system

Abstract

The system according to this embodiment aims to convert website content into a format that can be efficiently learned by a generating AI, and to optimize the learning results. [Solution] The system according to the embodiment comprises an analysis unit, a conversion unit, a provision unit, a monitoring unit, and a readjustment unit. The analysis unit analyzes the content of a website. The conversion unit converts the content analyzed by the analysis unit into a format that the generating AI can efficiently learn from. The provision unit provides the content converted by the conversion unit to the generating AI. The monitoring unit monitors the learning results of the generating AI based on the content provided by the provision unit. The readjustment unit readjusts the content based on the data monitored by the monitoring unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, the content of a website has not been sufficiently converted into an optimal format for an AI for generating website content to efficiently learn, and there is room for improvement.

[0005] The system according to the embodiment aims to convert the content of a website into a format in which an AI for generating website content can efficiently learn and optimize the learning results.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a conversion unit, a provision unit, a monitoring unit, and a readjustment unit. The analysis unit analyzes the content of a website. The conversion unit converts the content analyzed by the analysis unit into a format that the generating AI can efficiently learn from. The provision unit provides the content converted by the conversion unit to the generating AI. The monitoring unit monitors the learning results of the generating AI based on the content provided by the provision unit. The readjustment unit readjusts the content based on the data monitored by the monitoring unit. [Effects of the Invention]

[0007] The system according to this embodiment can convert website content into a format that can be efficiently learned by the AI ​​generating it, and optimize the learning results. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of 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 receiving 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 receiving 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 AI-optimized AI (AIO) countermeasure service according to an embodiment of the present invention is a service designed to facilitate learning by a generative AI. This AIO countermeasure service promotes learning by analyzing the content of a website, converting it into a format that is easy for the generative AI to learn, and providing it to the generative AI. For example, the AIO countermeasure service analyzes the content of a website. In this process, it analyzes the structure and keywords of the content in detail in order to convert it into a format that is easy for the generative AI to learn. For example, by simplifying the structure of the text and emphasizing important keywords, the generative AI can learn efficiently. Next, the converted content is provided to the generative AI. The generative AI learns from the provided content and generates appropriate answers to the user's search queries. For example, if a user searches using a specific keyword, the generative AI provides the optimal answer based on the learned content. Furthermore, the learning effect of the generative AI is monitored, and the content is readjusted as needed. This ensures that the generative AI is always learning the latest information and can provide the optimal answer to the user. For example, the content is regularly updated to respond to new topics and trends, and the generative AI is retrained. This allows the website to be effectively learned by the generative AI and viewed by many users. Users can more easily access the information on the website through the generative AI, and the number of website visitors increases. For example, a website providing information about a specific product or service can be effectively learned by a generative AI, making it easier for users to find that information. This allows AI-powered AI (AI-powered web analytics) services to maximize the learning effect of the generative AI by converting the website's content into a format that is easily learned by the AI, monitoring its learning progress, and making adjustments as needed.

[0029] The AI-controlled AI (AIO) countermeasure service according to this embodiment comprises an analysis unit, a conversion unit, a provision unit, a monitoring unit, and a readjustment unit. The analysis unit analyzes the content of a website. The analysis unit analyzes the content of a website using, for example, a natural language processing algorithm. The natural language processing algorithm uses techniques such as morphological analysis, grammatical analysis, and semantic analysis to analyze the structure and keywords of the content in detail. For example, the analysis unit uses morphological analysis to divide the text into words and identify the part of speech of each word. The analysis unit also uses grammatical analysis to analyze the structure of the text and clarify the relationships between subjects, predicates, objects, etc. Furthermore, the analysis unit uses semantic analysis to understand the meaning of the text and extract important keywords. The conversion unit converts the content analyzed by the analysis unit into a format that the generating AI can efficiently learn from. The conversion unit performs, for example, keyword emphasis and text simplification. Keyword emphasis is performed by methods such as changing the font or color. For example, the conversion unit makes it easier for the generating AI to recognize important keywords by making them bold or changing their color. The conversion unit also simplifies the text. For example, it shortens long sentences and replaces technical terms with simpler language, making it easier for the generating AI to understand the content. The provision unit provides the converted content to the generating AI. The provision unit provides the content, for example, through an API. The API is an interface for the generating AI to obtain content, and the provision unit sends the content to the generating AI through the API. The provision unit can also provide content in file format. For example, the provision unit provides the converted content to the generating AI as a text file or a JSON file. The monitoring unit monitors the learning results of the generating AI based on the content provided by the provision unit. The monitoring unit performs, for example, real-time monitoring and periodic data collection. Real-time monitoring is a method of monitoring the process of the generating AI learning content in real time and understanding the progress of learning. For example, the monitoring unit can detect errors and warnings in real time when the generating AI is learning content and take appropriate measures.Periodic data collection is a method of periodically collecting data learned by the generative AI and evaluating the effectiveness of the learning. For example, the monitoring unit periodically evaluates the accuracy and coverage of the content learned by the generative AI and monitors the effectiveness of the learning. The readjustment unit readjusts the content based on the data monitored by the monitoring unit. The readjustment unit performs, for example, parameter adjustments and data reanalysis. Parameter adjustment is a method of optimizing the parameters used when the generative AI learns. For example, the readjustment unit can adjust the learning rate and batch size of the generative AI to improve the efficiency of learning. Data reanalysis is a method of reanalyzing the data that the generative AI learns and correcting the data as needed. For example, if there are errors in the data learned by the generative AI, the readjustment unit can correct the data and allow the generative AI to learn again. As a result, the AIO countermeasure service according to the embodiment can maximize the learning effect by converting website content into a format that is easy for the generative AI to learn, monitoring the learning effect, and readjusting.

[0030] The analysis unit can analyze website content using natural language processing algorithms. These algorithms utilize techniques such as morphological analysis, grammatical analysis, and semantic analysis to analyze the content's structure and keywords in detail. For example, the analysis unit can use morphological analysis to divide sentences into individual words and identify the part of speech of each word. It can also use grammatical analysis to analyze the sentence structure and clarify relationships such as subject, predicate, and object. Furthermore, it can use semantic analysis to understand the meaning of the sentence and extract important keywords. This improves the accuracy of website content analysis by using natural language processing algorithms. Some or all of the above-described processes in the analysis unit may be performed using, for example, generative AI, or without generative AI. For example, the analysis unit can input website content into a generative AI, which can then perform morphological analysis, grammatical analysis, and semantic analysis.

[0031] The conversion unit can perform keyword emphasis and sentence simplification. Keyword emphasis is performed by methods such as changing the font or color. For example, the conversion unit can make important keywords bold or change their color to make them easier for the generating AI to recognize. The conversion unit also simplifies sentences. For example, the conversion unit can shorten long sentences and replace technical terms with simpler language to make the content easier for the generating AI to understand. This allows the text to be converted into a format that is easy for the generating AI to learn, through keyword emphasis and sentence simplification. Some or all of the above processing in the conversion unit may be performed using the generating AI, or not. For example, the conversion unit can input website content into the generating AI, which can then perform keyword emphasis and sentence simplification.

[0032] The provider can provide the converted content to the generating AI. The provider can provide the content, for example, through an API. The API is an interface for the generating AI to retrieve the content, and the provider sends the content to the generating AI through the API. The provider can also provide the content in file format. For example, the provider can provide the converted content to the generating AI as a text file or a JSON file. This allows the generating AI to learn by providing the converted content. Some or all of the above processing in the provider may be performed using the generating AI, or not using the generating AI. For example, the provider can input the converted content into the generating AI and have the generating AI retrieve the content.

[0033] The monitoring unit can monitor the effectiveness of the generation AI's learning. For example, the monitoring unit performs real-time monitoring and periodic data collection. Real-time monitoring is a method of monitoring the process of the generation AI learning content in real time and understanding the progress of learning. For example, the monitoring unit can detect errors and warnings in real time when the generation AI is learning content and take appropriate measures. Periodic data collection is a method of periodically collecting data learned by the generation AI and evaluating the effectiveness of learning. For example, the monitoring unit periodically evaluates the accuracy and coverage of the content learned by the generation AI and monitors the effectiveness of learning. This allows the monitoring unit to understand the progress of learning by monitoring the effectiveness of the generation AI's learning. Some or all of the above-described processes in the monitoring unit may be performed using the generation AI, or without using the generation AI. For example, the monitoring unit can input data learned by the generation AI into the generation AI and have the generation AI perform the monitoring of learning effectiveness.

[0034] The readjustment unit can readjust the content based on the monitored data. The readjustment unit can, for example, adjust parameters or reanalyze data. Parameter adjustment is a method of optimizing the parameters used by the generative AI when it learns. For example, the readjustment unit can adjust the learning rate and batch size of the generative AI to improve learning efficiency. Data reanalysis is a method of reanalyzing the data that the generative AI learns from and correcting the data as needed. For example, if there are errors in the data that the generative AI has learned from, the readjustment unit can correct that data and allow the generative AI to learn from it again. This optimizes the learning effect of the generative AI by readjusting the content based on the monitored data. Some or all of the above processes in the readjustment unit may be performed using the generative AI, or they may be performed without using the generative AI. For example, the readjustment unit can input the data that the generative AI has learned from into the generative AI and have the generative AI perform data reanalysis.

