system

Abstract

The system according to the embodiment aims to efficiently aggregate, organize, summarize, visualize, and compare data required for pharmaceutical applications. [Solution] A system according to an embodiment includes a data aggregation unit, a data reduction unit, a data summarization unit, a data visualization unit, and a data comparison unit. The data aggregation unit aggregates data. The data reduction unit organizes the data aggregated by the data aggregation unit. The data summarization unit summarizes the data reduced by the data reduction unit. The data visualization unit visualizes the data summarized by the data summarization unit. The data comparison unit compares the data visualized by the data visualization unit.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, the compilation, organization, summary, visualization, and comparison of data required for pharmaceutical applications requires time and effort, posing a major obstacle, especially for small biopharmaceutical companies and startups.

[0005] The system according to the embodiment aims to efficiently aggregate, organize, summarize, visualize, and compare data required for pharmaceutical applications. [Means for solving the problem]

[0006] The system according to the embodiment includes a data aggregation unit, a data reduction unit, a data summarization unit, a data visualization unit, and a data comparison unit. The data aggregation unit aggregates data. The data reduction unit organizes the data aggregated by the data aggregation unit. The data reduction unit summarizes the data organized by the data reduction unit. The data visualization unit visualizes the data summarized by the data summarization unit. The data comparison unit compares the data visualized by the data visualization unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently aggregate, organize, summarize, visualize, and compare data required for pharmaceutical applications. [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 pharmaceutical consulting system according to an embodiment of the present invention supports the regulatory application process for pharmaceuticals, medical devices, regenerative medicine products, cosmetics, and healthcare-related products. This system automatically generates data for the compilation, organization, summarization, visualization, and comparison of clinical and non-clinical trial data; correlates data with previous scientific papers and existing patents; collects and summarizes scientific data; compares it with existing results; evolves AI specialized for target products by learning from previous clinical trial and safety test data; and automatically acquires the latest data on pharmaceutical, safety, and ethical regulations. For example, the generative AI quickly compiles and organizes massive amounts of test data. It converts test results into graphs and tables and automatically generates summary reports, facilitating data visualization and enabling rapid comparative analysis. The generative AI also searches for relevant scientific papers and patents and provides summaries of them. When comparing the effects of new drugs with existing research, it automatically collects and summarizes relevant data. Furthermore, the generative AI learns from past clinical trial and safety test data to provide advice optimized for specific products. In safety evaluations of new medical devices, it predicts risks based on past data. In addition, the generative AI automatically acquires and updates data related to the latest pharmaceutical, safety, and ethical regulations. When new regulations come into effect, the system acquires that information in real time and reflects it in application documents. This AI-assisted service can significantly reduce the labor costs and document organization time required for pharmaceutical applications. Generative AI automatically collects data from existing public documents and related literature, instantly suggesting the scientific data and related literature required for pharmaceutical application documents, shortening the need for tedious and specialized tasks such as literature searches. Furthermore, responding to the latest data, such as regulatory changes, in real time improves accuracy, reducing costs and shortening the review process. This allows the pharmaceutical consulting system to streamline the pharmaceutical application process and support the creation of fast and accurate application documents.

[0029] The pharmaceutical affairs consulting system according to the embodiment includes a data aggregation unit, a data reduction unit, a data summarization unit, a data visualization unit, and a data comparison unit. The data aggregation unit aggregates data. The data aggregation unit can aggregate, for example, clinical trial data and non-clinical trial data. The data aggregation unit quickly aggregates large amounts of data using a generation AI. For example, the data aggregation unit can aggregate test results and perform statistical analysis. The data aggregation unit can also apply different aggregation algorithms depending on the type of data. For example, it can use statistical methods for clinical trial data and machine learning algorithms for non-clinical trial data. The data reduction unit organizes the data aggregated by the data aggregation unit. For example, the data reduction unit can classify and organize the data. The data reduction unit uses a generation AI to organize the data based on data classification criteria. For example, the data reduction unit can determine the priority of organization based on the importance of the data. The data reduction unit can also apply different organization methods depending on the category of data. For example, it can use statistical methods for clinical trial data and machine learning algorithms for non-clinical trial data. The data summarization unit summarizes the data organized by the data reduction unit. The data summarization unit can, for example, summarize data and generate a summary report. The data summarization unit uses a generative AI to summarize data based on a data summarization algorithm. For example, the data summarization unit can adjust the level of detail of the summary based on the importance of the data. The data summarization unit can also apply different summarization algorithms depending on the category of data. For example, a statistical method is used for clinical trial data, and a machine learning algorithm is used for non-clinical trial data. The data visualization unit visualizes the data summarized by the data summarization unit. For example, the data visualization unit can convert and visualize the data into a graph or a table. The data visualization unit uses a generative AI to visualize the data based on a data visualization algorithm. For example, the data visualization unit can adjust the level of detail of the visualization based on the importance of the data. The data visualization unit can also apply different visualization methods depending on the category of data.For example, statistical graphs are used for clinical trial data, and heat maps are used for non-clinical trial data. The data comparison unit compares the data visualized by the data visualization unit. The data comparison unit can, for example, calculate and compare the similarity of the data. The data comparison unit uses a generative AI to compare the data based on a data comparison algorithm. For example, the data comparison unit can improve the accuracy of the comparison by taking into account the interrelationships between the data. The data comparison unit can also apply different comparison methods depending on the data category. For example, statistical methods are used for clinical trial data, and machine learning algorithms are used for non-clinical trial data. This allows the pharmaceutical affairs consulting system according to the embodiment to efficiently aggregate, organize, summarize, visualize, and compare data.

[0030] The pharmaceutical consulting system includes a data collection unit that collects scientific data and relevance to previous research scientific papers or existing patents. The data collection unit collects scientific data and relevance to previous research scientific papers and existing patents. The data collection unit, for example, uses generative AI to search for relevant scientific papers and patents and provide summaries of them. For example, the data collection unit automatically collects and summarizes relevant data when comparing the effects of a new drug with existing research. The data collection unit also clarifies the methods and standards for collecting scientific data. For example, the data collection unit collects specific types of data, such as experimental data, observational data, and simulation data. This allows the data collection unit to automatically collect relevance to previous research and existing patents.

[0031] The pharmaceutical consulting system includes a data learning unit that learns from past clinical trial data or safety test data. The data learning unit learns from past clinical trial data and safety test data. The data learning unit learns from past data, for example, using generative AI, and provides advice optimized for specific products. For example, the data learning unit predicts risks based on past data in safety evaluations of new medical devices. The data learning unit also clarifies the specific types and collection methods of learning data. For example, the data learning unit learns from clinical trial result data and safety test reports. This enables the data learning unit to learn from past data and provide advice optimized for specific products.

[0032] The pharmaceutical affairs consulting system includes a risk prediction unit that predicts risks based on learned data. The risk prediction unit predicts risks based on learned data. The risk prediction unit predicts risks based on learned data, for example, using generative AI. For example, the risk prediction unit predicts risks based on past data in safety assessments of new medical devices. The risk prediction unit also clarifies specific methods and criteria for risk prediction. For example, the risk prediction unit clarifies the algorithm to be used and the risk assessment criteria. This enables the risk prediction unit to predict risks and take appropriate measures.

[0033] The pharmaceutical consulting system includes a data acquisition unit that automatically acquires the latest data on pharmaceutical regulations or safety and ethical regulations. The data acquisition unit automatically acquires the latest data on pharmaceutical regulations, safety, ethical regulations, etc. The data acquisition unit automatically acquires and updates the latest data on pharmaceutical regulations, safety, and ethical regulations, for example, using generative AI. For example, when new regulations are enacted, the data acquisition unit acquires that information in real time and reflects it in application documents. The data acquisition unit also clarifies the specific types of regulatory data and the collection method. For example, the data acquisition unit collects data from legal databases and announcements by regulatory authorities. This allows the data acquisition unit to automatically acquire the latest regulatory information and reflect it in application documents.

[0034] The pharmaceutical affairs consulting system includes a data update unit that updates the latest acquired data. The data update unit updates the latest acquired data. The data update unit automatically updates the latest acquired data, for example, using generation AI. For example, the data update unit updates new regulatory information in real time and reflects it in application documents. The data update unit also clarifies the specific methods and standards for data updates. For example, the data update unit clarifies the frequency of updates, the tools to be used, and the update procedures. This allows the data update unit to always reflect the latest data and provide accurate information.

[0035] The data aggregation unit can evaluate the reliability of the data and prioritize aggregation of highly reliable data. The data aggregation unit can evaluate the reliability of the data, for example, using a generation AI. For example, the data aggregation unit can evaluate the source of the data and prioritize aggregation of data from highly reliable data sources. The data aggregation unit can also evaluate the consistency of the data and prioritize aggregation of consistent data. Furthermore, the data aggregation unit can evaluate the recency of the data and prioritize aggregation of the most recent data. This allows the data aggregation unit to obtain highly accurate results by prioritizing aggregation of highly reliable data. The reliability evaluation of the data is performed using, for example, the source of the data, the consistency of the data, an evaluation algorithm, etc. Methods and criteria for preferentially aggregating highly reliable data include priorities based on reliability scores and aggregation procedures, etc.

