System

Abstract

An object of the system according to the embodiment is to understand steps of data analysis, select an appropriate analysis model, and create an analysis action or an action plan.SOLUTION: A system includes a step guide part, a data cooperation part, a model selection part, and an action plan creation part. The step guide portion understands and guides the steps of data analysis. The data linkage unit performs data linkage using a prompt or a RAG. The model selection unit selects an appropriate analysis model. The action plan generation unit generates an analysis action and an action plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult to understand the steps of data analysis, select an appropriate analytical model, and create analytical actions and action plans.

[0005] The system according to the embodiment aims to understand the steps of data analysis, select an appropriate analysis model, and create analysis actions and action plans. [Means for solving the problem]

[0006] The system according to the embodiment includes a step guide unit, a data linking unit, a model selection unit, and an action plan creation unit. The step guide unit understands and guides the steps of data analysis. The data linking unit performs data linking using prompts or RAGs. The model selection unit selects an appropriate analysis model. The action plan creation unit creates analysis actions and action plans. [Effects of the Invention]

[0007] The system according to the embodiment can understand the steps of data analysis, select an appropriate analysis model, and create analysis actions and action plans. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A data analysis guide system according to an embodiment of the present invention is a system that uses LLM to guide users through the steps of data analysis, performing data integration, model selection, and action plan creation. This allows users to easily perform data analysis, improving work efficiency and decision-making accuracy.

[0029] A data analysis guide system according to an embodiment includes a step guide unit, a data linking unit, a model selection unit, and an action plan creation unit. The step guide unit guides the user through data analysis steps. For example, the step guide unit explains steps such as data collection, preprocessing, modeling, and evaluation based on the analysis content the user wants to perform. The data linking unit uses prompts or RAG to link data. For example, if a user requests a profit margin analysis, the data linking unit generates a prompt such as "Please provide profit margin data" to prompt the user to enter data. The data linking unit also uses RAG to automatically acquire related data and link the data required for the analysis. The model selection unit selects an appropriate analysis model. For example, the model selection unit determines that a regression analysis model is appropriate for profit margin analysis and a classification model is appropriate for defect rate analysis, and proposes each model. The action plan creation unit creates analysis actions and action plans. For example, the action plan creation unit proposes an action, such as "review a specific process to reduce costs," based on the profit margin analysis results and provides a specific plan for that action. As a result, the data analysis guide system according to the embodiment can guide the steps of data analysis and consistently perform data integration, model selection, and action plan creation.

[0030] The step guide unit can learn the user's past data analysis history and provide individually optimized step guides. For example, the LLM can learn the user's past data analysis history and provide individually optimized step guides. For example, for a user who has previously analyzed profit margins, similar steps can be suggested to efficiently proceed with the analysis. Furthermore, based on the user's past data analysis history, the LLM can identify stumbling blocks at specific steps and provide guides that include solutions. For example, it can show specific steps to prevent errors in data preprocessing. Furthermore, the LLM can learn the user's past analysis history and prioritize frequently used analysis methods and tools in the guide. For example, for a user who frequently uses a specific regression analysis model, it can provide guides centered on that model. This enables efficient data analysis by providing optimized guides based on the user's past data analysis history.

[0031] The step guide unit can understand the terminology and methods specific to the user's industry and generate a customized guide based on that. For example, the LLM learns the terminology and methods specific to the user's industry and generates a customized guide based on that. For example, a user in the manufacturing industry can be provided with a guide using terminology and methods specialized for defect rate analysis. The step guide unit also understands industry-specific data sets and analysis methods and customizes the step guide based on that. For example, a user in the financial industry can be provided with a guide specialized for risk analysis. The step guide unit also generates a guide tailored to the needs specific to the user's industry and incorporates industry-standard methods and tools. For example, a user in the medical industry can be provided with a guide specialized for patient data analysis. This allows the provision of customized guides based on industry-specific terminology and methods, enabling data analysis tailored to the user's business.

[0032] The step guide unit can provide seamless guidance across different devices. For example, the LLM can provide seamless guidance across different devices, such as smartphones, tablets, and PCs. For example, data analysis started on a PC can be continued on a smartphone. The step guide unit also synchronizes data between devices, allowing users to receive the same guidance from any device. For example, data input on a tablet can be reflected in analysis on a PC. The step guide unit also provides an interface optimized for each device, allowing users to receive guidance comfortably on any device. For example, a simplified guide is provided on a smartphone, and a detailed guide is provided on a PC. This allows seamless guidance across different devices, allowing users to continue data analysis on any device.

[0033] The step guide unit can work in conjunction with a voice assistant to provide voice guidance. For example, the LLM works in conjunction with the voice assistant to provide voice guidance. For example, when a user asks, "What should I do next?", the step guide unit responds by voice, saying, "Preprocess the data." The voice assistant also enables the user to proceed through the steps of data analysis without using their hands. For example, data loading and preprocessing can be instructed by voice command. The voice assistant also responds to the user's questions in real time and provides guidance for data analysis. For example, when the user asks, "What's the next step for this data?" appropriate guidance is provided by voice. In this way, by working in conjunction with the voice assistant, the user can proceed through the steps of data analysis without using their hands.

