System

Abstract

An object of the system according to the embodiment is to repeat hypothesis verification at high speed and frequently and to quickly announce a result useful for the industry.SOLUTION: A system includes a data analysis part, a document review part, an experiment design part, a report creation part, and a communication support part. The data analysis unit performs data analysis. The document review unit performs a document review. The experiment design unit proposes an experiment design. The report creator supports creation of a report. The communication support unit promotes communication and cooperation.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of making it difficult to rapidly and frequently repeat hypothesis testing and quickly publish results that are useful to industry.

[0005] The system according to the embodiment aims to rapidly and frequently repeat hypothesis verification and quickly publish results that are useful to industry. [Means for solving the problem]

[0006] The system according to the embodiment includes a data analysis unit, a literature review unit, an experiment design unit, a report creation unit, and a communication support unit. The data analysis unit performs data analysis. The literature review unit performs literature review. The experiment design unit proposes an experiment design. The report creation unit supports report creation. The communication support unit promotes communication and cooperation. [Effects of the Invention]

[0007] The system according to the embodiment can rapidly and frequently repeat hypothesis testing and quickly publish results that are useful to industry. [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 hypothesis verification system according to an embodiment of the present invention is a system that utilizes generative AI to rapidly and frequently repeat hypothesis verification and externally announce results that are useful to industry. As a result, the hypothesis verification system can rapidly and frequently verify hypotheses using generative AI and externally announce results that are useful to industry.

[0029] A hypothesis verification system according to an embodiment includes a data analysis unit, a literature review unit, an experiment design unit, a report creation unit, and a communication support unit. The data analysis unit performs data analysis. For example, the data analysis unit receives a dataset as input, applies statistical analysis and machine learning models, and outputs results. The data analysis unit can also automatically detect specific patterns and outliers from the dataset and reconstruct a hypothesis based on the detected patterns and outliers. The data analysis unit can also automatically remove noise during data preprocessing to generate a clean dataset. For example, the data analysis unit analyzes the dataset and automatically detects specific patterns and outliers. The data analysis unit preprocesses the dataset and automatically removes noise. The data analysis unit analyzes the dataset and, when an outlier is detected, evaluates the impact of the outlier and constructs a new hypothesis. The literature review unit performs a literature review. For example, the literature review unit receives as input a prompt to search for literature on a specific research topic and outputs summaries of related literature. The literature review unit can also analyze citation relationships between literature and evaluate the influence of important research. The literature review department can also automatically extract not only the literature summary but also the background and purpose of the research, providing a comprehensive review. For example, the literature review department analyzes the citation relationships of literature and evaluates the influence of important research. The literature review department automatically extracts the background and purpose of the research along with the literature summary. The literature review department visualizes the literature summary and provides it in a visually easy-to-understand format. The experimental design department proposes experimental designs. For example, the experimental design department receives the research objectives and conditions as input and outputs the optimal experimental design. The experimental design department can also analyze past experimental data and automatically propose optimal experimental conditions. The experimental design department can also perform experimental risk assessments and propose experimental designs that minimize risk. For example, the experimental design department receives the research objectives and conditions as input and outputs the optimal experimental design. The experimental design department analyzes past experimental data and automatically proposes optimal experimental conditions. The experimental design department performs experimental risk assessments and proposes experimental designs that minimize risk. The report writing department supports the creation of reports and papers.For example, the report writing department receives research data and results as input and suggests improvements to the document's structure and expression. The report writing department can also automatically optimize the document's structure and generate reports and papers in an easy-to-read format. The report writing department can also proofread documents and automatically correct typographical and grammatical errors. For example, the report writing department receives research data and results as input and suggests improvements to the document's structure and expression. The report writing department can automatically optimize the document's structure and generate reports and papers in an easy-to-read format. The report writing department can also proofread documents and automatically correct typographical and grammatical errors. The communication support department promotes communication and collaboration. For example, the communication support department receives research topics and objectives as input and suggests related researchers and collaborative research opportunities. The communication support department can also analyze communication history between researchers and suggest optimal communication methods. The communication support department can also monitor the progress of collaborative research in real time and automatically provide necessary feedback. For example, the communication support department receives research topics and objectives as input and suggests related researchers and collaborative research opportunities. The communication support unit analyzes communication history between researchers and proposes optimal communication methods. The communication support unit monitors the progress of collaborative research in real time and automatically provides necessary feedback. As a result, the hypothesis verification system according to the embodiment uses generative AI to quickly and frequently verify hypotheses and publish results useful to industry. For example, the data analysis unit analyzes datasets and automatically detects specific patterns and outliers. The literature review unit analyzes literature citations and evaluates the impact of important research. The experiment design unit analyzes past experimental data and automatically proposes optimal experimental conditions. The report creation unit automatically optimizes document structure and generates reports and papers in an easy-to-read format. The communication support unit receives research topics and objectives as input and proposes related researchers and collaborative research opportunities.

[0030] The data analysis unit can receive a dataset as input, apply statistical analysis or machine learning models, and output results. The data analysis unit, for example, analyzes a dataset and automatically detects specific patterns or outliers. For example, when an outlier is detected, it identifies the cause and proposes a new hypothesis. The data analysis unit can also analyze patterns within a dataset and discover specific trends or anomalies. For example, it can detect abnormal peaks in time series data and investigate the background behind them. The data analysis unit can also analyze a dataset and, when an outlier is detected, evaluate the impact of the outlier and construct a new hypothesis. This allows the data set to be analyzed, and statistical analysis or machine learning models to be applied to output results.

[0031] The literature review unit can receive as input a prompt to search for literature related to a research topic and output summaries of related literature. In the literature review unit, for example, the generative AI automatically removes noise during the data preprocessing stage to generate a clean dataset. For example, it filters noise from sensor data to generate a clean dataset. In addition, in the dataset preprocessing stage, the generative AI automatically detects outliers and missing values ​​and performs appropriate imputation. For example, it imputes missing values ​​with the average value. In addition, in the literature review unit, the generative AI preprocesses the dataset and removes noise, improving the accuracy of analysis. For example, it removes noise from image data to generate a clean image. This makes it possible to search for literature related to a specific research topic and output summaries of related literature.

[0032] The experimental design unit can receive the research objectives or conditions as input and output the optimal experimental design. For example, the generative AI in the experimental design unit evaluates the researchers' emotional responses to the data analysis results and proposes data interpretations that elicit positive emotions. For example, it can highlight success stories. The experimental design unit also uses an emotion estimation function to monitor the researchers' emotions regarding the data analysis results in real time and provide feedback to elicit positive emotions. The generative AI in the experimental design unit evaluates the researchers' emotional responses to the data analysis results and proposes data interpretations that elicit positive emotions. For example, it can highlight the possibility of success. This makes it possible to output the optimal experimental design based on the research objectives and conditions.

[0033] The report creation unit receives research data or results as input and can suggest improvements to the structure or expression of a document. For example, the report creation unit uses a generative AI to automatically optimize the structure of a document and generate a report or paper in an easy-to-read format. For example, the order of paragraphs may be adjusted. The report creation unit also builds a generative AI system that automatically optimizes the structure of a document and generates a report or paper in an easy-to-read format. For example, headings and subheadings may be appropriately positioned ... charts and graphs may be appropriately positioned. This makes it possible to suggest improvements to the structure and expression of a document based on the research data and results.