[0035] Furthermore, the AIO (AI-driven computer) support service includes an answer provision unit that provides appropriate answers to users based on content learned by the generating AI. The answer provision unit provides the user with the most suitable answer based on content learned by the generating AI. For example, the answer provision unit generates an appropriate answer to the user's search query based on content learned by the generating AI. The generating AI analyzes the user's search query, extracts the most relevant information from the learned content, and generates an answer. For example, if a user searches using a specific keyword, the generating AI extracts information related to that keyword from the learned content and provides it to the user. The answer provision unit can also provide detailed answers to the user's questions based on content learned by the generating AI. For example, if a user asks a question about a specific topic, the generating AI extracts detailed information about that topic from the learned content and provides it to the user. This improves user satisfaction by providing the user with the most suitable answer based on content learned by the generating AI. Some or all of the above-described processes in the answer provision unit may be performed using the generating AI, or not. For example, the answer provision unit can input content learned by the generating AI into the generating AI, and have the generating AI generate an answer to the user's search query.

[0036] The analysis unit can improve the accuracy of its analysis by referring to past website access data during the analysis process. For example, the analysis unit can identify pages that users frequently visit from past access data and focus its analysis on those pages. Past access data includes access logs and user behavior data. For example, the analysis unit can analyze access logs to understand which pages users accessed and how long they stayed on them. The analysis unit can also analyze user behavior data to understand what actions users took. By referring to past access data, the accuracy of the analysis is improved. For example, the analysis unit can extract keywords that users are interested in based on past access data and incorporate them into the analysis. The analysis unit can also analyze past access data to understand user behavior patterns and improve the accuracy of the analysis. Some or all of the above processes in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input past access data into a generative AI and have the generative AI perform data analysis and accuracy improvement.

[0037] The analysis unit can apply different analysis algorithms to each category of website content during analysis. For example, the analysis unit applies an analysis algorithm that prioritizes the latest information to news articles. Techniques such as topic modeling and time series analysis are used for analyzing news articles. For example, the analysis unit can use topic modeling to extract the main topics of news articles and time series analysis to understand the evolution of the news. The analysis unit also applies an analysis algorithm that prioritizes user ratings and comments to product reviews. Techniques such as sentiment analysis and opinion mining are used for analyzing product reviews. For example, the analysis unit can use sentiment analysis to determine whether user ratings are positive or negative and opinion mining to extract specific user opinions. Furthermore, the analysis unit applies an analysis algorithm that prioritizes comprehension to educational content. Techniques such as knowledge graphs and learning analysis are used for analyzing educational content. For example, the analysis unit can use knowledge graphs to understand the relationships between knowledge in educational content and learning analysis to evaluate the user's comprehension. By applying different analysis algorithms to each category, the accuracy of the analysis is improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input the content of a website into a generative AI, and have the generative AI apply a category-specific analysis algorithm.

[0038] The analysis unit can perform analysis while considering the geographical distribution of websites. For example, the analysis unit can analyze the access patterns of geographically different users and perform analysis while considering the characteristics of each region. Geographical distribution includes access data by region and user location information. For example, the analysis unit can analyze access data by region and identify content that is popular in a particular region. The analysis unit can also analyze user location information and understand the interests of users in each region. This makes it possible to perform analysis that reflects the characteristics of each region by considering geographical distribution. For example, the analysis unit can prioritize the analysis of content that is popular in a particular region based on geographical distribution. The analysis unit can also perform analysis that reflects the interests of users in each region based on geographical data. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or it may be performed without using a generative AI. For example, the analysis unit can input geographical distribution data into a generative AI and have the generative AI perform data analysis and reflect the characteristics of each region.

[0039] The analysis unit can improve the accuracy of its analysis by referring to relevant literature on the website during the analysis process. For example, the analysis unit can improve the accuracy of its analysis based on the latest information obtained from relevant literature. Relevant literature includes academic papers, technical reports, and patent documents. For example, the analysis unit can refer to academic papers and reflect in-depth knowledge on a specific topic in its analysis. It can also refer to technical reports and reflect the latest technical information in its analysis. Furthermore, it can refer to patent documents and reflect detailed information on a specific technology in its analysis. In this way, the accuracy of the analysis is improved by referring to relevant literature. For example, the analysis unit can extract keywords that are of interest to the user based on the relevant literature and reflect them in its analysis. It can also reflect in-depth knowledge on a specific topic based on the relevant literature in its analysis. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input the relevant literature data into a generative AI and have the generative AI perform data analysis and accuracy improvement.

[0040] The conversion unit can adjust the level of detail in the conversion based on the importance of the content. For example, the conversion unit can adjust the level of detail in the conversion based on the importance of the content. The importance of the content includes access count, user rating, relevance, etc. For example, the conversion unit can add detailed explanations to content with a high access count. It can also add visual effects to content with a high user rating. Furthermore, it can highlight important keywords in content with high relevance. In this way, important information can be emphasized by adjusting the level of detail in the conversion based on the importance of the content. For example, the conversion unit can add detailed explanations to important content. It can also add concise explanations to general content. Furthermore, it can add visual effects to content that is of high interest to users. Some or all of the above processing in the conversion unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the conversion unit can input content importance data into a generative AI and have the generative AI perform the adjustment of the level of detail in the conversion.

[0041] The conversion unit can apply different conversion algorithms depending on the content category during conversion. For example, the conversion unit applies a conversion algorithm that prioritizes the latest information to news articles. Techniques such as topic modeling and time series analysis are used for converting news articles. For example, the conversion unit can extract the main topics of a news article using topic modeling and understand the evolution of the news using time series analysis. The conversion unit also applies a conversion algorithm that prioritizes user ratings and comments to product reviews. Techniques such as sentiment analysis and opinion mining are used for converting product reviews. For example, the conversion unit can determine whether user ratings are positive or negative using sentiment analysis and extract specific user opinions using opinion mining. Furthermore, the conversion unit applies a conversion algorithm that prioritizes comprehension to educational content. Techniques such as knowledge graphs and learning analysis are used for converting educational content. For example, the conversion unit can understand the relationships between knowledge in educational content using knowledge graphs and evaluate the user's comprehension using learning analysis. By applying different conversion algorithms for each category, the accuracy of the conversion is improved. Some or all of the above-described processing in the conversion unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the conversion unit can input content category data into a generating AI, and the generating AI can apply a conversion algorithm for each category.

[0042] The conversion unit can determine the conversion priority based on the content creation date during the conversion process. For example, the conversion unit can determine the conversion priority based on the content creation date. The content creation date includes the creation date, update date, publication date, etc. For example, the conversion unit can prioritize the conversion of the newest content. Older content can be converted while being updated as needed. Furthermore, content related to trends can be converted as needed. This allows for the prioritization of the conversion of the latest information by determining the conversion priority based on the content creation date. For example, the conversion unit can prioritize the conversion of the newest content. Older content can be converted while being updated as needed. Furthermore, content related to trends can be converted as needed. Some or all of the above processing in the conversion unit may be performed using, for example, a generation AI, or without a generation AI. For example, the conversion unit can input content creation date data into a generation AI and have the generation AI perform the determination of the conversion priority.

[0043] The conversion unit can adjust the order of conversion based on the relevance of the content during conversion. For example, the conversion unit can adjust the order of conversion based on the relevance of the content. Content relevance includes common keywords, link relationships, etc. For example, the conversion unit can prioritize the conversion of content related to the user's search query. It can also group and convert highly relevant content. Furthermore, it can prioritize the conversion of highly relevant content based on the user's interests. This allows for the prioritization of highly relevant information by adjusting the order of conversion based on the relevance of the content. For example, the conversion unit can prioritize the conversion of content related to the user's search query. It can also group and convert highly relevant content. Furthermore, it can prioritize the conversion of highly relevant content based on the user's interests. Some or all of the above processing in the conversion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversion unit can input content relevance data into a generative AI and have the generative AI adjust the order of conversion.

[0044] The service provider can improve the accuracy of its deliveries by referring to the generative AI's past training data at the time of delivery. For example, the service provider can provide optimal content based on the generative AI's past training data. Past training data includes training datasets and learning history. For example, the service provider can refer to the generative AI's training dataset and provide the best possible answers to the user's search queries. The service provider can also refer to the generative AI's learning history and provide content based on the user's interests. This improves the accuracy of deliveries by referring to the generative AI's past training data. For example, the service provider can provide optimal content based on the generative AI's past training data. The service provider can also analyze the generative AI's past training data and provide content based on the user's interests. Furthermore, the service provider can refer to the generative AI's past training data and provide the best possible answers to the user's search queries. Some or all of the above processing in the service provider may be performed using the generative AI, or not. For example, the service provider can input the generative AI's past training data into the generative AI and have the generative AI perform data referencing and improve the accuracy of deliveries.

[0045] The service provider can apply different delivery methods depending on the learning algorithm of the generative AI at the time of delivery. For example, the service provider can select the optimal delivery method based on the learning algorithm of the generative AI. Learning algorithms include reinforcement learning, supervised learning, and unsupervised learning. For example, the service provider can use a reinforcement learning algorithm to provide optimal content based on user behavior. The service provider can also use a supervised learning algorithm to provide optimal content based on labeled data. Furthermore, the service provider can use an unsupervised learning algorithm to perform clustering and dimensionality reduction and provide content based on user interests. This makes it possible to provide optimal information to users by applying the optimal delivery method according to the learning algorithm of the generative AI. For example, the service provider can select the optimal delivery method based on the learning algorithm of the generative AI. Furthermore, the service provider can provide content based on user interests according to the learning algorithm of the generative AI. Furthermore, the service provider can provide the optimal answer to the user's search query, taking into account the learning algorithm of the generative AI. Some or all of the above processing in the service provider may be performed using a generative AI, for example, or without using a generative AI. For example, the supply unit can input the learning algorithm data of the generation AI into the generation AI, and have the generation AI select and apply a delivery method.

