System

Abstract

To provide a system that efficiently searches for and formats necessary information from a large amount of log data.SOLUTION: A system comprises a reading unit, an analysis unit, an extraction unit, and a formatting unit. The reading unit reads log data. The analysis unit analyzes the log data read by the reading unit to analyze the structure of the data. The extraction unit analyzes a user query on the basis of the data analyzed by the analysis unit and extracts relevant information. The formatting unit formats the information extracted by the extraction 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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult and time-consuming to search for and organize the necessary information from vast amounts of log data.

[0005] The system according to the embodiment aims to efficiently search for and organize necessary information from a huge amount of log data. [Means for solving the problem]

[0006] The system according to the embodiment includes a reading unit, an analysis unit, an extraction unit, and a formatting unit. The reading unit reads log data. The analysis unit analyzes the log data read by the reading unit and analyzes the structure of the data. The extraction unit analyzes a user's query based on the data analyzed by the analysis unit and extracts related information. The formatting unit formats the information extracted by the extraction unit. Effect of the Invention

[0007] The system according to the embodiment can efficiently search for and organize required information from a huge amount of log data. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed 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 and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The log data analysis system according to the embodiment of the present invention is a system that easily searches for desired information and formats data by having a generation AI read and analyze log data acquired from a network device. This log data analysis system has a generation AI read log data acquired from a network device. The generation AI analyzes the format and contents of the log data and understands the structure of the data. Next, when a user searches for desired information, the user inputs a query in natural language to the generation AI. The generation AI analyzes this query and extracts the relevant information from the log data. Furthermore, the generation AI formats the extracted information in a format that is easy for the user to view. This makes the search and formatting of log data more efficient, and significantly reduces the user's work time. In addition, since it can handle data formats that differ from vendor to vendor, it is highly versatile. For example, log data acquired from network devices of different vendors can be managed in a unified manner and displayed in a unified format. First, the log data acquired from the network device is read into the generation AI. At this time, the generation AI analyzes the format and contents of the log data and understands the structure of the data. For example, the log data includes error messages and access records, and the generation AI classifies and organizes this information. Next, when a user searches for the information they want, they input a query in natural language to the generation AI. For example, they input a query such as "I want to search for access logs from a specific IP address." The generation AI analyzes this query and extracts the relevant information from the log data. The generation AI then formats the extracted information in a format that is easy for the user to view. For example, data can be displayed in a table format or graphed according to a specific format. This allows users to quickly and easily obtain the information they need. This mechanism makes the search and formatting of log data more efficient, significantly reducing the user's work time. It is also highly versatile because it can handle data formats that differ from vendor to vendor. For example, log data obtained from network devices from different vendors can be managed in a centralized manner and displayed in a unified format. This allows the log data analysis system to significantly reduce the user's work time.

[0029] The log data analysis system according to the embodiment includes a reading unit, an analysis unit, an extraction unit, and a formatting unit. The reading unit reads log data acquired from a network device. The log data includes, for example, a server log, an access log, an error log, and the like, but is not limited to such examples. The reading unit uses a generation AI to analyze the format and contents of the log data and understand the structure of the data. For example, the generation AI analyzes the type and format of the log data and recognizes the pattern of the data. The analysis unit analyzes the log data read by the reading unit and understands the structure of the data. The analysis unit uses a generation AI to classify and organize information such as error messages and access records. For example, the generation AI analyzes the classification criteria of the types of error messages and the access records and organizes the data. The extraction unit analyzes the user's query based on the data analyzed by the analysis unit and extracts the relevant information. The extraction unit uses a generation AI to analyze a query input by a user in natural language and extracts the relevant information from the log data. For example, the generation AI analyzes the query using morphological analysis, grammatical analysis, and semantic analysis, and extracts related information. The shaping unit shapes the information extracted by the extraction unit. The shaping unit uses the generation AI to display the extracted information in a table format according to a specific format. For example, the generation AI shapes the data according to a CSV format, a JSON format, or a specific table format. The shaping unit can also graph the extracted information. For example, the generation AI displays the data in a format such as a bar graph, a line graph, or a pie chart. This allows the log data analysis system according to the embodiment to significantly reduce the user's work time. Some or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the information extracted by the extraction unit to the generation AI and have the generation AI execute the shaping of the information.

[0030] The reading unit reads the log data acquired from the network device. The log data includes, but is not limited to, server logs, access logs, error logs, and the like. The reading unit uses the generation AI to analyze the format and content of the log data and understand the structure of the data. Specifically, the generation AI analyzes the type and format of the log data and recognizes the pattern of the data. For example, the server log records the operation status of the server and error messages, the access log records the user's access history and request details, and the error log records the occurrence status of system errors and failures. The generation AI analyzes these log data and automatically identifies the format and content of each log. Furthermore, the generation AI extracts important information from the log data and lays the foundation for understanding the structure of the data. For example, the generation AI identifies important fields such as the timestamp and IP address of the log data and the code of the error message, and recognizes the pattern of the data based on them. This allows the reading unit to efficiently read a wide variety of log data acquired from the network device and understand the structure of the data. Furthermore, the reading unit can also use the generation AI to perform pre-processing of the log data. For example, by removing noise from the log data and complementing missing data, the subsequent processing of the analysis unit and extraction unit can proceed smoothly. This allows the reading unit to improve the quality of the log data and the performance of the entire system.

[0031] The analysis unit analyzes the log data read by the reading unit and understands the structure of the data. The analysis unit uses the generation AI to classify and organize information such as error messages and access records. Specifically, the generation AI analyzes the classification criteria for the types of error messages and access records and organizes the data. For example, the generation AI analyzes the contents of error messages to identify the types of errors and the causes of occurrence. It also analyzes the access records to understand the user's behavior patterns and access frequency. Furthermore, the generation AI can detect abnormal patterns and trends from the log data. For example, it detects a sudden increase in access during a specific time period or the frequent occurrence of a specific error message, and detects system abnormalities early. This allows the analysis unit to quickly and accurately analyze the read log data and understand the structure of the data. Furthermore, the analysis unit can also perform trend analysis and prediction based on past log data. For example, it analyzes past access logs to predict the increase or decrease in access during a specific period. It also analyzes error logs to predict situations where a specific error is likely to occur. This allows the analysis unit to contribute not only to real-time data analysis but also to future risk management and countermeasure planning. Furthermore, the analysis unit can also use the generation AI to visualize the log data. For example, the frequency of error messages or the distribution of access records can be displayed in graphs and charts to make the data easier to understand. This allows the analysis unit to not only understand the structure of the data, but also provide users with easy-to-understand information through data visualization.

[0032] The extraction unit analyzes the user's query based on the data analyzed by the analysis unit and extracts the relevant information. The extraction unit uses the generation AI to analyze the query entered by the user in natural language and extracts the relevant information from the log data. Specifically, the generation AI analyzes the query using morphological analysis, grammatical analysis, and semantic analysis, and extracts the relevant information. For example, if the user enters "I want to display the error log for a specific time period," the generation AI analyzes the content of the query and extracts the error log for the corresponding time period. Also, if the user enters "I want to display the access record from a specific IP address," the generation AI analyzes the content of the query and extracts the access record from the corresponding IP address. Furthermore, the extraction unit can set complex search conditions by combining multiple queries. For example, if the user enters "I want to display the error log from a specific IP address for a specific time period," the generation AI analyzes the content of the query and extracts the error log that matches the relevant condition. As a result, the extraction unit can quickly and accurately extract the relevant information for the user's query and meet the user's needs. Furthermore, the extraction unit can use the generation AI to resolve ambiguity in queries. For example, if a user inputs "I want to see recent error logs," the generation AI will ask the user for a definition of "recent" and extract the relevant error logs by setting a specific period. This allows the extraction unit to flexibly and appropriately respond to user queries and provide accurate information.

