system

Abstract

The system according to this embodiment aims to identify the cause of incorrect answers, automatically collect necessary data, and retrain the model. [Solution] The system according to the embodiment comprises an analysis unit, a data collection unit, a retraining unit, and an integration unit. The analysis unit analyzes the causes of incorrect answers. The data collection unit automatically collects the necessary data identified by the analysis unit from the internet. The retraining unit retrains the model with the new data collected by the data collection unit. The integration unit integrates the model retrained by the retraining unit with other analysis tools.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the process of identifying the cause of an incorrect answer, collecting necessary data, and retraining the model requires time and effort and is difficult to perform efficiently.

[0005] The system according to the embodiment aims to identify the cause of an incorrect answer, automatically collect necessary data, and retrain the model.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a data collection unit, a retraining unit, and an integration unit. The analysis unit analyzes the causes of incorrect answers. The data collection unit automatically collects the necessary data identified by the analysis unit from the network. The retraining unit retrains the model with the new data collected by the data collection unit. The integration unit integrates the model retrained by the retraining unit with other analysis tools. [Effects of the Invention]

[0007] The system according to this embodiment can identify the cause of incorrect answers, automatically collect the necessary data, and retrain the model. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The system according to an embodiment of the present invention is a system that uses AI to reduce the burden of data preparation, identify the causes of errors, and efficiently repeat learning to rapidly develop a highly accurate model. In this system, first, the AI ​​analyzes the cause of errors and identifies the necessary data. Next, it automatically collects the necessary data from the internet and supplements the dataset. Furthermore, it retrains with the new data and repeats until the target accuracy rate is reached. Finally, it integrates with other analysis tools to achieve efficient work. This mechanism enables the rapid development of highly accurate models, reducing effort and improving efficiency. For example, the AI ​​analyzes the cause of errors. In this process, the AI ​​identifies the reason for the error and determines which data is missing. For example, in an image classification model, if there are many errors for a particular image category, it is determined that there is a lack of data related to that category. Next, it automatically collects the necessary data from the internet. The AI ​​collects the identified data from the internet and supplements the dataset. For example, it automatically collects images related to a specific image category and adds them to the dataset. Furthermore, it retrains with the new data. The AI ​​retrains the model using the newly collected data and repeats this process until the target accuracy rate is reached. For example, the model is retrained using newly collected image data, and this process is repeated until the accuracy improves. Finally, it is integrated with other analytical tools. AI works in conjunction with other analytical tools to enable efficient work. For example, it can provide the results of error analysis to other tools for data visualization and further analysis. This allows for the rapid development of highly accurate models. By reducing effort and increasing efficiency, time and labor can be saved. For example, data preparation and identification of error causes, which required a tremendous amount of time and effort with traditional methods, can be done quickly and efficiently using AI. Also, compared to traditional methods that involved a lot of repetition, learning can be repeated more efficiently using AI. As a result, AI researchers and data scientists can develop highly accurate models quickly and work efficiently.This allows AI-based systems to reduce the burden of data preparation, identify the causes of errors, and rapidly develop highly accurate models through efficient iterative learning.

[0029] The system according to the embodiment comprises an analysis unit, a data collection unit, a retraining unit, and an integration unit. The analysis unit analyzes the cause of incorrect answers. The analysis unit, for example, identifies the reason for the incorrect answer and determines which data is missing. For example, if the image classification model has many incorrect answers for a particular image category, the analysis unit determines that there is insufficient data related to that category. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. The data collection unit automatically collects the necessary data identified by the analysis unit from the internet. The data collection unit, for example, collects the identified data from the internet and supplements the dataset. For example, the data collection unit automatically collects images related to a specific image category and adds them to the dataset. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. The retraining unit retrains the model with the new data collected by the data collection unit. The retraining unit, for example, retrains the model using the newly collected data and repeats this process until the target accuracy rate is reached. For example, the retraining unit retrains the model using newly collected image data and repeats this process until the accuracy improves. Some or all of the above processes in the retraining unit may be performed using AI, for example, or without AI. The integration unit integrates the model retrained by the retraining unit with other analysis tools. The integration unit works in conjunction with other analysis tools, for example, to achieve efficient operation. For example, the integration unit provides the analysis results of the causes of errors to other tools for data visualization and further analysis. Some or all of the above processes in the integration unit may be performed using AI, for example, or without AI. As a result, the system according to the embodiment can rapidly develop highly accurate models by analyzing the causes of errors, automatically collecting necessary data, retraining, and integrating with other analysis tools.

[0030] The analysis unit analyzes the cause of incorrect answers. For example, the analysis unit identifies the reason for the incorrect answer and determines which data is missing. Specifically, the analysis unit analyzes the frequency and patterns of incorrect answers in detail to understand the trends of incorrect answers under specific conditions. For example, in an image classification model, if there are many incorrect answers for a particular image category, it will be determined that there is insufficient data related to that category. To identify the cause of an incorrect answer, the analysis unit compares the input data at the time the incorrect answer occurred with the output results of the model and analyzes in detail where the error occurred. Furthermore, to identify the cause of an incorrect answer, the analysis unit can also use AI-based natural language processing technology to analyze text data related to the incorrect answer. For example, it can analyze explanatory texts and comments related to the incorrect answer to identify the cause of the incorrect answer. Some or all of the above processing in the analysis unit may be performed using AI, or not using AI. When using AI, generative AI or LLM (Large-Scale Language Model) is used to generate prompts to identify the cause of the incorrect answer and input them into the AI. Based on the input prompts, the AI ​​performs a detailed analysis to identify the cause of the incorrect answer and outputs the results. This allows the analysis unit to quickly and accurately identify the cause of incorrect answers and determine the necessary data.

[0031] The data collection unit automatically collects the necessary data identified by the analysis unit from the internet. For example, the data collection unit collects the identified data from the internet to supplement the dataset. Specifically, the data collection unit automatically collects images related to a specific image category and adds them to the dataset. The data collection unit uses web scraping techniques to collect the necessary data from publicly available databases and websites on the internet. For example, to collect images related to a specific image category, the data collection unit uses a search engine with relevant keywords and collects images from the search results. The data collection unit filters the collected data and adds only high-quality data to the dataset. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. When using AI, generative AI or LLM is utilized to generate prompts for the conditions of the data to be collected and input them into the AI. Based on the input prompts, the AI ​​automatically collects the necessary data from the internet and outputs the results. This allows the data collection unit to collect the necessary data quickly and efficiently and supplement the dataset.