[0046] The service provider can provide content while considering the geographical distribution of the generating AI. For example, the service provider can analyze the access patterns of geographically different users and provide content while considering the characteristics of each region. Geographical distribution includes access data by region and user location information. For example, the service provider can analyze access data by region to identify content that is popular in a particular region. The service provider can also analyze user location information to understand the interests of users in each region. By considering geographical distribution, it becomes possible to provide information that reflects the characteristics of each region. For example, the service provider can prioritize providing content that is popular in a particular region based on geographical distribution. The service provider can also provide content that reflects the interests of users in each region based on geographical data. Some or all of the above processing in the service provider may be performed using, for example, the generating AI, or without using the generating AI. For example, the service provider can input geographical distribution data into the generating AI and have the generating AI perform data analysis and reflect the characteristics of each region.

[0047] The service provider can improve the accuracy of its service by referring to relevant literature generated by the AI ​​during the service provision process. For example, the service provider can improve the accuracy of its service based on the latest information obtained from relevant literature. Relevant literature includes academic papers, technical reports, and patent documents. For example, the service provider can refer to academic papers and reflect in-depth knowledge on a specific topic in its service provision. It can also refer to technical reports and reflect in-depth technical information in its service provision. Furthermore, it can refer to patent documents and reflect in-depth information on a specific technology in its service provision. This improves the accuracy of the service provision by referring to relevant literature. For example, the service provider can extract keywords that will interest the user based on relevant literature and reflect them in its service provision. It can also reflect in-depth knowledge on a specific topic based on relevant literature in its service provision. Some or all of the above processing in the service provider may be performed using, for example, a generating AI, or without using a generating AI. For example, the service provider can input relevant literature data into a generating AI and have the generating AI perform data referencing and improve the accuracy of the service provision.

[0048] The monitoring unit can track the learning effectiveness of the generative AI in real time during monitoring. For example, the monitoring unit can track the learning effectiveness of the generative AI in real time and grasp the progress of learning. Technologies such as real-time data streaming and immediate feedback are used to track in real time. For example, the monitoring unit can monitor the process by which the generative AI learns content in real time and grasp the progress of learning. The monitoring unit can also detect errors and warnings when the generative AI is learning in real time and take appropriate measures. Furthermore, the monitoring unit can track the learning effectiveness of the generative AI in real time and adjust the learning content as needed. In this way, the progress of learning can be grasped by tracking the learning effectiveness of the generative AI in real time. For example, the monitoring unit can track the learning effectiveness of the generative AI in real time and improve the efficiency of learning. Some or all of the above processing in the monitoring unit may be performed using the generative AI, or not using the generative AI. For example, the monitoring unit can input the learning data of the generative AI into the generative AI and have the generative AI perform real-time tracking of the learning effectiveness.

[0049] The monitoring unit can perform monitoring while considering the attribute information of the generation AI's training data. For example, the monitoring unit can improve the accuracy of monitoring based on the attribute information of the generation AI's training data. Attribute information includes user attributes and data attributes. For example, the monitoring unit can perform monitoring related to specific attributes by considering user attributes. Also, the monitoring unit can perform monitoring related to specific data by considering data attributes. This improves the accuracy of monitoring by considering the attribute information of the training data. For example, the monitoring unit can improve the accuracy of monitoring based on the attribute information of the generation AI's training data. Also, the monitoring unit can perform monitoring related to specific attributes by considering the attribute information of the generation AI's training data. Furthermore, the monitoring unit can perform monitoring that improves the efficiency of learning based on the attribute information of the generation AI's training data. Some or all of the above processing in the monitoring unit may be performed using the generation AI, or without using the generation AI. For example, the monitoring unit can input the attribute information of the generation AI's training data into the generation AI, and have the generation AI perform the improvement of monitoring accuracy.

[0050] The monitoring unit can perform monitoring while considering the geographical distribution of the generated AI. For example, the monitoring unit can analyze the access patterns of geographically different users and monitor while considering the characteristics of each region. Geographical distribution includes regional access data and user location information. For example, the monitoring unit can analyze regional access data and identify content that is popular in a particular region. The monitoring unit can also analyze user location information and understand the interests of users in each region. This makes it possible to perform monitoring that reflects the characteristics of each region by considering geographical distribution. For example, the monitoring unit can prioritize monitoring of content that is popular in a particular region based on geographical distribution. The monitoring unit can also perform monitoring that reflects the interests of users in each region based on geographical data. Some or all of the above processing in the monitoring unit may be performed using, for example, the generated AI, or without using the generated AI. For example, the monitoring unit can input geographical distribution data into the generated AI and have the generated AI perform data analysis and reflect the characteristics of each region.

[0051] The monitoring unit can improve the accuracy of monitoring by referring to relevant literature generated by the AI ​​during monitoring. For example, the monitoring unit improves the accuracy of monitoring based on the latest information obtained from relevant literature. Relevant literature includes academic papers, technical reports, and patent documents. For example, the monitoring unit can refer to academic papers and reflect in-depth knowledge on a specific topic in the monitoring. The monitoring unit can also refer to technical reports and reflect the latest technical information in the monitoring. Furthermore, the monitoring unit can refer to patent documents and reflect detailed information on a specific technology in the monitoring. As a result, the accuracy of monitoring is improved by referring to relevant literature. For example, the monitoring unit can extract keywords that are of interest to the user based on relevant literature and reflect them in the monitoring. The monitoring unit can also reflect in-depth knowledge on a specific topic based on relevant literature in the monitoring. Some or all of the above processing in the monitoring unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the monitoring unit can input relevant literature data into a generating AI, and have the generating AI perform data referencing and improve the accuracy of monitoring.

[0052] The readjustment unit can improve the accuracy of readjustment by referring to the past training data of the generating AI during readjustment. For example, the readjustment unit performs optimal readjustment based on the past training data of the generating AI. Past training data includes training datasets and training history. For example, the readjustment unit can refer to the training dataset of the generating AI and perform optimal readjustment for the user's search query. The readjustment unit can also refer to the training history of the generating AI and perform readjustment based on the user's interests. This improves the accuracy of readjustment by referring to the past training data of the generating AI. For example, the readjustment unit can perform optimal readjustment based on the past training data of the generating AI. The readjustment unit can also analyze the past training data of the generating AI and perform readjustment based on the user's interests. Furthermore, the readjustment unit can refer to the past training data of the generating AI and perform optimal readjustment for the user's search query. Some or all of the above processing in the readjustment unit may be performed using the generating AI, for example, or without using the generating AI. For example, the readjustment unit can input past training data of the generating AI into the generating AI, allowing the generating AI to perform data referencing and improve the accuracy of readjustment.

[0053] The readjustment unit can apply different readjustment methods depending on the learning algorithm of the generative AI during readjustment. For example, the readjustment unit selects the optimal readjustment method based on the learning algorithm of the generative AI. Learning algorithms include reinforcement learning, supervised learning, and unsupervised learning. For example, the readjustment unit can use a reinforcement learning algorithm to perform optimal readjustment based on user behavior. It can also use a supervised learning algorithm to perform optimal readjustment based on labeled data. Furthermore, it can use an unsupervised learning algorithm to perform clustering and dimensionality reduction, and readjust based on user interests. This improves the accuracy of readjustment by applying the optimal readjustment method according to the generative AI's learning algorithm. For example, the readjustment unit can select the optimal readjustment method based on the generative AI's learning algorithm. It can also perform readjustment based on user interests according to the generative AI's learning algorithm. Furthermore, the readjustment unit can consider the generative AI's learning algorithm and perform optimal readjustment for the user's search queries. Some or all of the above-described processes in the readjustment unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the readjustment unit can input the generative AI's learning algorithm data into the generative AI, and have the generative AI select and apply a readjustment method.

[0054] The readjustment unit can perform readjustments while considering the geographical distribution of the generated AI. For example, the readjustment unit analyzes the access patterns of geographically different users and readjusts while considering the characteristics of each region. Geographical distribution includes access data by region and user location information. For example, the readjustment unit can analyze access data by region to identify content that is popular in a particular region. The readjustment unit can also analyze user location information to understand the interests of users in each region. This makes it possible to readjust content that reflects the characteristics of each region by considering geographical distribution. For example, the readjustment unit can prioritize the readjustment of content that is popular in a particular region based on geographical distribution. The readjustment unit can also perform readjustments that reflect the interests of users in each region based on geographical data. Some or all of the above processing in the readjustment unit may be performed using, for example, the generated AI, or without using the generated AI. For example, the readjustment unit can input geographical distribution data into the generated AI and have the generated AI perform data analysis and reflect the characteristics of each region.