[0033] The formatting unit formats the information extracted by the extraction unit. The formatting unit uses the generation AI to display the extracted information in a table format according to a specific format. Specifically, the generation AI formats the data according to CSV format, JSON format, or a specific table format. For example, the generation AI formats the extracted error log or access record in CSV format so that the user can easily view and analyze it with spreadsheet software. In addition, formatting in JSON format can facilitate data integration with other systems and applications. In addition, the formatting unit can graph the extracted information. For example, the generation AI displays data in the form of a bar graph, line graph, pie chart, etc., making it easier for the user to visually understand the data. In this way, the formatting unit can provide the extracted information in a format that is easy for the user to use and promote understanding of the data. In addition, the formatting unit can automate the data formatting process using the generation AI. For example, the extracted information can be automatically formatted into a specific format and regularly updated data can be provided to the user. In addition, the formatting unit can provide data in a customized format according to the user's request. This allows the formatting unit to provide flexible data according to the user's needs, improving the user's work efficiency. Furthermore, the formatting unit can also use the generative AI to check the quality of the data. For example, it checks the consistency and integrity of the data and detects errors and missing data. This allows the formatting unit to provide the user with high-quality data and highly reliable information.

[0034] The reading unit can analyze the format and contents of the log data and analyze the data structure. The reading unit uses the generation AI to analyze the format and contents of the log data and understand the data structure. For example, the generation AI analyzes the type and format of the log data and recognizes the data pattern. This allows the format and contents of the log data to be analyzed and the data structure to be understood, thereby making subsequent processing more efficient. Some or all of the above-mentioned processing in the reading unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the log data to the generation AI and have the generation AI analyze the format and contents of the data.

[0035] The analysis unit can classify and organize information such as error messages or access records. The analysis unit classifies and organizes information such as error messages and access records using the generation AI. For example, the generation AI analyzes the classification criteria for error messages and access records and organizes the data. This makes it easier to manage data by classifying and organizing information such as error messages and access records. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input data such as error messages and access records to the generation AI and have the generation AI classify and organize the information.

[0036] The extraction unit can analyze a query input by a user in natural language and extract relevant information from the log data. The extraction unit uses a generation AI to analyze a query input by a user in natural language and extract relevant information from the log data. For example, the generation AI analyzes the query using morphological analysis, grammatical analysis, and semantic analysis to extract relevant information. This makes it easier to search by analyzing a query input by a user in natural language and extracting relevant information. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using the generation AI or may be performed without using the generation AI. For example, the extraction unit can input a user's query to the generation AI and have the generation AI execute the extraction of information.

[0037] The shaping unit can display the extracted information in a table format according to a specified format. The shaping unit uses the generation AI to display the extracted information in a table format according to a specific format. For example, the generation AI formats data according to CSV format, JSON format, or a specific table format. As a result, the extracted information is displayed in a table format according to a specific format, thereby improving the visibility of the information. Some or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the information extracted by the extraction unit to the generation AI and have the generation AI perform shaping of the information.

[0038] The shaping unit can display the extracted information as a graph. The shaping unit graphs the extracted information using the generation AI. For example, the generation AI displays data in the form of a bar graph, a line graph, a pie chart, or the like. This makes it easier to visually understand the information by graphing the extracted information. Some or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the information extracted by the extraction unit to the generation AI and cause the generation AI to graph the information.

[0039] The reading unit can set a priority order based on the importance of the data when reading the log data. The reading unit uses the generation AI to set a priority order based on the importance of the data when reading the log data. For example, security-related log data is read with the highest priority. Also, the system error log can be read with the next highest priority. Furthermore, the normal access log can be read last. In this way, important data can be quickly acquired by setting a priority order based on the importance of the data. A part or all of the above-mentioned processing in the reading unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the log data to the generation AI and cause the generation AI to set a priority order based on the importance of the data.

[0040] The reading unit can apply an appropriate reading algorithm according to the type of data when reading the log data. The reading unit uses the generation AI to apply different reading algorithms according to the type of data when reading the log data. For example, a high-speed text analysis algorithm is applied to log data in text format. A dedicated binary analysis algorithm can also be applied to log data in binary format. Furthermore, a JSON analysis algorithm can also be applied to log data in JSON format. This enables efficient data reading by applying different reading algorithms according to the type of data. A part or all of the above-mentioned processing in the reading unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the log data to the generation AI and cause the generation AI to apply a reading algorithm according to the type of data.

[0041] The reading unit can preferentially read highly relevant data based on the geographical location information of the network device when reading the log data. The reading unit uses the generation AI to preferentially read highly relevant data taking into account the geographical location information of the network device when reading the log data. For example, log data from nearby network devices can be preferentially read. Error logs occurring in a specific area can also be preferentially read. Furthermore, data with high geographical relevance can also be preferentially read. As a result, highly relevant data can be quickly acquired by taking into account the geographical location information of the network device. A part or all of the above-mentioned processing in the reading unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the geographical location information of the network device to the generation AI and cause the generation AI to execute setting of the priority order of highly relevant data.

[0042] The reading unit can analyze the operation status of the network device when reading the log data, and read the data at an appropriate timing. The reading unit uses the generation AI to analyze the operation status of the network device when reading the log data, and reads the data at an optimal timing. For example, the log data is read when the network device is under low load. Also, the reading can be delayed when the network device is under high load. Furthermore, the reading timing can be adjusted according to the operation status of the network device. This allows the optimization of system resources by adjusting the data reading timing according to the operation status of the network device. A part or all of the above-mentioned processing in the reading unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the operation status data of the network device to the generation AI, and cause the generation AI to execute data reading at an optimal timing.

[0043] The analysis unit can improve the accuracy of the analysis based on the interrelationships of the log data during the analysis. The analysis unit uses the generation AI to improve the accuracy of the analysis by considering the interrelationships of the log data during the analysis. For example, the analysis unit analyzes the interrelationships between error logs and access logs. The analysis unit can also analyze the interrelationships between security logs and system logs. Furthermore, the analysis unit can analyze the interrelationships between network traffic logs and performance logs. As a result, the analysis accuracy is improved by considering the interrelationships of the log data. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the log data to the generation AI and have the generation AI execute the analysis of the interrelationships.

[0044] The analysis unit can apply an appropriate analysis method for each type of log data during analysis. The analysis unit uses the generation AI to apply different analysis methods for each type of log data during analysis. For example, natural language processing is applied to text logs. A binary analysis method can also be applied to binary logs. Furthermore, a JSON analysis method can be applied to JSON logs. This enables efficient analysis by applying different analysis methods to each type of log data. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input log data to the generation AI and have the generation AI apply the analysis method for each type.

[0045] The analysis unit can perform the analysis based on the temporal fluctuation of the log data during the analysis. The analysis unit uses the generation AI to perform the analysis while taking into account the temporal fluctuation of the log data during the analysis. For example, the analysis unit analyzes the fluctuation of the access log for each time period. The analysis unit can also analyze the fluctuation of the error log by day. Furthermore, the analysis unit can analyze the fluctuation of the security log by month. In this way, by taking into account the temporal fluctuation of the log data, a more accurate analysis result can be obtained. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the log data to the generation AI and have the generation AI execute the analysis of the temporal fluctuation.