[0036] The data aggregation unit can apply different aggregation algorithms depending on the type of data. The data aggregation unit can apply different aggregation algorithms depending on the type of data, for example, using a generative AI. For example, the data aggregation unit can aggregate clinical trial data using statistical methods. The data aggregation unit can also aggregate non-clinical trial data using a machine learning algorithm. Furthermore, the data aggregation unit can aggregate safety data using a risk assessment algorithm. This allows the data aggregation unit to perform optimal aggregation depending on the type of data. Methods and standards for applying different aggregation algorithms depending on the type of data include algorithms for numerical data, text data, image data, etc.

[0037] The data reduction unit can determine the priority of the reduction based on the importance of the data. The data reduction unit evaluates the importance of the data, for example, using a generation AI. For example, the data reduction unit evaluates the impact of the data and prioritizes reducing data with high impact. The data reduction unit can also evaluate the reliability of the data and prioritize reducing data with high reliability. Furthermore, the data reduction unit can evaluate the frequency of data use and prioritize reducing data with high use. This allows the data reduction unit to prioritize reducing data with high importance. Methods and criteria for determining the priority of the reduction based on the importance of the data include the impact of the data, frequency of use, importance score, etc.

[0038] The data reduction unit can apply different reduction methods depending on the data category. The data reduction unit can apply different reduction methods depending on the data category, for example, using generative AI. For example, the data reduction unit can reduce clinical trial data using statistical methods. The data reduction unit can also reduce non-clinical trial data using machine learning algorithms. Furthermore, the data reduction unit can reduce safety data using risk assessment algorithms. This allows the data reduction unit to perform optimal reduction depending on the data category. Methods and standards for applying different reduction methods depending on the data category include methods for text data, numerical data, image data, etc.

[0039] When generating a summary, the data summarization unit can adjust the level of detail of the summary based on the importance of the data. The data summarization unit, for example, uses generation AI to evaluate the importance of the data. For example, the data summarization unit can evaluate the impact of the data and summarize highly impactful data in detail. The data summarization unit can also evaluate the reliability of the data and summarize highly reliable data in detail. Furthermore, the data summarization unit can evaluate the frequency of use of the data and summarize frequently used data in detail. This allows the data summarization unit to perform detailed summarization according to the importance of the data. Methods and criteria for adjusting the level of detail of the summary include the impact of the data, frequency of use, importance score, etc.

[0040] The data summarization unit can apply different summarization algorithms depending on the data category when generating summaries. The data summarization unit can apply different summarization algorithms depending on the data category, for example, using generation AI. For example, the data summarization unit can use statistical methods to summarize clinical trial data. The data summarization unit can also use machine learning algorithms to summarize non-clinical trial data. Furthermore, the data summarization unit can use risk assessment algorithms to summarize safety data. This allows the data summarization unit to generate an optimal summary depending on the data category. Methods and standards for applying different summarization algorithms depending on the data category include algorithms for text data, numerical data, image data, etc.

[0041] The data visualization unit can adjust the level of detail of visualization based on the importance of the data. The data visualization unit evaluates the importance of the data, for example, using generative AI. For example, the data visualization unit can evaluate the impact of the data and visualize highly impactful data in detail. The data visualization unit can also evaluate the reliability of the data and visualize highly reliable data in detail. Furthermore, the data visualization unit can evaluate the frequency of use of the data and visualize frequently used data in detail. This allows the data visualization unit to perform detailed visualization according to the importance of the data. Methods and criteria for adjusting the level of detail of visualization include the impact of the data, frequency of use, importance score, etc.

[0042] The data visualization unit can apply different visualization techniques depending on the data category. The data visualization unit can apply different visualization techniques depending on the data category, for example, by using generative AI. For example, the data visualization unit can perform visualization using statistical graphs for clinical trial data. The data visualization unit can also perform visualization using heat maps for non-clinical trial data. Furthermore, the data visualization unit can perform visualization using risk assessment charts for safety data. This allows the data visualization unit to perform optimal visualization depending on the data category. Methods and standards for applying different visualization techniques depending on the data category include techniques for text data, numerical data, image data, etc.

[0043] The data comparison unit can improve the accuracy of the comparison by taking into account the interrelationships of the data. The data comparison unit evaluates the correlations of the data, for example, using a generation AI. For example, the data comparison unit prioritizes the comparison of highly correlated data. The data comparison unit can also prioritize the comparison of data that are causally related. Furthermore, the data comparison unit can prioritize the comparison of data that have many commonalities. This allows the data comparison unit to improve the accuracy of the comparison by taking into account the interrelationships of the data. Methods and standards for improving the accuracy of the comparison include methods for evaluating the interrelationships, algorithms for improving accuracy, etc.

[0044] The data comparison unit can make comparisons based on the attribute information of the data submitter. The data comparison unit can use, for example, a generation AI to evaluate the attribute information of the data submitter. For example, the data comparison unit can evaluate the expertise of the submitter and prioritize comparing data from submitters with high expertise. The data comparison unit can also evaluate the reliability of the submitter and prioritize comparing data from submitters with high reliability. Furthermore, the data comparison unit can evaluate the submitter's past performance and prioritize comparing data from submitters with a proven track record. This allows the data comparison unit to make comparisons taking into account the attribute information of the data submitter. Methods and standards for making comparisons based on the attribute information of the data submitter include the submitter's field of expertise, years of experience, and the method for collecting attribute information.

[0045] The data comparison unit can take into account geographical data distribution when comparing data. The data comparison unit evaluates geographical data distribution, for example, using generation AI. For example, the data comparison unit compares data by region and provides comparison results that reflect the characteristics of each region. The data comparison unit can also compare data by country and provide comparison results that reflect the regulations and characteristics of each country. Furthermore, the data comparison unit can compare data by city and provide comparison results that reflect the characteristics of each city. This allows the data comparison unit to make comparisons that take into account geographical data distribution. Methods and standards for making comparisons that take into account geographical data distribution include methods for evaluating data distribution by region and geographical characteristics.

[0046] The data comparison unit can improve the accuracy of the comparison by referring to related literature when comparing data. The data comparison unit can, for example, use generative AI to refer to related literature. For example, the data comparison unit can refer to related scientific papers to improve the accuracy of the comparison. The data comparison unit can also improve the accuracy of the comparison by referring to related patents. Furthermore, the data comparison unit can improve the accuracy of the comparison by referring to related government public data. In this way, the data comparison unit can improve the accuracy of the comparison by referring to related literature. Methods and criteria for improving the accuracy of the comparison based on related literature include cited literature, related research, literature evaluation methods, etc.

[0047] The data collection unit can evaluate the reliability of the data and prioritize collecting reliable data. The data collection unit can evaluate the reliability of the data, for example, using generative AI. For example, the data collection unit can evaluate the source of the data and prioritize collecting data from reliable data sources. The data collection unit can also evaluate the consistency of the data and prioritize collecting consistent data. Furthermore, the data collection unit can evaluate the recency of the data and prioritize collecting the latest data. This allows the data collection unit to obtain highly accurate results by prioritized collection of reliable data. The reliability evaluation of the data is performed using, for example, the source of the data, the consistency of the data, an evaluation algorithm, etc. Methods and criteria for prioritized collection of reliable data include priorities based on reliability scores and collection procedures, etc.

[0048] The data collection unit can perform data collection taking into account geographical data distribution. The data collection unit evaluates the geographical data distribution, for example, using generative AI. For example, the data collection unit collects data by region and provides collection results that reflect the characteristics of each region. The data collection unit can also collect data by country and provide collection results that take into account the regulations and characteristics of each country. Furthermore, the data collection unit can collect data by city and provide collection results that reflect the characteristics of each city. This allows the data collection unit to perform collection taking into account geographical data distribution. Methods and standards for collection that take into account geographical data distribution include methods for evaluating data distribution by region and geographical characteristics, etc.

[0049] During learning, the data learning unit can optimize the learning algorithm by referring to past learning data. The data learning unit, for example, uses a generation AI to refer to past learning data. For example, the data learning unit refers to past learning data and selects an optimal learning algorithm. The data learning unit can also optimize the parameters of the learning algorithm by referring to past learning data. Furthermore, the data learning unit can improve the accuracy of the learning algorithm by referring to past learning data. This allows the data learning unit to optimize the learning algorithm by referring to past learning data. Methods and standards for optimizing the learning algorithm include methods for referring to past data, methods for adjusting the algorithm, etc.

[0050] During learning, the data learning unit can weight the learning data based on the time of data submission. The data learning unit evaluates the time of data submission using, for example, a generative AI. For example, the data learning unit performs learning by assigning a higher weight to the most recent data. The data learning unit can also perform learning by assigning a lower weight to older data. Furthermore, the data learning unit can adjust the weighting of the learning data based on the time of submission. This allows the data learning unit to weight the learning data based on the time of data submission. Methods and standards for weighting the learning data include weighting methods and weighting algorithms based on the time of submission.

