. The emotion estimation is realized using an emotion estimation function, such as 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. This makes it possible to adjust the learning frequency according to the user's emotions.

[0110] The learning unit can customize the learning data based on the location of the error. For example, when an error occurs in a specific module, the learning unit preferentially uses learning data related to that module. For example, when an error occurs in a specific module, the learning unit preferentially uses learning data related to that module. Furthermore, when an error occurs in a specific function, the learning unit can preferentially use learning data related to that function. Furthermore, the learning unit can customize the learning data based on the location of the error. For example, when an error occurs in a specific module, the learning unit preferentially uses learning data related to that module. For example, when an error occurs in a specific function, the learning unit preferentially uses learning data related to that function. The location of the error is identified as a specific module, server, user terminal, etc. This allows appropriate learning data to be used depending on the location of the error.

[0111] The learning unit can refer to the user's operation history and prioritize learning related error information. The learning unit, for example, prioritizes learning error information related to the operation performed most recently by the user. For example, the learning unit analyzes the user's click log and operation log, and prioritizes learning error information related to the operation performed most recently. The learning unit can also prioritize learning frequently occurring error information from the user's operation history. The learning unit can also analyze the user's operation history and prioritize learning highly relevant error information. For example, the learning unit analyzes the user's click log and operation log, and prioritizes learning error information related to the operation performed most recently. Frequently occurring error information is identified from the user's operation history and learned with priority. The user's operation history is collected using click logs, operation logs, session data, etc. This makes it possible to prioritize learning related error information based on the user's operation history. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, analysis unit, and generation unit described above is realized, for example, in at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects error information using the camera 42 or microphone 38B of the smart device 14, and the error information is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the error information by the specific processing unit 290 of the data processing device 12, and the generation unit generates a correction code by the specific processing unit 290 of the data processing device 12. For example, the collection unit collects error information by the control unit 46A of the smart device 14, the analysis unit analyzes the error information by the specific processing unit 290 of the data processing device 12, and the generation unit generates a correction code by the control unit 46A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned collection unit, analysis unit, and generation unit is realized, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects error information using the camera 42 or microphone 238 of the smart glasses 214, and the error information is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the error information by the specific processing unit 290 of the data processing device 12, and the generation unit generates a correction code by the specific processing unit 290 of the data processing device 12. For example, the collection unit collects error information by the control unit 46A of the smart glasses 214, the analysis unit analyzes the error information by the specific processing unit 290 of the data processing device 12, and the generation unit generates a correction code by the control unit 46A of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned collection unit, analysis unit, and generation unit is realized, for example, in at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects error information using the camera 42 or the microphone 238 of the headset type terminal 314, and the error information is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the error information by the specific processing unit 290 of the data processing device 12, and the generation unit generates a correction code by the specific processing unit 290 of the data processing device 12. For example, the collection unit collects error information by the control unit 46A of the headset type terminal 314, the analysis unit analyzes the error information by the specific processing unit 290 of the data processing device 12, and the generation unit generates a correction code by the control unit 46A of the headset type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, and generation unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects error information using the camera 42 or microphone 238 of the robot 414, and the error information is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the error information by the specific processing unit 290 of the data processing device 12, and the generation unit generates a correction code by the specific processing unit 290 of the data processing device 12. For example, the collection unit collects error information by the control unit 46A of the robot 414, the analysis unit analyzes the error information by the specific processing unit 290 of the data processing device 12, and the generation unit generates a correction code by the control unit 46A of the robot 414.

[0112] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0113] The analysis unit can customize the analysis method based on the location of the error. For example, if an error occurs in a specific module, it can perform a detailed analysis related to that module. If an error occurs in a specific function, it can also analyze log information related to that function. The location of the error can be identified as a specific module, server, user terminal, etc. This allows the appropriate analysis method to be applied depending on the location of the error.

[0114] The generator can adjust the level of detail of the generated code based on the impact of the error. For example, for a serious error, detailed correction code is generated. For a minor error, simplified correction code can be generated. The impact of the error is evaluated based on the impact on the entire system, the impact on users, the impact on business operations, etc. This allows the level of detail of the generated code to be adjusted according to the impact of the error.

[0115] The collection unit can estimate the user's emotions and adjust the timing of collecting error information based on the estimated user emotions. For example, if the user is feeling stressed, the collection of error information can be delayed to prioritize the user's work. If the user is relaxed, the collection unit can collect error information immediately to enable a prompt response. This makes it possible to adjust the timing of collecting error information according to the user's emotions.