[0046] The analysis unit can improve the accuracy of the analysis based on the literature related to the log data during the analysis. The analysis unit uses the generation AI to improve the accuracy of the analysis by referring to the literature related to the log data during the analysis. For example, when analyzing a security log, the analysis unit refers to a related security report. Also, when analyzing a system error log, the analysis unit can refer to related technical literature. Furthermore, when analyzing a network traffic log, the analysis unit can refer to related research papers. As a result, the analysis accuracy is improved by referring to the related literature. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the related literature to the generation AI and cause the generation AI to perform the literature reference.

[0047] The extraction unit can improve the accuracy of extraction based on the interrelationships of the log data at the time of extraction. The extraction unit improves the accuracy of extraction by considering the interrelationships of the log data at the time of extraction using the generation AI. For example, extraction is performed by considering the interrelationships between the error log and the access log. Extraction can also be performed by considering the interrelationships between the security log and the system log. Furthermore, extraction can also be performed by considering the interrelationships between the network traffic log and the performance log. As a result, the accuracy of extraction is improved by considering the interrelationships of the log data. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the extraction unit can input the log data to the generation AI and have the generation AI execute an analysis of the interrelationships.

[0048] The extraction unit can extract appropriate information by referring to the user's past query history at the time of extraction. The extraction unit uses the generation AI to extract optimal information by referring to the user's past query history at the time of extraction. For example, related information is extracted based on queries previously searched by the user. Frequently searched information can also be preferentially extracted from the user's past query history. Furthermore, the user's past query history can be analyzed and the most relevant information can be extracted. This makes it possible to extract highly relevant information by referring to the user's past query history. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the extraction unit can input the user's query history to the generation AI and cause the generation AI to refer to the history.

[0049] The extraction unit can perform extraction based on the geographical distribution of the log data at the time of extraction. The extraction unit performs extraction by using the generation AI, taking into consideration the geographical distribution of the log data at the time of extraction. For example, error logs occurring in a specific region can be preferentially extracted. Data with high geographical relevance can also be preferentially extracted. Furthermore, log data from nearby network devices can also be preferentially extracted. In this way, by taking into consideration the geographical distribution of the log data, highly relevant information can be extracted. A part or all of the above-mentioned processing in the extraction unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the extraction unit can input the geographical distribution of the log data to the generation AI and cause the generation AI to perform an analysis of the geographical distribution.

[0050] The extraction unit can improve the accuracy of extraction based on the related literature of the log data at the time of extraction. The extraction unit uses the generation AI to improve the accuracy of extraction by referring to the related literature of the log data at the time of extraction. For example, when extracting a security log, the extraction unit refers to a related security report. Also, when extracting a system error log, the extraction unit can refer to related technical literature. Furthermore, when extracting a network traffic log, the extraction unit can refer to related research papers. As a result, the extraction accuracy is improved by referring to the related literature. A part or all of the above-mentioned processing in the extraction unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the extraction unit can input the related literature to the generation AI and cause the generation AI to execute the literature reference.

[0051] The shaping unit can adjust the level of detail of the shaping based on the importance of the extracted information during shaping. The shaping unit adjusts the level of detail of the shaping based on the importance of the extracted information during shaping using the generation AI. For example, important security information is shaped in detail. Also, normal access information can be shaped concisely. Furthermore, error messages can be shaped to focus on the main points. As a result, important information can be displayed in detail by adjusting the level of detail of the shaping based on the importance of the information. Some or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the extracted information to the generation AI and cause the generation AI to adjust the level of detail of the shaping based on the importance of the information.

[0052] The shaping unit can apply an appropriate shaping method for each type of information during shaping. The shaping unit uses the generation AI to apply different shaping methods for each type of information during shaping. For example, a text shaping method is applied to text information. A numerical shaping method can also be applied to numerical information. Furthermore, a graph shaping method can be applied to graph information. This enables efficient information shaping by applying different shaping methods for each type of information. Some or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input information to the generation AI and cause the generation AI to apply the shaping method for each type.

[0053] The shaping unit can determine the priority of shaping based on the submission date and time of the information at the time of shaping. The shaping unit uses the generation AI to determine the priority of shaping based on the submission date and time of the information at the time of shaping. For example, urgent information is given the highest priority for shaping. Periodic report information can also be given the next priority for shaping. Furthermore, normal information can also be shaped last. In this way, by determining the priority of shaping based on the submission date and time of the information, urgent information can be quickly shaped. A part or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the submission date and time of the information to the generation AI and have the generation AI execute the determination of the priority.

[0054] The shaping unit can adjust the order of shaping based on the relevance of information during shaping. The shaping unit adjusts the order of shaping based on the relevance of information during shaping using the generation AI. For example, highly relevant information is given priority for shaping. Also, information with low relevance can be shaped later. Furthermore, the order of shaping can be dynamically adjusted according to the relevance of information. As a result, by adjusting the order of shaping based on the relevance of information, highly relevant information can be displayed with priority. Part or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the relevance of information to the generation AI and cause the generation AI to adjust the order.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The log data analysis system can further include a prediction unit. The prediction unit analyzes past log data and predicts future traffic and error occurrences. For example, if access tends to be concentrated during a specific time period, measures to reduce the load on the server during that time period are proposed. Also, if a specific error message occurs frequently, the cause can be identified and measures can be taken in advance. Furthermore, the prediction unit can predict traffic fluctuations according to seasons and events and optimize resources. In this way, the prediction unit can improve the stability of the system by predicting future traffic and error occurrences and taking measures in advance.

[0057] The log data analysis system may further include a notification unit. The notification unit notifies the user in real time based on the analysis result. For example, if a critical error message is detected, an alert is immediately sent to the user. In addition, a report may be generated periodically based on a specific condition and sent to the user. Furthermore, the notification unit may notify in different ways, such as by email, SMS, or push notification, depending on the user's settings. In this way, the notification unit provides important information to the user in real time, enabling a quick response.

[0058] The log data analysis system may further include a filtering unit. The filtering unit filters the log data based on conditions specified by the user. For example, the filtering unit may extract only access logs from a specific IP address. Log data within a specific period of time may also be extracted. Furthermore, the filtering unit may extract log data related to a specific error message or event. In this way, the filtering unit quickly extracts information required by the user and supports efficient data analysis.

[0059] The log data analysis system may further include a learning unit. The learning unit learns the user's operation history and query history, and uses the information for future searches and analyses. For example, the learning unit may store queries that the user frequently searches for, and provide an auto-completion function for future searches. The learning unit may also suggest related information based on the results of analyses performed by the user in the past. Furthermore, the learning unit may analyze the user's operation patterns and suggest optimal operating procedures. In this way, the learning unit learns the user's operation history and query history, and makes future searches and analyses more efficient.

[0060] The log data analysis system may further include a dashboard section. The dashboard section provides an interface for visually displaying the analysis results. For example, the real-time traffic situation may be displayed in graphs or charts. Also, the occurrence of error messages may be displayed in chronological order. Furthermore, the dashboard section may provide a widget that can be customized by the user, allowing the user to check required information at a glance. In this way, the dashboard section visually displays the analysis results, allowing the user to quickly grasp the situation.

[0061] The process flow of the first embodiment will be briefly described below.