[0051] The risk prediction unit can improve the accuracy of risk prediction by referring to past risk data. The risk prediction unit, for example, uses a generation AI to refer to past risk data. For example, the risk prediction unit can improve the accuracy of risk prediction by referring to past risk data. The risk prediction unit can also optimize parameters of the risk prediction algorithm by referring to past risk data. Furthermore, the risk prediction unit can improve the accuracy of the risk prediction algorithm by referring to past risk data. In this way, the risk prediction unit can improve the accuracy of risk prediction by referring to past risk data. Methods and standards for improving the accuracy of risk prediction include methods for referring to past data, algorithms for improving accuracy, etc.

[0052] The risk prediction unit can make risk predictions taking into account geographical data distribution. The risk prediction unit evaluates the geographical data distribution, for example, using a generative AI. For example, the risk prediction unit predicts risk data for each region and provides a risk prediction result that reflects the characteristics of each region. The risk prediction unit can also predict risk data for each country and provide a risk prediction result that takes into account the regulations and characteristics of each country. Furthermore, the risk prediction unit can predict risk data for each city and provide a risk prediction result that reflects the characteristics of each city. This allows the risk prediction unit to make predictions taking into account geographical data distribution. Methods and standards for making predictions taking into account geographical data distribution include methods for evaluating the data distribution for each region and the geographical characteristics.

[0053] The data acquisition unit can evaluate the reliability of data and prioritize acquisition of highly reliable data. The data acquisition unit can evaluate the reliability of data, for example, using a generation AI. For example, the data acquisition unit can evaluate the source of data and prioritize acquisition of data from highly reliable data sources. The data acquisition unit can also evaluate the consistency of data and prioritize acquisition of consistent data. Furthermore, the data acquisition unit can evaluate the recency of data and prioritize acquisition of the latest data. As a result, the data acquisition unit can obtain highly accurate results by prioritizing acquisition of highly reliable data. The reliability evaluation of data is performed using, for example, the source of data, the consistency of data, an evaluation algorithm, etc. Methods and criteria for preferentially acquiring highly reliable data include priorities based on reliability scores and acquisition procedures, etc.

[0054] The data acquisition unit can acquire data while taking into account geographical data distribution. The data acquisition unit evaluates the geographical data distribution, for example, using a generation AI. For example, the data acquisition unit acquires data by region and provides acquisition results that reflect the characteristics of each region. The data acquisition unit can also acquire data by country and provide acquisition results that take into account the regulations and characteristics of each country. Furthermore, the data acquisition unit can acquire data by city and provide acquisition results that reflect the characteristics of each city. This allows the data acquisition unit to acquire data while taking into account geographical data distribution. Methods and standards for acquiring data while taking into account geographical data distribution include methods for evaluating the data distribution by region and the geographical characteristics.

[0055] The data updating unit can evaluate the reliability of data and prioritize updating highly reliable data. The data updating unit can evaluate the reliability of data, for example, using a generation AI. For example, the data updating unit can evaluate the source of data and prioritize updating data from a highly reliable data source. The data updating unit can also evaluate the consistency of data and prioritize updating consistent data. Furthermore, the data updating unit can evaluate the recency of data and prioritize updating the latest data. This allows the data updating unit to obtain highly accurate results by preferentially updating highly reliable data. The reliability evaluation of data is performed using, for example, the source of data, the consistency of data, an evaluation algorithm, etc. Methods and criteria for preferentially updating highly reliable data include priorities based on reliability scores and update procedures, etc.

[0056] The data update unit can perform the update taking into account the geographical data distribution when updating data. The data update unit evaluates the geographical data distribution, for example, using a generation AI. For example, the data update unit can update the data for each region and provide an update result that reflects the characteristics of each region. The data update unit can also update the data for each country and provide an update result that takes into account the regulations and characteristics of each country. Furthermore, the data update unit can update the data for each city and provide an update result that reflects the characteristics of each city. This allows the data update unit to perform the update taking into account the geographical data distribution. Methods and standards for performing the update taking into account the geographical data distribution include methods for evaluating the data distribution for each region and the geographical characteristics.

[0057] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0058] The data aggregation unit can learn the user's past operation history and suggest the optimal aggregation method. For example, it can prioritize the aggregation method that the user has frequently used in the past. It can also record the operations performed by the user on a specific data set and automatically apply them to similar data sets. Furthermore, it can automatically set the optimal aggregation parameters based on the aggregation results performed by the user in the past. This enables efficient data aggregation based on the user's operation history.

[0059] The data collection unit can learn the user's areas of interest and prioritize collecting related data. For example, it can automatically collect new related literature based on the keywords the user has searched for and the literature they have viewed in the past. Also, if the user is interested in a specific research field, it can prioritize collecting the latest data related to that field. Furthermore, it can prioritize collecting data from reliable data sources based on the reliability of data evaluated by the user in the past. This enables efficient data collection according to the user's areas of interest.

[0060] The data organizing unit can determine the order of priorities for organizing based on the importance of the data. For example, the data organizing unit can evaluate the impact of the data and prioritize organizing data with high impact. The data organizing unit can also evaluate the reliability of the data and prioritize organizing data with high reliability. Furthermore, the data organizing unit can evaluate the frequency of data use and prioritize organizing data with high frequency of use. This allows the data organizing unit to prioritize organizing data with high importance.

[0061] When generating a summary, the data summarizing unit can adjust the level of detail of the summary based on the importance of the data. For example, the data summarizing unit can evaluate the impact of the data and summarize data with high impact in detail. The data summarizing unit can also evaluate the reliability of the data and summarize highly reliable data in detail. Furthermore, the data summarizing unit can evaluate the frequency of use of the data and summarize frequently used data in detail. This allows the data summarizing unit to generate a detailed summary according to the importance of the data.

[0062] The data visualization unit can adjust the level of detail of visualization based on the importance of the data. For example, the data visualization unit can evaluate the impact of data and visualize data with high impact in detail. The data visualization unit can also evaluate the reliability of data and visualize highly reliable data in detail. Furthermore, the data visualization unit can evaluate the frequency of use of data and visualize frequently used data in detail. This allows the data visualization unit to perform detailed visualization according to the importance of the data.

[0063] The data comparison unit can make comparisons based on attribute information of data submitters. For example, the data comparison unit can evaluate the expertise of the submitter and prioritize comparing data of submitters with high expertise. The data comparison unit can also evaluate the reliability of the submitter and prioritize comparing data of submitters with high reliability. Furthermore, the data comparison unit can evaluate the submitter's past performance and prioritize comparing data of submitters with a proven track record. This allows the data comparison unit to make comparisons taking into account attribute information of the data submitter.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The data aggregation unit aggregates data. For example, it aggregates clinical trial data and non-clinical trial data, and uses generative AI to quickly aggregate large amounts of data. The data aggregation unit aggregates test results and can perform statistical analysis. It can also apply different aggregation algorithms depending on the type of data. For example, it uses statistical methods for clinical trial data and machine learning algorithms for non-clinical trial data. Step 2: The data reduction unit organizes the data collected by the data aggregation unit. For example, the data can be classified and organized. The data reduction unit uses generative AI to organize the data based on data classification criteria. For example, it can determine the priority of organization based on the importance of the data. It can also apply different organization methods depending on the data category. For example, it uses statistical methods for clinical trial data and machine learning algorithms for non-clinical trial data. Step 3: The data summarization unit summarizes the data organized by the data reduction unit. For example, it can summarize the data and generate a summary report. The data summarization unit summarizes the data based on a data summarization algorithm using generative AI. For example, it can adjust the level of detail in the summary based on the importance of the data. It can also apply different summarization algorithms depending on the data category. For example, it can use statistical methods for clinical trial data and machine learning algorithms for non-clinical trial data. Step 4: The data visualization unit visualizes the data summarized by the data summarization unit. For example, it can convert the data into graphs or tables and visualize them. The data visualization unit uses generative AI to visualize the data based on a data visualization algorithm. For example, it can adjust the level of detail in the visualization based on the importance of the data. It can also apply different visualization techniques depending on the category of data. For example, it can use statistical graphs for clinical trial data and heat maps for non-clinical trial data. Step 5: The data comparison unit compares the data visualized by the data visualization unit. For example, it can calculate and compare the similarity of the data. The data comparison unit uses generative AI to compare the data based on a data comparison algorithm. For example, it can improve the accuracy of the comparison by taking into account the correlation between the data. It can also apply different comparison methods depending on the data category. For example, it uses statistical methods for clinical trial data and machine learning algorithms for non-clinical trial data.