[0032] The retraining unit retrains the model with new data collected by the data collection unit. For example, the retraining unit retrains the model using the newly collected data and repeats this process until the target accuracy is reached. Specifically, the retraining unit retrains the model using the newly collected image data and repeats this process until the accuracy improves. The retraining unit adjusts the model parameters and tunes the hyperparameters to achieve optimal performance. Some or all of the above processes in the retraining unit may be performed using AI, for example, or without AI. If AI is used, generative AI or LLM is utilized to automate the retraining process. For example, the retraining conditions and goals are generated as prompts and input into the AI. Based on the input prompts, the AI ​​automatically executes the retraining process and generates an optimal model. This allows the retraining unit to improve the model's performance quickly and efficiently.

[0033] The Integration Unit integrates the models retrained by the Retraining Unit with other analytical tools. For example, the Integration Unit works in conjunction with other analytical tools to achieve efficient operations. Specifically, the Integration Unit provides the results of error analysis to other tools for data visualization and further analysis. The Integration Unit integrates the retrained models into other systems and applications, making them usable in actual operating environments. Some or all of the above processes in the Integration Unit may be performed using AI, for example, or without AI. When using AI, generative AI or LLM are utilized to automate the integration process. For example, integration conditions and goals are generated as prompts and input into the AI. Based on the input prompts, the AI ​​automatically executes the integration process to achieve optimal integration. This allows the Integration Unit to quickly and efficiently integrate the retrained models with other analytical tools, improving overall system performance.

[0034] The analysis unit can identify the reasons for incorrect answers. The analysis unit identifies the reasons for incorrect answers by considering, for example, the type, frequency, and impact of the incorrect answers. For example, the analysis unit can analyze the types of errors and identify the causes of frequent occurrences of specific errors. The analysis unit can also analyze the frequency of incorrect answers and prioritize identifying the causes of frequently occurring incorrect answers. Furthermore, the analysis unit can evaluate the impact of incorrect answers and identify the causes of highly impactful incorrect answers. By identifying the reasons for incorrect answers, the necessary data can be clarified. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or without using AI.

[0035] The data collection unit can collect identified data from the internet. The data collection unit collects data considering, for example, the format, reliability, and relevance of the identified data. For example, the data collection unit can collect data based on a specific data format (e.g., images, text, audio, etc.). The data collection unit can also collect data from reliable data sources. Furthermore, the data collection unit can prioritize the collection of highly relevant data. This allows the dataset to be complemented by collecting identified data from the internet. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI.

[0036] The retraining unit can retrain the model using newly collected data. The retraining unit retrains the model considering, for example, the format, reliability, and relevance of the newly collected data. For example, the retraining unit can retrain the model based on new data formats (e.g., images, text, audio, etc.). The retraining unit can also retrain the model using highly reliable data. Furthermore, the retraining unit can retrain the model by prioritizing the use of highly relevant data. This allows for improved model accuracy by retraining the model with newly collected data. Some or all of the above processing in the retraining unit may be performed using AI, for example, or without AI.

[0037] The integration unit can perform data visualization and further analysis in conjunction with other analytical tools. For example, the integration unit performs data visualization and further analysis while considering data compatibility and integration methods with other analytical tools. For example, the integration unit can convert data formats and integrate with other analytical tools. The integration unit can also integrate data with other analytical tools using APIs. Furthermore, the integration unit can visually display data using data visualization tools and perform further analysis. This enables efficient work by integrating with other analytical tools. Some or all of the above processes in the integration unit may be performed using AI, for example, or without AI.

[0038] The analysis unit can optimize its analysis algorithm by referring to past error data when analyzing the cause of incorrect answers. For example, the analysis unit can analyze past error data, identify common error patterns, and adjust the analysis algorithm. For example, the analysis unit can learn from past error data and optimize an algorithm to quickly identify the cause of incorrect answers. The analysis unit can also refer to past error data and improve the accuracy of the analysis based on the frequency and patterns of incorrect answers. In this way, by referring to past error data, the analysis algorithm can be optimized and the accuracy of the analysis can be improved. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI.

[0039] The analysis unit can improve the accuracy of its analysis by considering the frequency and patterns of incorrect answers when analyzing the causes of incorrect answers. For example, the analysis unit can analyze the frequency of incorrect answers and prioritize identifying the causes of frequently occurring incorrect answers. For example, the analysis unit can analyze the patterns of incorrect answers and identify the causes of incorrect answers based on specific patterns. Furthermore, the analysis unit can combine the frequency and patterns of incorrect answers in its analysis to more accurately identify the causes of incorrect answers. In this way, the accuracy of the analysis can be improved by considering the frequency and patterns of incorrect answers. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without using AI.

[0040] The analysis unit can perform its analysis while considering the user's geographical location information when analyzing the cause of incorrect answers. For example, the analysis unit can refer to the user's geographical location information to identify region-specific incorrect answer patterns and perform analysis. For example, the analysis unit can identify the cause of incorrect answers for each region based on the user's geographical location information. Furthermore, the analysis unit can improve the accuracy of the analysis by considering the user's geographical location information and using region-specific data. This makes it possible to identify region-specific incorrect answer patterns and improve the accuracy of the analysis by considering the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0041] The analysis unit can improve the accuracy of its analysis by referring to relevant literature and databases when analyzing the causes of incorrect answers. For example, the analysis unit can refer to relevant literature and incorporate the latest research results on the causes of incorrect answers into its analysis. For example, the analysis unit can refer to databases and improve the accuracy of its analysis by comparing it with past incorrect answer data. Furthermore, the analysis unit can refer to a combination of relevant literature and databases to more accurately identify the causes of incorrect answers. In this way, the accuracy of the analysis can be improved by referring to relevant literature and databases. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI.

[0042] The data collection unit can optimize its collection algorithm by referring to past collected data when collecting necessary data. For example, the data collection unit can analyze past collected data and optimize its collection algorithm to collect data efficiently. For example, the data collection unit can learn from past collected data and adjust its algorithm to improve the accuracy of collection. The data collection unit can also refer to past collected data and optimize the frequency and timing of collection. In this way, by referring to past collected data, the data collection algorithm can be optimized and the accuracy of collection can be improved. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without using AI.

[0043] The data collection unit can improve the accuracy of data collection by considering the reliability and quality of the data when collecting the necessary data. For example, the data collection unit can evaluate the reliability of the data and prioritize the collection of reliable data. For example, the data collection unit can analyze the quality of the data and adjust the algorithm to collect high-quality data. The data collection unit can also select the optimal method to improve the accuracy of data collection by considering the reliability and quality of the data. In this way, the accuracy of data collection can be improved by considering the reliability and quality of the data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without using AI.

[0044] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location when collecting necessary data. For example, the data collection unit can refer to the user's geographical location and prioritize the collection of region-specific data. For example, the data collection unit can adjust the algorithm for collecting highly relevant data based on the user's geographical location. The data collection unit can also select the optimal method for collecting region-specific data by considering the user's geographical location. This allows for the priority collection of highly relevant data and improves the accuracy of data collection by considering the user's geographical location. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without using AI.