[0062] Step 1: The reading unit reads log data obtained from network devices. The log data includes server logs, access logs, error logs, etc. The reading unit uses the generation AI to analyze the format and content of the log data and understand the data structure. For example, the generation AI analyzes the type and format of the log data and recognizes data patterns. Step 2: The analysis unit analyzes the log data read by the reading unit and understands the structure of the data. The analysis unit uses the generation AI to classify and organize information such as error messages and access records. For example, the generation AI analyzes the classification criteria for error message types and access records and organizes the data. Step 3: The extraction unit analyzes the user's query based on the data analyzed by the analysis unit, and extracts the relevant information. The extraction unit uses the generation AI to analyze the query entered by the user in natural language, and extracts the relevant information from the log data. For example, the generation AI analyzes the query using morphological analysis, grammatical analysis, and semantic analysis, and extracts the relevant information. Step 4: The formatting unit formats the information extracted by the extraction unit. The formatting unit uses the generation AI to display the extracted information in a table format according to a specific format. For example, the generation AI formats the data according to CSV format, JSON format, or a specific table format. The formatting unit can also graph the extracted information. For example, the generation AI displays the data in the format of a bar graph, line graph, pie chart, etc.

[0063] (Example 2) The log data analysis system according to the embodiment of the present invention is a system that easily searches for desired information and formats data by having a generation AI read and analyze log data acquired from a network device. This log data analysis system has a generation AI read log data acquired from a network device. The generation AI analyzes the format and contents of the log data and understands the structure of the data. Next, when a user searches for desired information, the user inputs a query in natural language to the generation AI. The generation AI analyzes this query and extracts the relevant information from the log data. Furthermore, the generation AI formats the extracted information in a format that is easy for the user to view. This makes the search and formatting of log data more efficient, and significantly reduces the user's work time. In addition, since it can handle data formats that differ from vendor to vendor, it is highly versatile. For example, log data acquired from network devices of different vendors can be managed in a unified manner and displayed in a unified format. First, the log data acquired from the network device is read into the generation AI. At this time, the generation AI analyzes the format and contents of the log data and understands the structure of the data. For example, the log data includes error messages and access records, and the generation AI classifies and organizes this information. Next, when a user searches for the information they want, they input a query in natural language to the generation AI. For example, they input a query such as "I want to search for access logs from a specific IP address." The generation AI analyzes this query and extracts the relevant information from the log data. The generation AI then formats the extracted information in a format that is easy for the user to view. For example, data can be displayed in a table format or graphed according to a specific format. This allows users to quickly and easily obtain the information they need. This mechanism makes the search and formatting of log data more efficient, significantly reducing the user's work time. It is also highly versatile because it can handle data formats that differ from vendor to vendor. For example, log data obtained from network devices from different vendors can be managed in a centralized manner and displayed in a unified format. This allows the log data analysis system to significantly reduce the user's work time.

[0064] The log data analysis system according to the embodiment includes a reading unit, an analysis unit, an extraction unit, and a formatting unit. The reading unit reads log data acquired from a network device. The log data includes, for example, a server log, an access log, an error log, and the like, but is not limited to such examples. The reading unit uses a generation AI to analyze the format and contents of the log data and understand the structure of the data. For example, the generation AI analyzes the type and format of the log data and recognizes the pattern of the data. The analysis unit analyzes the log data read by the reading unit and understands the structure of the data. The analysis unit uses a generation AI to classify and organize information such as error messages and access records. For example, the generation AI analyzes the classification criteria of the types of error messages and the access records and organizes the data. The extraction unit analyzes the user's query based on the data analyzed by the analysis unit and extracts the relevant information. The extraction unit uses a generation AI to analyze a query input by a user in natural language and extracts the relevant information from the log data. For example, the generation AI analyzes the query using morphological analysis, grammatical analysis, and semantic analysis, and extracts related information. The shaping unit shapes the information extracted by the extraction unit. The shaping unit uses the generation AI to display the extracted information in a table format according to a specific format. For example, the generation AI shapes the data according to a CSV format, a JSON format, or a specific table format. The shaping unit can also graph the extracted information. For example, the generation AI displays the data in a format such as a bar graph, a line graph, or a pie chart. This allows the log data analysis system according to the embodiment to significantly reduce the user's work time. Some or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the information extracted by the extraction unit to the generation AI and have the generation AI execute the shaping of the information.

[0065] The reading unit reads the log data acquired from the network device. The log data includes, but is not limited to, server logs, access logs, error logs, and the like. The reading unit uses the generation AI to analyze the format and content of the log data and understand the structure of the data. Specifically, the generation AI analyzes the type and format of the log data and recognizes the pattern of the data. For example, the server log records the operation status of the server and error messages, the access log records the user's access history and request details, and the error log records the occurrence status of system errors and failures. The generation AI analyzes these log data and automatically identifies the format and content of each log. Furthermore, the generation AI extracts important information from the log data and lays the foundation for understanding the structure of the data. For example, the generation AI identifies important fields such as the timestamp and IP address of the log data and the code of the error message, and recognizes the pattern of the data based on them. This allows the reading unit to efficiently read a wide variety of log data acquired from the network device and understand the structure of the data. Furthermore, the reading unit can also use the generation AI to perform pre-processing of the log data. For example, by removing noise from the log data and complementing missing data, the subsequent processing of the analysis unit and extraction unit can proceed smoothly. This allows the reading unit to improve the quality of the log data and the performance of the entire system.

[0066] The analysis unit analyzes the log data read by the reading unit and understands the structure of the data. The analysis unit uses the generation AI to classify and organize information such as error messages and access records. Specifically, the generation AI analyzes the classification criteria for the types of error messages and access records and organizes the data. For example, the generation AI analyzes the contents of error messages to identify the types of errors and the causes of occurrence. It also analyzes the access records to understand the user's behavior patterns and access frequency. Furthermore, the generation AI can detect abnormal patterns and trends from the log data. For example, it detects a sudden increase in access during a specific time period or the frequent occurrence of a specific error message, and detects system abnormalities early. This allows the analysis unit to quickly and accurately analyze the read log data and understand the structure of the data. Furthermore, the analysis unit can also perform trend analysis and prediction based on past log data. For example, it analyzes past access logs to predict the increase or decrease in access during a specific period. It also analyzes error logs to predict situations where a specific error is likely to occur. This allows the analysis unit to contribute not only to real-time data analysis but also to future risk management and countermeasure planning. Furthermore, the analysis unit can also use the generation AI to visualize the log data. For example, the frequency of error messages or the distribution of access records can be displayed in graphs and charts to make the data easier to understand. This allows the analysis unit to not only understand the structure of the data, but also provide users with easy-to-understand information through data visualization.

[0067] The extraction unit analyzes the user's query based on the data analyzed by the analysis unit and extracts the relevant information. The extraction unit uses the generation AI to analyze the query entered by the user in natural language and extracts the relevant information from the log data. Specifically, the generation AI analyzes the query using morphological analysis, grammatical analysis, and semantic analysis, and extracts the relevant information. For example, if the user enters "I want to display the error log for a specific time period," the generation AI analyzes the content of the query and extracts the error log for the corresponding time period. Also, if the user enters "I want to display the access record from a specific IP address," the generation AI analyzes the content of the query and extracts the access record from the corresponding IP address. Furthermore, the extraction unit can set complex search conditions by combining multiple queries. For example, if the user enters "I want to display the error log from a specific IP address for a specific time period," the generation AI analyzes the content of the query and extracts the error log that matches the relevant condition. As a result, the extraction unit can quickly and accurately extract the relevant information for the user's query and meet the user's needs. Furthermore, the extraction unit can use the generation AI to resolve ambiguity in queries. For example, if a user inputs "I want to see recent error logs," the generation AI will ask the user for a definition of "recent" and extract the relevant error logs by setting a specific period. This allows the extraction unit to flexibly and appropriately respond to user queries and provide accurate information.