[0066] (Example 2) A pharmaceutical consulting system according to an embodiment of the present invention supports the regulatory application process for pharmaceuticals, medical devices, regenerative medicine products, cosmetics, and healthcare-related products. This system automatically generates data for the compilation, organization, summarization, visualization, and comparison of clinical and non-clinical trial data; correlates data with previous scientific papers and existing patents; collects and summarizes scientific data; compares it with existing results; evolves AI specialized for target products by learning from previous clinical trial and safety test data; and automatically acquires the latest data on pharmaceutical, safety, and ethical regulations. For example, the generative AI quickly compiles and organizes massive amounts of test data. It converts test results into graphs and tables and automatically generates summary reports, facilitating data visualization and enabling rapid comparative analysis. The generative AI also searches for relevant scientific papers and patents and provides summaries of them. When comparing the effects of new drugs with existing research, it automatically collects and summarizes relevant data. Furthermore, the generative AI learns from past clinical trial and safety test data to provide advice optimized for specific products. In safety evaluations of new medical devices, it predicts risks based on past data. In addition, the generative AI automatically acquires and updates data related to the latest pharmaceutical, safety, and ethical regulations. When new regulations come into effect, the system acquires that information in real time and reflects it in application documents. This AI-assisted service can significantly reduce the labor costs and document organization time required for pharmaceutical applications. Generative AI automatically collects data from existing public documents and related literature, instantly suggesting the scientific data and related literature required for pharmaceutical application documents, shortening the need for tedious and specialized tasks such as literature searches. Furthermore, responding to the latest data, such as regulatory changes, in real time improves accuracy, reducing costs and shortening the review process. This allows the pharmaceutical consulting system to streamline the pharmaceutical application process and support the creation of fast and accurate application documents.

[0067] The pharmaceutical affairs consulting system according to the embodiment includes a data aggregation unit, a data reduction unit, a data summarization unit, a data visualization unit, and a data comparison unit. The data aggregation unit aggregates data. The data aggregation unit can aggregate, for example, clinical trial data and non-clinical trial data. The data aggregation unit quickly aggregates large amounts of data using a generation AI. For example, the data aggregation unit can aggregate test results and perform statistical analysis. The data aggregation unit can also apply different aggregation algorithms depending on the type of data. For example, it can use statistical methods for clinical trial data and machine learning algorithms for non-clinical trial data. The data reduction unit organizes the data aggregated by the data aggregation unit. For example, the data reduction unit can classify and organize the data. The data reduction unit uses a generation AI to organize the data based on data classification criteria. For example, the data reduction unit can determine the priority of organization based on the importance of the data. The data reduction unit can also apply different organization methods depending on the category of data. For example, it can use statistical methods for clinical trial data and machine learning algorithms for non-clinical trial data. The data summarization unit summarizes the data organized by the data reduction unit. The data summarization unit can, for example, summarize data and generate a summary report. The data summarization unit uses a generative AI to summarize data based on a data summarization algorithm. For example, the data summarization unit can adjust the level of detail of the summary based on the importance of the data. The data summarization unit can also apply different summarization algorithms depending on the category of data. For example, a statistical method is used for clinical trial data, and a machine learning algorithm is used for non-clinical trial data. The data visualization unit visualizes the data summarized by the data summarization unit. For example, the data visualization unit can convert and visualize the data into a graph or a table. The data visualization unit uses a generative AI to visualize the data based on a data visualization algorithm. For example, the data visualization unit can adjust the level of detail of the visualization based on the importance of the data. The data visualization unit can also apply different visualization methods depending on the category of data.For example, statistical graphs are used for clinical trial data, and heat maps are used for non-clinical trial data. The data comparison unit compares the data visualized by the data visualization unit. The data comparison unit can, for example, calculate and compare the similarity of the data. The data comparison unit uses a generative AI to compare the data based on a data comparison algorithm. For example, the data comparison unit can improve the accuracy of the comparison by taking into account the interrelationships between the data. The data comparison unit can also apply different comparison methods depending on the data category. For example, statistical methods are used for clinical trial data, and machine learning algorithms are used for non-clinical trial data. This allows the pharmaceutical affairs consulting system according to the embodiment to efficiently aggregate, organize, summarize, visualize, and compare data.

[0068] The pharmaceutical consulting system includes a data collection unit that collects scientific data and relevance to previous research scientific papers or existing patents. The data collection unit collects scientific data and relevance to previous research scientific papers and existing patents. The data collection unit, for example, uses generative AI to search for relevant scientific papers and patents and provide summaries of them. For example, the data collection unit automatically collects and summarizes relevant data when comparing the effects of a new drug with existing research. The data collection unit also clarifies the methods and standards for collecting scientific data. For example, the data collection unit collects specific types of data, such as experimental data, observational data, and simulation data. This allows the data collection unit to automatically collect relevance to previous research and existing patents.

[0069] The pharmaceutical consulting system includes a data learning unit that learns from past clinical trial data or safety test data. The data learning unit learns from past clinical trial data and safety test data. The data learning unit learns from past data, for example, using generative AI, and provides advice optimized for specific products. For example, the data learning unit predicts risks based on past data in safety evaluations of new medical devices. The data learning unit also clarifies the specific types and collection methods of learning data. For example, the data learning unit learns from clinical trial result data and safety test reports. This enables the data learning unit to learn from past data and provide advice optimized for specific products.

[0070] The pharmaceutical affairs consulting system includes a risk prediction unit that predicts risks based on learned data. The risk prediction unit predicts risks based on learned data. The risk prediction unit predicts risks based on learned data, for example, using generative AI. For example, the risk prediction unit predicts risks based on past data in safety assessments of new medical devices. The risk prediction unit also clarifies specific methods and criteria for risk prediction. For example, the risk prediction unit clarifies the algorithm to be used and the risk assessment criteria. This enables the risk prediction unit to predict risks and take appropriate measures.

[0071] The pharmaceutical consulting system includes a data acquisition unit that automatically acquires the latest data on pharmaceutical regulations or safety and ethical regulations. The data acquisition unit automatically acquires the latest data on pharmaceutical regulations, safety, ethical regulations, etc. The data acquisition unit automatically acquires and updates the latest data on pharmaceutical regulations, safety, and ethical regulations, for example, using generative AI. For example, when new regulations are enacted, the data acquisition unit acquires that information in real time and reflects it in application documents. The data acquisition unit also clarifies the specific types of regulatory data and the collection method. For example, the data acquisition unit collects data from legal databases and announcements by regulatory authorities. This allows the data acquisition unit to automatically acquire the latest regulatory information and reflect it in application documents.

[0072] The pharmaceutical affairs consulting system includes a data update unit that updates the latest acquired data. The data update unit updates the latest acquired data. The data update unit automatically updates the latest acquired data, for example, using generation AI. For example, the data update unit updates new regulatory information in real time and reflects it in application documents. The data update unit also clarifies the specific methods and standards for data updates. For example, the data update unit clarifies the frequency of updates, the tools to be used, and the update procedures. This allows the data update unit to always reflect the latest data and provide accurate information.

[0073] The data aggregation unit can estimate the user's emotions and adjust the timing of data aggregation based on the estimated user emotions. The data aggregation unit estimates the user's emotions using, for example, a generation AI. For example, the data aggregation unit analyzes the user's facial expressions and voice data to estimate emotions. The data aggregation unit also adjusts the timing of data aggregation based on the estimated user emotions. For example, if the user is stressed, the data aggregation unit reduces the frequency of data aggregation and performs aggregation during times when the user is relaxed. Also, if the user is relaxed, the data aggregation unit increases the frequency of data aggregation to efficiently aggregate data. Furthermore, if the user is in a hurry, the data aggregation unit quickly aggregates data and provides the necessary data immediately. This allows the timing of data aggregation to be adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0074] The data aggregation unit can evaluate the reliability of the data and prioritize aggregation of highly reliable data. The data aggregation unit can evaluate the reliability of the data, for example, using a generation AI. For example, the data aggregation unit can evaluate the source of the data and prioritize aggregation of data from highly reliable data sources. The data aggregation unit can also evaluate the consistency of the data and prioritize aggregation of consistent data. Furthermore, the data aggregation unit can evaluate the recency of the data and prioritize aggregation of the most recent data. This allows the data aggregation unit to obtain highly accurate results by prioritizing aggregation of highly reliable data. The reliability evaluation of the data is performed using, for example, the source of the data, the consistency of the data, an evaluation algorithm, etc. Methods and criteria for preferentially aggregating highly reliable data include priorities based on reliability scores and aggregation procedures, etc.

[0075] The data aggregation unit can apply different aggregation algorithms depending on the type of data. The data aggregation unit can apply different aggregation algorithms depending on the type of data, for example, using a generative AI. For example, the data aggregation unit can aggregate clinical trial data using statistical methods. The data aggregation unit can also aggregate non-clinical trial data using a machine learning algorithm. Furthermore, the data aggregation unit can aggregate safety data using a risk assessment algorithm. This allows the data aggregation unit to perform optimal aggregation depending on the type of data. Methods and standards for applying different aggregation algorithms depending on the type of data include algorithms for numerical data, text data, image data, etc.