[0034] The data linking unit can learn the user's data input patterns and automatically generate optimal prompts. In the data linking unit, for example, the LLM learns the user's data input patterns and automatically generates optimal prompts. For example, it provides prompts in a format that is easy for the user to input based on past input history. It also analyzes the user's data input patterns and generates prompts to reduce input errors. For example, it automatically completes frequently entered data items. The LLM also learns the user's input patterns and provides prompts that improve data entry efficiency. For example, it predicts the next item to be entered based on past input content. In this way, it improves data entry efficiency by providing optimal prompts based on the user's data input patterns.

[0035] The data integration unit can automatically integrate data from different data sources to generate consistent data sets. For example, the LLM automatically integrates data from different data sources to generate consistent data sets. For example, it integrates data from multiple databases and eliminates duplication and inconsistencies. It also automatically converts data in different formats to generate consistent data sets. For example, it integrates CSV files and JSON files and provides them in a unified format. The LLM also analyzes the relationships between data sources and automatically extracts and integrates the necessary data. For example, it links customer data and sales data to generate a consistent data set. This integrates data from different data sources to generate consistent data sets and improves the accuracy of data analysis.

[0036] The data integration unit can support data input in different languages, enabling international data integration. For example, the LLM supports data input in different languages, enabling international data integration. For example, it accepts data input in multiple languages, such as English, Japanese, and Chinese. It also automatically translates data entered in different languages ​​to generate a consistent dataset. For example, it translates data entered in Japanese into English and integrates it. The LLM also provides multilingual prompts, allowing users to enter data in their native language. For example, it displays prompts according to the user's language settings. This supports data input in different languages, enabling international data integration.

[0037] The data linking unit can support multimodal data linking, including image and audio data. For example, the LLM supports multimodal data linking, including image and audio data. For example, it analyzes image data and integrates it with text data. It also converts audio data into text and integrates it with other data. For example, it automatically converts voice-input data into text and adds it to a dataset. It also uses image recognition technology to extract necessary information from image data and integrate it with other data. For example, it extracts product information from product images and registers it in a database. This supports multimodal data linking, including image and audio data, enabling analysis using a wider variety of data.

[0038] The model selection unit can learn from the user's past analysis results and propose the optimal analysis model. For example, the LLM in the model selection unit learns from the user's past analysis results and proposes the optimal analysis model. For example, it proposes a model suitable for similar analysis based on analytical models that have been successful in the past. It can also analyze the user's past analysis results, find specific patterns, and propose the optimal analytical model based on those patterns. For example, it can prioritize the proposal of models that have shown high accuracy for a specific data set. The LLM can also learn from the user's past analysis history and prioritize the proposal of frequently used analytical models. For example, for a user who frequently uses regression analysis models, it will propose those models first. This improves the accuracy and efficiency of analysis by proposing the optimal analytical model based on the user's past analysis results.

[0039] The model selection unit can evaluate model performance in real time and dynamically select the optimal model. In the model selection unit, for example, the LLM evaluates model performance in real time and dynamically selects the optimal model. For example, it evaluates model accuracy according to data fluctuations and selects the optimal model. It also builds a system that monitors model performance in real time and switches models as needed. For example, it switches to a different model if performance deteriorates under certain conditions. The LLM also evaluates model performance in real time and proposes the optimal model. For example, it selects the optimal model according to the characteristics of the data and proposes it to the user. In this way, evaluating model performance in real time and dynamically selecting the optimal model improves the accuracy and efficiency of analysis.

[0040] The model selection unit can learn best practices from different industries and propose the optimal analytical model. For example, the LLM in the model selection unit learns best practices from different industries and proposes the optimal analytical model. For example, it proposes a model suitable for defect rate analysis based on best practices in the manufacturing industry. It also learns successful cases from different industries and proposes the optimal analytical model based on those. For example, it proposes a model suitable for risk analysis in the financial industry. The LLM also learns best practices from different industries and proposes the optimal analytical model for the user's industry. For example, it proposes a model suitable for data analysis in the medical industry. In this way, by proposing the optimal analytical model based on best practices from different industries, the accuracy and efficiency of analysis are improved.

[0041] The model selection unit selects a model according to the user's skill level, making it suitable for everyone from beginners to experts. For example, the model selection unit uses an LLM to select a model according to the user's skill level, making it suitable for everyone from beginners to experts. For example, it proposes a simple model for beginners and an advanced model for experts. It also builds a system that analyzes the user's skill level and selects a model accordingly. For example, it evaluates the user's skill level based on the user's past analysis history. It also provides a guide according to the user's skill level to support appropriate model selection. For example, it provides detailed explanations for beginners and simple explanations for experts. This allows it to select a model according to the user's skill level, making it suitable for a wide range of users, from beginners to experts.

[0042] The action plan creation unit can learn the user's past action plans and propose the optimal action plan. For example, the action plan creation unit uses the LLM to learn the user's past action plans and propose the optimal action plan. For example, it proposes a plan suitable for a similar situation based on action plans that have been successful in the past. It can also analyze the user's past action plans, find specific patterns, and propose the optimal action plan based on those patterns. For example, it can prioritize the proposal of action plans that are effective for a specific data set. It can also learn the user's past action plans and prioritize the proposal of frequently used action plans. For example, for a user who frequently uses action plans for cost reduction, it can mainly propose those plans. In this way, the optimal action plan is proposed based on the user's past action plans, improving the efficiency and accuracy of work.

