System

Abstract

An object of a system according to an embodiment is to perform data processing efficiently and with high accuracy.SOLUTION: A system includes a data preprocessing part, a data conversion part, and a feature quantity engineering part. The data preprocessing unit preprocesses data. The data conversion unit performs data conversion based on the data preprocessed by the data preprocessing unit. The feature quantity engineering unit performs feature quantity engineering based on the data converted by the data conversion unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology requires data scientists to spend a lot of time processing data, resulting in low efficiency in obtaining highly accurate analytical data.

[0005] The system according to the embodiment aims to process data efficiently and with high precision. [Means for solving the problem]

[0006] The system according to the embodiment includes a data preprocessing unit, a data conversion unit, and a feature engineering unit. The data preprocessing unit preprocesses data. The data conversion unit performs data conversion based on the data preprocessed by the data preprocessing unit. The feature engineering unit performs feature engineering based on the data converted by the data conversion unit. [Effects of the Invention]

[0007] The system according to the embodiment can process data efficiently and with high precision. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's 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 read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The data processing system according to an embodiment of the present invention is a system that uses generative AI to process data quickly and accurately. As a result, the data processing system improves the accuracy of data processing in the work of data scientists, and can have a significant impact on the indicators of subsequent analytical models.

[0029] A data processing system according to an embodiment includes a data preprocessing unit, a data conversion unit, and a feature engineering unit. The data preprocessing unit receives raw data input by a data scientist, completes missing values, detects and corrects outliers, and normalizes the data. For example, the data preprocessing unit receives as input a prompt containing instructions from the generation AI, such as "complete missing values ​​with the average value and detect and correct outliers," and preprocesses the data based on the instructions. The data conversion unit encodes categorical data, decomposes temporal data, and vectorizes text data based on the preprocessed data. For example, the data conversion unit receives as input a prompt containing instructions from the generation AI, such as "perform one-hot encoding of categorical data and decompose temporal data into years, months, days, and hours," and converts the data based on the instructions. The feature engineering unit performs the necessary data conversion and feature engineering. For example, the feature engineering unit receives as input a prompt containing instructions from the generation AI, such as "extract specific features and generate new features," and performs feature engineering based on the instructions. This enables rapid and accurate data preprocessing, conversion, and feature engineering.

[0030] The data preprocessing unit understands the context of the data and can complement and correct missing values ​​and outliers based on that context. In the data preprocessing unit, for example, the generative AI analyzes the context of the data and identifies the cause of the missing value. For example, if a specific sensor fails and data is missing, the data from that sensor is complemented using data from other sensors. The generative AI understands the context of the data and uses an algorithm to complement and correct missing values ​​and outliers. For example, the generative AI complements missing values ​​and corrects outliers based on the context and related information of the data. In this way, data quality is improved by understanding the context of the data and complementing and correcting missing values ​​and outliers.

[0031] The data preprocessing unit can evaluate the origin and reliability of data and automatically exclude unreliable data. For example, the generation AI in the data preprocessing unit analyzes the origin of data and identifies unreliable data sources. For example, if data from a specific sensor or database lacks consistency, the data is excluded. The generation AI uses an algorithm to evaluate the reliability of data and automatically exclude unreliable data. For example, the generation AI scores reliability based on the origin of the data and the generation process, and excludes unreliable data. This improves data quality by automatically excluding unreliable data.

[0032] The data preprocessing unit can also perform preprocessing on different data formats. In the data preprocessing unit, for example, the generation AI analyzes image data and performs preprocessing. For example, it automatically performs image noise removal and resolution adjustment. The generation AI analyzes audio data and performs preprocessing. For example, it automatically performs audio noise removal and volume normalization. The generation AI analyzes text data and performs preprocessing. For example, it automatically performs text normalization and deletion of unnecessary characters. This makes it possible to handle data diversity by performing preprocessing on different data formats.

[0033] The data preprocessing section can provide feedback to data scientists in real time, allowing them to check the results of preprocessing immediately. For example, the data preprocessing section has a generative AI that provides feedback on the results of preprocessing to data scientists in real time, allowing them to check the results immediately. For example, it displays the progress and results of preprocessing on a dashboard. The generative AI builds a system for providing feedback on the results of preprocessing in real time. For example, it updates the results of preprocessing in real time and notifies the data scientist. The generative AI provides an interface that allows the results of preprocessing to be checked immediately. For example, it visualizes the results of preprocessing in graphs and charts and provides them to the data scientist. This allows data scientists to check the results of preprocessing in real time, improving their work efficiency.

[0034] The data conversion unit can automatically detect data correlations and propose the optimal conversion method. In the data conversion unit, for example, the generation AI analyzes data correlations and proposes the optimal conversion method. For example, it generates new features by combining highly correlated variables. The generation AI uses an algorithm to automatically detect data correlations. For example, the generation AI evaluates data correlations based on correlation coefficients and covariances. The generation AI builds a system to propose the optimal conversion method. For example, the generation AI selects the optimal conversion method based on data correlations and proposes it to a data scientist. In this way, data quality is improved by automatically detecting data correlations and proposing the optimal conversion method.

[0035] The data conversion unit can refer to past data analysis results and automatically generate the most effective features. In the data conversion unit, for example, the generation AI refers to past data analysis results and automatically generates the most effective features. For example, it generates new features based on past success stories. The generation AI builds a system for referring to past data analysis results. For example, the generation AI selects the most effective features based on past analysis reports and databases. The generation AI uses an algorithm for automatically generating the most effective features. For example, the generation AI proposes a specific method for generating new features based on past data analysis results. In this way, the quality of data is improved by referring to past data analysis results and automatically generating the most effective features.