[0045] The data collection unit can analyze users' social media activity and collect relevant data when collecting necessary data. For example, the data collection unit can analyze users' social media activity and collect relevant data. For example, the data collection unit can collect data from users' social media activity based on their interests. The data collection unit can also refer to users' social media activity and adjust algorithms to collect highly relevant data. This allows for the collection of relevant data and improved data collection accuracy by analyzing users' social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI.

[0046] The retraining unit can optimize the training algorithm by referring to past training data when performing retraining. For example, the retraining unit can analyze past training data and optimize the training algorithm to perform retraining efficiently. For example, the retraining unit can learn from past training data and adjust the algorithm to improve training accuracy. The retraining unit can also refer to past training data and optimize the training frequency and timing. In this way, by referring to past training data, the training algorithm can be optimized and the accuracy of retraining can be improved. Some or all of the above processes in the retraining unit may be performed using AI, for example, or without using AI.

[0047] The retraining unit can improve training accuracy by considering the balance and diversity of the training data when performing retraining. For example, the retraining unit can evaluate the balance of the training data and perform retraining using a balanced dataset. For example, the retraining unit can analyze the diversity of the training data and improve training accuracy by using diverse data. The retraining unit can also select the optimal training method by considering the balance and diversity of the training data. In this way, the accuracy of retraining can be improved by considering the balance and diversity of the training data. Some or all of the above processes in the retraining unit may be performed using AI, for example, or without using AI.

[0048] The retraining unit can select optimal training data by considering the user's geographical location information when performing retraining. For example, the retraining unit can refer to the user's geographical location information and perform retraining using region-specific data. For example, the retraining unit can select highly relevant training data based on the user's geographical location information. Furthermore, the retraining unit can improve the accuracy of training by considering the user's geographical location information and using region-specific data. This allows for improved accuracy of retraining using region-specific data by considering the user's geographical location information. Some or all of the above processing in the retraining unit may be performed using AI, for example, or without using AI.

[0049] The retraining unit can improve the accuracy of training by referring to relevant literature and databases when performing retraining. For example, the retraining unit can refer to relevant literature and incorporate the latest research findings to improve training accuracy. For example, the retraining unit can refer to databases and improve training accuracy by comparing it with past training data. The retraining unit can also improve training accuracy by referring to a combination of relevant literature and databases. In this way, training accuracy can be improved by referring to relevant literature and databases. Some or all of the above processes in the retraining unit may be performed using AI, for example, or without using AI.

[0050] The integration unit can optimize its integration algorithm by referencing historical integration data when integrating with other analytical tools. For example, the integration unit can analyze historical integration data and optimize its integration algorithm to perform integration efficiently. For example, the integration unit can learn from historical integration data and adjust its algorithm to improve the accuracy of integration. The integration unit can also refer to historical integration data to optimize the frequency and timing of integration. This allows for the optimization of the integration algorithm and improvement of integration accuracy by referencing historical integration data. Some or all of the above processes in the integration unit may be performed using AI, for example, or without AI.

[0051] The integration unit can improve the accuracy of integration by considering data compatibility and communication methods between tools when integrating with other analytical tools. For example, the integration unit can evaluate data compatibility between tools and prioritize the integration of highly compatible data. For example, the integration unit can analyze communication methods between tools and adjust algorithms to improve the accuracy of communication. The integration unit can also consider data compatibility and communication methods between tools and select the optimal method to improve the accuracy of integration. In this way, the accuracy of integration can be improved by considering data compatibility and communication methods between tools. Some or all of the above processing in the integration unit may be performed using AI, for example, or without using AI.

[0052] The integration unit can select the optimal integration method when integrating with other analytical tools, taking into account the user's geographical location. For example, the integration unit can refer to the user's geographical location and prioritize the integration of region-specific data. For example, the integration unit can select a highly relevant integration method based on the user's geographical location. Furthermore, the integration unit can improve the accuracy of the integration by considering the user's geographical location and using region-specific data. This allows for improved integration accuracy by considering the user's geographical location and using region-specific data. Some or all of the above processing in the integration unit may be performed using AI, for example, or without AI.

[0053] The integration unit can improve the accuracy of the integration by referring to relevant literature and databases when integrating with other analytical tools. For example, the integration unit can refer to relevant literature and incorporate the latest research findings to improve the accuracy of the integration. For example, the integration unit can refer to databases and improve the accuracy of the integration by comparing them with past integrated data. The integration unit can also improve the accuracy of the integration by referring to a combination of relevant literature and databases. In this way, the accuracy of the integration can be improved by referring to relevant literature and databases. Some or all of the above processing in the integration unit may be performed using AI, for example, or not using AI.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The analysis unit can optimize its analysis algorithm by referring to past error data when analyzing the causes of incorrect answers. For example, it can analyze past error data to identify common error patterns and adjust the analysis algorithm. It can also learn from past error data and optimize the algorithm to quickly identify the causes of errors. Furthermore, it can improve the accuracy of the analysis based on the frequency and patterns of errors by referring to past error data. In this way, by referring to past error data, the analysis algorithm can be optimized and the accuracy of the analysis can be improved.

[0056] The data collection unit can optimize its collection algorithm by referring to past data collection data when collecting necessary data. For example, it can analyze past data collection data and optimize the collection algorithm to collect data efficiently. It can also learn from past data collection data and adjust the algorithm to improve collection accuracy. Furthermore, it can refer to past data collection data to optimize the frequency and timing of collection. In this way, by referring to past data collection data, the collection algorithm can be optimized and collection accuracy can be improved.

[0057] The retraining unit can optimize the training algorithm by referring to past training data during retraining. For example, it can analyze past training data and optimize the training algorithm to perform retraining efficiently. It can also learn from past training data and adjust the algorithm to improve training accuracy. Furthermore, it can optimize the training frequency and timing by referring to past training data. In this way, by referring to past training data, the training algorithm can be optimized and the accuracy of retraining can be improved.

[0058] The integration unit can optimize its integration algorithm by referencing historical integration data when integrating with other analytical tools. For example, it can analyze historical integration data and optimize the integration algorithm to perform integration efficiently. It can also learn from historical integration data and adjust the algorithm to improve the accuracy of integration. Furthermore, it can refer to historical integration data to optimize the frequency and timing of integration. In this way, referencing historical integration data allows for the optimization of the integration algorithm and improvement of integration accuracy.