[0116] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, a simple, highly visible display method can be provided. If the user is relaxed, a display method including detailed information can also be provided. This makes it possible to adjust the display method of the analysis results according to the user's emotions.

[0117] The learning unit can weight the learning data based on the frequency of error occurrence. For example, a high weight can be set for error information that occurs frequently. A low weight can also be set for error information that occurs infrequently. This allows the learning data to be weighted based on the frequency of error occurrence.

[0118] The generation unit can estimate the user's emotions and adjust the expression method of the generated correction code based on the estimated user's emotions. For example, if the user is nervous, a simple and highly visible correction code can be generated. If the user is relaxed, a correction code including detailed comments can also be generated. This makes it possible to adjust the expression method of the correction code according to the user's emotions.

[0119] The collection unit can determine the collection priority based on the frequency of error occurrence. For example, it can prioritize collection of information about errors that occur frequently and respond quickly. It can also prioritize error information that occurs less frequently and prioritize error information that is more important. This makes it possible to efficiently collect error information based on the frequency of error occurrence.

[0120] The analysis unit can apply different analysis algorithms depending on the type of error. For example, for input format errors, it applies a format check algorithm. For network errors, it can also apply an algorithm that analyzes connection status and communication logs. This makes it possible to apply an appropriate analysis algorithm depending on the type of error.

[0121] The learning unit can estimate the user's emotions and select learning data based on the estimated user emotions. For example, if the user is feeling stressed, error information with high importance can be preferentially selected as learning data. If the user is relaxed, all error information can be selected equally as learning data. This allows the selection of learning data according to the user's emotions.

[0122] The instant correction unit can estimate the user's emotions and adjust the instant correction method based on the estimated user's emotions. For example, if the user is nervous, a simple and highly visible correction method can be provided. If the user is relaxed, a correction method including detailed explanations can also be provided. This makes it possible to adjust the instant correction method according to the user's emotions.

[0123] The processing flow of the second embodiment will be briefly explained below.

[0124] Step 1: The collection unit collects error information generated by the RPA. This information includes log files, system error messages, and user reports. The collection unit collects error information from log files, collects system error messages in real time, and analyzes user reports to collect error information. For example, the collection unit analyzes log files to extract error information, immediately analyzes system error messages, and analyzes user reports using natural language processing technology. Step 2: The analysis unit uses AI to analyze the error information collected by the collection unit. The analysis is performed using methods such as error cause analysis, pattern recognition, and statistical analysis. For example, it identifies the cause of the error and proposes a correction method, recognizes error patterns and proposes correction methods for similar errors, and evaluates the frequency and impact of errors using statistical analysis. Step 3: The generator uses AI to generate correction code based on the analysis results obtained by the analyzer. The correction code can be generated using methods such as automatic code generation or template-based correction. For example, if a specific input format is incorrect, it can generate code to correct it to the correct format, perform template-based correction, quickly generate correction code for known errors, and use machine learning algorithms to learn the correction process for unknown errors, automatically generating correction code the next time the same error occurs.

[0125] 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.

[0126] 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 generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0127] 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.

[0128] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0129] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0130] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0143] 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.

[0144] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0145] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0159] 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.

[0160] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0161] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0162] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0176] 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.

[0177] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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).

[0182] 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 expressed, and when they approach the ideal, a state of pleasure is expressed. 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 expressed, and when they approach the ideal, a state of pleasure is expressed. 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.

[0183] 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."

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] [Explanation of symbols]

[0197] 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. a collection unit for collecting error information; an analysis unit that analyzes the error information collected by the collection unit; a generation unit that generates a modified code based on the analysis result obtained by the analysis unit; Equipped with A system characterized by:

2. The generation unit Equipped with an on-the-fly correction unit that immediately generates correction code for known errors 2. The system of claim 1.

3. The generation unit Equipped with a learning unit that learns the correction process for unknown errors 2. The system of claim 1.

4. The collecting unit Collecting error information from log files 2. The system of claim 1.

5. The learning unit Use machine learning algorithms to learn the correction process 4. The system of claim 3.

6. The collecting unit The method estimates the user's emotions and adjusts the timing of collecting error information based on the estimated user emotions.

2. The system of claim 1.

7. The collecting unit Prioritize collection based on frequency of errors 2. The system of claim 1.

8. The collecting unit Apply different collection techniques depending on the type of error 2. The system of claim 1.

Images