[0034] The communication support unit can receive a research theme or purpose as input and suggest related researchers or collaborative research opportunities. For example, the communication support unit uses a generative AI to analyze the communication history between researchers and suggest the optimal communication method. For example, it analyzes email and chat history. The communication support unit can also build a generative AI system that analyzes the communication history and suggests the optimal communication method. For example, it can analyze meeting minutes. The communication support unit can also use a generative AI to analyze the communication history between researchers and suggest the optimal communication method. For example, it can analyze the frequency and content of communication. This makes it possible to suggest related researchers and collaborative research opportunities based on the research theme and purpose.

[0035] The data analysis unit can automatically detect specific patterns and outliers within a dataset and reconstruct hypotheses based on them. For example, the data analysis unit has the generation AI analyze the dataset and automatically detect specific patterns and outliers. For example, if an outlier is detected, it identifies the cause and proposes a new hypothesis. The data analysis unit also has the generation AI analyze patterns within the dataset and discover specific trends and anomalies. For example, it detects abnormal peaks in time series data and investigates the background to them. Furthermore, when the generation AI analyzes a dataset and detects an outlier, the data analysis unit evaluates the impact of the outlier and constructs a new hypothesis. This makes it possible to automatically detect specific patterns and outliers within a dataset and reconstruct hypotheses based on them.

[0036] The data analysis unit can automatically remove noise at the data preprocessing stage and generate a clean dataset. In the data analysis unit, for example, the generation AI preprocesses the dataset and automatically removes noise. For example, it filters noise from sensor data and generates a clean dataset. In addition, in the data dataset preprocessing stage, the generation AI automatically detects outliers and missing values ​​and performs appropriate imputation. For example, it imputes missing values ​​with the average value. In addition, in the data analysis unit, the generation AI preprocesses the dataset and removes noise, improving the accuracy of the analysis. For example, it removes noise from image data and generates a clean image. In this way, noise can be automatically removed at the data preprocessing stage and a clean dataset can be generated.

[0037] The data analysis unit can integrate different data sources to perform more comprehensive data analysis. For example, the generation AI integrates sensor data and social media data to perform comprehensive data analysis. For example, it combines environmental sensor data with users' social media posts for analysis. The data analysis unit also integrates different data sources to enable the generation AI to perform more comprehensive data analysis. For example, it combines weather data and traffic data for analysis. The data analysis unit also integrates different data sources to enable the generation AI to analyze data correlations. For example, it combines health data and dietary data for analysis. This allows the generation AI to integrate different data sources to perform more comprehensive data analysis.

[0038] The data analysis unit can perform data analysis in real time and provide immediate feedback on the results. For example, the data analysis unit builds a system in which a generative AI performs data analysis in real time and provides immediate feedback on the results. For example, it analyzes sensor data in real time and detects anomalies. The data analysis unit also builds a generative AI system that performs data analysis in real time and provides immediate feedback on the results. For example, it analyzes financial data in real time and evaluates risk. The data analysis unit also develops a system in which a generative AI performs data analysis in real time and provides immediate feedback on the results. For example, it analyzes medical data in real time and assists in diagnosis. This makes it possible to perform data analysis in real time and provide immediate feedback on the results.

[0039] The literature review department can analyze the citation relationships of literature and evaluate the influence of important research. For example, the literature review department uses a generative AI to analyze the citation relationships of literature and evaluate the influence of important research. For example, it evaluates influence based on the number of citations and the number of times cited. The literature review department also builds a generative AI system that analyzes the citation relationships of literature and evaluates the influence of important research. For example, it analyzes citation networks. The literature review department also uses a generative AI to analyze the citation relationships of literature and identify highly influential research. For example, it prioritizes the evaluation of literature with a large number of citations. This makes it possible to analyze the citation relationships of literature and evaluate the influence of important research.

[0040] The literature review unit automatically extracts not only the literature summary but also the background and purpose of the research, thereby providing a comprehensive review. For example, the generative AI in the literature review unit automatically extracts not only the literature summary but also the background and purpose of the research, thereby providing a comprehensive review. For example, the purpose and background of the research are included in the summary. The literature review unit also builds a generative AI system that automatically extracts the background and purpose of the research along with the literature summary. For example, background information about the research is added to the summary. The literature review unit also builds a generative AI system that automatically extracts the background and purpose of the research along with the literature summary, thereby providing a comprehensive review. For example, the purpose of the research is clarified. This allows the generative AI to automatically extract not only the literature summary but also the background and purpose of the research, thereby providing a comprehensive review.

[0041] The literature review unit can automatically translate literature in different languages ​​and grasp international research trends. For example, the literature review unit uses a generative AI to automatically translate literature in different languages ​​and grasp international research trends. For example, it translates literature in English, French, Chinese, etc. The literature review unit also builds a generative AI system that automatically translates literature in different languages ​​and grasps international research trends. For example, it performs literature reviews that support multiple languages. The literature review unit also uses a generative AI to automatically translate literature in different languages ​​and grasp international research trends. For example, it analyzes research trends based on the translated literature. This makes it possible to automatically translate literature in different languages ​​and grasp international research trends.

[0042] The literature review unit can visualize the literature summary and provide it in a visually easy-to-understand format. For example, the literature review unit uses a generative AI to visualize the literature summary and provide it in a visually easy-to-understand format. For example, the literature review unit displays the summary using graphs and charts. The literature review unit also builds a generative AI system that visualizes the literature summary and provides it in a visually easy-to-understand format. For example, the literature review unit converts the summary into a diagram or table. The literature review unit also uses a generative AI to visualize the literature summary and provide it in a visually easy-to-understand format. For example, the summary is converted into an infographic. This allows the literature summary to be visualized and provided in a visually easy-to-understand format.

[0043] The experimental design department can analyze past experimental data and automatically propose optimal experimental conditions. In the experimental design department, for example, a generative AI analyzes past experimental data and automatically proposes optimal experimental conditions. For example, experimental conditions are set based on past successful cases. The experimental design department also builds a generative AI system that analyzes past experimental data and proposes optimal experimental conditions. For example, it optimizes experimental conditions. In addition, the experimental design department has a generative AI analyze past experimental data and automatically propose optimal experimental conditions. For example, it adjusts the parameters of the experimental conditions. This makes it possible to analyze past experimental data and automatically propose optimal experimental conditions.

[0044] The experimental design department can perform a risk assessment of an experiment and propose an experimental design that minimizes the risk. For example, the experimental design department has a generative AI perform a risk assessment of an experiment and propose an experimental design that minimizes the risk. For example, high-risk conditions are avoided. The experimental design department also builds a generative AI system that performs a risk assessment of an experiment and proposes an experimental design that minimizes the risk. For example, the experimental conditions are set based on the results of the risk assessment. The experimental design department also has a generative AI perform a risk assessment of an experiment and propose an experimental design that minimizes the risk. For example, low-risk conditions are selected as a priority. This makes it possible to perform a risk assessment of an experiment and propose an experimental design that minimizes the risk.