[0036] The data conversion unit can develop general-purpose conversion methods that can be applied to data from different industries and fields. In the data conversion unit, for example, the generation AI analyzes data from different industries and fields and develops general-purpose conversion methods. For example, it proposes a conversion method that can be applied to both financial data and medical data. The generation AI builds a system for analyzing data from different industries and fields. For example, the generation AI develops an industry-wide conversion algorithm and applies it to data from different industries and fields. The generation AI uses an algorithm to develop a general-purpose conversion method. For example, the generation AI proposes a general-purpose conversion method based on data from different industries and fields. This makes it possible to deal with data diversity by developing a general-purpose conversion method that can be applied to data from different industries and fields.

[0037] The data transformation unit can visualize the data when performing data transformation and feature engineering and provide the results in a visually easy-to-understand format. For example, the data transformation unit causes the generation AI to visualize the results of data transformation and feature engineering and provide them in a visually easy-to-understand format. For example, the data transformation unit displays the results using graphs and charts. The generation AI builds a system for visualizing the results of data transformation and feature engineering. For example, the generation AI updates the data transformation results in real time and provides them visually to data scientists. The generation AI provides an interface for providing the results in a visually easy-to-understand format. For example, the generation AI visualizes the data transformation results in graphs and charts and provides them to data scientists. This improves the work efficiency of data scientists by providing the results of data transformation and feature engineering in a visually easy-to-understand format.

[0038] The data integration unit can automatically check the consistency of data when integrating data and make correction suggestions if there are any inconsistencies. In the data integration unit, for example, the generation AI checks the consistency of data when integrating data and makes correction suggestions if there are any inconsistencies. For example, if data from different data sources does not match, the cause is identified and corrected. The generation AI uses an algorithm to automatically check the consistency of data. For example, the generation AI evaluates the consistency based on data consistency checks and inconsistency detection methods. The generation AI builds a system to make correction suggestions if there are any inconsistencies. For example, the generation AI identifies inconsistencies in the data and suggests how to correct them. In this way, the quality of data is improved by automatically checking consistency when integrating data and making correction suggestions if there are any inconsistencies.

[0039] The data integration unit can try different aggregation methods when aggregating data and automatically select the most effective aggregation result. In the data integration unit, for example, the generation AI tries different aggregation methods and automatically selects the most effective aggregation result. For example, it compares aggregation methods such as the mean, median, and mode. The generation AI uses an algorithm to try different aggregation methods. For example, the generation AI selects the most effective aggregation result based on the type of aggregation method and the method tried. The generation AI builds a system for automatically selecting the most effective aggregation result. For example, the generation AI compares different aggregation methods and selects the most effective aggregation result. In this way, by trying different aggregation methods and automatically selecting the most effective aggregation result, the quality of the data is improved.

[0040] The data integration unit can integrate data from different data sources in real time and provide aggregated results instantly. In the data integration unit, for example, the generation AI integrates data from different data sources in real time and provides aggregated results instantly. For example, it combines data from multiple databases in real time. The generation AI builds a system for integrating data from different data sources in real time. For example, the generation AI integrates data in real time based on the frequency of data updates and the timing of feedback provision. The generation AI provides an interface for providing aggregated results instantly. For example, the generation AI displays aggregated results updated in real time on a dashboard. This improves data quality by integrating data from different data sources in real time and providing aggregated results instantly.

[0041] When integrating and aggregating data, the data integration unit can visualize the data and provide the results in a visually easy-to-understand format. For example, the data integration unit uses the generation AI to visualize the results of data integration and aggregation and provide them in a visually easy-to-understand format. For example, the results are displayed using graphs and charts. The generation AI builds a system for visualizing the results of data integration and aggregation. For example, the generation AI updates the data integration results in real time and provides them visually to data scientists. The generation AI provides an interface for providing the results in a visually easy-to-understand format. For example, the generation AI visualizes the data integration results in graphs and charts and provides them to data scientists. This improves the work efficiency of data scientists by providing the results of data integration and aggregation in a visually easy-to-understand format.

[0042] The data verification unit can evaluate the reliability of data and automatically exclude low-reliability data in data quality checks. In the data verification unit, for example, the generation AI evaluates the reliability of data and automatically excludes low-reliability data. For example, it scores reliability based on the origin and consistency of the data. The generation AI uses an algorithm to evaluate the reliability of data. For example, the generation AI evaluates reliability based on the origin and generation process of the data. The generation AI builds a system to automatically exclude low-reliability data. For example, the generation AI identifies low-reliability data and suggests a method for excluding it. In this way, the quality of data is improved by evaluating the reliability of data and automatically excluding low-reliability data.

[0043] The data verification unit can also perform quality checks on different data formats. In the data verification unit, for example, the generation AI analyzes image data and performs a quality check. For example, it evaluates the image resolution and noise level. The generation AI analyzes audio data and performs a quality check. For example, it evaluates the audio noise level and volume normalization. The generation AI analyzes text data and performs a quality check. For example, it evaluates text normalization and the deletion of unnecessary characters. This allows quality checks to be performed on different data formats, making it possible to handle data diversity.