[0043] The action plan creation department can monitor the progress of the action plan in real time and revise the plan as necessary. In the action plan creation department, for example, the LLM monitors the progress of the action plan in real time and revise the plan as necessary. For example, if progress is delayed, they will propose a review of the plan. In addition, a system can be built that monitors the progress of the action plan in real time and adjusts the plan according to the progress status. For example, if a specific task is not completed, they will propose a reallocation of resources. In addition, the LLM monitors the progress of the action plan in real time and revise the plan according to the progress status. For example, if progress is going well, they will present the next step early. In this way, by monitoring the progress of the action plan in real time and revising the plan as necessary, the efficiency and accuracy of work can be improved.

[0044] The action plan creation unit can study success stories from different industries and propose action plans based on them. In the action plan creation unit, for example, the LLM studies success stories from different industries and proposes action plans based on them. For example, an action plan for reducing defect rates is proposed based on success stories from the manufacturing industry. The action plan creation unit also studies success stories from different industries and proposes the optimal action plan based on them. For example, an action plan suitable for risk management in the financial industry is proposed. The LLM also studies success stories from different industries and proposes the optimal action plan for the user's industry. For example, an action plan based on data analysis from the medical industry is proposed. In this way, by proposing action plans based on success stories from different industries, the efficiency and accuracy of operations are improved.

[0045] The action plan creation unit can provide a function that promotes the sharing and cooperation of action plans among team members. For example, the action plan creation unit provides a function that allows LLM to promote the sharing and cooperation of action plans among team members. For example, it provides a platform for sharing action plans. It also builds a system that shares the progress of action plans among team members in real time and promotes cooperation. For example, it visualizes the progress and adjusts task allocation. It also provides communication tools that allow LLM to promote the sharing and cooperation of action plans among team members. For example, it integrates chat and comment functions. This promotes the sharing and cooperation of action plans among team members, thereby improving the efficiency and accuracy of work.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The step guide section can learn a user's past data analysis history and provide individually optimized step guides. For example, for a user who has previously analyzed profit margins, similar steps can be suggested, allowing for efficient analysis. It can also identify stumbling blocks at specific steps based on the user's past data analysis history and provide guides that include solutions. For example, it can show specific steps to prevent errors in data preprocessing. Furthermore, the LLM learns a user's past analysis history and prioritizes frequently used analysis methods and tools in the guide. For example, a user who frequently uses a specific regression analysis model will receive guides focused on that model. This allows for efficient data analysis by providing optimized guides based on the user's past data analysis history.

[0048] The step guide unit can understand the terminology and methods specific to the user's industry and generate a customized guide based on that. For example, the LLM learns the terminology and methods specific to the user's industry and generates a customized guide based on that. For example, a user in the manufacturing industry can be provided with a guide using terminology and methods specialized for defect rate analysis. The step guide can also be customized based on an understanding of industry-specific data sets and analysis methods. For example, a user in the financial industry can be provided with a guide specialized for risk analysis. The step guide can also be generated to meet the needs specific to the user's industry and incorporate industry-standard methods and tools. For example, a user in the medical industry can be provided with a guide specialized for patient data analysis. This allows for customized guides based on industry-specific terminology and methods, enabling data analysis tailored to the user's business.

[0049] The step guide unit can provide seamless guidance across different devices. For example, the LLM can provide seamless guidance across different devices, such as smartphones, tablets, and PCs. For example, data analysis started on a PC can be continued on a smartphone. It also synchronizes data between devices, allowing users to receive the same guidance from any device. For example, data input on a tablet can be reflected in analysis on a PC. It also provides an interface optimized for each device, allowing users to receive guidance comfortably on any device. For example, it provides a simplified guide on a smartphone and a detailed guide on a PC. This allows seamless guidance across different devices, allowing users to continue data analysis on any device.

[0050] The step guide unit can work with a voice assistant to provide voice guidance. For example, the LLM can work with a voice assistant to provide voice guidance. For example, when a user asks, "What should I do next?", the LLM can respond by voice, saying, "Preprocess the data." The voice assistant can also be used to allow users to proceed through the steps of data analysis without using their hands. For example, data loading and preprocessing can be instructed by voice command. The voice assistant can also respond to user questions in real time and provide guidance for data analysis. For example, when asking, "What's the next step for this data?", appropriate guidance can be provided by voice. In this way, by working with the voice assistant, users can proceed through the steps of data analysis without using their hands.

[0051] The data linking unit can learn a user's data input patterns and automatically generate optimal prompts. For example, the LLM learns a user's data input patterns and automatically generates optimal prompts. For example, it provides prompts in a format that is easy for the user to input based on past input history. It also analyzes a user's data input patterns and generates prompts to reduce input errors. For example, it automatically completes frequently entered data items. The LLM also learns a user's input patterns and provides prompts that improve data entry efficiency. For example, it predicts the next item to be entered based on past input content. This improves data entry efficiency by providing optimal prompts based on the user's data input patterns.

[0052] The data integration unit can automatically integrate data from different data sources to generate consistent data sets. For example, LLM automatically integrates data from different data sources to generate consistent data sets. For example, it integrates data from multiple databases and eliminates duplication and inconsistencies. It also automatically converts data in different formats to generate consistent data sets. For example, it integrates CSV files and JSON files and provides them in a unified format. LLM also analyzes the relationships between data sources and automatically extracts and integrates the necessary data. For example, it links customer data and sales data to generate a consistent data set. This allows data from different data sources to be integrated to generate consistent data sets and improve the accuracy of data analysis.