[0045] The Experimental Design Department can combine experimental methods from different fields to propose new experimental designs. For example, the generative AI in the Experimental Design Department combines experimental methods from different fields to propose new experimental designs. For example, combining methods from chemistry and biology. The Experimental Design Department can also build a generative AI system that combines experimental methods from different fields to propose new experimental designs. For example, integrating methods from physics and engineering. The Experimental Design Department can also build a generative AI system that combines experimental methods from different fields to propose new experimental designs. For example, combining methods from medicine and information science. This makes it possible to combine experimental methods from different fields to propose new experimental designs.

[0046] The experimental design department can simulate the experimental design and feed back optimal experimental conditions in real time. In the experimental design department, for example, a generation AI simulates the experimental design and feeds back optimal experimental conditions in real time. For example, the experimental conditions are adjusted based on the simulation results. The experimental design department also builds a generation AI system that simulates the experimental design and feeds back optimal experimental conditions in real time. For example, the experimental conditions are optimized based on the simulation results. In addition, the experimental design department can simulate the experimental design and feed back optimal experimental conditions in real time. For example, the experimental conditions are dynamically adjusted based on the simulation results. This allows the experimental design to be simulated and optimal experimental conditions to be fed back in real time.

[0047] The report creation unit can automatically optimize the structure of a document and generate reports or papers in an easy-to-read format. For example, the report creation unit uses a generative AI to automatically optimize the structure of a document and generate reports or papers in an easy-to-read format. For example, the order of paragraphs is adjusted. The report creation unit also builds a generative AI system that automatically optimizes the structure of a document and generates reports or papers in an easy-to-read format. For example, headings and subheadings are appropriately positioned. The report creation unit also uses a generative AI to automatically optimize the structure of a document and generate reports or papers in an easy-to-read format. For example, charts and graphs are appropriately positioned. In this way, the structure of a document can be automatically optimized and reports or papers can be generated in an easy-to-read format.

[0048] The report creation unit can proofread documents and automatically correct typos and grammatical errors. In the report creation unit, for example, a generation AI proofreads documents and automatically corrects typos and grammatical errors. For example, spelling mistakes are automatically corrected. The report creation unit also builds a generation AI system that proofreads documents and automatically corrects typos and grammatical errors. For example, grammar checks are performed. In the report creation unit, a generation AI proofreads documents and automatically corrects typos and grammatical errors. For example, grammatical errors are automatically corrected. This makes it possible to proofread documents and automatically correct typos and grammatical errors.

[0049] The report creation unit can support the creation of reports and papers in different formats. For example, the report creation unit uses a generative AI to support the creation of reports and papers in different formats. For example, it automatically generates slides for presentations. The report creation unit also builds a generative AI system that supports the creation of reports and papers in different formats. For example, it automatically generates designs for posters. The report creation unit also supports the creation of reports and papers in different formats. For example, it automatically generates graphs and charts for presentations. This makes it possible to support the creation of reports and papers in different formats.

[0050] The report creation unit can visualize the contents of the document and provide it in a format that is visually easy to understand. For example, the report creation unit uses a generation AI to visualize the contents of the document and provide it in a format that is visually easy to understand. For example, data is displayed using graphs and charts. The report creation unit also builds a generation AI system that visualizes the contents of the document and provides it in a format that is visually easy to understand. For example, infographics are created. The report creation unit also builds a generation AI system that visualizes the contents of the document and provides it in a format that is visually easy to understand. For example, data is visualized. This allows the contents of the document to be visualized and provided in a format that is visually easy to understand.

[0051] The communication support unit can analyze the communication history between researchers and propose the optimal communication method. For example, the communication support unit uses a generation AI to analyze the communication history between researchers and propose the optimal communication method. For example, it analyzes email and chat history. The communication support unit can also build a generation AI system that analyzes the communication history and propose the optimal communication method. For example, it can analyze meeting minutes. The communication support unit can also use a generation AI to analyze the communication history between researchers and propose the optimal communication method. For example, it can analyze the frequency and content of communication. This makes it possible to analyze the communication history between researchers and propose the optimal communication method.

[0052] The communication support unit can monitor the progress of collaborative research in real time and automatically provide necessary feedback. For example, the communication support unit allows a generative AI to monitor the progress of collaborative research in real time and automatically provide necessary feedback. For example, it visualizes the progress. The communication support unit also builds a generative AI system that monitors the progress of collaborative research in real time and automatically provides necessary feedback. For example, it tracks the progress of tasks. The communication support unit also allows a generative AI to monitor the progress of collaborative research in real time and automatically provide necessary feedback. For example, it provides advice according to the progress. This makes it possible to monitor the progress of collaborative research in real time and automatically provide necessary feedback.

[0053] The communication support unit can automatically match researchers from different fields and provide new opportunities for collaborative research. For example, the generative AI in the communication support unit can automatically match researchers from different fields and provide new opportunities for collaborative research. For example, matching can be done based on research themes or areas of expertise. The communication support unit can also build a generative AI system that automatically matches researchers from different fields and provide new opportunities for collaborative research. For example, by analyzing researchers' profiles. The communication support unit can also automatically match researchers from different fields and provide new opportunities for collaborative research. For example, matching can be done based on researchers' past achievements. This makes it possible to automatically match researchers from different fields and provide new opportunities for collaborative research.

[0054] The communication support unit can automatically translate communication content to support international collaborative research. For example, the communication support unit uses a generative AI to automatically translate communication content to support international collaborative research. For example, it translates the content of emails and chats. The communication support unit can also build a generative AI system that automatically translates communication content to support international collaborative research. For example, it translates meeting minutes. The communication support unit can also automatically translate communication content to support international collaborative research. For example, it translates research reports and papers. This allows the communication content to be automatically translated to support international collaborative research.

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

[0056] Hypothesis testing systems can also integrate data from different data sources to perform more comprehensive hypothesis testing. For example, integrating and analyzing sensor data and social media data can clarify the relationship between environmental factors and user behavior patterns. Furthermore, integrating and analyzing weather data and traffic data can evaluate the impact of weather on traffic flow. Furthermore, integrating and analyzing health data and dietary data can evaluate the impact of diet on health.

[0057] Hypothesis testing systems can also be equipped with the functionality to combine experimental methods from different fields and propose new experimental designs. For example, by combining methods from chemistry and biology, it can propose an experimental design to evaluate the effects of a new drug. Similarly, by integrating methods from physics and engineering, it can propose an experimental design to evaluate the properties of a new material. Furthermore, by combining methods from medicine and information science, it can analyze patient data and propose an experimental design to suggest the optimal treatment.

[0058] Hypothesis testing systems can also be equipped with functions to support the creation of reports and papers in different formats. For example, by automatically generating presentation slides, research results can be communicated effectively. By automatically generating poster designs, presentations at academic conferences and exhibitions can be supported. Furthermore, by automatically generating graphs and charts for presentations, data can be visualized and reports and papers can be provided in a format that is visually easy to understand.

[0059] Hypothesis testing systems can also be equipped with the ability to automatically translate literature in different languages ​​and grasp international research trends. For example, by translating literature from English, French, Chinese, etc., it is possible to integrate research results from different languages ​​and provide a comprehensive review. In addition, by conducting multilingual literature reviews, it is possible to grasp international research trends and incorporate the latest research results. Furthermore, by analyzing research trends based on translated literature, it is possible to compare research results from different languages ​​and obtain integrated knowledge.