[0044] The data verification unit can provide feedback to data scientists in real time when verifying data and checking quality, allowing them to check the verification results immediately. For example, the data verification unit may have the generation AI provide feedback on the results of data verification and quality checks to data scientists in real time, allowing them to check the results immediately. For example, the generation AI may display the verification results on a dashboard. The generation AI may build a system for providing feedback on the results of data verification and quality checks in real time. For example, the generation AI may update the verification results in real time and notify the data scientist. The generation AI may provide an interface that allows the verification results to be checked immediately. For example, the generation AI may visualize the verification results in graphs or charts and provide them to the data scientist. This improves the work efficiency of data scientists by allowing them to check the results of data verification and quality checks in real time.

[0045] When outputting highly accurate analytical data, the data output unit can refer to past analysis results and propose the most effective output method. In the data output unit, for example, the generation AI refers to past analysis results and proposes the most effective output method. For example, it selects the optimal output method based on past success stories. The generation AI builds a system for referring to past analysis results. For example, the generation AI selects the most effective output method based on past analysis reports and databases. The generation AI uses an algorithm to propose the most effective output method. For example, the generation AI proposes the optimal output method based on past analysis results. In this way, by referring to past analysis results and proposing the most effective output method, the quality of the data is improved.

[0046] The data output unit can use the generation AI to output highly accurate analytical data in different formats. For example, the generation AI outputs highly accurate analytical data in different formats. For example, the data is provided in the form of graphs, charts, or reports. The generation AI builds a system for outputting highly accurate analytical data in different formats. For example, the generation AI outputs data in different formats using technologies such as text generation and image generation. The generation AI uses an algorithm for outputting data in different formats. For example, the generation AI outputs data in the optimal format depending on the characteristics of the data. This makes it possible to deal with data diversity by outputting highly accurate analytical data in different formats.

[0047] When outputting highly accurate analytical data, the data output unit can visualize the data and provide the results in a visually easy-to-understand format. In the data output unit, for example, the generation AI visualizes the highly accurate analytical data and provides it in a visually easy-to-understand format. For example, the results are displayed using graphs and charts. The generation AI builds a system for visualizing the highly accurate analytical data. For example, the generation AI updates the data visualization results in real time and provides them visually to data scientists. The generation AI provides an interface for providing the results in a visually easy-to-understand format. For example, the generation AI visualizes the data visualization results in graphs and charts and provides them to data scientists. This improves the work efficiency of data scientists by providing highly accurate analytical data in a visually easy-to-understand format.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The data preprocessing section can evaluate the origin and reliability of data and automatically exclude unreliable data. For example, the generation AI analyzes the origin of the data and identifies unreliable data sources. If data from a particular sensor or database lacks consistency, the data is excluded. The generation AI uses an algorithm to evaluate the reliability of data and automatically exclude unreliable data. It scores reliability based on the data origin and generation process and excludes unreliable data. This improves data quality by automatically excluding unreliable data.

[0050] The data conversion unit can develop general-purpose conversion methods that can be applied to data from different industries and fields. For example, the generative AI analyzes data from different industries and fields and develops a general-purpose conversion method. It proposes a conversion method that can be applied to both financial data and medical data. The generative AI builds a system for analyzing data from different industries and fields. It develops an industry-wide conversion algorithm and applies it to data from different industries and fields. It uses an algorithm to develop a general-purpose conversion method. It proposes a general-purpose conversion method based on data from different industries and fields. This allows it to deal with data diversity by developing a general-purpose conversion method that can be applied to data from different industries and fields.

[0051] The data integration unit can automatically check the consistency of data when integrating data and make correction suggestions if there are any inconsistencies. For example, the generation AI checks consistency when integrating data and makes correction suggestions if there are any inconsistencies. If data from different data sources does not match, it identifies the cause and corrects it. The generation AI uses an algorithm to automatically check data consistency. It evaluates consistency based on data consistency checks and inconsistency detection methods. It builds a system to make correction suggestions if there are any inconsistencies. It identifies data inconsistencies and suggests how to correct them. This improves data quality by automatically checking consistency when integrating data and making correction suggestions if there are any inconsistencies.

[0052] The data output unit can use generative AI to output highly accurate analytical data in different formats. For example, generative AI outputs highly accurate analytical data in different formats. It provides data in the form of graphs, charts, and reports. Generative AI builds a system for outputting highly accurate analytical data in different formats. It outputs data in different formats using technologies such as text generation and image generation. It uses algorithms to output data in different formats. It outputs data in the optimal format depending on the characteristics of the data. This makes it possible to handle data diversity by outputting highly accurate analytical data in different formats.

[0053] The data verification unit can also perform quality checks on different data formats. For example, the generation AI analyzes image data and performs a quality check, evaluating the image resolution and noise level. The generation AI analyzes audio data and performs a quality check, evaluating the audio noise level and volume normalization. The generation AI analyzes text data and performs a quality check, evaluating text normalization and the deletion of unnecessary characters. This allows quality checks to be performed on different data formats, making it possible to handle data diversity.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The data preprocessing unit receives the raw data entered by the data scientist, completes missing values, detects and corrects outliers, and normalizes the data. For example, the data preprocessing unit receives as input a prompt containing instructions from the generative AI such as "complete missing values ​​with the average value, and detect and correct outliers," and preprocesses the data based on those instructions. Step 2: The data conversion unit encodes categorical data, decomposes temporal data, and vectorizes text data based on the preprocessed data. For example, the data conversion unit receives a prompt containing instructions from the generation AI such as "one-hot encode categorical data and decompose temporal data into years, months, days, and hours," and converts the data based on those instructions. Step 3: The feature engineering unit performs the necessary data conversion and feature engineering based on the data converted by the data conversion unit. For example, the feature engineering unit receives as input a prompt containing instructions from the generation AI such as "extract specific features and generate new features," and performs feature engineering based on those instructions.