[0053] The data integration unit can support data input in different languages, enabling international data integration. For example, the LLM supports data input in different languages, enabling international data integration. For example, it accepts data input in multiple languages, such as English, Japanese, and Chinese. It also automatically translates data entered in different languages ​​to generate a consistent dataset. For example, it translates data entered in Japanese into English and integrates it. The LLM also provides multilingual prompts, allowing users to enter data in their native language. For example, it displays prompts according to the user's language settings. This supports data input in different languages, enabling international data integration.

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

[0055] Step 1: The step guide section helps users understand and guide them through the steps of data analysis. For example, the step guide section explains steps such as data collection, preprocessing, modeling, and evaluation based on the analysis content the user wants to perform. Step 2: The data linking unit uses prompts or RAGs to link data. For example, if a user requests that they "analyze profit margins," the data linking unit generates a prompt such as "Please provide profit margin data" to prompt the user to enter data. Furthermore, the data linking unit automatically retrieves related data using RAGs and links the data required for analysis. Step 3: The model selection unit selects an appropriate analysis model. For example, the model selection unit determines that a regression analysis model is appropriate for analyzing profit margins, and a classification model is appropriate for analyzing defect rates, and proposes each model. Step 4: The Action Plan Creation Department creates an analysis action and an action plan. For example, based on the profit margin analysis results, the Action Plan Creation Department proposes an action such as "reviewing a specific process to reduce costs" and provides a specific plan.

[0056] (Example 2) A data analysis guide system according to an embodiment of the present invention is a system that uses LLM to guide users through the steps of data analysis, performing data integration, model selection, and action plan creation. This allows users to easily perform data analysis, improving work efficiency and decision-making accuracy.

[0057] A data analysis guide system according to an embodiment includes a step guide unit, a data linking unit, a model selection unit, and an action plan creation unit. The step guide unit guides the user through data analysis steps. For example, the step guide unit explains steps such as data collection, preprocessing, modeling, and evaluation based on the analysis content the user wants to perform. The data linking unit uses prompts or RAG to link data. For example, if a user requests a profit margin analysis, the data linking unit generates a prompt such as "Please provide profit margin data" to prompt the user to enter data. The data linking unit also uses RAG to automatically acquire related data and link the data required for the analysis. The model selection unit selects an appropriate analysis model. For example, the model selection unit determines that a regression analysis model is appropriate for profit margin analysis and a classification model is appropriate for defect rate analysis, and proposes each model. The action plan creation unit creates analysis actions and action plans. For example, the action plan creation unit proposes an action, such as "review a specific process to reduce costs," based on the profit margin analysis results and provides a specific plan for that action. As a result, the data analysis guide system according to the embodiment can guide the steps of data analysis and consistently perform data integration, model selection, and action plan creation.

[0058] The step guide unit can learn the user's past data analysis history and provide individually optimized step guides. For example, the LLM can learn the user's past data analysis history and provide individually optimized step guides. For example, for a user who has previously analyzed profit margins, similar steps can be suggested to efficiently proceed with the analysis. Furthermore, based on the user's past data analysis history, the LLM can identify stumbling blocks at specific steps and provide guides that include solutions. For example, it can show specific steps to prevent errors in data preprocessing. Furthermore, the LLM can learn the user's past analysis history and prioritize frequently used analysis methods and tools in the guide. For example, for a user who frequently uses a specific regression analysis model, it can provide guides centered on that model. This enables efficient data analysis by providing optimized guides based on the user's past data analysis history.

[0059] The step guide unit can understand the terminology and methods specific to the user's industry and generate a customized guide based on that. For example, the LLM learns the terminology and methods specific to the user's industry and generates a customized guide based on that. For example, a user in the manufacturing industry can be provided with a guide using terminology and methods specialized for defect rate analysis. The step guide unit also understands industry-specific data sets and analysis methods and customizes the step guide based on that. For example, a user in the financial industry can be provided with a guide specialized for risk analysis. The step guide unit also generates a guide tailored to the needs specific to the user's industry and incorporates industry-standard methods and tools. For example, a user in the medical industry can be provided with a guide specialized for patient data analysis. This allows the provision of customized guides based on industry-specific terminology and methods, enabling data analysis tailored to the user's business.

[0060] The step guide unit uses the emotion estimation function to provide guidance according to the user's emotional state, thereby reducing stress. The step guide unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and provide simplified guidance when stress is high. For example, if the user is feeling impatient, the step guide unit presents steps in an easy-to-understand manner. The step guide unit also provides guidance including encouragement and advice according to the user's emotional state. For example, if the user is feeling anxious, the step guide unit presents success stories and positive feedback. The emotion estimation function also adjusts the pace of the guidance according to the user's emotional state. For example, if the user is relaxed, the step guide unit provides guidance including detailed explanations to help the user concentrate. In this way, by providing guidance according to the user's emotional state, stress is reduced and the efficiency of data analysis is improved.

[0061] The step guide unit can provide seamless guidance across different devices. For example, the LLM can provide seamless guidance across different devices, such as smartphones, tablets, and PCs. For example, data analysis started on a PC can be continued on a smartphone. The step guide unit also synchronizes data between devices, allowing users to receive the same guidance from any device. For example, data input on a tablet can be reflected in analysis on a PC. The step guide unit also provides an interface optimized for each device, allowing users to receive guidance comfortably on any device. For example, a simplified guide is provided on a smartphone, and a detailed guide is provided on a PC. This allows seamless guidance across different devices, allowing users to continue data analysis on any device.