[0060] Hypothesis testing systems can also be equipped with a function that automatically matches researchers from different fields and provides new opportunities for collaborative research. For example, by matching based on research themes or areas of expertise, researchers from different fields can collaborate to advance new research. Furthermore, by analyzing researchers' profiles, it is possible to match researchers with common interests and goals. Furthermore, by matching based on researchers' past achievements, it is possible to find researchers who complement each other and provide new opportunities for collaborative research.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The data analysis unit performs data analysis. The data analysis unit receives a dataset as input, applies statistical analysis and machine learning models, and outputs the results. It can also automatically detect specific patterns and outliers in the dataset and reconstruct hypotheses based on them. Furthermore, it can automatically remove noise during the data preprocessing stage to generate a clean dataset. Step 2: The literature review module performs a literature review. The literature review module receives a prompt to search for literature on a specific research topic as input and outputs summaries of relevant literature. It can also analyze citation relationships between literature and evaluate the influence of important research. Furthermore, it can automatically extract not only literature summaries but also the background and purpose of the research to provide a comprehensive review. Step 3: The experimental design department proposes an experimental design. The experimental design department receives the research objectives and conditions as input and outputs the optimal experimental design. It can also analyze past experimental data and automatically propose optimal experimental conditions. It can also perform a risk assessment of the experiment and propose an experimental design that minimizes the risks. Step 4: The Report Writer assists in the creation of reports and papers. The Report Writer receives research data and results as input and suggests improvements to the structure and presentation of the document. It can also automatically optimize the structure of the document and generate reports and papers in an easy-to-read format. It can also proofread the document and automatically correct typos and grammatical errors. Step 5: The Communication Support Unit promotes communication and collaboration. The Communication Support Unit receives research topics and objectives as input and suggests related researchers and collaborative research opportunities. It can also analyze communication history between researchers and suggest optimal communication methods. It can also monitor the progress of collaborative research in real time and automatically provide necessary feedback.

[0063] (Example 2) A hypothesis verification system according to an embodiment of the present invention is a system that utilizes generative AI to rapidly and frequently repeat hypothesis verification and externally announce results that are useful to industry. As a result, the hypothesis verification system can rapidly and frequently verify hypotheses using generative AI and externally announce results that are useful to industry.

[0064] A hypothesis verification system according to an embodiment includes a data analysis unit, a literature review unit, an experiment design unit, a report creation unit, and a communication support unit. The data analysis unit performs data analysis. For example, the data analysis unit receives a dataset as input, applies statistical analysis and machine learning models, and outputs results. The data analysis unit can also automatically detect specific patterns and outliers from the dataset and reconstruct a hypothesis based on the detected patterns and outliers. The data analysis unit can also automatically remove noise during data preprocessing to generate a clean dataset. For example, the data analysis unit analyzes the dataset and automatically detects specific patterns and outliers. The data analysis unit preprocesses the dataset and automatically removes noise. The data analysis unit analyzes the dataset and, when an outlier is detected, evaluates the impact of the outlier and constructs a new hypothesis. The literature review unit performs a literature review. For example, the literature review unit receives as input a prompt to search for literature on a specific research topic and outputs summaries of related literature. The literature review unit can also analyze citation relationships between literature and evaluate the influence of important research. The literature review department can also automatically extract not only the literature summary but also the background and purpose of the research, providing a comprehensive review. For example, the literature review department analyzes the citation relationships of literature and evaluates the influence of important research. The literature review department automatically extracts the background and purpose of the research along with the literature summary. The literature review department visualizes the literature summary and provides it in a visually easy-to-understand format. The experimental design department proposes experimental designs. For example, the experimental design department receives the research objectives and conditions as input and outputs the optimal experimental design. The experimental design department can also analyze past experimental data and automatically propose optimal experimental conditions. The experimental design department can also perform experimental risk assessments and propose experimental designs that minimize risk. For example, the experimental design department receives the research objectives and conditions as input and outputs the optimal experimental design. The experimental design department analyzes past experimental data and automatically proposes optimal experimental conditions. The experimental design department performs experimental risk assessments and proposes experimental designs that minimize risk. The report writing department supports the creation of reports and papers.For example, the report writing department receives research data and results as input and suggests improvements to the document's structure and expression. The report writing department can also automatically optimize the document's structure and generate reports and papers in an easy-to-read format. The report writing department can also proofread documents and automatically correct typographical and grammatical errors. For example, the report writing department receives research data and results as input and suggests improvements to the document's structure and expression. The report writing department can automatically optimize the document's structure and generate reports and papers in an easy-to-read format. The report writing department can also proofread documents and automatically correct typographical and grammatical errors. The communication support department promotes communication and collaboration. For example, the communication support department receives research topics and objectives as input and suggests related researchers and collaborative research opportunities. The communication support department can also analyze communication history between researchers and suggest optimal communication methods. The communication support department can also monitor the progress of collaborative research in real time and automatically provide necessary feedback. For example, the communication support department receives research topics and objectives as input and suggests related researchers and collaborative research opportunities. The communication support unit analyzes communication history between researchers and proposes optimal communication methods. The communication support unit monitors the progress of collaborative research in real time and automatically provides necessary feedback. As a result, the hypothesis verification system according to the embodiment uses generative AI to quickly and frequently verify hypotheses and publish results useful to industry. For example, the data analysis unit analyzes datasets and automatically detects specific patterns and outliers. The literature review unit analyzes literature citations and evaluates the impact of important research. The experiment design unit analyzes past experimental data and automatically proposes optimal experimental conditions. The report creation unit automatically optimizes document structure and generates reports and papers in an easy-to-read format. The communication support unit receives research topics and objectives as input and proposes related researchers and collaborative research opportunities.

[0065] The data analysis unit can receive a dataset as input, apply statistical analysis or machine learning models, and output results. The data analysis unit, for example, analyzes a dataset and automatically detects specific patterns or outliers. For example, when an outlier is detected, it identifies the cause and proposes a new hypothesis. The data analysis unit can also analyze patterns within a dataset and discover specific trends or anomalies. For example, it can detect abnormal peaks in time series data and investigate the background behind them. The data analysis unit can also analyze a dataset and, when an outlier is detected, evaluate the impact of the outlier and construct a new hypothesis. This allows the data set to be analyzed, and statistical analysis or machine learning models to be applied to output results.

[0066] The literature review unit can receive as input a prompt to search for literature related to a research topic and output summaries of related literature. In the literature review unit, for example, the generative AI automatically removes noise during the data preprocessing stage to generate a clean dataset. For example, it filters noise from sensor data to generate a clean dataset. In addition, in the dataset preprocessing stage, the generative AI automatically detects outliers and missing values ​​and performs appropriate imputation. For example, it imputes missing values ​​with the average value. In addition, in the literature review unit, the generative AI preprocesses the dataset and removes noise, improving the accuracy of analysis. For example, it removes noise from image data to generate a clean image. This makes it possible to search for literature related to a specific research topic and output summaries of related literature.