[0056] (Example 2) The data processing system according to an embodiment of the present invention is a system that uses generative AI to process data quickly and accurately. As a result, the data processing system improves the accuracy of data processing in the work of data scientists, and can have a significant impact on the indicators of subsequent analytical models.

[0057] A data processing system according to an embodiment includes a data preprocessing unit, a data conversion unit, and a feature engineering unit. The data preprocessing unit receives raw data input by a data scientist, completes missing values, detects and corrects outliers, and normalizes the data. For example, the data preprocessing unit receives as input a prompt containing instructions from the generation AI, such as "complete missing values ​​with the average value and detect and correct outliers," and preprocesses the data based on the instructions. The data conversion unit encodes categorical data, decomposes temporal data, and vectorizes text data based on the preprocessed data. For example, the data conversion unit receives as input a prompt containing instructions from the generation AI, such as "perform one-hot encoding of categorical data and decompose temporal data into years, months, days, and hours," and converts the data based on the instructions. The feature engineering unit performs the necessary data conversion and feature engineering. For example, the feature engineering unit receives as input a prompt containing instructions from the generation AI, such as "extract specific features and generate new features," and performs feature engineering based on the instructions. This enables rapid and accurate data preprocessing, conversion, and feature engineering.

[0058] The data preprocessing unit understands the context of the data and can complement and correct missing values ​​and outliers based on that context. In the data preprocessing unit, for example, the generative AI analyzes the context of the data and identifies the cause of the missing value. For example, if a specific sensor fails and data is missing, the data from that sensor is complemented using data from other sensors. The generative AI understands the context of the data and uses an algorithm to complement and correct missing values ​​and outliers. For example, the generative AI complements missing values ​​and corrects outliers based on the context and related information of the data. In this way, data quality is improved by understanding the context of the data and complementing and correcting missing values ​​and outliers.

[0059] The data preprocessing unit can evaluate the origin and reliability of data and automatically exclude unreliable data. For example, the generation AI in the data preprocessing unit analyzes the origin of data and identifies unreliable data sources. For example, if data from a specific sensor or database lacks consistency, the data is excluded. The generation AI uses an algorithm to evaluate the reliability of data and automatically exclude unreliable data. For example, the generation AI scores reliability based on the origin of the data and the generation process, and excludes unreliable data. This improves data quality by automatically excluding unreliable data.

[0060] The data preprocessing unit can also perform preprocessing on different data formats. In the data preprocessing unit, for example, the generation AI analyzes image data and performs preprocessing. For example, it automatically performs image noise removal and resolution adjustment. The generation AI analyzes audio data and performs preprocessing. For example, it automatically performs audio noise removal and volume normalization. The generation AI analyzes text data and performs preprocessing. For example, it automatically performs text normalization and deletion of unnecessary characters. This makes it possible to handle data diversity by performing preprocessing on different data formats.

[0061] The data preprocessing section can provide feedback to data scientists in real time, allowing them to check the results of preprocessing immediately. For example, the data preprocessing section has a generative AI that provides feedback on the results of preprocessing to data scientists in real time, allowing them to check the results immediately. For example, it displays the progress and results of preprocessing on a dashboard. The generative AI builds a system for providing feedback on the results of preprocessing in real time. For example, it updates the results of preprocessing in real time and notifies the data scientist. The generative AI provides an interface that allows the results of preprocessing to be checked immediately. For example, it visualizes the results of preprocessing in graphs and charts and provides them to the data scientist. This allows data scientists to check the results of preprocessing in real time, improving their work efficiency.

[0062] The data preprocessing unit uses an emotion estimation function to analyze the emotions of data scientists and, if it determines that stress is high, makes suggestions to simplify the preprocessing steps. For example, the data preprocessing unit uses the emotion estimation function to monitor the stress level of data scientists in real time and, if stress is high, makes suggestions to simplify the preprocessing steps. For example, it automates complex preprocessing. The generation AI analyzes the emotions of data scientists and uses an algorithm to simplify the preprocessing steps if stress is high. For example, the generation AI adjusts the preprocessing steps based on the data scientist's emotion score. The generation AI makes suggestions to simplify the preprocessing steps based on the data scientist's emotions. For example, if stress is high, it suggests specific methods to simplify the preprocessing steps. This reduces the stress of data scientists and improves their work efficiency.

[0063] The data conversion unit can automatically detect data correlations and propose the optimal conversion method. In the data conversion unit, for example, the generation AI analyzes data correlations and proposes the optimal conversion method. For example, it generates new features by combining highly correlated variables. The generation AI uses an algorithm to automatically detect data correlations. For example, the generation AI evaluates data correlations based on correlation coefficients and covariances. The generation AI builds a system to propose the optimal conversion method. For example, the generation AI selects the optimal conversion method based on data correlations and proposes it to a data scientist. In this way, data quality is improved by automatically detecting data correlations and proposing the optimal conversion method.

[0064] The data conversion unit can refer to past data analysis results and automatically generate the most effective features. In the data conversion unit, for example, the generation AI refers to past data analysis results and automatically generates the most effective features. For example, it generates new features based on past success stories. The generation AI builds a system for referring to past data analysis results. For example, the generation AI selects the most effective features based on past analysis reports and databases. The generation AI uses an algorithm for automatically generating the most effective features. For example, the generation AI proposes a specific method for generating new features based on past data analysis results. In this way, the quality of data is improved by referring to past data analysis results and automatically generating the most effective features.