[0062] The step guide unit can work in conjunction with a voice assistant to provide voice guidance. For example, the LLM works in conjunction with the voice assistant to provide voice guidance. For example, when a user asks, "What should I do next?", the step guide unit responds by voice, saying, "Preprocess the data." The voice assistant also enables the user to proceed through the steps of data analysis without using their hands. For example, data loading and preprocessing can be instructed by voice command. The voice assistant also responds to the user's questions in real time and provides guidance for data analysis. For example, when the user asks, "What's the next step for this data?" appropriate guidance is provided by voice. In this way, by working in conjunction with the voice assistant, the user can proceed through the steps of data analysis without using their hands.

[0063] The step guide unit can use the emotion estimation function to provide guidance at a timing when the user is most relaxed. The step guide unit, for example, uses the emotion estimation function to provide guidance at a timing when the user is most relaxed. For example, it sends notifications during times when the user is relaxed. It also analyzes the user's emotional state in real time and provides guidance at a timing when stress is low. For example, it presents the next step when the user is relaxed. It also uses the emotion estimation function to provide advice to create an environment where the user can relax. For example, it suggests playing relaxing music. This improves the efficiency of data analysis by providing guidance at a timing when the user is most relaxed.

[0064] The data linking unit can learn the user's data input patterns and automatically generate optimal prompts. In the data linking unit, for example, the LLM learns the user's data input patterns and automatically generates optimal prompts. For example, it provides prompts in a format that is easy for the user to input based on past input history. It also analyzes the user's data input patterns and generates prompts to reduce input errors. For example, it automatically completes frequently entered data items. The LLM also learns the user's input patterns and provides prompts that improve data entry efficiency. For example, it predicts the next item to be entered based on past input content. In this way, it improves data entry efficiency by providing optimal prompts based on the user's data input patterns.

[0065] The data integration unit can automatically integrate data from different data sources to generate consistent data sets. For example, the LLM automatically integrates data from different data sources to generate consistent data sets. For example, it integrates data from multiple databases and eliminates duplication and inconsistencies. It also automatically converts data in different formats to generate consistent data sets. For example, it integrates CSV files and JSON files and provides them in a unified format. The LLM also analyzes the relationships between data sources and automatically extracts and integrates the necessary data. For example, it links customer data and sales data to generate a consistent data set. This integrates data from different data sources to generate consistent data sets and improves the accuracy of data analysis.

[0066] The data linking unit can use the emotion estimation function to provide prompts that reduce the anxiety the user feels when entering data. The data linking unit, for example, uses the emotion estimation function to provide prompts that reduce the anxiety the user feels when entering data. For example, it displays a prompt that includes specific advice to prevent input errors. It also analyzes the user's emotional state in real time and provides a prompt that includes an encouraging message if the user feels anxious. For example, it displays a message such as "It's okay, let's move on to the next step." It also uses the emotion estimation function to provide prompts that create a relaxing environment for the user. For example, it suggests playing relaxing music. This reduces the anxiety the user feels when entering data, thereby improving the accuracy and efficiency of data entry.

[0067] The data integration unit can support data input in different languages, enabling international data integration. For example, the LLM supports data input in different languages, enabling international data integration. For example, it accepts data input in multiple languages, such as English, Japanese, and Chinese. It also automatically translates data entered in different languages ​​to generate a consistent dataset. For example, it translates data entered in Japanese into English and integrates it. The LLM also provides multilingual prompts, allowing users to enter data in their native language. For example, it displays prompts according to the user's language settings. This supports data input in different languages, enabling international data integration.

[0068] The data linking unit can support multimodal data linking, including image and audio data. For example, the LLM supports multimodal data linking, including image and audio data. For example, it analyzes image data and integrates it with text data. It also converts audio data into text and integrates it with other data. For example, it automatically converts voice-input data into text and adds it to a dataset. It also uses image recognition technology to extract necessary information from image data and integrate it with other data. For example, it extracts product information from product images and registers it in a database. This supports multimodal data linking, including image and audio data, enabling analysis using a wider variety of data.

[0069] The data linking unit can use the emotion estimation function to prompt the user to enter data at a time when the user can concentrate best. The data linking unit, for example, uses the emotion estimation function to prompt the user to enter data at a time when the user can concentrate best. For example, it sends notifications during times when the user is concentrating. It also analyzes the user's emotional state in real time and prompts the user to enter data at a time when the user is most focused. For example, it presents the next step when the user is relaxed. It also uses the emotion estimation function to provide advice on creating an environment where the user can concentrate best. For example, it suggests playing music to improve concentration. In this way, by prompting the user to enter data at a time when the user can concentrate best, the accuracy and efficiency of data entry are improved.

[0070] The model selection unit can learn from the user's past analysis results and propose the optimal analysis model. For example, the LLM in the model selection unit learns from the user's past analysis results and proposes the optimal analysis model. For example, it proposes a model suitable for similar analysis based on analytical models that have been successful in the past. It can also analyze the user's past analysis results, find specific patterns, and propose the optimal analytical model based on those patterns. For example, it can prioritize the proposal of models that have shown high accuracy for a specific data set. The LLM can also learn from the user's past analysis history and prioritize the proposal of frequently used analytical models. For example, for a user who frequently uses regression analysis models, it will propose those models first. This improves the accuracy and efficiency of analysis by proposing the optimal analytical model based on the user's past analysis results.