[0076] The data reduction unit can estimate the user's emotions and adjust the data reduction method based on the estimated user emotions. The data reduction unit estimates the user's emotions using, for example, a generative AI. For example, the data reduction unit analyzes the user's facial expressions and voice data to estimate emotions. The data reduction unit also adjusts the data reduction method based on the estimated user emotions. For example, if the user is stressed, the data reduction unit provides a simple reduction method to reduce the user's burden. If the user is relaxed, the data reduction unit provides a detailed reduction method to improve data accuracy. Furthermore, if the user is in a hurry, the data reduction unit can quickly reduce data and provide the necessary data immediately. This allows the data reduction method to be adjusted according to the user's emotions. Emotion reduction is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0077] The data reduction unit can determine the priority of the reduction based on the importance of the data. The data reduction unit evaluates the importance of the data, for example, using a generation AI. For example, the data reduction unit evaluates the impact of the data and prioritizes reducing data with high impact. The data reduction unit can also evaluate the reliability of the data and prioritize reducing data with high reliability. Furthermore, the data reduction unit can evaluate the frequency of data use and prioritize reducing data with high use. This allows the data reduction unit to prioritize reducing data with high importance. Methods and criteria for determining the priority of the reduction based on the importance of the data include the impact of the data, frequency of use, importance score, etc.

[0078] The data reduction unit can apply different reduction methods depending on the data category. The data reduction unit can apply different reduction methods depending on the data category, for example, using generative AI. For example, the data reduction unit can reduce clinical trial data using statistical methods. The data reduction unit can also reduce non-clinical trial data using machine learning algorithms. Furthermore, the data reduction unit can reduce safety data using risk assessment algorithms. This allows the data reduction unit to perform optimal reduction depending on the data category. Methods and standards for applying different reduction methods depending on the data category include methods for text data, numerical data, image data, etc.

[0079] The data summarization unit can estimate the user's emotions and adjust the presentation style of the summary based on the estimated user emotions. The data summarization unit estimates the user's emotions using, for example, a generative AI. For example, the data summarization unit analyzes the user's facial expressions and voice data to estimate emotions. The data summarization unit also adjusts the presentation style of the summary based on the estimated user emotions. For example, if the user is stressed, the data summarization unit can provide a simple and easy-to-understand summary. If the user is relaxed, the data summarization unit can provide a detailed summary. Furthermore, if the user is in a hurry, the data summarization unit can quickly provide a summary. This allows the presentation style of the summary to be adjusted according to the user's emotions. Emotion estimation is achieved using, for example, an emotion engine or generative AI with an emotion estimation function. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0080] When generating a summary, the data summarization unit can adjust the level of detail of the summary based on the importance of the data. The data summarization unit, for example, uses generation AI to evaluate the importance of the data. For example, the data summarization unit can evaluate the impact of the data and summarize highly impactful data in detail. The data summarization unit can also evaluate the reliability of the data and summarize highly reliable data in detail. Furthermore, the data summarization unit can evaluate the frequency of use of the data and summarize frequently used data in detail. This allows the data summarization unit to perform detailed summarization according to the importance of the data. Methods and criteria for adjusting the level of detail of the summary include the impact of the data, frequency of use, importance score, etc.

[0081] The data summarization unit can apply different summarization algorithms depending on the data category when generating summaries. The data summarization unit can apply different summarization algorithms depending on the data category, for example, using generation AI. For example, the data summarization unit can use statistical methods to summarize clinical trial data. The data summarization unit can also use machine learning algorithms to summarize non-clinical trial data. Furthermore, the data summarization unit can use risk assessment algorithms to summarize safety data. This allows the data summarization unit to generate an optimal summary depending on the data category. Methods and standards for applying different summarization algorithms depending on the data category include algorithms for text data, numerical data, image data, etc.

[0082] The data visualization unit can estimate the user's emotions and adjust the visualization method based on the estimated user emotions. The data visualization unit estimates the user's emotions using, for example, a generative AI. For example, the data visualization unit analyzes the user's facial expressions and voice data to estimate emotions. The data visualization unit also adjusts the visualization method based on the estimated user emotions. For example, if the user is stressed, the data visualization unit can provide a simple, easy-to-understand graph. If the user is relaxed, the data visualization unit can provide a detailed graph. Furthermore, if the user is in a hurry, the data visualization unit can quickly perform visualization and immediately provide the necessary data. This allows the visualization method to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0083] The data visualization unit can adjust the level of detail of visualization based on the importance of the data. The data visualization unit evaluates the importance of the data, for example, using generative AI. For example, the data visualization unit can evaluate the impact of the data and visualize highly impactful data in detail. The data visualization unit can also evaluate the reliability of the data and visualize highly reliable data in detail. Furthermore, the data visualization unit can evaluate the frequency of use of the data and visualize frequently used data in detail. This allows the data visualization unit to perform detailed visualization according to the importance of the data. Methods and criteria for adjusting the level of detail of visualization include the impact of the data, frequency of use, importance score, etc.

[0084] The data visualization unit can apply different visualization techniques depending on the data category. The data visualization unit can apply different visualization techniques depending on the data category, for example, by using generative AI. For example, the data visualization unit can perform visualization using statistical graphs for clinical trial data. The data visualization unit can also perform visualization using heat maps for non-clinical trial data. Furthermore, the data visualization unit can perform visualization using risk assessment charts for safety data. This allows the data visualization unit to perform optimal visualization depending on the data category. Methods and standards for applying different visualization techniques depending on the data category include techniques for text data, numerical data, image data, etc.

[0085] The data comparison unit can estimate the user's emotions and adjust the comparison criteria based on the estimated user emotions. The data comparison unit estimates the user's emotions using, for example, a generation AI. For example, the data comparison unit analyzes the user's facial expressions and voice data to estimate emotions. The data comparison unit also adjusts the comparison criteria based on the estimated user emotions. For example, if the user is stressed, the data comparison unit provides simple comparison criteria to reduce the user's burden. If the user is relaxed, the data comparison unit provides detailed comparison criteria to improve data accuracy. Furthermore, if the user is in a hurry, the data comparison unit can quickly perform comparison and immediately provide the necessary data. This allows the comparison criteria to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0086] The data comparison unit can improve the accuracy of the comparison by taking into account the interrelationships of the data. The data comparison unit evaluates the correlations of the data, for example, using a generation AI. For example, the data comparison unit prioritizes the comparison of highly correlated data. The data comparison unit can also prioritize the comparison of data that are causally related. Furthermore, the data comparison unit can prioritize the comparison of data that have many commonalities. This allows the data comparison unit to improve the accuracy of the comparison by taking into account the interrelationships of the data. Methods and standards for improving the accuracy of the comparison include methods for evaluating the interrelationships, algorithms for improving accuracy, etc.

[0087] The data comparison unit can make comparisons based on the attribute information of the data submitter. The data comparison unit can use, for example, a generation AI to evaluate the attribute information of the data submitter. For example, the data comparison unit can evaluate the expertise of the submitter and prioritize comparing data from submitters with high expertise. The data comparison unit can also evaluate the reliability of the submitter and prioritize comparing data from submitters with high reliability. Furthermore, the data comparison unit can evaluate the submitter's past performance and prioritize comparing data from submitters with a proven track record. This allows the data comparison unit to make comparisons taking into account the attribute information of the data submitter. Methods and standards for making comparisons based on the attribute information of the data submitter include the submitter's field of expertise, years of experience, and the method for collecting attribute information.

[0088] The data comparison unit can estimate the user's emotion and adjust the display order of the comparison results based on the estimated user's emotion. The data comparison unit estimates the user's emotion using, for example, a generation AI. For example, the data comparison unit analyzes the user's facial expressions and voice data to estimate the emotion. The data comparison unit also adjusts the display order of the comparison results based on the estimated user's emotion. For example, if the user is stressed, the data comparison unit postpones less important comparison results and prioritizes displaying more important comparison results. Also, if the user is relaxed, the data comparison unit can display all comparison results evenly. Furthermore, if the user is in a hurry, the data comparison unit can quickly display the most important comparison results. This allows the display order of the comparison results to be adjusted according to the user's emotion. Emotion estimation is achieved using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0089] The data comparison unit can take into account geographical data distribution when comparing data. The data comparison unit evaluates geographical data distribution, for example, using generation AI. For example, the data comparison unit compares data by region and provides comparison results that reflect the characteristics of each region. The data comparison unit can also compare data by country and provide comparison results that reflect the regulations and characteristics of each country. Furthermore, the data comparison unit can compare data by city and provide comparison results that reflect the characteristics of each city. This allows the data comparison unit to make comparisons that take into account geographical data distribution. Methods and standards for making comparisons that take into account geographical data distribution include methods for evaluating data distribution by region and geographical characteristics.