[0065] The data conversion unit can use the emotion estimation function to analyze the emotions of data scientists and propose feature engineering methods to elicit positive emotions. The data conversion unit, for example, uses the emotion estimation function to analyze the emotions of data scientists and proposes feature engineering methods to elicit positive emotions. For example, it proposes a simple and effective feature generation method. The generation AI uses an algorithm to analyze the emotions of data scientists and propose positive emotions. For example, the generation AI adjusts the feature engineering method based on the emotion score of the data scientist. The generation AI builds a system for proposing feature engineering methods based on the emotions of the data scientist. For example, the generation AI proposes specific feature engineering methods to elicit positive emotions based on the emotions of the data scientist. This improves work efficiency by analyzing the emotions of data scientists and proposing feature engineering methods to elicit positive emotions.

[0066] The data conversion unit can develop general-purpose conversion methods that can be applied to data from different industries and fields. In the data conversion unit, for example, the generation AI analyzes data from different industries and fields and develops general-purpose conversion methods. For example, it proposes a conversion method that can be applied to both financial data and medical data. The generation AI builds a system for analyzing data from different industries and fields. For example, the generation AI develops an industry-wide conversion algorithm and applies it to data from different industries and fields. The generation AI uses an algorithm to develop a general-purpose conversion method. For example, the generation AI proposes a general-purpose conversion method based on data from different industries and fields. This makes it possible to deal with data diversity by developing a general-purpose conversion method that can be applied to data from different industries and fields.

[0067] The data transformation unit can visualize the data when performing data transformation and feature engineering and provide the results in a visually easy-to-understand format. For example, the data transformation unit causes the generation AI to visualize the results of data transformation and feature engineering and provide them in a visually easy-to-understand format. For example, the data transformation unit displays the results using graphs and charts. The generation AI builds a system for visualizing the results of data transformation and feature engineering. For example, the generation AI updates the data transformation results in real time and provides them visually to data scientists. The generation AI provides an interface for providing the results in a visually easy-to-understand format. For example, the generation AI visualizes the data transformation results in graphs and charts and provides them to data scientists. This improves the work efficiency of data scientists by providing the results of data transformation and feature engineering in a visually easy-to-understand format.

[0068] The data conversion unit can use the emotion estimation function to dynamically adjust the conversion method based on the data scientist's emotions, thereby improving work efficiency. The data conversion unit, for example, uses the emotion estimation function to analyze the data scientist's emotions and dynamically adjust the conversion method if stress is high. For example, it proposes a simple conversion method. The generation AI uses an algorithm to analyze the data scientist's emotions and dynamically adjust the conversion method. For example, the generation AI adjusts the conversion method based on the data scientist's emotion score. The generation AI builds a system for dynamically adjusting the conversion method based on the data scientist's emotions. For example, the generation AI proposes a simple conversion method if stress is high based on the data scientist's emotions. In this way, work efficiency is improved by dynamically adjusting the conversion method based on the data scientist's emotions.

[0069] The data integration unit can automatically check the consistency of data when integrating data and make correction suggestions if there are any inconsistencies. In the data integration unit, for example, the generation AI checks the consistency of data when integrating data and makes correction suggestions if there are any inconsistencies. For example, if data from different data sources does not match, the cause is identified and corrected. The generation AI uses an algorithm to automatically check the consistency of data. For example, the generation AI evaluates the consistency based on data consistency checks and inconsistency detection methods. The generation AI builds a system to make correction suggestions if there are any inconsistencies. For example, the generation AI identifies inconsistencies in the data and suggests how to correct them. In this way, the quality of data is improved by automatically checking consistency when integrating data and making correction suggestions if there are any inconsistencies.

[0070] The data integration unit can try different aggregation methods when aggregating data and automatically select the most effective aggregation result. In the data integration unit, for example, the generation AI tries different aggregation methods and automatically selects the most effective aggregation result. For example, it compares aggregation methods such as the mean, median, and mode. The generation AI uses an algorithm to try different aggregation methods. For example, the generation AI selects the most effective aggregation result based on the type of aggregation method and the method tried. The generation AI builds a system for automatically selecting the most effective aggregation result. For example, the generation AI compares different aggregation methods and selects the most effective aggregation result. In this way, by trying different aggregation methods and automatically selecting the most effective aggregation result, the quality of the data is improved.

[0071] The data integration unit can use the emotion estimation function to analyze the emotions of data scientists and propose an integration and aggregation method that elicits positive emotions. For example, the data integration unit can use the emotion estimation function to analyze the emotions of data scientists and propose an integration and aggregation method that elicits positive emotions. For example, it can propose a simple and effective aggregation method. The generation AI uses an algorithm to analyze the emotions of data scientists and elicit positive emotions. For example, the generation AI can adjust the integration and aggregation method based on the emotion score of the data scientist. The generation AI builds a system to propose an integration and aggregation method based on the emotions of the data scientist. For example, the generation AI can propose a specific integration and aggregation method that elicits positive emotions based on the emotions of the data scientist. This improves work efficiency by analyzing the emotions of data scientists and proposing an integration and aggregation method that elicits positive emotions.

[0072] The data integration unit can integrate data from different data sources in real time and provide aggregated results instantly. In the data integration unit, for example, the generation AI integrates data from different data sources in real time and provides aggregated results instantly. For example, it combines data from multiple databases in real time. The generation AI builds a system for integrating data from different data sources in real time. For example, the generation AI integrates data in real time based on the frequency of data updates and the timing of feedback provision. The generation AI provides an interface for providing aggregated results instantly. For example, the generation AI displays aggregated results updated in real time on a dashboard. This improves data quality by integrating data from different data sources in real time and providing aggregated results instantly.