[0055] The readjustment unit can improve the accuracy of readjustment by referring to relevant literature for the generating AI during readjustment. For example, the readjustment unit improves the accuracy of readjustment based on the latest information obtained from relevant literature. Relevant literature includes academic papers, technical reports, and patent documents. For example, the readjustment unit can refer to academic papers and reflect in-depth knowledge on a specific topic in the readjustment. It can also refer to technical reports and reflect the latest technical information in the readjustment. Furthermore, it can refer to patent documents and reflect detailed information on a specific technology in the readjustment. As a result, the accuracy of readjustment is improved by referring to relevant literature. For example, the readjustment unit can extract keywords that are of interest to the user based on relevant literature and reflect them in the readjustment. It can also reflect in-depth knowledge on a specific topic based on relevant literature in the readjustment. Some or all of the above processing in the readjustment unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the readjustment unit can input relevant literature data into the generating AI, which can then perform data referencing and improve the accuracy of readjustment.

[0056] The answer provider can improve the accuracy of its answers by referring to the generator AI's past training data when providing answers. For example, the answer provider can provide the optimal answer based on the generator AI's past training data. Past training data includes training datasets and learning history. For example, the answer provider can refer to the generator AI's training dataset and provide the optimal answer to the user's search query. The answer provider can also refer to the generator AI's learning history and provide answers based on the user's interests. This improves the accuracy of answers by referring to the generator AI's past training data. For example, the answer provider can provide the optimal answer based on the generator AI's past training data. The answer provider can also analyze the generator AI's past training data and provide answers based on the user's interests. Furthermore, the answer provider can refer to the generator AI's past training data and provide the optimal answer to the user's search query. Some or all of the above processing in the answer provider may be performed using the generator AI, or without using the generator AI. For example, the answer provision unit can input past training data of the generating AI into the generating AI, allowing the generating AI to perform data referencing and improve the accuracy of its answers.

[0057] The answer provider can apply different answer methods depending on the learning algorithm of the generative AI when providing answers. For example, the answer provider can select the optimal answer method based on the learning algorithm of the generative AI. Learning algorithms include reinforcement learning, supervised learning, and unsupervised learning. For example, the answer provider can use a reinforcement learning algorithm to provide the optimal answer based on user behavior. The answer provider can also use a supervised learning algorithm to provide the optimal answer based on labeled data. Furthermore, the answer provider can use an unsupervised learning algorithm to perform clustering and dimensionality reduction and provide answers based on user interests. This makes it possible to provide the optimal answer for the user by applying the optimal answer method according to the learning algorithm of the generative AI. For example, the answer provider can select the optimal answer method based on the learning algorithm of the generative AI. Furthermore, the answer provider can provide answers based on user interests according to the learning algorithm of the generative AI. Furthermore, the answer provider can provide the optimal answer to the user's search query, taking into account the learning algorithm of the generative AI. Some or all of the above processing in the answer provider may be performed using a generative AI, for example, or without using a generative AI. For example, the response provision unit can input the learning algorithm data of the generating AI into the generating AI, and have the generating AI select and apply a response method.

[0058] The response provider can provide responses while considering the geographical distribution of the generating AI. For example, the response provider can analyze the access patterns of geographically different users and provide responses while considering the characteristics of each region. Geographical distribution includes access data by region and user location information. For example, the response provider can analyze access data by region and identify responses that are popular in a particular region. The response provider can also analyze user location information and understand the interests of users in each region. This makes it possible to provide responses that reflect the characteristics of each region by considering geographical distribution. For example, the response provider can prioritize providing responses that are popular in a particular region based on geographical distribution. The response provider can also provide responses that reflect the interests of users in each region based on geographical data. Some or all of the above processing in the response provider may be performed using, for example, a generating AI, or without using a generating AI. For example, the response provider can input geographical distribution data into a generating AI and have the generating AI perform data analysis and reflect the characteristics of each region.

[0059] The answer-providing unit can improve the accuracy of its answers by referring to relevant literature generated by the AI ​​when providing answers. For example, the answer-providing unit improves the accuracy of its answers based on the latest information obtained from relevant literature. Relevant literature includes academic papers, technical reports, and patent documents. For example, the answer-providing unit can refer to academic papers and reflect in-depth knowledge on a specific topic in its answers. It can also refer to technical reports and reflect in the latest technical information in its answers. Furthermore, it can refer to patent documents and reflect in-depth information on a specific technology in its answers. As a result, the accuracy of the answers is improved by referring to relevant literature. For example, the answer-providing unit can extract keywords that will interest the user based on the relevant literature and reflect them in its answers. It can also reflect in-depth knowledge on a specific topic in its answers based on the relevant literature. Some or all of the above processing in the answer-providing unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the answer-providing unit can input relevant literature data into a generating AI, and have the generating AI perform data referencing and improve the accuracy of the answers.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The analysis unit can improve the accuracy of its analysis by referring to past website access data during the analysis process. For example, it can identify pages that users frequently visit from past access data and focus its analysis on those pages. It can also extract keywords that users are interested in based on past access data and incorporate them into the analysis. Furthermore, by analyzing past access data, it can understand user behavior patterns and improve the accuracy of the analysis. In short, referring to past access data improves the accuracy of the analysis.

[0062] The conversion unit can adjust the level of detail in the conversion based on the importance of the content. For example, content with a high number of views can be converted with detailed explanations. Content with high user ratings can be converted with visual effects. Furthermore, highly relevant content can be converted with important keywords highlighted. This allows for the emphasis of important information by adjusting the level of detail in the conversion based on the importance of the content.

[0063] The delivery unit can improve the accuracy of its deliveries by referring to the generative AI's past training data. For example, it can refer to the generative AI's training dataset to provide the best possible answers to users' search queries. It can also refer to the generative AI's learning history to provide content based on the user's interests. In this way, the accuracy of deliveries is improved by referring to the generative AI's past training data.

[0064] The monitoring unit can perform monitoring while considering the attribute information of the training data of the generated AI. For example, it can perform monitoring related to specific attributes by considering user attributes. It can also perform monitoring related to specific data by considering data attributes. As a result, the accuracy of monitoring is improved by considering the attribute information of the training data.

[0065] The readjustment unit can apply different readjustment methods depending on the learning algorithm of the generative AI during readjustment. For example, it can use a reinforcement learning algorithm to perform optimal readjustment based on user behavior. It can also use a supervised learning algorithm to perform optimal readjustment based on labeled data. Furthermore, it can use an unsupervised learning algorithm to perform clustering and dimensionality reduction and readjustment based on user interests. By applying the optimal readjustment method according to the learning algorithm of the generative AI, the accuracy of readjustment is improved.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The analysis unit analyzes the website content. The analysis unit uses natural language processing algorithms to analyze the content structure and keywords in detail using techniques such as morphological analysis, grammatical analysis, and semantic analysis. For example, it divides sentences into individual words, identifies the part of speech of each word, analyzes the sentence structure, clarifies the relationships between subjects, predicates, objects, etc., and extracts important keywords. Step 2: The conversion unit converts the content analyzed by the analysis unit into a format that the generating AI can efficiently learn from. The conversion unit performs keyword highlighting and sentence simplification. For example, important keywords are made bold or their color is changed to make them easier for the generating AI to recognize, long sentences are shortened, and technical terms are replaced with simpler language to make the content easier for the generating AI to understand. Step 3: The provider provides the converted content to the generation AI. The provider can provide the content via API, or as a text file or JSON file. Step 4: The Monitoring Unit monitors the learning outcomes of the Generative AI based on the content provided by the Provider Unit. The Monitoring Unit performs real-time monitoring and periodic data collection to monitor the process of the Generative AI learning the content in real time and understand the progress of learning. It also periodically evaluates the accuracy and coverage of the data learned by the Generative AI and monitors the effectiveness of the learning. Step 5: The readjustment unit readjusts the content based on the data monitored by the monitoring unit. The readjustment unit adjusts parameters and reanalyzes the data. For example, it adjusts the learning rate and batch size of the generative AI to improve learning efficiency. Also, if there are errors in the data that the generative AI has learned, it corrects that data and trains the generative AI again.

[0068] (Example of form 2) The AI-optimized AI (AIO) countermeasure service according to an embodiment of the present invention is a service designed to facilitate learning by a generative AI. This AIO countermeasure service promotes learning by analyzing the content of a website, converting it into a format that is easy for the generative AI to learn, and providing it to the generative AI. For example, the AIO countermeasure service analyzes the content of a website. In this process, it analyzes the structure and keywords of the content in detail in order to convert it into a format that is easy for the generative AI to learn. For example, by simplifying the structure of the text and emphasizing important keywords, the generative AI can learn efficiently. Next, the converted content is provided to the generative AI. The generative AI learns from the provided content and generates appropriate answers to the user's search queries. For example, if a user searches using a specific keyword, the generative AI provides the optimal answer based on the learned content. Furthermore, the learning effect of the generative AI is monitored, and the content is readjusted as needed. This ensures that the generative AI is always learning the latest information and can provide the optimal answer to the user. For example, the content is regularly updated to respond to new topics and trends, and the generative AI is retrained. This allows the website to be effectively learned by the generative AI and viewed by many users. Users can more easily access the information on the website through the generative AI, and the number of website visitors increases. For example, a website providing information about a specific product or service can be effectively learned by a generative AI, making it easier for users to find that information. This allows AI-powered AI (AI-powered web analytics) services to maximize the learning effect of the generative AI by converting the website's content into a format that is easily learned by the AI, monitoring its learning progress, and making adjustments as needed.