[0090] The data comparison unit can improve the accuracy of the comparison by referring to related literature when comparing data. The data comparison unit can, for example, use generative AI to refer to related literature. For example, the data comparison unit can refer to related scientific papers to improve the accuracy of the comparison. The data comparison unit can also improve the accuracy of the comparison by referring to related patents. Furthermore, the data comparison unit can improve the accuracy of the comparison by referring to related government public data. In this way, the data comparison unit can improve the accuracy of the comparison by referring to related literature. Methods and criteria for improving the accuracy of the comparison based on related literature include cited literature, related research, literature evaluation methods, etc.

[0091] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated user emotions. The data collection unit estimates the user's emotions using, for example, a generative AI. For example, the data collection unit analyzes the user's facial expressions and voice data to estimate emotions. The data collection unit also adjusts the timing of data collection based on the estimated user emotions. For example, if the user is stressed, the data collection unit reduces the frequency of data collection and collects data during times when the user is relaxed. Also, if the user is relaxed, the data collection unit increases the frequency of data collection to efficiently collect data. Furthermore, if the user is in a hurry, the data collection unit can quickly collect data and provide the necessary data immediately. This allows the timing of data collection to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0092] The data collection unit can evaluate the reliability of the data and prioritize collecting reliable data. The data collection unit can evaluate the reliability of the data, for example, using generative AI. For example, the data collection unit can evaluate the source of the data and prioritize collecting data from reliable data sources. The data collection unit can also evaluate the consistency of the data and prioritize collecting consistent data. Furthermore, the data collection unit can evaluate the recency of the data and prioritize collecting the latest data. This allows the data collection unit to obtain highly accurate results by prioritized collection of reliable data. The reliability evaluation of the data is performed using, for example, the source of the data, the consistency of the data, an evaluation algorithm, etc. Methods and criteria for prioritized collection of reliable data include priorities based on reliability scores and collection procedures, etc.

[0093] The data collection unit can estimate the user's emotions and prioritize the data to be collected based on the estimated user emotions. The data collection unit estimates the user's emotions using, for example, a generative AI. For example, the data collection unit analyzes the user's facial expressions and voice data to estimate emotions. The data collection unit also prioritizes the data to be collected based on the estimated user emotions. For example, if the user is stressed, the data collection unit postpones less important data and prioritizes collecting more important data. If the user is relaxed, the data collection unit can collect all data equally. If the user is in a hurry, the data collection unit can quickly collect the most important data. This allows the priority of data to be collected to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0094] The data collection unit can perform data collection taking into account geographical data distribution. The data collection unit evaluates the geographical data distribution, for example, using generative AI. For example, the data collection unit collects data by region and provides collection results that reflect the characteristics of each region. The data collection unit can also collect data by country and provide collection results that take into account the regulations and characteristics of each country. Furthermore, the data collection unit can collect data by city and provide collection results that reflect the characteristics of each city. This allows the data collection unit to perform collection taking into account geographical data distribution. Methods and standards for collection that take into account geographical data distribution include methods for evaluating data distribution by region and geographical characteristics, etc.

[0095] The data learning unit can estimate a user's emotions and select training data based on the estimated user emotions. The data learning unit estimates the user's emotions using, for example, a generative AI. For example, the data learning unit analyzes the user's facial expressions and voice data to estimate emotions. The data learning unit also selects training data based on the estimated user emotions. For example, if the user is stressed, the data learning unit selects simple training data to reduce the user's burden. If the user is relaxed, the data learning unit can select detailed training data to improve data accuracy. Furthermore, if the user is in a hurry, the data learning unit can quickly select training data and immediately provide the necessary data. This allows training data to be selected according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0096] During learning, the data learning unit can optimize the learning algorithm by referring to past learning data. The data learning unit, for example, uses a generation AI to refer to past learning data. For example, the data learning unit refers to past learning data and selects an optimal learning algorithm. The data learning unit can also optimize the parameters of the learning algorithm by referring to past learning data. Furthermore, the data learning unit can improve the accuracy of the learning algorithm by referring to past learning data. This allows the data learning unit to optimize the learning algorithm by referring to past learning data. Methods and standards for optimizing the learning algorithm include methods for referring to past data, methods for adjusting the algorithm, etc.

[0097] The data learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. The data learning unit estimates the user's emotions using, for example, a generative AI. For example, the data learning unit analyzes the user's facial expressions and voice data to estimate emotions. The data learning unit also adjusts the frequency of learning based on the estimated user emotions. For example, if the user is stressed, the data learning unit reduces the frequency of learning and performs learning during times when the user is relaxed. Also, if the user is relaxed, the data learning unit increases the frequency of learning, allowing for efficient learning. Furthermore, if the user is in a hurry, the data learning unit can quickly perform learning and provide the necessary data immediately. This allows the frequency of learning to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0098] During learning, the data learning unit can weight the learning data based on the time of data submission. The data learning unit evaluates the time of data submission using, for example, a generative AI. For example, the data learning unit performs learning by assigning a higher weight to the most recent data. The data learning unit can also perform learning by assigning a lower weight to older data. Furthermore, the data learning unit can adjust the weighting of the learning data based on the time of submission. This allows the data learning unit to weight the learning data based on the time of data submission. Methods and standards for weighting the learning data include weighting methods and weighting algorithms based on the time of submission.

[0099] The risk prediction unit can estimate the user's emotions and adjust the risk prediction method based on the estimated user emotions. The risk prediction unit estimates the user's emotions using, for example, a generative AI. For example, the risk prediction unit analyzes the user's facial expressions and voice data to estimate emotions. The risk prediction unit also adjusts the risk prediction method based on the estimated user emotions. For example, if the user is stressed, the risk prediction unit provides a simple risk prediction method to reduce the user's burden. If the user is relaxed, the risk prediction unit provides a detailed risk prediction method to improve data accuracy. Furthermore, if the user is in a hurry, the risk prediction unit can quickly perform risk prediction and immediately provide the necessary data. This allows the risk prediction method to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0100] The risk prediction unit can improve the accuracy of risk prediction by referring to past risk data. The risk prediction unit, for example, uses a generation AI to refer to past risk data. For example, the risk prediction unit can improve the accuracy of risk prediction by referring to past risk data. The risk prediction unit can also optimize parameters of the risk prediction algorithm by referring to past risk data. Furthermore, the risk prediction unit can improve the accuracy of the risk prediction algorithm by referring to past risk data. In this way, the risk prediction unit can improve the accuracy of risk prediction by referring to past risk data. Methods and standards for improving the accuracy of risk prediction include methods for referring to past data, algorithms for improving accuracy, etc.

[0101] The risk prediction unit can estimate the user's emotions and determine the priority of risk predictions based on the estimated user emotions. The risk prediction unit estimates the user's emotions using, for example, a generative AI. For example, the risk prediction unit analyzes the user's facial expressions and voice data to estimate emotions. The risk prediction unit also determines the priority of risk predictions based on the estimated user emotions. For example, if the user is stressed, the risk prediction unit postpones risk predictions of lower importance and prioritizes risk predictions of higher importance. Also, if the user is relaxed, the risk prediction unit can perform all risk predictions equally. Furthermore, if the user is in a hurry, the risk prediction unit can quickly perform the most important risk prediction. This allows the priority of risk predictions to be determined according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0102] The risk prediction unit can make risk predictions taking into account geographical data distribution. The risk prediction unit evaluates the geographical data distribution, for example, using a generative AI. For example, the risk prediction unit predicts risk data for each region and provides a risk prediction result that reflects the characteristics of each region. The risk prediction unit can also predict risk data for each country and provide a risk prediction result that takes into account the regulations and characteristics of each country. Furthermore, the risk prediction unit can predict risk data for each city and provide a risk prediction result that reflects the characteristics of each city. This allows the risk prediction unit to make predictions taking into account geographical data distribution. Methods and standards for making predictions taking into account geographical data distribution include methods for evaluating the data distribution for each region and the geographical characteristics.

[0103] The data acquisition unit can estimate the user's emotions and adjust the timing of data acquisition based on the estimated user emotions. The data acquisition unit estimates the user's emotions using, for example, a generation AI. For example, the data acquisition unit analyzes the user's facial expressions and voice data to estimate emotions. The data acquisition unit also adjusts the timing of data acquisition based on the estimated user emotions. For example, when the user is stressed, the data acquisition unit reduces the frequency of data acquisition and performs data acquisition during times when the user is relaxed. When the user is relaxed, the data acquisition unit increases the frequency of data acquisition to efficiently acquire data. Furthermore, when the user is in a hurry, the data acquisition unit can quickly acquire data and provide the necessary data immediately. This allows the timing of data acquisition to be adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0104] The data acquisition unit can evaluate the reliability of data and prioritize acquisition of highly reliable data. The data acquisition unit can evaluate the reliability of data, for example, using a generation AI. For example, the data acquisition unit can evaluate the source of data and prioritize acquisition of data from highly reliable data sources. The data acquisition unit can also evaluate the consistency of data and prioritize acquisition of consistent data. Furthermore, the data acquisition unit can evaluate the recency of data and prioritize acquisition of the latest data. As a result, the data acquisition unit can obtain highly accurate results by prioritizing acquisition of highly reliable data. The reliability evaluation of data is performed using, for example, the source of data, the consistency of data, an evaluation algorithm, etc. Methods and criteria for preferentially acquiring highly reliable data include priorities based on reliability scores and acquisition procedures, etc.