[0073] When integrating and aggregating data, the data integration unit can visualize the data and provide the results in a visually easy-to-understand format. For example, the data integration unit uses the generation AI to visualize the results of data integration and aggregation and provide them in a visually easy-to-understand format. For example, the results are displayed using graphs and charts. The generation AI builds a system for visualizing the results of data integration and aggregation. For example, the generation AI updates the data integration results in real time and provides them visually to data scientists. The generation AI provides an interface for providing the results in a visually easy-to-understand format. For example, the generation AI visualizes the data integration results in graphs and charts and provides them to data scientists. This improves the work efficiency of data scientists by providing the results of data integration and aggregation in a visually easy-to-understand format.

[0074] The data integration unit can use the emotion estimation function to dynamically adjust the integration and aggregation method based on the data scientist's emotions, improving work efficiency. For example, the data integration unit uses the emotion estimation function to analyze the data scientist's emotions and dynamically adjust the integration and aggregation method if stress levels are high. For example, it proposes a simple integration and aggregation method. The generation AI uses an algorithm to analyze the data scientist's emotions and dynamically adjust the integration and aggregation method. For example, the generation AI adjusts the integration and aggregation method based on the data scientist's emotion score. The generation AI builds a system for dynamically adjusting the integration and aggregation method based on the data scientist's emotions. For example, the generation AI proposes a simple integration and aggregation method if stress levels are high based on the data scientist's emotions. This improves work efficiency by dynamically adjusting the integration and aggregation method based on the data scientist's emotions.

[0075] The data verification unit can evaluate the reliability of data and automatically exclude low-reliability data in data quality checks. In the data verification unit, for example, the generation AI evaluates the reliability of data and automatically excludes low-reliability data. For example, it scores reliability based on the origin and consistency of the data. The generation AI uses an algorithm to evaluate the reliability of data. For example, the generation AI evaluates reliability based on the origin and generation process of the data. The generation AI builds a system to automatically exclude low-reliability data. For example, the generation AI identifies low-reliability data and suggests a method for excluding it. In this way, the quality of data is improved by evaluating the reliability of data and automatically excluding low-reliability data.

[0076] The data verification unit can use the emotion estimation function to analyze the emotions of data scientists and propose a quality check method that elicits positive emotions. For example, the data verification unit uses the emotion estimation function to analyze the emotions of data scientists and propose a quality check method that elicits positive emotions. For example, it proposes a simple and effective quality check method. The generation AI uses an algorithm to analyze the emotions of data scientists and elicit positive emotions. For example, the generation AI adjusts the quality check method based on the emotion score of the data scientist. The generation AI builds a system for proposing a quality check method based on the emotions of the data scientist. For example, the generation AI proposes a specific quality check method that elicits positive emotions based on the emotions of the data scientist. In this way, work efficiency is improved by analyzing the emotions of data scientists and proposing a quality check method that elicits positive emotions.

[0077] The data verification unit can also perform quality checks on different data formats. In the data verification unit, for example, the generation AI analyzes image data and performs a quality check. For example, it evaluates the image resolution and noise level. The generation AI analyzes audio data and performs a quality check. For example, it evaluates the audio noise level and volume normalization. The generation AI analyzes text data and performs a quality check. For example, it evaluates text normalization and the deletion of unnecessary characters. This allows quality checks to be performed on different data formats, making it possible to handle data diversity.

[0078] The data verification unit can provide feedback to data scientists in real time when verifying data and checking quality, allowing them to check the verification results immediately. For example, the data verification unit may have the generation AI provide feedback on the results of data verification and quality checks to data scientists in real time, allowing them to check the results immediately. For example, the generation AI may display the verification results on a dashboard. The generation AI may build a system for providing feedback on the results of data verification and quality checks in real time. For example, the generation AI may update the verification results in real time and notify the data scientist. The generation AI may provide an interface that allows the verification results to be checked immediately. For example, the generation AI may visualize the verification results in graphs or charts and provide them to the data scientist. This improves the work efficiency of data scientists by allowing them to check the results of data verification and quality checks in real time.

[0079] The data verification unit can use the emotion estimation function to dynamically adjust the quality check method based on the data scientist's emotions, thereby improving work efficiency. For example, the data verification unit uses the emotion estimation function to analyze the data scientist's emotions and dynamically adjust the quality check method when stress is high. For example, it proposes a simple quality check method. The generation AI uses an algorithm to analyze the data scientist's emotions and dynamically adjust the quality check method. For example, the generation AI adjusts the quality check method based on the data scientist's emotion score. The generation AI builds a system for dynamically adjusting the quality check method based on the data scientist's emotions. For example, the generation AI proposes a simple quality check method when stress is high based on the data scientist's emotions. This improves work efficiency by dynamically adjusting the quality check method based on the data scientist's emotions.

[0080] When outputting highly accurate analytical data, the data output unit can refer to past analysis results and propose the most effective output method. In the data output unit, for example, the generation AI refers to past analysis results and proposes the most effective output method. For example, it selects the optimal output method based on past success stories. The generation AI builds a system for referring to past analysis results. For example, the generation AI selects the most effective output method based on past analysis reports and databases. The generation AI uses an algorithm to propose the most effective output method. For example, the generation AI proposes the optimal output method based on past analysis results. In this way, by referring to past analysis results and proposing the most effective output method, the quality of the data is improved.