[0059] The analysis unit can improve the accuracy of its analysis by considering the frequency and patterns of incorrect answers when analyzing the causes of errors. For example, it can analyze the frequency of incorrect answers and prioritize the identification of the causes of frequently occurring errors. It can also analyze the patterns of incorrect answers and identify the causes of errors based on specific patterns. Furthermore, it can combine the frequency and patterns of incorrect answers in its analysis to more accurately identify the causes of errors. In this way, the accuracy of the analysis can be improved by considering the frequency and patterns of incorrect answers.

[0060] The data collection unit can improve the accuracy of data collection by considering data reliability and quality when collecting necessary data. For example, it can evaluate data reliability and prioritize the collection of reliable data. It can also analyze data quality and adjust algorithms to collect high-quality data. Furthermore, it can select the optimal method to improve collection accuracy by considering data reliability and quality. In this way, the accuracy of data collection can be improved by considering data reliability and quality.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The analysis unit analyzes the cause of the incorrect answers. For example, the analysis unit identifies the reason for the incorrect answers and determines which data is missing. For example, in an image classification model, if there are many incorrect answers for a particular image category, it will determine that there is insufficient data related to that category. Step 2: The collection unit automatically collects the necessary data identified by the analysis unit from the internet. The collection unit, for example, collects the identified data from the internet to supplement the dataset. For example, it automatically collects images related to a specific image category and adds them to the dataset. Step 3: The retraining unit retrains the model with the new data collected by the data collection unit. The retraining unit, for example, retrains the model using the newly collected data and repeats this process until the target accuracy is reached. Step 4: The Integration Unit integrates the model retrained by the Retraining Unit with other analytical tools. The Integration Unit works with other analytical tools, for example, to enable efficient operations. For example, it provides the results of the error cause analysis to other tools for data visualization and further analysis.

[0063] (Example of form 2) The system according to an embodiment of the present invention is a system that uses AI to reduce the burden of data preparation, identify the causes of errors, and efficiently repeat learning to rapidly develop a highly accurate model. In this system, first, the AI ​​analyzes the cause of errors and identifies the necessary data. Next, it automatically collects the necessary data from the internet and supplements the dataset. Furthermore, it retrains with the new data and repeats until the target accuracy rate is reached. Finally, it integrates with other analysis tools to achieve efficient work. This mechanism enables the rapid development of highly accurate models, reducing effort and improving efficiency. For example, the AI ​​analyzes the cause of errors. In this process, the AI ​​identifies the reason for the error and determines which data is missing. For example, in an image classification model, if there are many errors for a particular image category, it is determined that there is a lack of data related to that category. Next, it automatically collects the necessary data from the internet. The AI ​​collects the identified data from the internet and supplements the dataset. For example, it automatically collects images related to a specific image category and adds them to the dataset. Furthermore, it retrains with the new data. The AI ​​retrains the model using the newly collected data and repeats this process until the target accuracy rate is reached. For example, the model is retrained using newly collected image data, and this process is repeated until the accuracy improves. Finally, it is integrated with other analytical tools. AI works in conjunction with other analytical tools to enable efficient work. For example, it can provide the results of error analysis to other tools for data visualization and further analysis. This allows for the rapid development of highly accurate models. By reducing effort and increasing efficiency, time and labor can be saved. For example, data preparation and identification of error causes, which required a tremendous amount of time and effort with traditional methods, can be done quickly and efficiently using AI. Also, compared to traditional methods that involved a lot of repetition, learning can be repeated more efficiently using AI. As a result, AI researchers and data scientists can develop highly accurate models quickly and work efficiently.This allows AI-based systems to reduce the burden of data preparation, identify the causes of errors, and rapidly develop highly accurate models through efficient iterative learning.

[0064] The system according to the embodiment comprises an analysis unit, a data collection unit, a retraining unit, and an integration unit. The analysis unit analyzes the cause of incorrect answers. The analysis unit, for example, identifies the reason for the incorrect answer and determines which data is missing. For example, if the image classification model has many incorrect answers for a particular image category, the analysis unit determines that there is insufficient data related to that category. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. The data collection unit automatically collects the necessary data identified by the analysis unit from the internet. The data collection unit, for example, collects the identified data from the internet and supplements the dataset. For example, the data collection unit automatically collects images related to a specific image category and adds them to the dataset. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. The retraining unit retrains the model with the new data collected by the data collection unit. The retraining unit, for example, retrains the model using the newly collected data and repeats this process until the target accuracy rate is reached. For example, the retraining unit retrains the model using newly collected image data and repeats this process until the accuracy improves. Some or all of the above processes in the retraining unit may be performed using AI, for example, or without AI. The integration unit integrates the model retrained by the retraining unit with other analysis tools. The integration unit works in conjunction with other analysis tools, for example, to achieve efficient operation. For example, the integration unit provides the analysis results of the causes of errors to other tools for data visualization and further analysis. Some or all of the above processes in the integration unit may be performed using AI, for example, or without AI. As a result, the system according to the embodiment can rapidly develop highly accurate models by analyzing the causes of errors, automatically collecting necessary data, retraining, and integrating with other analysis tools.

[0065] The analysis unit analyzes the cause of incorrect answers. For example, the analysis unit identifies the reason for the incorrect answer and determines which data is missing. Specifically, the analysis unit analyzes the frequency and patterns of incorrect answers in detail to understand the trends of incorrect answers under specific conditions. For example, in an image classification model, if there are many incorrect answers for a particular image category, it will be determined that there is insufficient data related to that category. To identify the cause of an incorrect answer, the analysis unit compares the input data at the time the incorrect answer occurred with the output results of the model and analyzes in detail where the error occurred. Furthermore, to identify the cause of an incorrect answer, the analysis unit can also use AI-based natural language processing technology to analyze text data related to the incorrect answer. For example, it can analyze explanatory texts and comments related to the incorrect answer to identify the cause of the incorrect answer. Some or all of the above processing in the analysis unit may be performed using AI, or not using AI. When using AI, generative AI or LLM (Large-Scale Language Model) is used to generate prompts to identify the cause of the incorrect answer and input them into the AI. Based on the input prompts, the AI ​​performs a detailed analysis to identify the cause of the incorrect answer and outputs the results. This allows the analysis unit to quickly and accurately identify the cause of incorrect answers and determine the necessary data.

[0066] The data collection unit automatically collects the necessary data identified by the analysis unit from the internet. For example, the data collection unit collects the identified data from the internet to supplement the dataset. Specifically, the data collection unit automatically collects images related to a specific image category and adds them to the dataset. The data collection unit uses web scraping techniques to collect the necessary data from publicly available databases and websites on the internet. For example, to collect images related to a specific image category, the data collection unit uses a search engine with relevant keywords and collects images from the search results. The data collection unit filters the collected data and adds only high-quality data to the dataset. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. When using AI, generative AI or LLM is utilized to generate prompts for the conditions of the data to be collected and input them into the AI. Based on the input prompts, the AI ​​automatically collects the necessary data from the internet and outputs the results. This allows the data collection unit to collect the necessary data quickly and efficiently and supplement the dataset.