[0067] The experimental design unit can receive the research objectives or conditions as input and output the optimal experimental design. For example, the generative AI in the experimental design unit evaluates the researchers' emotional responses to the data analysis results and proposes data interpretations that elicit positive emotions. For example, it can highlight success stories. The experimental design unit also uses an emotion estimation function to monitor the researchers' emotions regarding the data analysis results in real time and provide feedback to elicit positive emotions. The generative AI in the experimental design unit evaluates the researchers' emotional responses to the data analysis results and proposes data interpretations that elicit positive emotions. For example, it can highlight the possibility of success. This makes it possible to output the optimal experimental design based on the research objectives and conditions.

[0068] The report creation unit receives research data or results as input and can suggest improvements to the structure or expression of a document. For example, the report creation unit uses a generative AI to automatically optimize the structure of a document and generate a report or paper in an easy-to-read format. For example, the order of paragraphs may be adjusted. The report creation unit also builds a generative AI system that automatically optimizes the structure of a document and generates a report or paper in an easy-to-read format. For example, headings and subheadings may be appropriately positioned ... charts and graphs may be appropriately positioned. This makes it possible to suggest improvements to the structure and expression of a document based on the research data and results.

[0069] The communication support unit can receive a research theme or purpose as input and suggest related researchers or collaborative research opportunities. For example, the communication support unit uses a generative AI to analyze the communication history between researchers and suggest the optimal communication method. For example, it analyzes email and chat history. The communication support unit can also build a generative AI system that analyzes the communication history and suggests the optimal communication method. For example, it can analyze meeting minutes. The communication support unit can also use a generative AI to analyze the communication history between researchers and suggest the optimal communication method. For example, it can analyze the frequency and content of communication. This makes it possible to suggest related researchers and collaborative research opportunities based on the research theme and purpose.

[0070] The data analysis unit can automatically detect specific patterns and outliers within a dataset and reconstruct hypotheses based on them. For example, the data analysis unit has the generation AI analyze the dataset and automatically detect specific patterns and outliers. For example, if an outlier is detected, it identifies the cause and proposes a new hypothesis. The data analysis unit also has the generation AI analyze patterns within the dataset and discover specific trends and anomalies. For example, it detects abnormal peaks in time series data and investigates the background to them. Furthermore, when the generation AI analyzes a dataset and detects an outlier, the data analysis unit evaluates the impact of the outlier and constructs a new hypothesis. This makes it possible to automatically detect specific patterns and outliers within a dataset and reconstruct hypotheses based on them.

[0071] The data analysis unit can automatically remove noise at the data preprocessing stage and generate a clean dataset. In the data analysis unit, for example, the generation AI preprocesses the dataset and automatically removes noise. For example, it filters noise from sensor data and generates a clean dataset. In addition, in the data dataset preprocessing stage, the generation AI automatically detects outliers and missing values ​​and performs appropriate imputation. For example, it imputes missing values ​​with the average value. In addition, in the data analysis unit, the generation AI preprocesses the dataset and removes noise, improving the accuracy of the analysis. For example, it removes noise from image data and generates a clean image. In this way, noise can be automatically removed at the data preprocessing stage and a clean dataset can be generated.

[0072] The data analysis unit uses the emotion estimation function to evaluate the researcher's emotional response to the data analysis results and propose data interpretations that elicit positive emotions. For example, the data analysis unit uses the generative AI to evaluate the researcher's emotional response to the data analysis results and propose data interpretations that elicit positive emotions. For example, by emphasizing success stories. The data analysis unit also uses the emotion estimation function to monitor the researcher's emotions regarding the data analysis results in real time and provide feedback to elicit positive emotions. The data analysis unit also uses the generative AI to evaluate the researcher's emotional response to the data analysis results and propose data interpretations that elicit positive emotions. For example, by emphasizing the possibility of success. This makes it possible to evaluate the researcher's emotional response to the data analysis results and propose data interpretations that elicit positive emotions.

[0073] The data analysis unit can integrate different data sources to perform more comprehensive data analysis. For example, the generation AI integrates sensor data and social media data to perform comprehensive data analysis. For example, it combines environmental sensor data with users' social media posts for analysis. The data analysis unit also integrates different data sources to enable the generation AI to perform more comprehensive data analysis. For example, it combines weather data and traffic data for analysis. The data analysis unit also integrates different data sources to enable the generation AI to analyze data correlations. For example, it combines health data and dietary data for analysis. This allows the generation AI to integrate different data sources to perform more comprehensive data analysis.

[0074] The data analysis unit can perform data analysis in real time and provide immediate feedback on the results. For example, the data analysis unit builds a system in which a generative AI performs data analysis in real time and provides immediate feedback on the results. For example, it analyzes sensor data in real time and detects anomalies. The data analysis unit also builds a generative AI system that performs data analysis in real time and provides immediate feedback on the results. For example, it analyzes financial data in real time and evaluates risk. The data analysis unit also develops a system in which a generative AI performs data analysis in real time and provides immediate feedback on the results. For example, it analyzes medical data in real time and assists in diagnosis. This makes it possible to perform data analysis in real time and provide immediate feedback on the results.

[0075] The data analysis unit can use the emotion estimation function to monitor the user's emotions regarding the data analysis results in real time and dynamically adjust the analysis method. For example, the data analysis unit can use the emotion estimation function to monitor the user's emotions regarding the data analysis results in real time and dynamically adjust the analysis method. For example, the analysis method can be changed if negative emotions are strong. The data analysis unit also uses the generative AI to monitor the user's emotions regarding the data analysis results in real time and adjust the analysis method to elicit positive emotions. For example, success stories can be emphasized. The data analysis unit also uses the emotion estimation function to build a system that monitors the user's emotions regarding the data analysis results in real time and dynamically adjusts the analysis method. This makes it possible to monitor the user's emotions regarding the data analysis results in real time and dynamically adjust the analysis method.

[0076] The literature review department can analyze the citation relationships of literature and evaluate the influence of important research. For example, the literature review department uses a generative AI to analyze the citation relationships of literature and evaluate the influence of important research. For example, it evaluates influence based on the number of citations and the number of times cited. The literature review department also builds a generative AI system that analyzes the citation relationships of literature and evaluates the influence of important research. For example, it analyzes citation networks. The literature review department also uses a generative AI to analyze the citation relationships of literature and identify highly influential research. For example, it prioritizes the evaluation of literature with a large number of citations. This makes it possible to analyze the citation relationships of literature and evaluate the influence of important research.

[0077] The literature review unit automatically extracts not only the literature summary but also the background and purpose of the research, thereby providing a comprehensive review. For example, the generative AI in the literature review unit automatically extracts not only the literature summary but also the background and purpose of the research, thereby providing a comprehensive review. For example, the purpose and background of the research are included in the summary. The literature review unit also builds a generative AI system that automatically extracts the background and purpose of the research along with the literature summary. For example, background information about the research is added to the summary. The literature review unit also builds a generative AI system that automatically extracts the background and purpose of the research along with the literature summary, thereby providing a comprehensive review. For example, the purpose of the research is clarified. This allows the generative AI to automatically extract not only the literature summary but also the background and purpose of the research, thereby providing a comprehensive review.