[0081] The data output unit can use the emotion estimation function to analyze the emotions of the data scientist and propose an output method that elicits positive emotions. The data output unit, for example, uses the emotion estimation function to analyze the emotions of the data scientist and proposes an output method that elicits positive emotions. For example, it proposes a simple and effective output method. The generation AI analyzes the emotions of the data scientist and uses an algorithm to elicit positive emotions. For example, the generation AI adjusts the output method based on the emotion score of the data scientist. The generation AI builds a system for proposing an output method based on the emotions of the data scientist. For example, the generation AI proposes a specific output method that elicits positive emotions based on the emotions of the data scientist. In this way, work efficiency is improved by analyzing the emotions of the data scientist and proposing an output method that elicits positive emotions.

[0082] The data output unit can use the generation AI to output highly accurate analytical data in different formats. For example, the generation AI outputs highly accurate analytical data in different formats. For example, the data is provided in the form of graphs, charts, or reports. The generation AI builds a system for outputting highly accurate analytical data in different formats. For example, the generation AI outputs data in different formats using technologies such as text generation and image generation. The generation AI uses an algorithm for outputting data in different formats. For example, the generation AI outputs data in the optimal format depending on the characteristics of the data. This makes it possible to deal with data diversity by outputting highly accurate analytical data in different formats.

[0083] When outputting highly accurate analytical data, the data output unit can visualize the data and provide the results in a visually easy-to-understand format. In the data output unit, for example, the generation AI visualizes the highly accurate analytical data and provides it in a visually easy-to-understand format. For example, the results are displayed using graphs and charts. The generation AI builds a system for visualizing the highly accurate analytical data. For example, the generation AI updates the data visualization results in real time and provides them visually to data scientists. The generation AI provides an interface for providing the results in a visually easy-to-understand format. For example, the generation AI visualizes the data visualization results in graphs and charts and provides them to data scientists. This improves the work efficiency of data scientists by providing highly accurate analytical data in a visually easy-to-understand format.

[0084] The data output unit can use the emotion estimation function to dynamically adjust the output method based on the data scientist's emotions, thereby improving work efficiency. The data output unit, for example, uses the emotion estimation function to analyze the data scientist's emotions and dynamically adjust the output method if stress is high. For example, it proposes a simple output method. The generation AI uses an algorithm to analyze the data scientist's emotions and dynamically adjust the output method. For example, the generation AI adjusts the output method based on the data scientist's emotion score. The generation AI builds a system for dynamically adjusting the output method based on the data scientist's emotions. For example, the generation AI proposes a simple output method if stress is high based on the data scientist's emotions. In this way, work efficiency is improved by dynamically adjusting the output method based on the data scientist's emotions.

[0085] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0086] The data preprocessing section can evaluate the origin and reliability of data and automatically exclude unreliable data. For example, the generation AI analyzes the origin of the data and identifies unreliable data sources. If data from a particular sensor or database lacks consistency, the data is excluded. The generation AI uses an algorithm to evaluate the reliability of data and automatically exclude unreliable data. It scores reliability based on the data origin and generation process and excludes unreliable data. This improves data quality by automatically excluding unreliable data.

[0087] The data conversion unit can develop general-purpose conversion methods that can be applied to data from different industries and fields. For example, the generative AI analyzes data from different industries and fields and develops a general-purpose conversion method. It proposes a conversion method that can be applied to both financial data and medical data. The generative AI builds a system for analyzing data from different industries and fields. It develops an industry-wide conversion algorithm and applies it to data from different industries and fields. It uses an algorithm to develop a general-purpose conversion method. It proposes a general-purpose conversion method based on data from different industries and fields. This allows it to deal with data diversity by developing a general-purpose conversion method that can be applied to data from different industries and fields.

[0088] The data integration unit can automatically check the consistency of data when integrating data and make correction suggestions if there are any inconsistencies. For example, the generation AI checks consistency when integrating data and makes correction suggestions if there are any inconsistencies. If data from different data sources does not match, it identifies the cause and corrects it. The generation AI uses an algorithm to automatically check data consistency. It evaluates consistency based on data consistency checks and inconsistency detection methods. It builds a system to make correction suggestions if there are any inconsistencies. It identifies data inconsistencies and suggests how to correct them. This improves data quality by automatically checking consistency when integrating data and making correction suggestions if there are any inconsistencies.

[0089] The data output unit can use generative AI to output highly accurate analytical data in different formats. For example, generative AI outputs highly accurate analytical data in different formats. It provides data in the form of graphs, charts, and reports. Generative AI builds a system for outputting highly accurate analytical data in different formats. It outputs data in different formats using technologies such as text generation and image generation. It uses algorithms to output data in different formats. It outputs data in the optimal format depending on the characteristics of the data. This makes it possible to handle data diversity by outputting highly accurate analytical data in different formats.

[0090] The data verification unit can also perform quality checks on different data formats. For example, the generation AI analyzes image data and performs a quality check, evaluating the image resolution and noise level. The generation AI analyzes audio data and performs a quality check, evaluating the audio noise level and volume normalization. The generation AI analyzes text data and performs a quality check, evaluating text normalization and the deletion of unnecessary characters. This allows quality checks to be performed on different data formats, making it possible to handle data diversity.