[0067] The retraining unit retrains the model with new data collected by the data collection unit. For example, the retraining unit retrains the model using the newly collected data and repeats this process until the target accuracy is reached. Specifically, the retraining unit retrains the model using the newly collected image data and repeats this process until the accuracy improves. The retraining unit adjusts the model parameters and tunes the hyperparameters to achieve optimal performance. Some or all of the above processes in the retraining unit may be performed using AI, for example, or without AI. If AI is used, generative AI or LLM is utilized to automate the retraining process. For example, the retraining conditions and goals are generated as prompts and input into the AI. Based on the input prompts, the AI ​​automatically executes the retraining process and generates an optimal model. This allows the retraining unit to improve the model's performance quickly and efficiently.

[0068] The Integration Unit integrates the models retrained by the Retraining Unit with other analytical tools. For example, the Integration Unit works in conjunction with other analytical tools to achieve efficient operations. Specifically, the Integration Unit provides the results of error analysis to other tools for data visualization and further analysis. The Integration Unit integrates the retrained models into other systems and applications, making them usable in actual operating environments. Some or all of the above processes in the Integration Unit may be performed using AI, for example, or without AI. When using AI, generative AI or LLM are utilized to automate the integration process. For example, integration conditions and goals are generated as prompts and input into the AI. Based on the input prompts, the AI ​​automatically executes the integration process to achieve optimal integration. This allows the Integration Unit to quickly and efficiently integrate the retrained models with other analytical tools, improving overall system performance.

[0069] The analysis unit can identify the reasons for incorrect answers. The analysis unit identifies the reasons for incorrect answers by considering, for example, the type, frequency, and impact of the incorrect answers. For example, the analysis unit can analyze the types of errors and identify the causes of frequent occurrences of specific errors. The analysis unit can also analyze the frequency of incorrect answers and prioritize identifying the causes of frequently occurring incorrect answers. Furthermore, the analysis unit can evaluate the impact of incorrect answers and identify the causes of highly impactful incorrect answers. By identifying the reasons for incorrect answers, the necessary data can be clarified. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or without using AI.

[0070] The data collection unit can collect identified data from the internet. The data collection unit collects data considering, for example, the format, reliability, and relevance of the identified data. For example, the data collection unit can collect data based on a specific data format (e.g., images, text, audio, etc.). The data collection unit can also collect data from reliable data sources. Furthermore, the data collection unit can prioritize the collection of highly relevant data. This allows the dataset to be complemented by collecting identified data from the internet. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI.

[0071] The retraining unit can retrain the model using newly collected data. The retraining unit retrains the model considering, for example, the format, reliability, and relevance of the newly collected data. For example, the retraining unit can retrain the model based on new data formats (e.g., images, text, audio, etc.). The retraining unit can also retrain the model using highly reliable data. Furthermore, the retraining unit can retrain the model by prioritizing the use of highly relevant data. This allows for improved model accuracy by retraining the model with newly collected data. Some or all of the above processing in the retraining unit may be performed using AI, for example, or without AI.

[0072] The integration unit can perform data visualization and further analysis in conjunction with other analytical tools. For example, the integration unit performs data visualization and further analysis while considering data compatibility and integration methods with other analytical tools. For example, the integration unit can convert data formats and integrate with other analytical tools. The integration unit can also integrate data with other analytical tools using APIs. Furthermore, the integration unit can visually display data using data visualization tools and perform further analysis. This enables efficient work by integrating with other analytical tools. Some or all of the above processes in the integration unit may be performed using AI, for example, or without AI.

[0073] The analysis unit can estimate the user's emotions and adjust the method for identifying the cause of incorrect answers based on the estimated user emotions. For example, if the user is stressed, the AI ​​will consider stressors when analyzing the cause of incorrect answers. For example, if the user is relaxed, the AI ​​can perform a more detailed analysis to delve deeper into the cause of incorrect answers. Also, if the user is anxious, the AI ​​can quickly identify the cause of incorrect answers and provide immediate feedback. This allows for more appropriate analysis by adjusting the method for identifying the cause of incorrect answers based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI.

[0074] The analysis unit can optimize its analysis algorithm by referring to past error data when analyzing the cause of incorrect answers. For example, the analysis unit can analyze past error data, identify common error patterns, and adjust the analysis algorithm. For example, the analysis unit can learn from past error data and optimize an algorithm to quickly identify the cause of incorrect answers. The analysis unit can also refer to past error data and improve the accuracy of the analysis based on the frequency and patterns of incorrect answers. In this way, by referring to past error data, the analysis algorithm can be optimized and the accuracy of the analysis can be improved. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI.

[0075] The analysis unit can improve the accuracy of its analysis by considering the frequency and patterns of incorrect answers when analyzing the causes of incorrect answers. For example, the analysis unit can analyze the frequency of incorrect answers and prioritize identifying the causes of frequently occurring incorrect answers. For example, the analysis unit can analyze the patterns of incorrect answers and identify the causes of incorrect answers based on specific patterns. Furthermore, the analysis unit can combine the frequency and patterns of incorrect answers in its analysis to more accurately identify the causes of incorrect answers. In this way, the accuracy of the analysis can be improved by considering the frequency and patterns of incorrect answers. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without using AI.

[0076] The analysis unit can estimate the user's emotions and determine the priority for identifying the causes of incorrect answers based on the estimated user emotions. For example, if the user is stressed, the AI ​​will prioritize identifying causes of incorrect answers related to stressors. For example, if the user is relaxed, the AI ​​can perform a more detailed analysis to delve deeper into the causes of incorrect answers. Furthermore, if the user is anxious, the AI ​​can quickly identify the causes of incorrect answers and provide immediate feedback. This allows for more appropriate analysis by determining the priority for identifying the causes of incorrect answers based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI.

[0077] The analysis unit can perform its analysis while considering the user's geographical location information when analyzing the cause of incorrect answers. For example, the analysis unit can refer to the user's geographical location information to identify region-specific incorrect answer patterns and perform analysis. For example, the analysis unit can identify the cause of incorrect answers for each region based on the user's geographical location information. Furthermore, the analysis unit can improve the accuracy of the analysis by considering the user's geographical location information and using region-specific data. This makes it possible to identify region-specific incorrect answer patterns and improve the accuracy of the analysis by considering the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0078] The analysis unit can improve the accuracy of its analysis by referring to relevant literature and databases when analyzing the causes of incorrect answers. For example, the analysis unit can refer to relevant literature and incorporate the latest research results on the causes of incorrect answers into its analysis. For example, the analysis unit can refer to databases and improve the accuracy of its analysis by comparing it with past incorrect answer data. Furthermore, the analysis unit can refer to a combination of relevant literature and databases to more accurately identify the causes of incorrect answers. In this way, the accuracy of the analysis can be improved by referring to relevant literature and databases. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI.