[0071] The model selection unit can evaluate model performance in real time and dynamically select the optimal model. In the model selection unit, for example, the LLM evaluates model performance in real time and dynamically selects the optimal model. For example, it evaluates model accuracy according to data fluctuations and selects the optimal model. It also builds a system that monitors model performance in real time and switches models as needed. For example, it switches to a different model if performance deteriorates under certain conditions. The LLM also evaluates model performance in real time and proposes the optimal model. For example, it selects the optimal model according to the characteristics of the data and proposes it to the user. In this way, evaluating model performance in real time and dynamically selecting the optimal model improves the accuracy and efficiency of analysis.

[0072] The model selection unit can use the emotion estimation function to explain the reason for selecting a model in a manner that is easiest for the user to understand. The model selection unit, for example, uses the emotion estimation function to explain the reason for selecting a model in a manner that is easiest for the user to understand. For example, if the user is feeling anxious, a detailed explanation is provided. The model selection unit also analyzes the user's emotional state in real time and explains the reason for selecting a model in an easy-to-understand manner. For example, when the user is relaxed, a concise explanation is provided. The emotion estimation function also explains the reason for selecting a model in a way that is easy for the user to accept. For example, visual explanations and concrete examples are used depending on the user's emotional state. In this way, the reason for selecting a model can be explained in a manner that is easiest for the user to understand, thereby increasing the user's sense of acceptance and improving the accuracy and efficiency of the analysis.

[0073] The model selection unit can learn best practices from different industries and propose the optimal analytical model. For example, the LLM in the model selection unit learns best practices from different industries and proposes the optimal analytical model. For example, it proposes a model suitable for defect rate analysis based on best practices in the manufacturing industry. It also learns successful cases from different industries and proposes the optimal analytical model based on those. For example, it proposes a model suitable for risk analysis in the financial industry. The LLM also learns best practices from different industries and proposes the optimal analytical model for the user's industry. For example, it proposes a model suitable for data analysis in the medical industry. In this way, by proposing the optimal analytical model based on best practices from different industries, the accuracy and efficiency of analysis are improved.

[0074] The model selection unit selects a model according to the user's skill level, making it suitable for everyone from beginners to experts. For example, the model selection unit uses an LLM to select a model according to the user's skill level, making it suitable for everyone from beginners to experts. For example, it proposes a simple model for beginners and an advanced model for experts. It also builds a system that analyzes the user's skill level and selects a model accordingly. For example, it evaluates the user's skill level based on the user's past analysis history. It also provides a guide according to the user's skill level to support appropriate model selection. For example, it provides detailed explanations for beginners and simple explanations for experts. This allows it to select a model according to the user's skill level, making it suitable for a wide range of users, from beginners to experts.

[0075] The model selection unit can use the emotion estimation function to explain the reason for selecting a model in a manner that is most convincing to the user. The model selection unit, for example, uses the emotion estimation function to explain the reason for selecting a model in a manner that is most convincing to the user. For example, if the user is feeling anxious, a detailed explanation is provided. The model selection unit also analyzes the user's emotional state in real time and explains the reason for selecting a model in a manner that is most convincing to the user. For example, a concise explanation is provided when the user is relaxed. The emotion estimation function also explains the reason for selecting a model in a manner that is most convincing to the user. For example, visual explanations and concrete examples are used depending on the user's emotional state. In this way, the reason for selecting a model can be explained in a manner that is most convincing to the user, thereby increasing the user's sense of conviction and improving the accuracy and efficiency of the analysis.

[0076] The action plan creation unit can learn the user's past action plans and propose the optimal action plan. For example, the action plan creation unit uses the LLM to learn the user's past action plans and propose the optimal action plan. For example, it proposes a plan suitable for a similar situation based on action plans that have been successful in the past. It can also analyze the user's past action plans, find specific patterns, and propose the optimal action plan based on those patterns. For example, it can prioritize the proposal of action plans that are effective for a specific data set. It can also learn the user's past action plans and prioritize the proposal of frequently used action plans. For example, for a user who frequently uses action plans for cost reduction, it can mainly propose those plans. In this way, the optimal action plan is proposed based on the user's past action plans, improving the efficiency and accuracy of work.

[0077] The action plan creation department can monitor the progress of the action plan in real time and revise the plan as necessary. In the action plan creation department, for example, the LLM monitors the progress of the action plan in real time and revise the plan as necessary. For example, if progress is delayed, they will propose a review of the plan. In addition, a system can be built that monitors the progress of the action plan in real time and adjusts the plan according to the progress status. For example, if a specific task is not completed, they will propose a reallocation of resources. In addition, the LLM monitors the progress of the action plan in real time and revise the plan according to the progress status. For example, if progress is going well, they will present the next step early. In this way, by monitoring the progress of the action plan in real time and revising the plan as necessary, the efficiency and accuracy of work can be improved.