[0105] The data acquisition unit can estimate the user's emotions and determine the priority of data to be acquired based on the estimated user emotions. The data acquisition unit estimates the user's emotions using, for example, a generation AI. For example, the data acquisition unit analyzes the user's facial expressions and voice data to estimate emotions. The data acquisition unit also determines the priority of data to be acquired based on the estimated user emotions. For example, if the user is feeling stressed, the data acquisition unit postpones less important data and prioritizes acquiring more important data. If the user is relaxed, the data acquisition unit can acquire all data equally. If the user is in a hurry, the data acquisition unit can quickly acquire the most important data. This allows the priority of data to be acquired to be determined according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0106] The data acquisition unit can acquire data while taking into account geographical data distribution. The data acquisition unit evaluates the geographical data distribution, for example, using a generation AI. For example, the data acquisition unit acquires data by region and provides acquisition results that reflect the characteristics of each region. The data acquisition unit can also acquire data by country and provide acquisition results that take into account the regulations and characteristics of each country. Furthermore, the data acquisition unit can acquire data by city and provide acquisition results that reflect the characteristics of each city. This allows the data acquisition unit to acquire data while taking into account geographical data distribution. Methods and standards for acquiring data while taking into account geographical data distribution include methods for evaluating the data distribution by region and the geographical characteristics.

[0107] The data update unit can estimate the user's emotions and adjust the timing of data updates based on the estimated user emotions. The data update unit estimates the user's emotions using, for example, a generation AI. For example, the data update unit analyzes the user's facial expressions and voice data to estimate emotions. The data update unit also adjusts the timing of data updates based on the estimated user emotions. For example, if the user is feeling stressed, the data update unit reduces the frequency of data updates and performs updates during times when the user is relaxed. Also, if the user is relaxed, the data update unit increases the frequency of data updates to efficiently update data. Furthermore, if the user is in a hurry, the data update unit can quickly perform data updates and provide necessary data immediately. This makes it possible to adjust the timing of data updates according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0108] The data updating unit can evaluate the reliability of data and prioritize updating highly reliable data. The data updating unit can evaluate the reliability of data, for example, using a generation AI. For example, the data updating unit can evaluate the source of data and prioritize updating data from a highly reliable data source. The data updating unit can also evaluate the consistency of data and prioritize updating consistent data. Furthermore, the data updating unit can evaluate the recency of data and prioritize updating the latest data. This allows the data updating unit to obtain highly accurate results by preferentially updating highly reliable data. The reliability evaluation of data is performed using, for example, the source of data, the consistency of data, an evaluation algorithm, etc. Methods and criteria for preferentially updating highly reliable data include priorities based on reliability scores and update procedures, etc.

[0109] The data update unit can estimate the user's emotions and determine the priority of data to be updated based on the estimated user emotions. The data update unit estimates the user's emotions using, for example, a generation AI. For example, the data update unit analyzes the user's facial expressions and voice data to estimate emotions. The data update unit also determines the priority of data to be updated based on the estimated user emotions. For example, if the user is feeling stressed, the data update unit postpones less important data and prioritizes updating more important data. Also, if the user is relaxed, the data update unit can update all data evenly. Furthermore, if the user is in a hurry, the data update unit can quickly update the most important data. This makes it possible to determine the priority of data to be updated based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0110] The data update unit can perform the update taking into account the geographical data distribution when updating data. The data update unit evaluates the geographical data distribution, for example, using a generation AI. For example, the data update unit can update the data for each region and provide an update result that reflects the characteristics of each region. The data update unit can also update the data for each country and provide an update result that takes into account the regulations and characteristics of each country. Furthermore, the data update unit can update the data for each city and provide an update result that reflects the characteristics of each city. This allows the data update unit to perform the update taking into account the geographical data distribution. Methods and standards for performing the update taking into account the geographical data distribution include methods for evaluating the data distribution for each region and the geographical characteristics. === Hard Collateral 1-1 === Each of the multiple elements, including the data aggregation unit, data reduction unit, data summarization unit, data visualization unit, data comparison unit, data collection unit, data learning unit, risk prediction unit, data acquisition unit, and data update unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the data aggregation unit is implemented by the processor 46 of the smart device 14 and quickly aggregates clinical trial data and non-clinical trial data. The data reduction unit is implemented by the specific processing unit 290 of the data processing device 12 and classifies and organizes the aggregated data. The data summarization unit is implemented by the control unit 46A of the smart device 14 and summarizes the organized data and generates a summary report. The data visualization unit is implemented by the specific processing unit 290 of the data processing device 12 and converts the summarized data into graphs or tables for visualization. The data comparison unit is implemented by the control unit 46A of the smart device 14 and compares the visualized data. The data collection unit is implemented by the specific processing unit 290 of the data processing device 12 and collects scientific data and correlations with previous scientific papers and existing patents. The data learning unit is realized by the processor 46 of the smart device 14 and learns past clinical trial data and safety inspection data. The risk prediction unit is realized by the specific processing unit 290 of the data processing device 12 and predicts risk based on the learned data. The data acquisition unit is realized by the control unit 46A of the smart device 14 and automatically acquires the latest data on pharmaceutical regulations, safety, ethical regulations, etc. The data update unit is realized by the specific processing unit 290 of the data processing device 12 and updates the acquired latest data. === Hard Collateral 1-2 === Each of the multiple elements, including the data aggregation unit, data reduction unit, data summarization unit, data visualization unit, data comparison unit, data collection unit, data learning unit, risk prediction unit, data acquisition unit, and data update unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the data aggregation unit is implemented by the processor 46 of the smart glasses 214 and quickly aggregates clinical trial data and non-clinical trial data. The data reduction unit is implemented by the specific processing unit 290 of the data processing device 12 and classifies and organizes the aggregated data. The data summarization unit is implemented by the control unit 46A of the smart glasses 214 and summarizes the organized data and generates a summary report. The data visualization unit is implemented by the specific processing unit 290 of the data processing device 12 and converts the summarized data into graphs or tables for visualization. The data comparison unit is implemented by the control unit 46A of the smart glasses 214 and compares the visualized data. The data collection unit is implemented by the specific processing unit 290 of the data processing device 12 and collects scientific data and correlations with previous scientific papers and existing patents. The data learning unit is realized by the processor 46 of the smart glasses 214 and learns past clinical trial data and safety inspection data. The risk prediction unit is realized by the specific processing unit 290 of the data processing device 12 and predicts risk based on the learned data. The data acquisition unit is realized by the control unit 46A of the smart glasses 214 and automatically acquires the latest data on pharmaceutical regulations, safety, ethical regulations, etc. The data update unit is realized by the specific processing unit 290 of the data processing device 12 and updates the acquired latest data. === Hard Collateral 1-3 === Each of the multiple elements, including the data aggregation unit, data reduction unit, data summarization unit, data visualization unit, data comparison unit, data collection unit, data learning unit, risk prediction unit, data acquisition unit, and data update unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the data aggregation unit is implemented by the processor 46 of the headset terminal 314 and quickly compiles clinical trial data and non-clinical trial data. The data reduction unit is implemented by the specific processing unit 290 of the data processing device 12 and classifies and organizes the compiled data. The data summarization unit is implemented by the control unit 46A of the headset terminal 314 and summarizes the organized data and generates a summary report. The data visualization unit is implemented by the specific processing unit 290 of the data processing device 12 and converts the summarized data into graphs or tables for visualization. The data comparison unit is implemented by the control unit 46A of the headset terminal 314 and compares the visualized data. The data collection unit is implemented by the specific processing unit 290 of the data processing device 12 and collects scientific data and relevance to previous scientific papers and existing patents. The data learning unit is realized by the processor 46 of the headset terminal 314 and learns past clinical trial data and safety inspection data. The risk prediction unit is realized by the specific processing unit 290 of the data processing device 12 and predicts risk based on the learned data. The data acquisition unit is realized by the control unit 46A of the headset terminal 314 and automatically acquires the latest data on pharmaceutical regulations, safety, ethical regulations, etc. The data update unit is realized by the specific processing unit 290 of the data processing device 12 and updates the acquired latest data. === Hard Collateral 1-4 === Each of the multiple elements, including the data aggregation unit, data reduction unit, data summarization unit, data visualization unit, data comparison unit, data collection unit, data learning unit, risk prediction unit, data acquisition unit, and data update unit, is implemented, for example, by at least one of the robot 414 and the data processing device 12. For example, the data aggregation unit is implemented by the processor 46 of the robot 414 and quickly compiles clinical trial data and non-clinical trial data. The data reduction unit is implemented by the specific processing unit 290 of the data processing device 12 and classifies and organizes the compiled data. The data summarization unit is implemented by the control unit 46A of the robot 414 and summarizes the organized data and generates a summary report. The data visualization unit is implemented by the specific processing unit 290 of the data processing device 12 and converts the summarized data into graphs or tables for visualization. The data comparison unit is implemented by the control unit 46A of the robot 414 and compares the visualized data. The data collection unit is implemented by the specific processing unit 290 of the data processing device 12 and collects scientific data and correlations with previous scientific papers and existing patents. The data learning unit is realized by the processor 46 of the robot 414 and learns past clinical trial data and safety inspection data. The risk prediction unit is realized by the specific processing unit 290 of the data processing device 12 and predicts risk based on the learned data. The data acquisition unit is realized by the control unit 46A of the robot 414 and automatically acquires the latest data on pharmaceutical regulations, safety, ethical regulations, etc. The data update unit is realized by the specific processing unit 290 of the data processing device 12 and updates the acquired latest data.