[0079] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. For example, if the user is stressed, the AI ​​in the data collection unit can adjust the timing of data collection to reduce the user's burden. For example, if the user is relaxed, the AI ​​in the data collection unit can collect detailed data and enrich the dataset. Also, if the user is anxious, the AI ​​in the data collection unit can quickly collect data and immediately reflect it in the analysis. In this way, the user's burden can be reduced by adjusting the timing of data collection based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI.

[0080] The data collection unit can optimize its collection algorithm by referring to past collected data when collecting necessary data. For example, the data collection unit can analyze past collected data and optimize its collection algorithm to collect data efficiently. For example, the data collection unit can learn from past collected data and adjust its algorithm to improve the accuracy of collection. The data collection unit can also refer to past collected data and optimize the frequency and timing of collection. In this way, by referring to past collected data, the data collection algorithm can be optimized and the accuracy of collection can be improved. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without using AI.

[0081] The data collection unit can improve the accuracy of data collection by considering the reliability and quality of the data when collecting the necessary data. For example, the data collection unit can evaluate the reliability of the data and prioritize the collection of reliable data. For example, the data collection unit can analyze the quality of the data and adjust the algorithm to collect high-quality data. The data collection unit can also select the optimal method to improve the accuracy of data collection by considering the reliability and quality of the data. In this way, the accuracy of data collection can be improved by considering the reliability and quality of the data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without using AI.

[0082] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated user emotions. For example, if the user is stressed, the AI ​​will prioritize collecting data related to stressors. For example, if the user is relaxed, the AI ​​can collect detailed data and enrich the dataset. Also, if the user is anxious, the AI ​​can quickly collect the necessary data and immediately reflect it in the analysis. This allows for more appropriate data collection by prioritizing data collection based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not using AI.

[0083] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location when collecting necessary data. For example, the data collection unit can refer to the user's geographical location and prioritize the collection of region-specific data. For example, the data collection unit can adjust the algorithm for collecting highly relevant data based on the user's geographical location. The data collection unit can also select the optimal method for collecting region-specific data by considering the user's geographical location. This allows for the priority collection of highly relevant data and improves the accuracy of data collection by considering the user's geographical location. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without using AI.

[0084] The data collection unit can analyze users' social media activity and collect relevant data when collecting necessary data. For example, the data collection unit can analyze users' social media activity and collect relevant data. For example, the data collection unit can collect data from users' social media activity based on their interests. The data collection unit can also refer to users' social media activity and adjust algorithms to collect highly relevant data. This allows for the collection of relevant data and improved data collection accuracy by analyzing users' social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI.

[0085] The retraining unit can estimate the user's emotions and adjust the retraining method based on the estimated emotions. For example, if the user is stressed, the AI ​​adjusts the retraining method to reduce the user's burden. For example, if the user is relaxed, the AI ​​can perform detailed retraining to improve the model's accuracy. Also, if the user is anxious, the AI ​​can perform rapid retraining and reflect the results immediately. In this way, the user's burden can be reduced by adjusting the retraining method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the retraining unit may be performed using AI, for example, or without AI.

[0086] The retraining unit can optimize the training algorithm by referring to past training data when performing retraining. For example, the retraining unit can analyze past training data and optimize the training algorithm to perform retraining efficiently. For example, the retraining unit can learn from past training data and adjust the algorithm to improve training accuracy. The retraining unit can also refer to past training data and optimize the training frequency and timing. In this way, by referring to past training data, the training algorithm can be optimized and the accuracy of retraining can be improved. Some or all of the above processes in the retraining unit may be performed using AI, for example, or without using AI.

[0087] The retraining unit can improve training accuracy by considering the balance and diversity of the training data when performing retraining. For example, the retraining unit can evaluate the balance of the training data and perform retraining using a balanced dataset. For example, the retraining unit can analyze the diversity of the training data and improve training accuracy by using diverse data. The retraining unit can also select the optimal training method by considering the balance and diversity of the training data. In this way, the accuracy of retraining can be improved by considering the balance and diversity of the training data. Some or all of the above processes in the retraining unit may be performed using AI, for example, or without using AI.

[0088] The retraining unit can estimate the user's emotions and adjust the frequency of retraining based on the estimated emotions. For example, if the user is stressed, the AI ​​can adjust the frequency of retraining to reduce the user's burden. For example, if the user is relaxed, the AI ​​can perform detailed retraining to improve the model's accuracy. Also, if the user is anxious, the AI ​​can perform rapid retraining and reflect the results immediately. This reduces the user's burden by adjusting the frequency of retraining based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the retraining unit may be performed using AI, for example, or without AI.

[0089] The retraining unit can select optimal training data by considering the user's geographical location information when performing retraining. For example, the retraining unit can refer to the user's geographical location information and perform retraining using region-specific data. For example, the retraining unit can select highly relevant training data based on the user's geographical location information. Furthermore, the retraining unit can improve the accuracy of training by considering the user's geographical location information and using region-specific data. This allows for improved accuracy of retraining using region-specific data by considering the user's geographical location information. Some or all of the above processing in the retraining unit may be performed using AI, for example, or without using AI.

[0090] The retraining unit can improve the accuracy of training by referring to relevant literature and databases when performing retraining. For example, the retraining unit can refer to relevant literature and incorporate the latest research findings to improve training accuracy. For example, the retraining unit can refer to databases and improve training accuracy by comparing it with past training data. The retraining unit can also improve training accuracy by referring to a combination of relevant literature and databases. In this way, training accuracy can be improved by referring to relevant literature and databases. Some or all of the above processes in the retraining unit may be performed using AI, for example, or without using AI.

[0091] The integration unit can estimate the user's emotions and adjust the integration method based on the estimated emotions. For example, if the user is stressed, the AI ​​in the integration unit can adjust the integration method to reduce the user's burden. For example, if the user is relaxed, the AI ​​in the integration unit can perform detailed integration to improve the accuracy of the data. Also, if the user is anxious, the AI ​​in the integration unit can perform rapid integration and reflect the results immediately. In this way, the user's burden can be reduced by adjusting the integration method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the integration unit may be performed using AI, for example, or without AI.

[0092] The integration unit can optimize its integration algorithm by referencing historical integration data when integrating with other analytical tools. For example, the integration unit can analyze historical integration data and optimize its integration algorithm to perform integration efficiently. For example, the integration unit can learn from historical integration data and adjust its algorithm to improve the accuracy of integration. The integration unit can also refer to historical integration data to optimize the frequency and timing of integration. This allows for the optimization of the integration algorithm and improvement of integration accuracy by referencing historical integration data. Some or all of the above processes in the integration unit may be performed using AI, for example, or without AI.