[0078] The action plan creation unit can use the emotion estimation function to propose an action plan that will most motivate the user. The action plan creation unit, for example, uses the emotion estimation function to propose an action plan that will most motivate the user. For example, it prioritizes proposing tasks that the user feels positive about. It also analyzes the user's emotional state in real time to propose an action plan that will increase motivation. For example, it proposes challenging tasks when the user is relaxed. It also uses the emotion estimation function to propose an action plan that will most motivate the user. For example, it proposes tasks that are likely to give the user a sense of accomplishment depending on the user's emotional state. This allows it to propose an action plan that will most motivate the user, thereby improving work efficiency and accuracy.

[0079] The action plan creation unit can study success stories from different industries and propose action plans based on them. In the action plan creation unit, for example, the LLM studies success stories from different industries and proposes action plans based on them. For example, an action plan for reducing defect rates is proposed based on success stories from the manufacturing industry. The action plan creation unit also studies success stories from different industries and proposes the optimal action plan based on them. For example, an action plan suitable for risk management in the financial industry is proposed. The LLM also studies success stories from different industries and proposes the optimal action plan for the user's industry. For example, an action plan based on data analysis from the medical industry is proposed. In this way, by proposing action plans based on success stories from different industries, the efficiency and accuracy of operations are improved.

[0080] The action plan creation unit can provide a function that promotes the sharing and cooperation of action plans among team members. For example, the action plan creation unit provides a function that allows LLM to promote the sharing and cooperation of action plans among team members. For example, it provides a platform for sharing action plans. It also builds a system that shares the progress of action plans among team members in real time and promotes cooperation. For example, it visualizes the progress and adjusts task allocation. It also provides communication tools that allow LLM to promote the sharing and cooperation of action plans among team members. For example, it integrates chat and comment functions. This promotes the sharing and cooperation of action plans among team members, thereby improving the efficiency and accuracy of work.

[0081] The action plan creation unit can use the emotion estimation function to present an action plan at a timing when the user feels most motivated. The action plan creation unit, for example, uses the emotion estimation function to present an action plan at a timing when the user feels most motivated. For example, it sends a notification during a time period when the user feels positive. It also analyzes the user's emotional state in real time and presents an action plan at a timing when the user feels most motivated. For example, it presents the next step when the user is relaxed. It also uses the emotion estimation function to provide advice for creating an environment that motivates the user. For example, it suggests playing music to increase motivation. In this way, by presenting an action plan at a timing when the user feels most motivated, the efficiency and accuracy of work are improved.

[0082] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0083] The step guide section can learn a user's past data analysis history and provide individually optimized step guides. For example, for a user who has previously analyzed profit margins, similar steps can be suggested, allowing for efficient analysis. It can also identify stumbling blocks at specific steps based on the user's past data analysis history and provide guides that include solutions. For example, it can show specific steps to prevent errors in data preprocessing. Furthermore, the LLM learns a user's past analysis history and prioritizes frequently used analysis methods and tools in the guide. For example, a user who frequently uses a specific regression analysis model will receive guides focused on that model. This allows for efficient data analysis by providing optimized guides based on the user's past data analysis history.

[0084] The step guide unit can understand the terminology and methods specific to the user's industry and generate a customized guide based on that. For example, the LLM learns the terminology and methods specific to the user's industry and generates a customized guide based on that. For example, a user in the manufacturing industry can be provided with a guide using terminology and methods specialized for defect rate analysis. The step guide can also be customized based on an understanding of industry-specific data sets and analysis methods. For example, a user in the financial industry can be provided with a guide specialized for risk analysis. The step guide can also be generated to meet the needs specific to the user's industry and incorporate industry-standard methods and tools. For example, a user in the medical industry can be provided with a guide specialized for patient data analysis. This allows for customized guides based on industry-specific terminology and methods, enabling data analysis tailored to the user's business.

[0085] The step guide unit can use the emotion estimation function to provide guidance according to the user's emotional state, thereby reducing stress. For example, the emotion estimation function can be used to analyze the user's emotional state in real time, and if stress is high, a simplified guide can be provided. For example, if the user is feeling impatient, steps can be divided into easy-to-understand sections and presented. Furthermore, guides including encouragement and advice can be provided according to the user's emotional state. For example, if the user is feeling anxious, success stories and positive feedback can be presented. Furthermore, the emotion estimation function can be used to adjust the pace of the guide according to the user's emotional state. For example, if the user is relaxed, a guide including detailed explanations can be provided to increase concentration. Thus, by providing guides according to the user's emotional state, stress can be reduced and the efficiency of data analysis can be improved.

[0086] The step guide unit can provide seamless guidance across different devices. For example, the LLM can provide seamless guidance across different devices, such as smartphones, tablets, and PCs. For example, data analysis started on a PC can be continued on a smartphone. It also synchronizes data between devices, allowing users to receive the same guidance from any device. For example, data input on a tablet can be reflected in analysis on a PC. It also provides an interface optimized for each device, allowing users to receive guidance comfortably on any device. For example, it provides a simplified guide on a smartphone and a detailed guide on a PC. This allows seamless guidance across different devices, allowing users to continue data analysis on any device.

[0087] The step guide unit can work with a voice assistant to provide voice guidance. For example, the LLM can work with a voice assistant to provide voice guidance. For example, when a user asks, "What should I do next?", the LLM can respond by voice, saying, "Preprocess the data." The voice assistant can also be used to allow users to proceed through the steps of data analysis without using their hands. For example, data loading and preprocessing can be instructed by voice command. The voice assistant can also respond to user questions in real time and provide guidance for data analysis. For example, when asking, "What's the next step for this data?", appropriate guidance can be provided by voice. In this way, by working with the voice assistant, users can proceed through the steps of data analysis without using their hands.