[0111] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0112] The data aggregation unit can learn the user's past operation history and suggest the optimal aggregation method. For example, it can prioritize the aggregation method that the user has frequently used in the past. It can also record the operations performed by the user on a specific data set and automatically apply them to similar data sets. Furthermore, it can automatically set the optimal aggregation parameters based on the aggregation results performed by the user in the past. This enables efficient data aggregation based on the user's operation history.

[0113] The data collection unit can learn the user's areas of interest and prioritize collecting related data. For example, it can automatically collect new related literature based on the keywords the user has searched for and the literature they have viewed in the past. Also, if the user is interested in a specific research field, it can prioritize collecting the latest data related to that field. Furthermore, it can prioritize collecting data from reliable data sources based on the reliability of data evaluated by the user in the past. This enables efficient data collection according to the user's areas of interest.

[0114] The data learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is feeling stressed, the data learning unit selects simple training data to reduce the user's burden. If the user is relaxed, the data learning unit can select detailed training data to improve the accuracy of the data. Furthermore, if the user is in a hurry, the data learning unit can quickly select training data and provide the necessary data immediately. This makes it possible to select training data according to the user's emotions.

[0115] The risk prediction unit can estimate the user's emotions and adjust the risk prediction method based on the estimated user's emotions. For example, if the user is feeling stressed, the risk prediction unit can provide a simple risk prediction method to reduce the user's burden. If the user is relaxed, the risk prediction unit can provide a detailed risk prediction method to improve data accuracy. Furthermore, if the user is in a hurry, the risk prediction unit can quickly make a risk prediction and immediately provide the necessary data. This makes it possible to adjust the risk prediction method according to the user's emotions.

[0116] The data acquisition unit can estimate the user's emotions and adjust the timing of data acquisition based on the estimated user emotions. For example, if the user is feeling stressed, the data acquisition unit reduces the frequency of data acquisition and performs data acquisition during times when the user is relaxed. Also, if the user is relaxed, the data acquisition unit can increase the frequency of data acquisition and acquire data efficiently. Furthermore, if the user is in a hurry, the data acquisition unit can quickly acquire data and provide the necessary data immediately. This makes it possible to adjust the timing of data acquisition according to the user's emotions.

[0117] The data update unit can estimate the user's emotions and determine the priority of data to be updated based on the estimated user's emotions. For example, if the user is feeling stressed, the data update unit postpones data of low importance and prioritizes updating data of high importance. Also, if the user is relaxed, the data update unit can update all data evenly. Furthermore, if the user is in a hurry, the data update unit can quickly update the most important data. In this way, the priority of data to be updated can be determined according to the user's emotions.

[0118] The data organizing unit can determine the order of priorities for organizing based on the importance of the data. For example, the data organizing unit can evaluate the impact of the data and prioritize organizing data with high impact. The data organizing unit can also evaluate the reliability of the data and prioritize organizing data with high reliability. Furthermore, the data organizing unit can evaluate the frequency of data use and prioritize organizing data with high frequency of use. This allows the data organizing unit to prioritize organizing data with high importance.

[0119] When generating a summary, the data summarizing unit can adjust the level of detail of the summary based on the importance of the data. For example, the data summarizing unit can evaluate the impact of the data and summarize data with high impact in detail. The data summarizing unit can also evaluate the reliability of the data and summarize highly reliable data in detail. Furthermore, the data summarizing unit can evaluate the frequency of use of the data and summarize frequently used data in detail. This allows the data summarizing unit to generate a detailed summary according to the importance of the data.

[0120] The data visualization unit can adjust the level of detail of visualization based on the importance of the data. For example, the data visualization unit can evaluate the impact of data and visualize data with high impact in detail. The data visualization unit can also evaluate the reliability of data and visualize highly reliable data in detail. Furthermore, the data visualization unit can evaluate the frequency of use of data and visualize frequently used data in detail. This allows the data visualization unit to perform detailed visualization according to the importance of the data.

[0121] The data comparison unit can make comparisons based on attribute information of data submitters. For example, the data comparison unit can evaluate the expertise of the submitter and prioritize comparing data of submitters with high expertise. The data comparison unit can also evaluate the reliability of the submitter and prioritize comparing data of submitters with high reliability. Furthermore, the data comparison unit can evaluate the submitter's past performance and prioritize comparing data of submitters with a proven track record. This allows the data comparison unit to make comparisons taking into account attribute information of the data submitter.

[0122] The processing flow of the second embodiment will be briefly explained below.

[0123] Step 1: The data aggregation unit aggregates data. For example, it aggregates clinical trial data and non-clinical trial data, and uses generative AI to quickly aggregate large amounts of data. The data aggregation unit aggregates test results and can perform statistical analysis. It can also apply different aggregation algorithms depending on the type of data. For example, it uses statistical methods for clinical trial data and machine learning algorithms for non-clinical trial data. Step 2: The data reduction unit organizes the data collected by the data aggregation unit. For example, the data can be classified and organized. The data reduction unit uses generative AI to organize the data based on data classification criteria. For example, it can determine the priority of organization based on the importance of the data. It can also apply different organization methods depending on the data category. For example, it uses statistical methods for clinical trial data and machine learning algorithms for non-clinical trial data. Step 3: The data summarization unit summarizes the data organized by the data reduction unit. For example, it can summarize the data and generate a summary report. The data summarization unit summarizes the data based on a data summarization algorithm using generative AI. For example, it can adjust the level of detail in the summary based on the importance of the data. It can also apply different summarization algorithms depending on the data category. For example, it can use statistical methods for clinical trial data and machine learning algorithms for non-clinical trial data. Step 4: The data visualization unit visualizes the data summarized by the data summarization unit. For example, it can convert the data into graphs or tables and visualize them. The data visualization unit uses generative AI to visualize the data based on a data visualization algorithm. For example, it can adjust the level of detail in the visualization based on the importance of the data. It can also apply different visualization techniques depending on the category of data. For example, it can use statistical graphs for clinical trial data and heat maps for non-clinical trial data. Step 5: The data comparison unit compares the data visualized by the data visualization unit. For example, it can calculate and compare the similarity of the data. The data comparison unit uses generative AI to compare the data based on a data comparison algorithm. For example, it can improve the accuracy of the comparison by taking into account the correlation between the data. It can also apply different comparison methods depending on the data category. For example, it uses statistical methods for clinical trial data and machine learning algorithms for non-clinical trial data.

[0124] 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.

[0125] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0126] 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.

[0127] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0128] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0129] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0130] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0131] The 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.

[0132] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (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).

[0134] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0142] 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.

[0143] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0144] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0155] 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.

[0156] 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.

[0157] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0158] 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.

[0159] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0160] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0161] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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).

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0172] 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.

[0173] 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.

[0174] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0175] 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.

[0176] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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).

[0181] 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.

[0182] 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."

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] [Explanation of symbols]

[0196] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a data aggregation unit that aggregates data; a data organizing unit that organizes the data compiled by the data compilation unit; a data summarizing unit that summarizes the data organized by the data organizing unit; a data visualization unit that visualizes the data summarized by the data summarization unit; a data comparison unit that compares the data visualized by the data visualization unit. A system characterized by:

2. Equipped with a data collection department that collects scientific data and links it to previous scientific papers or existing patents 2. The system of claim 1.

3. Equipped with a data learning unit that learns from past clinical trial data or safety test data 2. The system of claim 1.

4. Equipped with a risk prediction unit that predicts risks based on learned data 4. The system of claim 3.

5. Equipped with a data acquisition unit that automatically acquires the latest data on pharmaceutical regulations or safety and ethical regulations 2. The system of claim 1.

6. Equipped with a data update unit that updates the latest acquired data 6. The system of claim 5.

7. The data aggregation unit Estimate user emotions and adjust the timing of data aggregation based on the estimated user emotions.

2. The system of claim 1.

8. The data aggregation unit Evaluate the reliability of data and prioritize aggregation of reliable data 2. The system of claim 1.

9. The data aggregation unit Apply different aggregation algorithms depending on the type of data 2. The system of claim 1.

Images