[0093] The integration unit can improve the accuracy of integration by considering data compatibility and communication methods between tools when integrating with other analytical tools. For example, the integration unit can evaluate data compatibility between tools and prioritize the integration of highly compatible data. For example, the integration unit can analyze communication methods between tools and adjust algorithms to improve the accuracy of communication. The integration unit can also consider data compatibility and communication methods between tools and select the optimal method to improve the accuracy of integration. In this way, the accuracy of integration can be improved by considering data compatibility and communication methods between tools. Some or all of the above processing in the integration unit may be performed using AI, for example, or without using AI.

[0094] The integration unit can estimate the user's emotions and determine the integration priority based on the estimated user emotions. For example, if the user is stressed, the AI ​​in the integration unit will prioritize the integration of data related to stressors. For example, if the user is relaxed, the AI ​​in the integration unit can perform a more detailed integration to improve the accuracy of the data. Also, if the user is anxious, the AI ​​in the integration unit can perform a rapid integration and reflect the results immediately. This allows for more appropriate integration by determining the integration priority based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the integration unit may be performed using AI, for example, or not using AI.

[0095] The integration unit can select the optimal integration method when integrating with other analytical tools, taking into account the user's geographical location. For example, the integration unit can refer to the user's geographical location and prioritize the integration of region-specific data. For example, the integration unit can select a highly relevant integration method based on the user's geographical location. Furthermore, the integration unit can improve the accuracy of the integration by considering the user's geographical location and using region-specific data. This allows for improved integration accuracy by considering the user's geographical location and using region-specific data. Some or all of the above processing in the integration unit may be performed using AI, for example, or without AI.

[0096] The integration unit can improve the accuracy of the integration by referring to relevant literature and databases when integrating with other analytical tools. For example, the integration unit can refer to relevant literature and incorporate the latest research findings to improve the accuracy of the integration. For example, the integration unit can refer to databases and improve the accuracy of the integration by comparing them with past integrated data. The integration unit can also improve the accuracy of the integration by referring to a combination of relevant literature and databases. In this way, the accuracy of the integration can be improved by referring to relevant literature and databases. Some or all of the above processing in the integration unit may be performed using AI, for example, or not using AI.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] The analysis unit can estimate the user's emotions and adjust the method for identifying the cause of incorrect answers based on those emotions. For example, if the user is stressed, the analysis unit can take stressors into account during the analysis. If the user is relaxed, it can perform a more detailed analysis to delve deeper into the cause of the incorrect answer. Furthermore, if the user is anxious, it can quickly identify the cause of the incorrect answer and provide immediate feedback. In this way, by adjusting the method for identifying the cause of incorrect answers based on the user's emotions, more appropriate analysis becomes possible.

[0099] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on those emotions. For example, if the user is stressed, the unit can adjust the timing of data collection to reduce the user's burden. If the user is relaxed, the unit can collect more detailed data to enrich the dataset. Furthermore, if the user is anxious, the unit can collect data quickly and immediately reflect it in the analysis. In this way, by adjusting the timing of data collection based on the user's emotions, the user's burden can be reduced.

[0100] The retraining unit can estimate the user's emotions and adjust the retraining method based on those emotions. For example, if the user is stressed, the retraining unit can adjust the retraining method to reduce the user's burden. If the user is relaxed, it can perform detailed retraining to improve the model's accuracy. Furthermore, if the user is anxious, it can perform rapid retraining and reflect the results immediately. In this way, by adjusting the retraining method based on the user's emotions, the user's burden can be reduced.

[0101] The integration unit can estimate the user's emotions and adjust the integration method based on those emotions. For example, if the user is stressed, the integration unit can adjust the integration method to reduce the user's burden. If the user is relaxed, it can perform a more detailed integration to improve data accuracy. Furthermore, if the user is anxious, it can perform a rapid integration to reflect the results immediately. In this way, by adjusting the integration method based on the user's emotions, the user's burden can be reduced.

[0102] The analysis unit can optimize its analysis algorithm by referring to past error data when analyzing the causes of incorrect answers. For example, it can analyze past error data to identify common error patterns and adjust the analysis algorithm. It can also learn from past error data and optimize the algorithm to quickly identify the causes of errors. Furthermore, it can improve the accuracy of the analysis based on the frequency and patterns of errors by referring to past error data. In this way, by referring to past error data, the analysis algorithm can be optimized and the accuracy of the analysis can be improved.

[0103] The data collection unit can optimize its collection algorithm by referring to past data collection data when collecting necessary data. For example, it can analyze past data collection data and optimize the collection algorithm to collect data efficiently. It can also learn from past data collection data and adjust the algorithm to improve collection accuracy. Furthermore, it can refer to past data collection data to optimize the frequency and timing of collection. In this way, by referring to past data collection data, the collection algorithm can be optimized and collection accuracy can be improved.

[0104] The retraining unit can optimize the training algorithm by referring to past training data during retraining. For example, it can analyze past training data and optimize the training algorithm to perform retraining efficiently. It can also learn from past training data and adjust the algorithm to improve training accuracy. Furthermore, it can optimize the training frequency and timing by referring to past training data. In this way, by referring to past training data, the training algorithm can be optimized and the accuracy of retraining can be improved.

[0105] The integration unit can optimize its integration algorithm by referencing historical integration data when integrating with other analytical tools. For example, it can analyze historical integration data and optimize the integration algorithm to perform integration efficiently. It can also learn from historical integration data and adjust the algorithm to improve the accuracy of integration. Furthermore, it can refer to historical integration data to optimize the frequency and timing of integration. In this way, referencing historical integration data allows for the optimization of the integration algorithm and improvement of integration accuracy.

[0106] The analysis unit can improve the accuracy of its analysis by considering the frequency and patterns of incorrect answers when analyzing the causes of errors. For example, it can analyze the frequency of incorrect answers and prioritize the identification of the causes of frequently occurring errors. It can also analyze the patterns of incorrect answers and identify the causes of errors based on specific patterns. Furthermore, it can combine the frequency and patterns of incorrect answers in its analysis to more accurately identify the causes of errors. In this way, the accuracy of the analysis can be improved by considering the frequency and patterns of incorrect answers.