[0088] The step guide unit can use the emotion estimation function to provide guidance at the timing when the user is most relaxed. For example, the emotion estimation function can be used to provide guidance at the timing when the user is most relaxed. For example, notifications can be sent during times when the user is relaxed. The step guide unit can also analyze the user's emotional state in real time and provide guidance at a timing when stress is low. For example, the step guide unit can present the next step when the user is relaxed. The emotion estimation function can also be used to provide advice on creating an environment where the user can relax. For example, the step guide unit can suggest playing relaxing music. This improves the efficiency of data analysis by providing guidance at a timing when the user is most relaxed.

[0089] The data linking unit can learn a user's data input patterns and automatically generate optimal prompts. For example, the LLM learns a user's data input patterns and automatically generates optimal prompts. For example, it provides prompts in a format that is easy for the user to input based on past input history. It also analyzes a user's data input patterns and generates prompts to reduce input errors. For example, it automatically completes frequently entered data items. The LLM also learns a user's input patterns and provides prompts that improve data entry efficiency. For example, it predicts the next item to be entered based on past input content. This improves data entry efficiency by providing optimal prompts based on the user's data input patterns.

[0090] The data integration unit can automatically integrate data from different data sources to generate consistent data sets. For example, LLM automatically integrates data from different data sources to generate consistent data sets. For example, it integrates data from multiple databases and eliminates duplication and inconsistencies. It also automatically converts data in different formats to generate consistent data sets. For example, it integrates CSV files and JSON files and provides them in a unified format. LLM also analyzes the relationships between data sources and automatically extracts and integrates the necessary data. For example, it links customer data and sales data to generate a consistent data set. This allows data from different data sources to be integrated to generate consistent data sets and improve the accuracy of data analysis.

[0091] The data linking unit can use the emotion estimation function to provide prompts that reduce the anxiety the user feels when entering data. For example, the emotion estimation function can be used to provide prompts that reduce the anxiety the user feels when entering data. For example, a prompt containing specific advice to prevent input errors can be displayed. The data linking unit can also analyze the user's emotional state in real time and provide a prompt containing an encouraging message if the user feels anxious. For example, a message such as "It's okay, let's move on to the next step" can be displayed. The emotion estimation function can also be used to provide prompts that create a relaxing environment for the user. For example, the function can suggest playing relaxing music. This reduces the anxiety the user feels when entering data, thereby improving the accuracy and efficiency of data entry.

[0092] The data integration unit can support data input in different languages, enabling international data integration. For example, the LLM supports data input in different languages, enabling international data integration. For example, it accepts data input in multiple languages, such as English, Japanese, and Chinese. It also automatically translates data entered in different languages ​​to generate a consistent dataset. For example, it translates data entered in Japanese into English and integrates it. The LLM also provides multilingual prompts, allowing users to enter data in their native language. For example, it displays prompts according to the user's language settings. This supports data input in different languages, enabling international data integration.

[0093] The processing flow of the second embodiment will be briefly explained below.

[0094] Step 1: The step guide section helps users understand and guide them through the steps of data analysis. For example, the step guide section explains steps such as data collection, preprocessing, modeling, and evaluation based on the analysis content the user wants to perform. Step 2: The data linking unit uses prompts or RAGs to link data. For example, if a user requests that they "analyze profit margins," the data linking unit generates a prompt such as "Please provide profit margin data" to prompt the user to enter data. Furthermore, the data linking unit automatically retrieves related data using RAGs and links the data required for analysis. Step 3: The model selection unit selects an appropriate analysis model. For example, the model selection unit determines that a regression analysis model is appropriate for analyzing profit margins, and a classification model is appropriate for analyzing defect rates, and proposes each model. Step 4: The Action Plan Creation Department creates an analysis action and an action plan. For example, based on the profit margin analysis results, the Action Plan Creation Department proposes an action such as "reviewing a specific process to reduce costs" and provides a specific plan.

[0095] 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.

[0096] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0097] 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.

[0098] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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).

[0104] 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.

[0105] 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.

[0106] 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.

[0107] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0108] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0109] 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.

[0110] 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.

[0111] 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 AI 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.

[0112] 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.

[0113] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0114] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0123] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0124] 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.

[0125] 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.

[0126] 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 AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0127] 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.

[0128] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0138] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0139] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0141] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0142] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0143] The data processing system 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0149] 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."

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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]

[0162] 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 step guide section that helps you understand and guide you through the steps of data analysis, a data linking unit that links data using prompts or RAG; a model selection unit for selecting an appropriate analysis model; and an action plan creation unit that creates an analysis action and an action plan. A system characterized by:

2. The step guide portion is Learns the user's past data analysis history and provides individually optimized step-by-step guides The system of claim 1 .

3. The step guide portion is Understand your industry-specific terminology and techniques and generate customized guides based on them The system of claim 1 .

4. The step guide portion is Provide guidance based on the user's emotional state to reduce stress The system of claim 1 .

5. The step guide portion is Provide seamless guidance across devices The system of claim 1 .

6. The step guide portion is Links with voice assistants to provide audio guidance The system of claim 1 .

Images