[0078] The literature review unit can use the emotion estimation function to evaluate the researcher's emotions regarding the results of the literature review and generate summaries that elicit positive emotions. For example, the literature review unit can use the emotion estimation function to evaluate the researcher's emotions regarding the results of the literature review and generate summaries that elicit positive emotions. For example, by emphasizing success stories. The literature review unit also uses a generation AI to monitor the researcher's emotions regarding the results of the literature review in real time and generate summaries that elicit positive emotions. For example, by emphasizing positive elements. The literature review unit also uses the emotion estimation function to build a system that evaluates the researcher's emotions regarding the results of the literature review and generates summaries that elicit positive emotions. This makes it possible to evaluate the researcher's emotions regarding the results of the literature review and generate summaries that elicit positive emotions.

[0079] The literature review unit can automatically translate literature in different languages ​​and grasp international research trends. For example, the literature review unit uses a generative AI to automatically translate literature in different languages ​​and grasp international research trends. For example, it translates literature in English, French, Chinese, etc. The literature review unit also builds a generative AI system that automatically translates literature in different languages ​​and grasps international research trends. For example, it performs literature reviews that support multiple languages. The literature review unit also uses a generative AI to automatically translate literature in different languages ​​and grasp international research trends. For example, it analyzes research trends based on the translated literature. This makes it possible to automatically translate literature in different languages ​​and grasp international research trends.

[0080] The literature review unit can visualize the literature summary and provide it in a visually easy-to-understand format. For example, the literature review unit uses a generative AI to visualize the literature summary and provide it in a visually easy-to-understand format. For example, the literature review unit displays the summary using graphs and charts. The literature review unit also builds a generative AI system that visualizes the literature summary and provides it in a visually easy-to-understand format. For example, the literature review unit converts the summary into a diagram or table. The literature review unit also uses a generative AI to visualize the literature summary and provide it in a visually easy-to-understand format. For example, the summary is converted into an infographic. This allows the literature summary to be visualized and provided in a visually easy-to-understand format.

[0081] The literature review unit can use the emotion estimation function to monitor the user's emotions regarding the results of the literature review in real time and dynamically adjust the review content. For example, the literature review unit can use the emotion estimation function to monitor the user's emotions regarding the results of the literature review in real time and dynamically adjust the review content. For example, the review content can be changed if negative emotions are strong. The literature review unit also uses a generation AI to monitor the user's emotions regarding the results of the literature review in real time and adjust the review content to elicit positive emotions. For example, it can emphasize success stories. The literature review unit also uses the emotion estimation function to build a system that monitors the user's emotions regarding the results of the literature review in real time and dynamically adjusts the review content. This makes it possible to monitor the user's emotions regarding the results of the literature review in real time and dynamically adjust the review content.

[0082] The experimental design department can analyze past experimental data and automatically propose optimal experimental conditions. In the experimental design department, for example, a generative AI analyzes past experimental data and automatically proposes optimal experimental conditions. For example, experimental conditions are set based on past successful cases. The experimental design department also builds a generative AI system that analyzes past experimental data and proposes optimal experimental conditions. For example, it optimizes experimental conditions. In addition, the experimental design department has a generative AI analyze past experimental data and automatically propose optimal experimental conditions. For example, it adjusts the parameters of the experimental conditions. This makes it possible to analyze past experimental data and automatically propose optimal experimental conditions.

[0083] The experimental design department can perform a risk assessment of an experiment and propose an experimental design that minimizes the risk. For example, the experimental design department has a generative AI perform a risk assessment of an experiment and propose an experimental design that minimizes the risk. For example, high-risk conditions are avoided. The experimental design department also builds a generative AI system that performs a risk assessment of an experiment and proposes an experimental design that minimizes the risk. For example, the experimental conditions are set based on the results of the risk assessment. The experimental design department also has a generative AI perform a risk assessment of an experiment and propose an experimental design that minimizes the risk. For example, low-risk conditions are selected as a priority. This makes it possible to perform a risk assessment of an experiment and propose an experimental design that minimizes the risk.

[0084] The experimental design department can use the emotion estimation function to evaluate researchers' emotions regarding the experimental design and propose an experimental plan that will elicit positive emotions. For example, the experimental design department can use the emotion estimation function to evaluate researchers' emotions regarding the experimental design and propose an experimental plan that will elicit positive emotions. For example, by emphasizing the possibility of success. The experimental design department also uses a generative AI to monitor researchers' emotions regarding the experimental design in real time and provide feedback to elicit positive emotions. The experimental design department also uses the emotion estimation function to build a system that evaluates researchers' emotions regarding the experimental design and proposes an experimental plan that will elicit positive emotions. This makes it possible to evaluate researchers' emotions regarding the experimental design and propose an experimental plan that will elicit positive emotions.

[0085] The Experimental Design Department can combine experimental methods from different fields to propose new experimental designs. For example, the generative AI in the Experimental Design Department combines experimental methods from different fields to propose new experimental designs. For example, combining methods from chemistry and biology. The Experimental Design Department can also build a generative AI system that combines experimental methods from different fields to propose new experimental designs. For example, integrating methods from physics and engineering. The Experimental Design Department can also build a generative AI system that combines experimental methods from different fields to propose new experimental designs. For example, combining methods from medicine and information science. This makes it possible to combine experimental methods from different fields to propose new experimental designs.

[0086] The experimental design department can simulate the experimental design and feed back optimal experimental conditions in real time. In the experimental design department, for example, a generation AI simulates the experimental design and feeds back optimal experimental conditions in real time. For example, the experimental conditions are adjusted based on the simulation results. The experimental design department also builds a generation AI system that simulates the experimental design and feeds back optimal experimental conditions in real time. For example, the experimental conditions are optimized based on the simulation results. In addition, the experimental design department can simulate the experimental design and feed back optimal experimental conditions in real time. For example, the experimental conditions are dynamically adjusted based on the simulation results. This allows the experimental design to be simulated and optimal experimental conditions to be fed back in real time.

[0087] The experimental design department can use the emotion estimation function to monitor user emotions regarding the experimental design in real time and dynamically adjust the design method. For example, the experimental design department can use the emotion estimation function to monitor user emotions regarding the experimental design in real time and dynamically adjust the design method. For example, the design method can be changed if negative emotions are strong. The experimental design department also uses a generative AI to monitor user emotions regarding the experimental design in real time and adjust the design method to elicit positive emotions. For example, success stories can be emphasized. The experimental design department also uses the emotion estimation function to build a system that monitors user emotions regarding the experimental design in real time and dynamically adjusts the design method. This makes it possible to monitor user emotions regarding the experimental design in real time and dynamically adjust the design method.

[0088] The report creation unit can automatically optimize the structure of a document and generate reports or papers in an easy-to-read format. For example, the report creation unit uses a generative AI to automatically optimize the structure of a document and generate reports or papers in an easy-to-read format. For example, the order of paragraphs is adjusted. The report creation unit also builds a generative AI system that automatically optimizes the structure of a document and generates reports or papers in an easy-to-read format. For example, headings and subheadings are appropriately positioned. The report creation unit also uses a generative AI to automatically optimize the structure of a document and generate reports or papers in an easy-to-read format. For example, charts and graphs are appropriately positioned. In this way, the structure of a document can be automatically optimized and reports or papers can be generated in an easy-to-read format.