[0068] The formatting unit formats the information extracted by the extraction unit. The formatting unit uses the generation AI to display the extracted information in a table format according to a specific format. Specifically, the generation AI formats the data according to CSV format, JSON format, or a specific table format. For example, the generation AI formats the extracted error log or access record in CSV format so that the user can easily view and analyze it with spreadsheet software. In addition, formatting in JSON format can facilitate data integration with other systems and applications. In addition, the formatting unit can graph the extracted information. For example, the generation AI displays data in the form of a bar graph, line graph, pie chart, etc., making it easier for the user to visually understand the data. In this way, the formatting unit can provide the extracted information in a format that is easy for the user to use and promote understanding of the data. In addition, the formatting unit can automate the data formatting process using the generation AI. For example, the extracted information can be automatically formatted into a specific format and regularly updated data can be provided to the user. In addition, the formatting unit can provide data in a customized format according to the user's request. This allows the formatting unit to provide flexible data according to the user's needs, improving the user's work efficiency. Furthermore, the formatting unit can also use the generative AI to check the quality of the data. For example, it checks the consistency and integrity of the data and detects errors and missing data. This allows the formatting unit to provide the user with high-quality data and highly reliable information.

[0069] The reading unit can analyze the format and contents of the log data and analyze the data structure. The reading unit uses the generation AI to analyze the format and contents of the log data and understand the data structure. For example, the generation AI analyzes the type and format of the log data and recognizes the data pattern. This allows the format and contents of the log data to be analyzed and the data structure to be understood, thereby making subsequent processing more efficient. Some or all of the above-mentioned processing in the reading unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the log data to the generation AI and have the generation AI analyze the format and contents of the data.

[0070] The analysis unit can classify and organize information such as error messages or access records. The analysis unit classifies and organizes information such as error messages and access records using the generation AI. For example, the generation AI analyzes the classification criteria for error messages and access records and organizes the data. This makes it easier to manage data by classifying and organizing information such as error messages and access records. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input data such as error messages and access records to the generation AI and have the generation AI classify and organize the information.

[0071] The extraction unit can analyze a query input by a user in natural language and extract relevant information from the log data. The extraction unit uses a generation AI to analyze a query input by a user in natural language and extract relevant information from the log data. For example, the generation AI analyzes the query using morphological analysis, grammatical analysis, and semantic analysis to extract relevant information. This makes it easier to search by analyzing a query input by a user in natural language and extracting relevant information. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using the generation AI or may be performed without using the generation AI. For example, the extraction unit can input a user's query to the generation AI and have the generation AI execute the extraction of information.

[0072] The shaping unit can display the extracted information in a table format according to a specified format. The shaping unit uses the generation AI to display the extracted information in a table format according to a specific format. For example, the generation AI formats data according to CSV format, JSON format, or a specific table format. As a result, the extracted information is displayed in a table format according to a specific format, thereby improving the visibility of the information. Some or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the information extracted by the extraction unit to the generation AI and have the generation AI perform shaping of the information.

[0073] The shaping unit can display the extracted information as a graph. The shaping unit graphs the extracted information using the generation AI. For example, the generation AI displays data in the form of a bar graph, a line graph, a pie chart, or the like. This makes it easier to visually understand the information by graphing the extracted information. Some or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the information extracted by the extraction unit to the generation AI and cause the generation AI to graph the information.

[0074] The reading unit can estimate the user's emotion and adjust the timing of reading the log data based on the emotion. The reading unit uses the generation AI to estimate the user's emotion and adjust the timing of reading the log data based on the estimated emotion of the user. For example, when the user is stressed, the log data is read quickly to reduce the waiting time. Also, when the user is relaxed, the log data can be read at a normal speed to optimize the system resources. Furthermore, when the user is in a hurry, the log data with a high priority can be adjusted to be read first. In this way, the timing of reading the log data is adjusted according to the user's emotion, thereby reducing the user's stress. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reading unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0075] The reading unit can set a priority order based on the importance of the data when reading the log data. The reading unit uses the generation AI to set a priority order based on the importance of the data when reading the log data. For example, security-related log data is read with the highest priority. Also, the system error log can be read with the next highest priority. Furthermore, the normal access log can be read last. In this way, important data can be quickly acquired by setting a priority order based on the importance of the data. A part or all of the above-mentioned processing in the reading unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the log data to the generation AI and cause the generation AI to set a priority order based on the importance of the data.

[0076] The reading unit can apply an appropriate reading algorithm according to the type of data when reading the log data. The reading unit uses the generation AI to apply different reading algorithms according to the type of data when reading the log data. For example, a high-speed text analysis algorithm is applied to log data in text format. A dedicated binary analysis algorithm can also be applied to log data in binary format. Furthermore, a JSON analysis algorithm can also be applied to log data in JSON format. This enables efficient data reading by applying different reading algorithms according to the type of data. A part or all of the above-mentioned processing in the reading unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the log data to the generation AI and cause the generation AI to apply a reading algorithm according to the type of data.

[0077] The reading unit can estimate the user's emotion and determine the priority of the log data to be read based on the emotion. The reading unit uses the generation AI to estimate the user's emotion and determines the priority of the log data to be read based on the estimated user's emotion. For example, if the user is nervous, important security logs are read with priority. Also, if the user is relaxed, normal access logs can be read with priority. Furthermore, if the user is in a hurry, error logs can be read with priority. This makes it possible to acquire data according to the user's needs by determining the priority of the log data based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reading unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0078] The reading unit can preferentially read highly relevant data based on the geographical location information of the network device when reading the log data. The reading unit uses the generation AI to preferentially read highly relevant data taking into account the geographical location information of the network device when reading the log data. For example, log data from nearby network devices can be preferentially read. Error logs occurring in a specific area can also be preferentially read. Furthermore, data with high geographical relevance can also be preferentially read. As a result, highly relevant data can be quickly acquired by taking into account the geographical location information of the network device. A part or all of the above-mentioned processing in the reading unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the geographical location information of the network device to the generation AI and cause the generation AI to execute setting of the priority order of highly relevant data.

[0079] The reading unit can analyze the operation status of the network device when reading the log data, and read the data at an appropriate timing. The reading unit uses the generation AI to analyze the operation status of the network device when reading the log data, and reads the data at an optimal timing. For example, the log data is read when the network device is under low load. Also, the reading can be delayed when the network device is under high load. Furthermore, the reading timing can be adjusted according to the operation status of the network device. This allows the optimization of system resources by adjusting the data reading timing according to the operation status of the network device. A part or all of the above-mentioned processing in the reading unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reading unit can input the operation status data of the network device to the generation AI, and cause the generation AI to execute data reading at an optimal timing.