[0069] The AI-controlled AI (AIO) countermeasure service according to this embodiment comprises an analysis unit, a conversion unit, a provision unit, a monitoring unit, and a readjustment unit. The analysis unit analyzes the content of a website. The analysis unit analyzes the content of a website using, for example, a natural language processing algorithm. The natural language processing algorithm uses techniques such as morphological analysis, grammatical analysis, and semantic analysis to analyze the structure and keywords of the content in detail. For example, the analysis unit uses morphological analysis to divide the text into words and identify the part of speech of each word. The analysis unit also uses grammatical analysis to analyze the structure of the text and clarify the relationships between subjects, predicates, objects, etc. Furthermore, the analysis unit uses semantic analysis to understand the meaning of the text and extract important keywords. The conversion unit converts the content analyzed by the analysis unit into a format that the generating AI can efficiently learn from. The conversion unit performs, for example, keyword emphasis and text simplification. Keyword emphasis is performed by methods such as changing the font or color. For example, the conversion unit makes it easier for the generating AI to recognize important keywords by making them bold or changing their color. The conversion unit also simplifies the text. For example, it shortens long sentences and replaces technical terms with simpler language, making it easier for the generating AI to understand the content. The provision unit provides the converted content to the generating AI. The provision unit provides the content, for example, through an API. The API is an interface for the generating AI to obtain content, and the provision unit sends the content to the generating AI through the API. The provision unit can also provide content in file format. For example, the provision unit provides the converted content to the generating AI as a text file or a JSON file. The monitoring unit monitors the learning results of the generating AI based on the content provided by the provision unit. The monitoring unit performs, for example, real-time monitoring and periodic data collection. Real-time monitoring is a method of monitoring the process of the generating AI learning content in real time and understanding the progress of learning. For example, the monitoring unit can detect errors and warnings in real time when the generating AI is learning content and take appropriate measures.Periodic data collection is a method of periodically collecting data learned by the generative AI and evaluating the effectiveness of the learning. For example, the monitoring unit periodically evaluates the accuracy and coverage of the content learned by the generative AI and monitors the effectiveness of the learning. The readjustment unit readjusts the content based on the data monitored by the monitoring unit. The readjustment unit performs, for example, parameter adjustments and data reanalysis. Parameter adjustment is a method of optimizing the parameters used when the generative AI learns. For example, the readjustment unit can adjust the learning rate and batch size of the generative AI to improve the efficiency of learning. Data reanalysis is a method of reanalyzing the data that the generative AI learns and correcting the data as needed. For example, if there are errors in the data learned by the generative AI, the readjustment unit can correct the data and allow the generative AI to learn again. As a result, the AIO countermeasure service according to the embodiment can maximize the learning effect by converting website content into a format that is easy for the generative AI to learn, monitoring the learning effect, and readjusting.

[0070] The analysis unit can analyze website content using natural language processing algorithms. These algorithms utilize techniques such as morphological analysis, grammatical analysis, and semantic analysis to analyze the content's structure and keywords in detail. For example, the analysis unit can use morphological analysis to divide sentences into individual words and identify the part of speech of each word. It can also use grammatical analysis to analyze the sentence structure and clarify relationships such as subject, predicate, and object. Furthermore, it can use semantic analysis to understand the meaning of the sentence and extract important keywords. This improves the accuracy of website content analysis by using natural language processing algorithms. Some or all of the above-described processes in the analysis unit may be performed using, for example, generative AI, or without generative AI. For example, the analysis unit can input website content into a generative AI, which can then perform morphological analysis, grammatical analysis, and semantic analysis.

[0071] The conversion unit can perform keyword emphasis and sentence simplification. Keyword emphasis is performed by methods such as changing the font or color. For example, the conversion unit can make important keywords bold or change their color to make them easier for the generating AI to recognize. The conversion unit also simplifies sentences. For example, the conversion unit can shorten long sentences and replace technical terms with simpler language to make the content easier for the generating AI to understand. This allows the text to be converted into a format that is easy for the generating AI to learn, through keyword emphasis and sentence simplification. Some or all of the above processing in the conversion unit may be performed using the generating AI, or not. For example, the conversion unit can input website content into the generating AI, which can then perform keyword emphasis and sentence simplification.

[0072] The provider can provide the converted content to the generating AI. The provider can provide the content, for example, through an API. The API is an interface for the generating AI to retrieve the content, and the provider sends the content to the generating AI through the API. The provider can also provide the content in file format. For example, the provider can provide the converted content to the generating AI as a text file or a JSON file. This allows the generating AI to learn by providing the converted content. Some or all of the above processing in the provider may be performed using the generating AI, or not using the generating AI. For example, the provider can input the converted content into the generating AI and have the generating AI retrieve the content.

[0073] The monitoring unit can monitor the effectiveness of the generation AI's learning. For example, the monitoring unit performs real-time monitoring and periodic data collection. Real-time monitoring is a method of monitoring the process of the generation AI learning content in real time and understanding the progress of learning. For example, the monitoring unit can detect errors and warnings in real time when the generation AI is learning content and take appropriate measures. Periodic data collection is a method of periodically collecting data learned by the generation AI and evaluating the effectiveness of learning. For example, the monitoring unit periodically evaluates the accuracy and coverage of the content learned by the generation AI and monitors the effectiveness of learning. This allows the monitoring unit to understand the progress of learning by monitoring the effectiveness of the generation AI's learning. Some or all of the above-described processes in the monitoring unit may be performed using the generation AI, or without using the generation AI. For example, the monitoring unit can input data learned by the generation AI into the generation AI and have the generation AI perform the monitoring of learning effectiveness.

[0074] The readjustment unit can readjust the content based on the monitored data. The readjustment unit can, for example, adjust parameters or reanalyze data. Parameter adjustment is a method of optimizing the parameters used by the generative AI when it learns. For example, the readjustment unit can adjust the learning rate and batch size of the generative AI to improve learning efficiency. Data reanalysis is a method of reanalyzing the data that the generative AI learns from and correcting the data as needed. For example, if there are errors in the data that the generative AI has learned from, the readjustment unit can correct that data and allow the generative AI to learn from it again. This optimizes the learning effect of the generative AI by readjusting the content based on the monitored data. Some or all of the above processes in the readjustment unit may be performed using the generative AI, or they may be performed without using the generative AI. For example, the readjustment unit can input the data that the generative AI has learned from into the generative AI and have the generative AI perform data reanalysis.

[0075] Furthermore, the AIO (AI-driven computer) support service includes an answer provision unit that provides appropriate answers to users based on content learned by the generating AI. The answer provision unit provides the user with the most suitable answer based on content learned by the generating AI. For example, the answer provision unit generates an appropriate answer to the user's search query based on content learned by the generating AI. The generating AI analyzes the user's search query, extracts the most relevant information from the learned content, and generates an answer. For example, if a user searches using a specific keyword, the generating AI extracts information related to that keyword from the learned content and provides it to the user. The answer provision unit can also provide detailed answers to the user's questions based on content learned by the generating AI. For example, if a user asks a question about a specific topic, the generating AI extracts detailed information about that topic from the learned content and provides it to the user. This improves user satisfaction by providing the user with the most suitable answer based on content learned by the generating AI. Some or all of the above-described processes in the answer provision unit may be performed using the generating AI, or not. For example, the answer provision unit can input content learned by the generating AI into the generating AI, and have the generating AI generate an answer to the user's search query.

[0076] The analysis unit can estimate the user's emotions and set analysis priorities based on the estimated emotions. For example, the analysis unit uses techniques such as facial expression analysis, voice analysis, and text analysis to estimate the user's emotions. For example, the analysis unit can capture the user's facial expressions with a camera and estimate emotions using a facial expression analysis algorithm. The analysis unit can also record the user's voice and estimate emotions using voice analysis technology. Furthermore, the analysis unit can analyze the user's text data and estimate emotions using text analysis technology. This allows for more effective analysis by determining analysis priorities based on the user's emotions. For example, if the user is excited, important content can be prioritized for analysis. If the user is relaxed, all content can be analyzed evenly. Furthermore, if the user is stressed, simple and easy-to-understand content can be prioritized for analysis. Some or all of the above processing in the analysis unit may be performed using, for example, generative AI, or without generative AI. For example, the analysis unit can input the user's emotion data into a generative AI and have the generative AI perform emotion estimation and set analysis priorities.

[0077] The analysis unit can improve the accuracy of its analysis by referring to past website access data during the analysis process. For example, the analysis unit can identify pages that users frequently visit from past access data and focus its analysis on those pages. Past access data includes access logs and user behavior data. For example, the analysis unit can analyze access logs to understand which pages users accessed and how long they stayed on them. The analysis unit can also analyze user behavior data to understand what actions users took. By referring to past access data, the accuracy of the analysis is improved. For example, the analysis unit can extract keywords that users are interested in based on past access data and incorporate them into the analysis. The analysis unit can also analyze past access data to understand user behavior patterns and improve the accuracy of the analysis. Some or all of the above processes in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input past access data into a generative AI and have the generative AI perform data analysis and accuracy improvement.