[0089] The report creation unit can proofread documents and automatically correct typos and grammatical errors. In the report creation unit, for example, a generation AI proofreads documents and automatically corrects typos and grammatical errors. For example, spelling mistakes are automatically corrected. The report creation unit also builds a generation AI system that proofreads documents and automatically corrects typos and grammatical errors. For example, grammar checks are performed. In the report creation unit, a generation AI proofreads documents and automatically corrects typos and grammatical errors. For example, grammatical errors are automatically corrected. This makes it possible to proofread documents and automatically correct typos and grammatical errors.

[0090] The report creation unit can use the emotion estimation function to evaluate the reader's emotions regarding the content of a report or paper and suggest expressions that elicit positive emotions. For example, the report creation unit uses the emotion estimation function to evaluate the reader's emotions regarding the content of a report or paper and suggest expressions that elicit positive emotions. For example, the report creation unit emphasizes positive expressions. The report creation unit also uses a generative AI to monitor the reader's emotions regarding the content of a report or paper in real time and provide feedback to elicit positive emotions. The report creation unit also uses the emotion estimation function to build a system that evaluates the reader's emotions regarding the content of a report or paper and suggests expressions that elicit positive emotions. This makes it possible to evaluate the reader's emotions regarding the content of a report or paper and suggest expressions that elicit positive emotions.

[0091] The report creation unit can support the creation of reports and papers in different formats. For example, the report creation unit uses a generative AI to support the creation of reports and papers in different formats. For example, it automatically generates slides for presentations. The report creation unit also builds a generative AI system that supports the creation of reports and papers in different formats. For example, it automatically generates designs for posters. The report creation unit also supports the creation of reports and papers in different formats. For example, it automatically generates graphs and charts for presentations. This makes it possible to support the creation of reports and papers in different formats.

[0092] The report creation unit can visualize the contents of the document and provide it in a format that is visually easy to understand. For example, the report creation unit uses a generation AI to visualize the contents of the document and provide it in a format that is visually easy to understand. For example, data is displayed using graphs and charts. The report creation unit also builds a generation AI system that visualizes the contents of the document and provides it in a format that is visually easy to understand. For example, infographics are created. The report creation unit also builds a generation AI system that visualizes the contents of the document and provides it in a format that is visually easy to understand. For example, data is visualized. This allows the contents of the document to be visualized and provided in a format that is visually easy to understand.

[0093] The report creation unit can use the emotion estimation function to monitor the user's emotions regarding the content of a report or paper in real time and dynamically adjust the content. For example, the report creation unit can use the emotion estimation function to monitor the user's emotions regarding the content of a report or paper in real time and dynamically adjust the content. For example, the content can be changed if negative emotions are strong. The report creation unit also uses a generation AI to monitor the user's emotions regarding the content of a report or paper in real time and adjust the content to elicit positive emotions. For example, success stories can be emphasized. The report creation unit also uses the emotion estimation function to build a system that monitors the user's emotions regarding the content of a report or paper in real time and dynamically adjusts the content. This makes it possible to monitor the user's emotions regarding the content of a report or paper in real time and dynamically adjust the content.

[0094] The communication support unit can analyze the communication history between researchers and propose the optimal communication method. For example, the communication support unit uses a generation AI to analyze the communication history between researchers and propose the optimal communication method. For example, it analyzes email and chat history. The communication support unit can also build a generation AI system that analyzes the communication history and propose the optimal communication method. For example, it can analyze meeting minutes. The communication support unit can also use a generation AI to analyze the communication history between researchers and propose the optimal communication method. For example, it can analyze the frequency and content of communication. This makes it possible to analyze the communication history between researchers and propose the optimal communication method.

[0095] The communication support unit can monitor the progress of collaborative research in real time and automatically provide necessary feedback. For example, the communication support unit allows a generative AI to monitor the progress of collaborative research in real time and automatically provide necessary feedback. For example, it visualizes the progress. The communication support unit also builds a generative AI system that monitors the progress of collaborative research in real time and automatically provides necessary feedback. For example, it tracks the progress of tasks. The communication support unit also allows a generative AI to monitor the progress of collaborative research in real time and automatically provide necessary feedback. For example, it provides advice according to the progress. This makes it possible to monitor the progress of collaborative research in real time and automatically provide necessary feedback.

[0096] The communication support unit can use the emotion estimation function to evaluate researchers' emotions toward communication and propose communication methods that will elicit positive emotions. The communication support unit, for example, uses the emotion estimation function to evaluate researchers' emotions toward communication and propose communication methods that will elicit positive emotions. For example, emphasizing positive feedback. The communication support unit also uses a generation AI to monitor researchers' emotions toward communication in real time and provide feedback to elicit positive emotions. For example, emphasizing words of gratitude. The communication support unit also uses the emotion estimation function to build a system that evaluates researchers' emotions toward communication and proposes communication methods that will elicit positive emotions. This makes it possible to evaluate researchers' emotions toward communication and propose communication methods that will elicit positive emotions.

[0097] The communication support unit can automatically match researchers from different fields and provide new opportunities for collaborative research. For example, the generative AI in the communication support unit can automatically match researchers from different fields and provide new opportunities for collaborative research. For example, matching can be done based on research themes or areas of expertise. The communication support unit can also build a generative AI system that automatically matches researchers from different fields and provide new opportunities for collaborative research. For example, by analyzing researchers' profiles. The communication support unit can also automatically match researchers from different fields and provide new opportunities for collaborative research. For example, matching can be done based on researchers' past achievements. This makes it possible to automatically match researchers from different fields and provide new opportunities for collaborative research.

[0098] The communication support unit can automatically translate communication content to support international collaborative research. For example, the communication support unit uses a generative AI to automatically translate communication content to support international collaborative research. For example, it translates the content of emails and chats. The communication support unit can also build a generative AI system that automatically translates communication content to support international collaborative research. For example, it translates meeting minutes. The communication support unit can also automatically translate communication content to support international collaborative research. For example, it translates research reports and papers. This allows the communication content to be automatically translated to support international collaborative research.

[0099] The communication support unit can use the emotion estimation function to monitor the user's emotions regarding communication in real time and dynamically adjust the communication method. For example, the communication support unit uses the emotion estimation function to monitor the user's emotions regarding communication in real time and dynamically adjust the communication method. For example, the communication method is changed when negative emotions are strong. The communication support unit also uses a generation AI to monitor the user's emotions regarding communication in real time and adjust the communication method to elicit positive emotions. For example, words of gratitude are emphasized. The communication support unit also uses the emotion estimation function to build a system that monitors the user's emotions regarding communication in real time and dynamically adjusts the communication method. This makes it possible to monitor the user's emotions regarding communication in real time and dynamically adjust the communication method.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] The hypothesis verification system can further estimate the user's emotions and dynamically adjust the priority of hypotheses based on the estimated emotions. For example, if the user expresses positive emotions, the system can prioritize testing hypotheses with a high probability of success to maintain that emotion. On the other hand, if the user expresses negative emotions, the system can prioritize testing hypotheses with a low risk, thereby improving the user's emotions. Furthermore, the results of hypothesis verification can be presented in different formats based on the user's emotions. For example, a report can be generated that highlights success cases to elicit positive emotions.