[0080] The analysis unit can estimate the user's emotion and adjust the level of detail of the analysis based on the emotion. The analysis unit uses the generation AI to estimate the user's emotion and adjust the level of detail of the analysis based on the estimated user's emotion. For example, when the user is relaxed, a detailed analysis result is provided. Also, when the user is in a hurry, a concise analysis result can be provided. Furthermore, when the user is stressed, only important information can be extracted and provided. In this way, by adjusting the level of detail of the analysis according to the user's emotion, an analysis result according to the user's needs can be provided. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0081] The analysis unit can improve the accuracy of the analysis based on the interrelationships of the log data during the analysis. The analysis unit uses the generation AI to improve the accuracy of the analysis by considering the interrelationships of the log data during the analysis. For example, the analysis unit analyzes the interrelationships between error logs and access logs. The analysis unit can also analyze the interrelationships between security logs and system logs. Furthermore, the analysis unit can analyze the interrelationships between network traffic logs and performance logs. As a result, the analysis accuracy is improved by considering the interrelationships of the log data. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the log data to the generation AI and have the generation AI execute the analysis of the interrelationships.

[0082] The analysis unit can apply an appropriate analysis method for each type of log data during analysis. The analysis unit uses the generation AI to apply different analysis methods for each type of log data during analysis. For example, natural language processing is applied to text logs. A binary analysis method can also be applied to binary logs. Furthermore, a JSON analysis method can be applied to JSON logs. This enables efficient analysis by applying different analysis methods to each type of log data. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input log data to the generation AI and have the generation AI apply the analysis method for each type.

[0083] The analysis unit can estimate the user's emotion and adjust the display method of the analysis result based on the emotion. The analysis unit uses the generation AI to estimate the user's emotion and adjust the display method of the analysis result based on the estimated user's emotion. For example, when the user is nervous, a simple and highly visible display method is provided. When the user is relaxed, a display method including detailed information can be provided. When the user is in a hurry, a display method that focuses on the main points can be provided. This improves the user's visibility by adjusting the display method of the analysis result according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0084] The analysis unit can perform the analysis based on the temporal fluctuation of the log data during the analysis. The analysis unit uses the generation AI to perform the analysis while taking into account the temporal fluctuation of the log data during the analysis. For example, the analysis unit analyzes the fluctuation of the access log for each time period. The analysis unit can also analyze the fluctuation of the error log by day. Furthermore, the analysis unit can analyze the fluctuation of the security log by month. In this way, by taking into account the temporal fluctuation of the log data, a more accurate analysis result can be obtained. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the log data to the generation AI and have the generation AI execute the analysis of the temporal fluctuation.

[0085] The analysis unit can improve the accuracy of the analysis based on the literature related to the log data during the analysis. The analysis unit uses the generation AI to improve the accuracy of the analysis by referring to the literature related to the log data during the analysis. For example, when analyzing a security log, the analysis unit refers to a related security report. Also, when analyzing a system error log, the analysis unit can refer to related technical literature. Furthermore, when analyzing a network traffic log, the analysis unit can refer to related research papers. As a result, the analysis accuracy is improved by referring to the related literature. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the related literature to the generation AI and cause the generation AI to perform the literature reference.

[0086] The extraction unit can estimate the user's emotion and determine the priority of information to be extracted based on the emotion. The extraction unit estimates the user's emotion using the generation AI and determines the priority of information to be extracted based on the estimated user's emotion. For example, if the user is nervous, important security information is extracted with priority. Also, if the user is relaxed, normal access information can be extracted with priority. Furthermore, if the user is in a hurry, error messages can be extracted with priority. This makes it possible to provide information according to the user's needs by determining the priority of information based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the extraction unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the extraction unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0087] The extraction unit can improve the accuracy of extraction based on the interrelationships of the log data at the time of extraction. The extraction unit improves the accuracy of extraction by considering the interrelationships of the log data at the time of extraction using the generation AI. For example, extraction is performed by considering the interrelationships between the error log and the access log. Extraction can also be performed by considering the interrelationships between the security log and the system log. Furthermore, extraction can also be performed by considering the interrelationships between the network traffic log and the performance log. As a result, the accuracy of extraction is improved by considering the interrelationships of the log data. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the extraction unit can input the log data to the generation AI and have the generation AI execute an analysis of the interrelationships.

[0088] The extraction unit can extract appropriate information by referring to the user's past query history at the time of extraction. The extraction unit uses the generation AI to extract optimal information by referring to the user's past query history at the time of extraction. For example, related information is extracted based on queries previously searched by the user. Frequently searched information can also be preferentially extracted from the user's past query history. Furthermore, the user's past query history can be analyzed and the most relevant information can be extracted. This makes it possible to extract highly relevant information by referring to the user's past query history. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the extraction unit can input the user's query history to the generation AI and cause the generation AI to refer to the history.

[0089] The extraction unit can estimate the user's emotion and adjust the display method of the information to be extracted based on the emotion. The extraction unit uses the generation AI to estimate the user's emotion and adjust the display method of the information to be extracted based on the estimated user's emotion. For example, when the user is nervous, a simple and highly visible display method is provided. Also, when the user is relaxed, a display method including detailed information can be provided. Furthermore, when the user is in a hurry, a display method that focuses on the main points can be provided. This improves visibility by adjusting the display method of the information according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the extraction unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the extraction unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0090] The extraction unit can perform extraction based on the geographical distribution of the log data at the time of extraction. The extraction unit performs extraction by using the generation AI, taking into consideration the geographical distribution of the log data at the time of extraction. For example, error logs occurring in a specific region can be preferentially extracted. Data with high geographical relevance can also be preferentially extracted. Furthermore, log data from nearby network devices can also be preferentially extracted. In this way, by taking into consideration the geographical distribution of the log data, highly relevant information can be extracted. A part or all of the above-mentioned processing in the extraction unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the extraction unit can input the geographical distribution of the log data to the generation AI and cause the generation AI to perform an analysis of the geographical distribution.

[0091] The extraction unit can improve the accuracy of extraction based on the related literature of the log data at the time of extraction. The extraction unit uses the generation AI to improve the accuracy of extraction by referring to the related literature of the log data at the time of extraction. For example, when extracting a security log, the extraction unit refers to a related security report. Also, when extracting a system error log, the extraction unit can refer to related technical literature. Furthermore, when extracting a network traffic log, the extraction unit can refer to related research papers. As a result, the extraction accuracy is improved by referring to the related literature. A part or all of the above-mentioned processing in the extraction unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the extraction unit can input the related literature to the generation AI and cause the generation AI to execute the literature reference.

[0092] The shaping unit can estimate the user's emotion and adjust the format of the information to be shaped based on the emotion. The shaping unit uses the generation AI to estimate the user's emotion and adjust the format of the information to be shaped based on the estimated user's emotion. For example, when the user is nervous, the information is shaped in a simple and highly visible format. When the user is relaxed, the information can be shaped in a format including detailed information. Furthermore, when the user is in a hurry, the information can be shaped in a format that focuses on the main points. This improves visibility by adjusting the format of the information according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the shaping unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0093] The shaping unit can adjust the level of detail of the shaping based on the importance of the extracted information during shaping. The shaping unit adjusts the level of detail of the shaping based on the importance of the extracted information during shaping using the generation AI. For example, important security information is shaped in detail. Also, normal access information can be shaped concisely. Furthermore, error messages can be shaped to focus on the main points. As a result, important information can be displayed in detail by adjusting the level of detail of the shaping based on the importance of the information. Some or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the extracted information to the generation AI and cause the generation AI to adjust the level of detail of the shaping based on the importance of the information.

[0094] The shaping unit can apply an appropriate shaping method for each type of information during shaping. The shaping unit uses the generation AI to apply different shaping methods for each type of information during shaping. For example, a text shaping method is applied to text information. A numerical shaping method can also be applied to numerical information. Furthermore, a graph shaping method can be applied to graph information. This enables efficient information shaping by applying different shaping methods for each type of information. Some or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input information to the generation AI and cause the generation AI to apply the shaping method for each type.