[0078] The analysis unit can apply different analysis algorithms to each category of website content during analysis. For example, the analysis unit applies an analysis algorithm that prioritizes the latest information to news articles. Techniques such as topic modeling and time series analysis are used for analyzing news articles. For example, the analysis unit can use topic modeling to extract the main topics of news articles and time series analysis to understand the evolution of the news. The analysis unit also applies an analysis algorithm that prioritizes user ratings and comments to product reviews. Techniques such as sentiment analysis and opinion mining are used for analyzing product reviews. For example, the analysis unit can use sentiment analysis to determine whether user ratings are positive or negative and opinion mining to extract specific user opinions. Furthermore, the analysis unit applies an analysis algorithm that prioritizes comprehension to educational content. Techniques such as knowledge graphs and learning analysis are used for analyzing educational content. For example, the analysis unit can use knowledge graphs to understand the relationships between knowledge in educational content and learning analysis to evaluate the user's comprehension. By applying different analysis algorithms to each category, the accuracy of the analysis is improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input the content of a website into a generative AI, and have the generative AI apply a category-specific analysis algorithm.

[0079] The analysis unit can estimate the user's emotions and change the display method of the analysis results based on the estimated user emotions. For example, the analysis unit uses techniques such as facial expression analysis, voice analysis, and text analysis to estimate the user's emotions. For example, the analysis unit can capture the user's facial expressions with a camera and estimate emotions using a facial expression analysis algorithm. The analysis unit can also record the user's voice and estimate emotions using voice analysis technology. Furthermore, the analysis unit can analyze the user's text data and estimate emotions using text analysis technology. This allows for a user-friendly display by adjusting the display method of the analysis results based on the user's emotions. For example, if the user is nervous, a simple and highly visible display method can be provided. If the user is relaxed, a display method containing detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the essentials can be provided. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's emotion data into a generative AI and have the generative AI perform emotion estimation and adjustment of the display method.

[0080] The analysis unit can perform analysis while considering the geographical distribution of websites. For example, the analysis unit can analyze the access patterns of geographically different users and perform analysis while considering the characteristics of each region. Geographical distribution includes access data by region and user location information. For example, the analysis unit can analyze access data by region and identify content that is popular in a particular region. The analysis unit can also analyze user location information and understand the interests of users in each region. This makes it possible to perform analysis that reflects the characteristics of each region by considering geographical distribution. For example, the analysis unit can prioritize the analysis of content that is popular in a particular region based on geographical distribution. The analysis unit can also perform analysis that reflects the interests of users in each region based on geographical data. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or it may be performed without using a generative AI. For example, the analysis unit can input geographical distribution data into a generative AI and have the generative AI perform data analysis and reflect the characteristics of each region.

[0081] The analysis unit can improve the accuracy of its analysis by referring to relevant literature on the website during the analysis process. For example, the analysis unit can improve the accuracy of its analysis based on the latest information obtained from relevant literature. Relevant literature includes academic papers, technical reports, and patent documents. For example, the analysis unit can refer to academic papers and reflect in-depth knowledge on a specific topic in its analysis. It can also refer to technical reports and reflect the latest technical information in its analysis. Furthermore, it can refer to patent documents and reflect detailed information on a specific technology in its analysis. In this way, the accuracy of the analysis is improved by referring to relevant literature. For example, the analysis unit can extract keywords that are of interest to the user based on the relevant literature and reflect them in its analysis. It can also reflect in-depth knowledge on a specific topic based on the relevant literature in its analysis. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input the relevant literature data into a generative AI and have the generative AI perform data analysis and accuracy improvement.

[0082] The transformation unit can estimate the user's emotions and modify the transformation's presentation based on the estimated emotions. For example, the transformation unit can use techniques such as facial expression analysis, voice analysis, and text analysis to estimate the user's emotions. For instance, the transformation unit can capture the user's facial expressions with a camera and estimate emotions using a facial expression analysis algorithm. It can also record the user's voice and estimate emotions using voice analysis technology. Furthermore, the transformation unit can analyze the user's text data and estimate emotions using text analysis technology. This allows for a transformation that is easier for the user to understand by adjusting the presentation based on the user's emotions. For example, if the user is relaxed, a transformation including detailed explanations can be performed. If the user is in a hurry, a concise and to-the-point transformation can be performed. Furthermore, if the user is excited, a transformation with visually stimulating effects can be added. Some or all of the above-described processes in the transformation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the transformation unit can input the user's emotion data into a generative AI, which can then perform emotion estimation and adjust the transformation's presentation.

[0083] The conversion unit can adjust the level of detail in the conversion based on the importance of the content. For example, the conversion unit can adjust the level of detail in the conversion based on the importance of the content. The importance of the content includes access count, user rating, relevance, etc. For example, the conversion unit can add detailed explanations to content with a high access count. It can also add visual effects to content with a high user rating. Furthermore, it can highlight important keywords in content with high relevance. In this way, important information can be emphasized by adjusting the level of detail in the conversion based on the importance of the content. For example, the conversion unit can add detailed explanations to important content. It can also add concise explanations to general content. Furthermore, it can add visual effects to content that is of high interest to users. Some or all of the above processing in the conversion unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the conversion unit can input content importance data into a generative AI and have the generative AI perform the adjustment of the level of detail in the conversion.

[0084] The conversion unit can apply different conversion algorithms depending on the content category during conversion. For example, the conversion unit applies a conversion algorithm that prioritizes the latest information to news articles. Techniques such as topic modeling and time series analysis are used for converting news articles. For example, the conversion unit can extract the main topics of a news article using topic modeling and understand the evolution of the news using time series analysis. The conversion unit also applies a conversion algorithm that prioritizes user ratings and comments to product reviews. Techniques such as sentiment analysis and opinion mining are used for converting product reviews. For example, the conversion unit can determine whether user ratings are positive or negative using sentiment analysis and extract specific user opinions using opinion mining. Furthermore, the conversion unit applies a conversion algorithm that prioritizes comprehension to educational content. Techniques such as knowledge graphs and learning analysis are used for converting educational content. For example, the conversion unit can understand the relationships between knowledge in educational content using knowledge graphs and evaluate the user's comprehension using learning analysis. By applying different conversion algorithms for each category, the accuracy of the conversion is improved. Some or all of the above-described processing in the conversion unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the conversion unit can input content category data into a generating AI, and the generating AI can apply a conversion algorithm for each category.

[0085] The transformation unit can estimate the user's emotions and change the length of the transformation based on the estimated emotions. For example, the transformation unit uses techniques such as facial expression analysis, voice analysis, and text analysis to estimate the user's emotions. For example, the transformation unit can capture the user's facial expressions with a camera and estimate emotions using a facial expression analysis algorithm. The transformation unit can also record the user's voice and estimate emotions using voice analysis technology. Furthermore, the transformation unit can analyze the user's text data and estimate emotions using text analysis technology. This allows for a transformation of an appropriate length for the user by adjusting the length of the transformation based on the user's emotions. For example, if the user is in a hurry, a short, concise transformation can be performed. If the user is relaxed, a longer transformation including detailed explanations can be performed. Furthermore, if the user is excited, a transformation with visually stimulating effects can be added. Some or all of the above processing in the transformation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the transformation unit can input the user's emotion data into a generative AI, which can then perform emotion estimation and adjustment of the transformation length.

[0086] The conversion unit can determine the conversion priority based on the content creation date during the conversion process. For example, the conversion unit can determine the conversion priority based on the content creation date. The content creation date includes the creation date, update date, publication date, etc. For example, the conversion unit can prioritize the conversion of the newest content. Older content can be converted while being updated as needed. Furthermore, content related to trends can be converted as needed. This allows for the prioritization of the conversion of the latest information by determining the conversion priority based on the content creation date. For example, the conversion unit can prioritize the conversion of the newest content. Older content can be converted while being updated as needed. Furthermore, content related to trends can be converted as needed. Some or all of the above processing in the conversion unit may be performed using, for example, a generation AI, or without a generation AI. For example, the conversion unit can input content creation date data into a generation AI and have the generation AI perform the determination of the conversion priority.

[0087] The conversion unit can adjust the order of conversion based on the relevance of the content during conversion. For example, the conversion unit can adjust the order of conversion based on the relevance of the content. Content relevance includes common keywords, link relationships, etc. For example, the conversion unit can prioritize the conversion of content related to the user's search query. It can also group and convert highly relevant content. Furthermore, it can prioritize the conversion of highly relevant content based on the user's interests. This allows for the prioritization of highly relevant information by adjusting the order of conversion based on the relevance of the content. For example, the conversion unit can prioritize the conversion of content related to the user's search query. It can also group and convert highly relevant content. Furthermore, it can prioritize the conversion of highly relevant content based on the user's interests. Some or all of the above processing in the conversion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversion unit can input content relevance data into a generative AI and have the generative AI adjust the order of conversion.

[0088] The service provider can estimate the user's emotions and adjust the timing of service delivery based on the estimated emotions. For example, the service provider can use technologies such as facial expression analysis, voice analysis, and text analysis to estimate the user's emotions. For example, the service provider can capture the user's facial expressions with a camera and estimate their emotions using a facial expression analysis algorithm. The service provider can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the service provider can analyze the user's text data and estimate their emotions using text analysis technology. This allows the service provider to deliver information at the optimal time for the user by adjusting the timing of service delivery based on the user's emotions. For example, if the user is relaxed, the service provider can deliver information that includes detailed information. If the user is in a hurry, the service provider can deliver information that is concise and to the point. Furthermore, if the user is excited, the service provider can deliver information with visually stimulating effects. Some or all of the above processing in the service provider may be performed using, for example, generative AI, or without generative AI. For example, the service provider can input the user's emotion data into a generative AI and have the generative AI perform emotion estimation and adjustment of the service delivery timing.