[0102] Hypothesis testing systems can also integrate data from different data sources to perform more comprehensive hypothesis testing. For example, integrating and analyzing sensor data and social media data can clarify the relationship between environmental factors and user behavior patterns. Furthermore, integrating and analyzing weather data and traffic data can evaluate the impact of weather on traffic flow. Furthermore, integrating and analyzing health data and dietary data can evaluate the impact of diet on health.

[0103] The hypothesis testing system can further estimate the user's emotions and dynamically adjust the results of the literature review based on the estimated emotions. For example, if the user expresses negative emotions, the system can improve the user's emotions by providing a literature review that emphasizes positive elements. Alternatively, if the user expresses positive emotions, the system can provide a literature review that emphasizes success stories to maintain the user's emotions. Furthermore, the results of the literature review can be presented in different formats based on the user's emotions. For example, a visualized summary can be provided to elicit positive emotions.

[0104] Hypothesis testing systems can also be equipped with the functionality to combine experimental methods from different fields and propose new experimental designs. For example, by combining methods from chemistry and biology, it can propose an experimental design to evaluate the effects of a new drug. Similarly, by integrating methods from physics and engineering, it can propose an experimental design to evaluate the properties of a new material. Furthermore, by combining methods from medicine and information science, it can analyze patient data and propose an experimental design to suggest the optimal treatment.

[0105] The hypothesis testing system can further estimate the user's emotions and dynamically adjust the content of reports and papers based on the estimated emotions. For example, if the user expresses negative emotions, the system can generate a report that emphasizes positive elements to improve the user's emotions. Alternatively, if the user expresses positive emotions, the system can generate a report that emphasizes success stories to maintain those emotions. Furthermore, the report content can be presented in different formats based on the user's emotions. For example, visualized data can be provided to elicit positive emotions.

[0106] Hypothesis testing systems can also be equipped with functions to support the creation of reports and papers in different formats. For example, by automatically generating presentation slides, research results can be communicated effectively. By automatically generating poster designs, presentations at academic conferences and exhibitions can be supported. Furthermore, by automatically generating graphs and charts for presentations, data can be visualized and reports and papers can be provided in a format that is visually easy to understand.

[0107] The hypothesis verification system can further estimate the user's emotions and dynamically adjust the communication method based on the estimated emotions. For example, if the user is expressing negative emotions, the system can improve the user's emotions by emphasizing positive feedback. Also, if the user is expressing positive emotions, the system can emphasize words of gratitude to maintain those emotions. Furthermore, the content of the communication can be presented in different formats based on the user's emotions. For example, visualized feedback can be provided to elicit positive emotions.

[0108] Hypothesis testing systems can also be equipped with the ability to automatically translate literature in different languages ​​and grasp international research trends. For example, by translating literature from English, French, Chinese, etc., it is possible to integrate research results from different languages ​​and provide a comprehensive review. In addition, by conducting multilingual literature reviews, it is possible to grasp international research trends and incorporate the latest research results. Furthermore, by analyzing research trends based on translated literature, it is possible to compare research results from different languages ​​and obtain integrated knowledge.

[0109] The hypothesis verification system can further estimate the user's emotions, monitor the progress of the collaborative research in real time based on the estimated emotions, and automatically provide necessary feedback. For example, if the user shows negative emotions, the system can provide positive feedback to improve the user's emotions. Also, if the user shows positive emotions, the system can emphasize words of gratitude to maintain those emotions. Furthermore, the progress of the collaborative research can be presented in different formats based on the user's emotions. For example, a visualized progress report can be provided to elicit positive emotions.

[0110] Hypothesis testing systems can also be equipped with a function that automatically matches researchers from different fields and provides new opportunities for collaborative research. For example, by matching based on research themes or areas of expertise, researchers from different fields can collaborate to advance new research. Furthermore, by analyzing researchers' profiles, it is possible to match researchers with common interests and goals. Furthermore, by matching based on researchers' past achievements, it is possible to find researchers who complement each other and provide new opportunities for collaborative research.

[0111] The processing flow of the second embodiment will be briefly explained below.

[0112] Step 1: The data analysis unit performs data analysis. The data analysis unit receives a dataset as input, applies statistical analysis and machine learning models, and outputs the results. It can also automatically detect specific patterns and outliers in the dataset and reconstruct hypotheses based on them. Furthermore, it can automatically remove noise during the data preprocessing stage to generate a clean dataset. Step 2: The literature review module performs a literature review. The literature review module receives a prompt to search for literature on a specific research topic as input and outputs summaries of relevant literature. It can also analyze citation relationships between literature and evaluate the influence of important research. Furthermore, it can automatically extract not only literature summaries but also the background and purpose of the research to provide a comprehensive review. Step 3: The experimental design department proposes an experimental design. The experimental design department receives the research objectives and conditions as input and outputs the optimal experimental design. It can also analyze past experimental data and automatically propose optimal experimental conditions. It can also perform a risk assessment of the experiment and propose an experimental design that minimizes the risks. Step 4: The Report Writer assists in the creation of reports and papers. The Report Writer receives research data and results as input and suggests improvements to the structure and presentation of the document. It can also automatically optimize the structure of the document and generate reports and papers in an easy-to-read format. It can also proofread the document and automatically correct typos and grammatical errors. Step 5: The Communication Support Unit promotes communication and collaboration. The Communication Support Unit receives research topics and objectives as input and suggests related researchers and collaborative research opportunities. It can also analyze communication history between researchers and suggest optimal communication methods. It can also monitor the progress of collaborative research in real time and automatically provide necessary feedback.

[0113] 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.

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

[0115] 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.

[0116] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0117] 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.

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

[0119] The 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.

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

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

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

[0123] Fig. 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.

[0124] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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.

[0126] 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.

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

[0128] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0130] The data processing system 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.

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

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (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).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0138] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0139] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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.

[0141] 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.

[0142] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 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.

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires 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.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may 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.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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 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.

[0158] 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.

[0159] 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.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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).

[0166] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0167] 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."

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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]

[0180] 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. This is a system that utilizes generative AI to rapidly and frequently repeat hypothesis testing and publicly announce results that are useful to industry. A data analysis department that performs data analysis; A literature review department that conducts literature reviews; The experimental design department proposes experimental designs; a report writing department that assists in the preparation of reports; a communication support unit that promotes communication and cooperation; A system characterized by:

2. The data analysis unit Takes a dataset as input, applies statistical analysis or machine learning models, and outputs results 2. The system of claim 1.

3. The literature review section It accepts a prompt to search for literature on a research topic as input and outputs a summary of the relevant literature.

2. The system of claim 1.

4. The experiment design unit It receives the research objectives or conditions as input and outputs the optimal experimental design.

2. The system of claim 1.

5. The report creation unit Take research data or results as input and suggest improvements to the structure or presentation of the document 2. The system of claim 1.

6. The communication support unit Takes research topics or objectives as input and suggests relevant researchers or collaborative opportunities 2. The system of claim 1.

7. The data analysis unit Automatically detect specific patterns or outliers in a dataset and reshape hypotheses accordingly 2. The system of claim 1.

Images