[0095] The shaping unit can estimate the user's emotion and adjust the display method of the information to be shaped based on the emotion. The shaping unit uses the generation AI to estimate the user's emotion and adjust the display method of the information to be shaped based on the estimated user's emotion. For example, when the user is nervous, a simple and highly visible display method is provided. Also, when the user is relaxed, a display method including detailed information can be provided. Furthermore, when the user is in a hurry, a display method that focuses on the main points can be provided. This improves visibility by adjusting the display method of the information according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the shaping unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0096] The shaping unit can determine the priority of shaping based on the submission date and time of the information at the time of shaping. The shaping unit uses the generation AI to determine the priority of shaping based on the submission date and time of the information at the time of shaping. For example, urgent information is given the highest priority for shaping. Periodic report information can also be given the next priority for shaping. Furthermore, normal information can also be shaped last. In this way, by determining the priority of shaping based on the submission date and time of the information, urgent information can be quickly shaped. A part or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the submission date and time of the information to the generation AI and have the generation AI execute the determination of the priority.

[0097] The shaping unit can adjust the order of shaping based on the relevance of information during shaping. The shaping unit adjusts the order of shaping based on the relevance of information during shaping using the generation AI. For example, highly relevant information is given priority for shaping. Also, information with low relevance can be shaped later. Furthermore, the order of shaping can be dynamically adjusted according to the relevance of information. As a result, by adjusting the order of shaping based on the relevance of information, highly relevant information can be displayed with priority. Part or all of the above-mentioned processing in the shaping unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the shaping unit can input the relevance of information to the generation AI and cause the generation AI to adjust the order.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] The log data analysis system can further include a prediction unit. The prediction unit analyzes past log data and predicts future traffic and error occurrences. For example, if access tends to be concentrated during a specific time period, measures to reduce the load on the server during that time period are proposed. Also, if a specific error message occurs frequently, the cause can be identified and measures can be taken in advance. Furthermore, the prediction unit can predict traffic fluctuations according to seasons and events and optimize resources. In this way, the prediction unit can improve the stability of the system by predicting future traffic and error occurrences and taking measures in advance.

[0100] The log data analysis system may further include a notification unit. The notification unit notifies the user in real time based on the analysis result. For example, if a critical error message is detected, an alert is immediately sent to the user. In addition, a report may be generated periodically based on a specific condition and sent to the user. Furthermore, the notification unit may notify in different ways, such as by email, SMS, or push notification, depending on the user's settings. In this way, the notification unit provides important information to the user in real time, enabling a quick response.

[0101] The log data analysis system may further include a filtering unit. The filtering unit filters the log data based on conditions specified by the user. For example, the filtering unit may extract only access logs from a specific IP address. Log data within a specific period of time may also be extracted. Furthermore, the filtering unit may extract log data related to a specific error message or event. In this way, the filtering unit quickly extracts information required by the user and supports efficient data analysis.

[0102] The log data analysis system may further include a learning unit. The learning unit learns the user's operation history and query history, and uses the information for future searches and analyses. For example, the learning unit may store queries that the user frequently searches for, and provide an auto-completion function for future searches. The learning unit may also suggest related information based on the results of analyses performed by the user in the past. Furthermore, the learning unit may analyze the user's operation patterns and suggest optimal operating procedures. In this way, the learning unit learns the user's operation history and query history, and makes future searches and analyses more efficient.

[0103] The log data analysis system may further include a dashboard section. The dashboard section provides an interface for visually displaying the analysis results. For example, the real-time traffic situation may be displayed in graphs or charts. Also, the occurrence of error messages may be displayed in chronological order. Furthermore, the dashboard section may provide a widget that can be customized by the user, allowing the user to check required information at a glance. In this way, the dashboard section visually displays the analysis results, allowing the user to quickly grasp the situation.

[0104] The analysis unit can estimate the user's emotions and adjust the level of detail of the analysis results based on the estimated user's emotions. For example, if the user is feeling stressed, a concise analysis result that focuses on the main points can be provided. If the user is relaxed, a detailed analysis result can be provided. Furthermore, if the user is in a hurry, only important information can be extracted and provided. In this way, the analysis unit can adjust the level of detail of the analysis results according to the user's emotions and provide information that meets the user's needs.

[0105] The extraction unit can estimate the user's emotions and determine the priority of information to be extracted based on the estimated user's emotions. For example, if the user is nervous, important security information can be extracted with priority. Also, if the user is relaxed, normal access information can be extracted with priority. Furthermore, if the user is in a hurry, error messages can be extracted with priority. In this way, the extraction unit can determine the priority of information based on the user's emotions and provide information according to the user's needs.

[0106] The shaping unit can estimate the user's emotions and adjust the format of the information to be shaped based on the estimated user's emotions. For example, if the user is nervous, the information is shaped in a simple, highly visible format. If the user is relaxed, the information can be shaped in a format that includes detailed information. Furthermore, if the user is in a hurry, the information can be shaped in a format that focuses on the main points. In this way, the shaping unit can adjust the format of the information according to the user's emotions and improve visibility.

[0107] The reading unit can estimate the user's emotions and adjust the timing of reading the log data based on the estimated user's emotions. For example, when the user is stressed, the log data can be read quickly to reduce waiting time. When the user is relaxed, the log data can be read at a normal speed to optimize system resources. Furthermore, when the user is in a hurry, the reading unit can adjust the timing of reading the log data to be read first. This allows the reading unit to adjust the timing of reading the log data according to the user's emotions and reduce the user's stress.

[0108] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user's emotions. For example, if the user is nervous, a simple and highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the main points can be provided. In this way, the analysis unit can adjust the display method of the analysis results according to the user's emotions and improve visibility for the user.

[0109] The process flow of the second embodiment will be briefly described below.

[0110] Step 1: The reading unit reads log data obtained from network devices. The log data includes server logs, access logs, error logs, etc. The reading unit uses the generation AI to analyze the format and content of the log data and understand the data structure. For example, the generation AI analyzes the type and format of the log data and recognizes data patterns. Step 2: The analysis unit analyzes the log data read by the reading unit and understands the structure of the data. The analysis unit uses the generation AI to classify and organize information such as error messages and access records. For example, the generation AI analyzes the classification criteria for error message types and access records and organizes the data. Step 3: The extraction unit analyzes the user's query based on the data analyzed by the analysis unit, and extracts the relevant information. The extraction unit uses the generation AI to analyze the query entered by the user in natural language, and extracts the relevant information from the log data. For example, the generation AI analyzes the query using morphological analysis, grammatical analysis, and semantic analysis, and extracts the relevant information. Step 4: The formatting unit formats the information extracted by the extraction unit. The formatting unit uses the generation AI to display the extracted information in a table format according to a specific format. For example, the generation AI formats the data according to CSV format, JSON format, or a specific table format. The formatting unit can also graph the extracted information. For example, the generation AI displays the data in the format of a bar graph, line graph, pie chart, etc.

[0111] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0112] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0113] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0114] For example, the reading unit is realized by either the smart device 14 or the data processing device 12. For example, the control unit 46A of the smart device 14 can read log data acquired from a network device. The analysis unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and uses a generation AI to analyze the format and contents of the log data and understand the structure of the data. The extraction unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes a user's query and extracts relevant information. The shaping unit is realized by, for example, the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and shapes the extracted information according to a specific format. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 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.