[0089] The service provider can improve the accuracy of its deliveries by referring to the generative AI's past training data at the time of delivery. For example, the service provider can provide optimal content based on the generative AI's past training data. Past training data includes training datasets and learning history. For example, the service provider can refer to the generative AI's training dataset and provide the best possible answers to the user's search queries. The service provider can also refer to the generative AI's learning history and provide content based on the user's interests. This improves the accuracy of deliveries by referring to the generative AI's past training data. For example, the service provider can provide optimal content based on the generative AI's past training data. The service provider can also analyze the generative AI's past training data and provide content based on the user's interests. Furthermore, the service provider can refer to the generative AI's past training data and provide the best possible answers to the user's search queries. Some or all of the above processing in the service provider may be performed using the generative AI, or not. For example, the service provider can input the generative AI's past training data into the generative AI and have the generative AI perform data referencing and improve the accuracy of deliveries.

[0090] The service provider can apply different delivery methods depending on the learning algorithm of the generative AI at the time of delivery. For example, the service provider can select the optimal delivery method based on the learning algorithm of the generative AI. Learning algorithms include reinforcement learning, supervised learning, and unsupervised learning. For example, the service provider can use a reinforcement learning algorithm to provide optimal content based on user behavior. The service provider can also use a supervised learning algorithm to provide optimal content based on labeled data. Furthermore, the service provider can use an unsupervised learning algorithm to perform clustering and dimensionality reduction and provide content based on user interests. This makes it possible to provide optimal information to users by applying the optimal delivery method according to the learning algorithm of the generative AI. For example, the service provider can select the optimal delivery method based on the learning algorithm of the generative AI. Furthermore, the service provider can provide content based on user interests according to the learning algorithm of the generative AI. Furthermore, the service provider can provide the optimal answer to the user's search query, taking into account the learning algorithm of the generative AI. Some or all of the above processing in the service provider may be performed using a generative AI, for example, or without using a generative AI. For example, the supply unit can input the learning algorithm data of the generation AI into the generation AI, and have the generation AI select and apply a delivery method.

[0091] The service provider can estimate the user's emotions and prioritize the content to be provided based on those estimated emotions. For example, the service provider can use technologies such as facial expression analysis, voice analysis, and text analysis to estimate the user's emotions. For instance, the service provider can capture the user's facial expressions with a camera and estimate their emotions using a facial expression analysis algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, it can analyze the user's text data and estimate their emotions using text analysis technology. This allows the service provider to provide the most relevant information to the user by prioritizing the content based on their emotions. For example, if the user is relaxed, content containing detailed information can be prioritized. If the user is in a hurry, concise and to-the-point content can be prioritized. Furthermore, if the user is excited, content with visually stimulating effects can be prioritized. Some or all of the above-described processes in the service provider may be performed using, for example, generative AI, or without generative AI. For example, the service provider can input user emotion data into a generating AI, which can then perform emotion estimation and content prioritization.

[0092] The service provider can provide content while considering the geographical distribution of the generating AI. For example, the service provider can analyze the access patterns of geographically different users and provide content while considering the characteristics of each region. Geographical distribution includes access data by region and user location information. For example, the service provider can analyze access data by region to identify content that is popular in a particular region. The service provider can also analyze user location information to understand the interests of users in each region. By considering geographical distribution, it becomes possible to provide information that reflects the characteristics of each region. For example, the service provider can prioritize providing content that is popular in a particular region based on geographical distribution. The service provider can also provide content that reflects the interests of users in each region based on geographical data. Some or all of the above processing in the service provider may be performed using, for example, the generating AI, or without using the generating AI. For example, the service provider can input geographical distribution data into the generating AI and have the generating AI perform data analysis and reflect the characteristics of each region.

[0093] The service provider can improve the accuracy of its service by referring to relevant literature generated by the AI ​​during the service provision process. For example, the service provider can improve the accuracy of its service based on the latest information obtained from relevant literature. Relevant literature includes academic papers, technical reports, and patent documents. For example, the service provider can refer to academic papers and reflect in-depth knowledge on a specific topic in its service provision. It can also refer to technical reports and reflect in-depth technical information in its service provision. Furthermore, it can refer to patent documents and reflect in-depth information on a specific technology in its service provision. This improves the accuracy of the service provision by referring to relevant literature. For example, the service provider can extract keywords that will interest the user based on relevant literature and reflect them in its service provision. It can also reflect in-depth knowledge on a specific topic based on relevant literature in its service provision. Some or all of the above processing in the service provider may be performed using, for example, a generating AI, or without using a generating AI. For example, the service provider can input relevant literature data into a generating AI and have the generating AI perform data referencing and improve the accuracy of the service provision.

[0094] The monitoring unit can estimate the user's emotions and change the monitoring criteria based on the estimated emotions. For example, the monitoring unit uses technologies such as facial expression analysis, voice analysis, and text analysis to estimate the user's emotions. For example, the monitoring unit can capture the user's facial expressions with a camera and estimate their emotions using a facial expression analysis algorithm. The monitoring unit can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the monitoring unit can analyze the user's text data and estimate their emotions using text analysis technology. This allows for optimal monitoring for the user by adjusting the monitoring criteria based on their emotions. For example, if the user is nervous, simple and highly visible monitoring criteria can be provided. If the user is relaxed, monitoring criteria containing detailed information can be provided. Furthermore, if the user is in a hurry, concise monitoring criteria can be provided. Some or all of the above processing in the monitoring unit may be performed using, for example, generative AI, or without generative AI. For example, the monitoring unit can input the user's emotion data into a generative AI and have the generative AI perform emotion estimation and adjustment of monitoring criteria.

[0095] The monitoring unit can track the learning effectiveness of the generative AI in real time during monitoring. For example, the monitoring unit can track the learning effectiveness of the generative AI in real time and grasp the progress of learning. Technologies such as real-time data streaming and immediate feedback are used to track in real time. For example, the monitoring unit can monitor the process by which the generative AI learns content in real time and grasp the progress of learning. The monitoring unit can also detect errors and warnings when the generative AI is learning in real time and take appropriate measures. Furthermore, the monitoring unit can track the learning effectiveness of the generative AI in real time and adjust the learning content as needed. In this way, the progress of learning can be grasped by tracking the learning effectiveness of the generative AI in real time. For example, the monitoring unit can track the learning effectiveness of the generative AI in real time and improve the efficiency of learning. Some or all of the above processing in the monitoring unit may be performed using the generative AI, or not using the generative AI. For example, the monitoring unit can input the learning data of the generative AI into the generative AI and have the generative AI perform real-time tracking of the learning effectiveness.

[0096] The monitoring unit can perform monitoring while considering the attribute information of the generation AI's training data. For example, the monitoring unit can improve the accuracy of monitoring based on the attribute information of the generation AI's training data. Attribute information includes user attributes and data attributes. For example, the monitoring unit can perform monitoring related to specific attributes by considering user attributes. Also, the monitoring unit can perform monitoring related to specific data by considering data attributes. This improves the accuracy of monitoring by considering the attribute information of the training data. For example, the monitoring unit can improve the accuracy of monitoring based on the attribute information of the generation AI's training data. Also, the monitoring unit can perform monitoring related to specific attributes by considering the attribute information of the generation AI's training data. Furthermore, the monitoring unit can perform monitoring that improves the efficiency of learning based on the attribute information of the generation AI's training data. Some or all of the above processing in the monitoring unit may be performed using the generation AI, or without using the generation AI. For example, the monitoring unit can input the attribute information of the generation AI's training data into the generation AI, and have the generation AI perform the improvement of monitoring accuracy.

[0097] The monitoring unit can estimate the user's emotions and change the display method of the monitoring results based on the estimated user emotions. For example, the monitoring unit uses technologies such as facial expression analysis, voice analysis, and text analysis to estimate the user's emotions. For example, the monitoring unit can capture the user's facial expressions with a camera and estimate emotions using a facial expression analysis algorithm. The monitoring unit can also record the user's voice and estimate emotions using voice analysis technology. Furthermore, the monitoring unit can analyze the user's text data and estimate emotions using text analysis technology. This allows for a user-friendly display by adjusting the display method of the monitoring results based on the user's emotions. For example, if the user is nervous, a simple and highly visible display method can be provided. If the user is relaxed, a display method containing detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the essentials can be provided. Some or all of the above processing in the monitoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the monitoring unit can input the user's emotion data into a generative AI and have the generative AI perform emotion estimation and adjustment of the display method.

[0098] The monitoring unit can perform monitoring while considering the geographical distribution of the generated AI. For example, the monitoring unit can analyze the access patterns of geographically different users and monitor while considering the characteristics of each region. Geographical distribution includes regional access data and user location information. For example, the monitoring unit can analyze regional access data and identify content that is popular in a particular region. The monitoring unit can also analyze user location information and understand the interests of users in each region. This makes it possible to perform monitoring that reflects the characteristics of each region by considering geographical distribution. For example, the monitoring unit can prioritize monitoring of content that is popular in a particular region based on geographical distribution. The monitoring unit can also perform monitoring that reflects the interests of users in each region based on geographical data. Some or all of the above processing in the monitoring unit may be performed using, for example, the generated AI, or without using the generated AI. For example, the monitoring unit can input geographical distribution data into the generated AI and have the generated AI perform data analysis and reflect the characteristics of each region.