[0107] The data collection unit can improve the accuracy of data collection by considering data reliability and quality when collecting necessary data. For example, it can evaluate data reliability and prioritize the collection of reliable data. It can also analyze data quality and adjust algorithms to collect high-quality data. Furthermore, it can select the optimal method to improve collection accuracy by considering data reliability and quality. In this way, the accuracy of data collection can be improved by considering data reliability and quality.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The analysis unit analyzes the cause of the incorrect answers. For example, the analysis unit identifies the reason for the incorrect answers and determines which data is missing. For example, in an image classification model, if there are many incorrect answers for a particular image category, it will determine that there is insufficient data related to that category. Step 2: The collection unit automatically collects the necessary data identified by the analysis unit from the internet. The collection unit, for example, collects the identified data from the internet to supplement the dataset. For example, it automatically collects images related to a specific image category and adds them to the dataset. Step 3: The retraining unit retrains the model with the new data collected by the data collection unit. The retraining unit, for example, retrains the model using the newly collected data and repeats this process until the target accuracy is reached. Step 4: The Integration Unit integrates the model retrained by the Retraining Unit with other analytical tools. The Integration Unit works with other analytical tools, for example, to enable efficient operations. For example, it provides the results of the error cause analysis to other tools for data visualization and further analysis.

[0110] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0111] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, 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), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0112] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0113] Each of the multiple elements described above, including the analysis unit, data collection unit, retraining unit, and integration unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the smart device 14 and analyzes the cause of incorrect answers. The data collection unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically collects the necessary data from the network. The retraining unit is implemented by the specific processing unit 290 of the data processing unit 12 and retrains the model with new data. The integration unit is implemented by the control unit 46A of the smart device 14 and integrates with other analysis tools. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0114] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0115] As shown in Figure 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.

[0116] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0120] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0121] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0122] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0123] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0124] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0125] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0126] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0127] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0128] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements described above, including the analysis unit, data collection unit, retraining unit, and integration unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the smart glasses 214 and analyzes the cause of incorrect answers. The data collection unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and automatically collects the necessary data from the network. The retraining unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and retrains the model with new data. The integration unit is implemented, for example, by the control unit 46A of the smart glasses 214 and integrates with other analysis tools. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0133] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0134] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0136] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0137] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0138] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0139] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0140] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0141] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0144] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements described above, including the analysis unit, data collection unit, retraining unit, and integration unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the headset terminal 314 and analyzes the cause of incorrect answers. The data collection unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically collects the necessary data from the network. The retraining unit is implemented by the specific processing unit 290 of the data processing unit 12 and retrains the model with new data. The integration unit is implemented by the control unit 46A of the headset terminal 314 and integrates with other analysis tools. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

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

[0148] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0150] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0152] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0153] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0154] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0155] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0156] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0157] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the analysis unit, data collection unit, retraining unit, and integration unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the robot 414 and analyzes the cause of incorrect answers. The data collection unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically collects the necessary data from the network. The retraining unit is implemented by the specific processing unit 290 of the data processing unit 12 and retrains the model with new data. The integration unit is implemented by the control unit 46A of the robot 414 and integrates with other analysis tools. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0163] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0164] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0165] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0166] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0167] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0168] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0171] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0172] 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.

[0173] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0174] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0175] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0176] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0177] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0178] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0179] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0180] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0181] (Note 1) An analysis unit that analyzes the cause of incorrect answers, A collection unit that automatically collects the necessary data identified by the analysis unit from the network, A retraining unit retrains the model with the new data collected by the aforementioned collection unit, An integration unit that integrates the model retrained by the aforementioned retraining unit with other analysis tools, Equipped with A system characterized by the following features. (Note 2) The aforementioned analysis unit, Identify the reason for the incorrect answer. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is Collect the identified data from the internet. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned retraining unit, Retrain the model using the newly collected data. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned integration unit is It can be integrated with other analytical tools to visualize data and perform further analysis. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, We estimate the user's emotions and adjust the method for identifying the cause of incorrect answers based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, When analyzing the causes of incorrect answers, we optimize the analysis algorithm by referring to past incorrect answer data. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, When analyzing the causes of incorrect answers, consider the frequency and patterns of incorrect answers to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, The system estimates the user's emotions and prioritizes identifying the causes of incorrect answers based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, When analyzing the causes of incorrect answers, the analysis takes into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, When analyzing the causes of incorrect answers, we improve the accuracy of the analysis by referring to relevant literature and databases. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is When collecting necessary data, we optimize the collection algorithm by referring to past collected data. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned collection unit is When collecting necessary data, we improve the accuracy of the collection by considering the reliability and quality of the data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned collection unit is When collecting necessary data, the system prioritizes collecting highly relevant data by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned collection unit is When collecting necessary data, we analyze users' social media activity and collect relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned retraining unit, It estimates the user's emotions and adjusts the retraining method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned retraining unit, When retraining, the training algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned retraining unit, When retraining, consider the balance and diversity of training data to improve the accuracy of the training. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned retraining unit, It estimates the user's emotions and adjusts the frequency of retraining based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned retraining unit, When retraining, the optimal training data is selected considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned retraining unit, When retraining, we refer to relevant literature and databases to improve the accuracy of the training. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned integration unit is It estimates the user's emotions and adjusts the integration method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned integration unit is When integrating with other analytical tools, we optimize the integration algorithm by referencing historical integration data. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned integration unit is When integrating with other analytical tools, consider data compatibility and integration methods between tools to improve the accuracy of the integration. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned integration unit is It estimates user sentiment and determines integration priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned integration unit is When integrating with other analytical tools, the optimal integration method is selected by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned integration unit is When integrating with other analytical tools, referencing relevant literature and databases improves the accuracy of the integration. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An analysis unit that analyzes the cause of incorrect answers, A collection unit that automatically collects the necessary data identified by the analysis unit from the network, A retraining unit retrains the model with the new data collected by the aforementioned collection unit, An integration unit that integrates the model retrained by the aforementioned retraining unit with other analysis tools, Equipped with A system characterized by the following features.

2. The aforementioned analysis unit, Identify the reason for the incorrect answer. The system according to feature 1.

3. The aforementioned collection unit is Collect the identified data from the internet. The system according to feature 1.

4. The aforementioned retraining unit, Retrain the model using the newly collected data. The system according to feature 1.

5. The aforementioned integration unit is It can be integrated with other analytical tools to visualize data and perform further analysis. The system according to feature 1.

6. The aforementioned analysis unit, We estimate the user's emotions and adjust the method for identifying the cause of incorrect answers based on the estimated user emotions. The system according to feature 1.

7. The aforementioned analysis unit, When analyzing the causes of incorrect answers, we optimize the analysis algorithm by referring to past incorrect answer data. The system according to feature 1.

8. The aforementioned analysis unit, When analyzing the causes of incorrect answers, consider the frequency and patterns of incorrect answers to improve the accuracy of the analysis. The system according to feature 1.

Images