[0117] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0118] 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.

[0119] 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 the voice according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0121] 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 performed in a secure state.

[0122] Fig. 4 shows an example of 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.

[0123] 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.

[0124] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0125] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0126] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0127] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0128] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0129] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0130] For example, the reading unit is realized by either the smart glasses 214 or the data processing device 12. For example, the control unit 46A of the smart glasses 214 can read log data acquired from a network device. The analysis unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and uses a generation AI to analyze the format and contents of the log data and understand the structure of the data. The extraction unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes a user's query and extracts relevant information. The shaping unit is realized by, for example, the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and shapes the extracted information according to a specific format. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 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.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0134] 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.

[0135] 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 the voice according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0137] 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 performed in a secure state.

[0138] 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.

[0139] 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.

[0140] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0141] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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.

[0142] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0143] 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 voice indicating a user input for 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.

[0144] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0145] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0146] For example, the reading unit is realized by either the headset type terminal 314 or the data processing device 12. For example, the control unit 46A of the headset type terminal 314 can read log data acquired from a network device. The analysis unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and uses a generation AI to analyze the format and contents of the log data and understand the structure of the data. The extraction unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes a user's query and extracts relevant information. The shaping unit is realized by, for example, the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and shapes the extracted information according to a specific format. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0150] 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.

[0151] 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 the voice according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0153] 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 performed in a secure state.

[0154] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0155] 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.

[0156] 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.

[0157] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0158] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0159] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0160] 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 a voice indicating a user input for 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.

[0161] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0162] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0163] For example, the reading unit is realized by either the robot 414 or the data processing device 12. For example, the control unit 46A of the robot 414 can read log data acquired from a network device. The analysis unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and uses a generation AI to analyze the format and contents of the log data and understand the structure of the data. The extraction unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes a user's query and extracts the relevant information. The shaping unit is realized by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and shapes the extracted information according to a specific format. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0164] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0165] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0166] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0167] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0168] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0169] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0171] 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.

[0172] 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 Universal Serial Bus (USB) 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.

[0173] In addition, 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 upon request from the data processing device 12.

[0174] 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.

[0175] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0176] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0177] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0178] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0179] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0180] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0181] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0182] (Appendix 1) A reading unit that reads log data; an analysis unit that analyzes the log data read by the reading unit and analyzes a structure of the data; an extraction unit that analyzes a user's query based on the data analyzed by the analysis unit and extracts related information; A formatting unit that formats the information extracted by the extraction unit. A system characterized by: (Appendix 2) The reading unit is Analyze the format and content of log data and analyze the data structure 2. The system of claim 1, (Appendix 3) The analysis unit is Categorize and organize information in error messages or access logs 2. The system of claim 1, (Appendix 4) The extraction unit is Analyze queries entered by users in natural language and extract relevant information from log data 2. The system of claim 1, (Appendix 5) The shaping unit includes: Display the extracted information in a table format according to a specified format 2. The system of claim 1, (Appendix 6) The shaping unit includes: Displaying extracted information as a graph 2. The system of claim 1, (Appendix 7) The reading unit is Infer user emotions and adjust the timing of log data loading based on those emotions 2. The system of claim 1, (Appendix 8) The reading unit is Prioritize log data as it loads based on its importance 2. The system of claim 1, (Appendix 9) The reading unit is When loading log data, apply appropriate loading algorithms depending on the type of data 2. The system of claim 1, (Appendix 10) The reading unit is Infer user sentiment and prioritize which log data to load based on that sentiment 2. The system of claim 1, (Appendix 11) The reading unit is When loading log data, the most relevant data is loaded first based on the geographic location of the network device. 2. The system of claim 1, (Appendix 12) The reading unit is When reading log data, the operating status of network devices is analyzed and data is read at the appropriate time. 2. The system of claim 1, (Appendix 13) The analysis unit is Infer user sentiment and adjust analysis detail based on that sentiment 2. The system of claim 1, (Appendix 14) The analysis unit is During analysis, improve accuracy of analysis based on correlation of log data 2. The system of claim 1, (Appendix 15) The analysis unit is During analysis, apply appropriate analysis techniques for each type of log data. 2. The system of claim 1, (Appendix 16) The analysis unit is Infer user emotions and adjust how analysis results are displayed based on those emotions 2. The system of claim 1, (Appendix 17) The analysis unit is When analyzing, the analysis is performed based on the time fluctuation of the log data. 2. The system of claim 1, (Appendix 18) The analysis unit is During analysis, improve the accuracy of the analysis based on related literature of the log data 2. The system of claim 1, (Appendix 19) The extraction unit is Estimate the user's emotions and prioritize the information to be extracted based on those emotions. 2. The system of claim 1, (Appendix 20) The extraction unit is During extraction, improve extraction accuracy based on correlations in log data 2. The system of claim 1, (Appendix 21) The extraction unit is At extraction time, look at the user's past query history to extract the right information 2. The system of claim 1, (Appendix 22) The extraction unit is Infer the user's emotions and adjust the way information is displayed based on those emotions 2. The system of claim 1, (Appendix 23) The extraction unit is At extraction time, extraction is based on the geographic distribution of log data 2. The system of claim 1, (Appendix 24) The extraction unit is During extraction, improve extraction accuracy based on relevant literature in log data 2. The system of claim 1, (Appendix 25) The shaping unit includes: Infer the user's emotions and adjust the format of the information to be formatted based on those emotions 2. The system of claim 1, (Appendix 26) The shaping unit includes: During formatting, adjust the level of formatting detail based on the importance of the extracted information 2. The system of claim 1, (Appendix 27) The shaping unit includes: When formatting, use the appropriate formatting technique for each type of information. 2. The system of claim 1, (Appendix 28) The shaping unit includes: Infer the user's emotions and adjust how information is displayed based on those emotions 2. The system of claim 1, (Appendix 29) The shaping unit includes: During formatting, prioritize formatting based on the submission date and time of the information 2. The system of claim 1, (Appendix 30) The shaping unit includes: When formatting, adjust the formatting order based on the relevance of the information 2. The system of claim 1, [Explanation of symbols]

[0183] 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 reading unit that reads log data; an analysis unit that analyzes the log data read by the reading unit and analyzes a structure of the data; an extraction unit that analyzes a user's query based on the data analyzed by the analysis unit and extracts related information; A formatting unit that formats the information extracted by the extraction unit. A system characterized by:

2. The reading unit is Analyze the format and content of log data and analyze the data structure 2. The system of claim 1 .

3. The analysis unit is Classify and organize information in error messages or access logs 2. The system of claim 1 .

4. The extraction unit is Analyze queries entered by users in natural language and extract relevant information from log data 2. The system of claim 1 .

5. The shaping unit includes: The information extracted by the extracting unit is displayed in a table format according to a specified format.

2. The system of claim 1 .

6. The shaping unit includes: The information extracted by the extraction unit is displayed as a graph.

2. The system of claim 1 .

7. The reading unit is Infer user emotions and adjust the timing of log data loading based on those emotions 2. The system of claim 1 .

8. The reading unit is Prioritize log data as it loads based on its importance 2. The system of claim 1 .

9. The reading unit is When loading log data, apply appropriate loading algorithms depending on the type of data 2. The system of claim 1 .

10. The reading unit is Infer user sentiment and prioritize which log data to load based on that sentiment 2. The system of claim 1 .

Images