[0091] The data preprocessing unit uses the emotion estimation function to analyze the emotions of data scientists and, if it determines that stress is high, can make suggestions to simplify the preprocessing steps. For example, the emotion estimation function can be used to monitor the data scientist's stress level in real time and, if stress is high, make suggestions to simplify the preprocessing steps. This automates complex preprocessing. The generative AI analyzes the data scientist's emotions and uses an algorithm to simplify the preprocessing steps if stress is high. It adjusts the preprocessing steps based on the data scientist's emotion score. It makes suggestions to simplify the preprocessing steps based on the data scientist's emotions. It suggests specific methods to simplify the preprocessing steps if stress is high. This reduces the stress of data scientists and improves their work efficiency.

[0092] The data conversion unit can use the emotion estimation function to analyze the emotions of data scientists and propose feature engineering methods to elicit positive emotions. For example, the emotion estimation function is used to analyze the emotions of data scientists and propose feature engineering methods to elicit positive emotions. A simple and effective feature generation method is proposed. The generation AI uses an algorithm to analyze the emotions of data scientists and elicit positive emotions. The feature engineering method is adjusted based on the emotion score of the data scientists. A system is built to propose feature engineering methods based on the emotions of data scientists. A specific feature engineering method to elicit positive emotions is proposed based on the emotions of data scientists. This improves work efficiency by analyzing the emotions of data scientists and proposing feature engineering methods to elicit positive emotions.

[0093] The data integration unit can use the emotion estimation function to analyze data scientists' emotions and propose integration and aggregation methods that elicit positive emotions. For example, the emotion estimation function can be used to analyze data scientists' emotions and propose integration and aggregation methods that elicit positive emotions. A simple and effective aggregation method is proposed. The generative AI uses an algorithm to analyze data scientists' emotions and elicit positive emotions. The integration and aggregation method is adjusted based on the data scientists' emotion scores. A system is built to propose integration and aggregation methods based on data scientists' emotions. A specific integration and aggregation method that elicits positive emotions is proposed based on the data scientists' emotions. This improves work efficiency by analyzing data scientists' emotions and proposing integration and aggregation methods that elicit positive emotions.

[0094] The data verification department can use the emotion estimation function to analyze the emotions of data scientists and propose quality check methods that elicit positive emotions. For example, the emotion estimation function is used to analyze the emotions of data scientists and propose quality check methods that elicit positive emotions. A simple and effective quality check method is proposed. The generative AI analyzes the emotions of data scientists and uses an algorithm to elicit positive emotions. The quality check method is adjusted based on the emotion score of the data scientists. A system is built to propose quality check methods based on the emotions of data scientists. A specific quality check method is proposed to elicit positive emotions based on the emotions of data scientists. In this way, work efficiency is improved by analyzing the emotions of data scientists and proposing quality check methods that elicit positive emotions.

[0095] The data output unit can use the emotion estimation function to analyze the emotions of data scientists and propose an output method that elicits positive emotions. For example, the emotion estimation function is used to analyze the emotions of data scientists and propose an output method that elicits positive emotions. A simple and effective output method is proposed. The generative AI analyzes the emotions of data scientists and uses an algorithm to elicit positive emotions. The output method is adjusted based on the emotion score of the data scientist. A system is built to propose an output method based on the emotions of the data scientist. A specific output method that elicits positive emotions is proposed based on the emotions of the data scientist. In this way, work efficiency is improved by analyzing the emotions of data scientists and proposing an output method that elicits positive emotions.

[0096] The processing flow of the second embodiment will be briefly explained below.

[0097] Step 1: The data preprocessing unit receives the raw data entered by the data scientist, completes missing values, detects and corrects outliers, and normalizes the data. For example, the data preprocessing unit receives as input a prompt containing instructions from the generative AI such as "complete missing values ​​with the average value, and detect and correct outliers," and preprocesses the data based on those instructions. Step 2: The data conversion unit encodes categorical data, decomposes temporal data, and vectorizes text data based on the preprocessed data. For example, the data conversion unit receives a prompt containing instructions from the generation AI such as "one-hot encode categorical data and decompose temporal data into years, months, days, and hours," and converts the data based on those instructions. Step 3: The feature engineering unit performs the necessary data conversion and feature engineering based on the data converted by the data conversion unit. For example, the feature engineering unit receives as input a prompt containing instructions from the generation AI such as "extract specific features and generate new features," and performs feature engineering based on those instructions.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0100] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0101] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0102] 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.

[0103] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0104] 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.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0108] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] 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.

[0110] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0111] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0112] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0116] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0117] 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.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] 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.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] 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.

[0124] 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.

[0125] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0126] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0127] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0128] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0131] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0132] 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.

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] 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.

[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 audio according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[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 carried out in a secure state.

[0138] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0139] 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.

[0140] 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.

[0141] 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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0142] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0143] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0144] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0145] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0146] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0147] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0148] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0149] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0150] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0151] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0152] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0153] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0154] 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.

[0155] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0156] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0157] 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.

[0158] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0159] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0160] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0161] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0162] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0163] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0164] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0165] 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 data preprocessing unit; a data conversion unit that performs data conversion based on the data preprocessed by the data preprocessing unit; a feature engineering unit that performs feature engineering based on the data converted by the data conversion unit. A system characterized by:

2. The data preprocessing unit Evaluating the origin and reliability of the data and automatically excluding the data with low reliability 2. The system of claim 1.

3. The data conversion unit Automatically detects correlations in the data and suggests optimal conversion methods 2. The system of claim 1.

4. The Data Integration Department When integrating the data, the consistency of the data is automatically checked and corrections are suggested if there are any inconsistencies.

2. The system of claim 1.

5. The data preprocessing unit Analyze the emotions of data scientists and, if stress levels are found to be high, make suggestions to simplify the preprocessing steps.

2. The system of claim 1.

Images