[0099] The monitoring unit can improve the accuracy of monitoring by referring to relevant literature generated by the AI ​​during monitoring. For example, the monitoring unit improves the accuracy of monitoring based on the latest information obtained from relevant literature. Relevant literature includes academic papers, technical reports, and patent documents. For example, the monitoring unit can refer to academic papers and reflect in-depth knowledge on a specific topic in the monitoring. The monitoring unit can also refer to technical reports and reflect the latest technical information in the monitoring. Furthermore, the monitoring unit can refer to patent documents and reflect detailed information on a specific technology in the monitoring. As a result, the accuracy of monitoring is improved by referring to relevant literature. For example, the monitoring unit can extract keywords that are of interest to the user based on relevant literature and reflect them in the monitoring. The monitoring unit can also reflect in-depth knowledge on a specific topic based on relevant literature in the monitoring. Some or all of the above processing in the monitoring unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the monitoring unit can input relevant literature data into a generating AI, and have the generating AI perform data referencing and improve the accuracy of monitoring.

[0100] The readjustment unit can estimate the user's emotions and modify the readjustment method based on the estimated emotions. For example, the readjustment unit uses techniques such as facial expression analysis, voice analysis, and text analysis to estimate the user's emotions. For example, the readjustment unit can capture the user's facial expressions with a camera and estimate emotions using a facial expression analysis algorithm. The readjustment unit can also record the user's voice and estimate emotions using voice analysis technology. Furthermore, the readjustment unit can analyze the user's text data and estimate emotions using text analysis technology. This allows for optimal readjustment for the user by adjusting the readjustment method based on the user's emotions. For example, if the user is relaxed, a readjustment including detailed information can be performed. If the user is in a hurry, a concise and to-the-point readjustment can be performed. Furthermore, if the user is excited, a readjustment with visually stimulating effects can be added. Some or all of the above processing in the readjustment unit may be performed using, for example, generative AI, or without generative AI. For example, the readjustment unit can input user emotion data into a generating AI, which can then perform emotion estimation and adjust the readjustment method.

[0101] The readjustment unit can improve the accuracy of readjustment by referring to the past training data of the generating AI during readjustment. For example, the readjustment unit performs optimal readjustment based on the past training data of the generating AI. Past training data includes training datasets and training history. For example, the readjustment unit can refer to the training dataset of the generating AI and perform optimal readjustment for the user's search query. The readjustment unit can also refer to the training history of the generating AI and perform readjustment based on the user's interests. This improves the accuracy of readjustment by referring to the past training data of the generating AI. For example, the readjustment unit can perform optimal readjustment based on the past training data of the generating AI. The readjustment unit can also analyze the past training data of the generating AI and perform readjustment based on the user's interests. Furthermore, the readjustment unit can refer to the past training data of the generating AI and perform optimal readjustment for the user's search query. Some or all of the above processing in the readjustment unit may be performed using the generating AI, for example, or without using the generating AI. For example, the readjustment unit can input past training data of the generating AI into the generating AI, allowing the generating AI to perform data referencing and improve the accuracy of readjustment.

[0102] The readjustment unit can apply different readjustment methods depending on the learning algorithm of the generative AI during readjustment. For example, the readjustment unit selects the optimal readjustment method based on the learning algorithm of the generative AI. Learning algorithms include reinforcement learning, supervised learning, and unsupervised learning. For example, the readjustment unit can use a reinforcement learning algorithm to perform optimal readjustment based on user behavior. It can also use a supervised learning algorithm to perform optimal readjustment based on labeled data. Furthermore, it can use an unsupervised learning algorithm to perform clustering and dimensionality reduction, and readjust based on user interests. This improves the accuracy of readjustment by applying the optimal readjustment method according to the generative AI's learning algorithm. For example, the readjustment unit can select the optimal readjustment method based on the generative AI's learning algorithm. It can also perform readjustment based on user interests according to the generative AI's learning algorithm. Furthermore, the readjustment unit can consider the generative AI's learning algorithm and perform optimal readjustment for the user's search queries. Some or all of the above-described processes in the readjustment unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the readjustment unit can input the generative AI's learning algorithm data into the generative AI, and have the generative AI select and apply a readjustment method.

[0103] The readjustment unit can estimate the user's emotions and set readjustment priorities based on the estimated emotions. The readjustment unit uses techniques such as facial expression analysis, voice analysis, and text analysis to estimate the user's emotions. For example, the readjustment unit can capture the user's facial expressions with a camera and estimate emotions using a facial expression analysis algorithm. The readjustment unit can also record the user's voice and estimate emotions using voice analysis technology. Furthermore, the readjustment unit can analyze the user's text data and estimate emotions using text analysis technology. This allows for optimal readjustment for the user by determining readjustment priorities based on the user's emotions. For example, if the user is relaxed, readjustment containing detailed information can be prioritized. If the user is in a hurry, concise and to-the-point readjustment can be prioritized. Furthermore, if the user is excited, readjustment with visually stimulating effects can be prioritized. Some or all of the above processing in the readjustment unit may be performed using, for example, generative AI, or without generative AI. For example, the readjustment unit can input user emotion data into a generating AI, which can then perform emotion estimation and set priorities for readjustment.

[0104] The readjustment unit can perform readjustments while considering the geographical distribution of the generated AI. For example, the readjustment unit analyzes the access patterns of geographically different users and readjusts while considering the characteristics of each region. Geographical distribution includes access data by region and user location information. For example, the readjustment unit can analyze access data by region to identify content that is popular in a particular region. The readjustment unit can also analyze user location information to understand the interests of users in each region. This makes it possible to readjust content that reflects the characteristics of each region by considering geographical distribution. For example, the readjustment unit can prioritize the readjustment of content that is popular in a particular region based on geographical distribution. The readjustment unit can also perform readjustments that reflect the interests of users in each region based on geographical data. Some or all of the above processing in the readjustment unit may be performed using, for example, the generated AI, or without using the generated AI. For example, the readjustment unit can input geographical distribution data into the generated AI and have the generated AI perform data analysis and reflect the characteristics of each region.

[0105] The readjustment unit can improve the accuracy of readjustment by referring to relevant literature for the generating AI during readjustment. For example, the readjustment unit improves the accuracy of readjustment based on the latest information obtained from relevant literature. Relevant literature includes academic papers, technical reports, and patent documents. For example, the readjustment unit can refer to academic papers and reflect in-depth knowledge on a specific topic in the readjustment. It can also refer to technical reports and reflect the latest technical information in the readjustment. Furthermore, it can refer to patent documents and reflect detailed information on a specific technology in the readjustment. As a result, the accuracy of readjustment is improved by referring to relevant literature. For example, the readjustment unit can extract keywords that are of interest to the user based on relevant literature and reflect them in the readjustment. It can also reflect in-depth knowledge on a specific topic based on relevant literature in the readjustment. Some or all of the above processing in the readjustment unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the readjustment unit can input relevant literature data into the generating AI, which can then perform data referencing and improve the accuracy of readjustment.

[0106] The response provider can estimate the user's emotions and modify the way the response is presented based on the estimated emotions. For example, the response provider can use technologies such as facial expression analysis, voice analysis, and text analysis to estimate the user's emotions. For example, the response provider can capture the user's facial expressions with a camera and estimate their emotions using a facial expression analysis algorithm. The response provider can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, the response provider can analyze the user's text data and estimate their emotions using text analysis technology. This allows for responses that are easier for the user to understand by adjusting the way the response is presented based on the user's emotions. For example, if the user is relaxed, the response can include detailed explanations. If the user is in a hurry, the response can be concise and to the point. Furthermore, if the user is excited, the response can be provided with visually stimulating effects. Some or all of the above processing in the response provider may be performed using, for example, generative AI, or without generative AI. For example, the response provision unit can input user emotion data into a generating AI, which can then perform emotion estimation and adjust the way the response is expressed.

[0107] The answer provider can improve the accuracy of its answers by referring to the generator AI's past training data when providing answers. For example, the answer provider can provide the optimal answer based on the generator AI's past training data. Past training data includes training datasets and learning history. For example, the answer provider can refer to the generator AI's training dataset and provide the optimal answer to the user's search query. The answer provider can also refer to the generator AI's learning history and provide answers based on the user's interests. This improves the accuracy of answers by referring to the generator AI's past training data. For example, the answer provider can provide the optimal answer based on the generator AI's past training data. The answer provider can also analyze the generator AI's past training data and provide answers based on the user's interests. Furthermore, the answer provider can refer to the generator AI's past training data and provide the optimal answer to the user's search query. Some or all of the above processing in the answer provider may be performed using the generator AI, or without using the generator AI. For example, the answer provision unit can input past training data of the generating AI into the generating AI, allowing the generating AI to perform data referencing and improve the accuracy of its answers.

[0108] The answer provider can apply different answer methods depending on the learning algorithm of the generative AI when providing answers. For example, the answer provider can select the optimal answer method based on the learning algorithm of the generative AI. Learning algorithms include reinforcement learning, supervised learning, and unsupervised learning. For example, the answer provider can use a reinforcement learning algorithm to provide the optimal answer based on user behavior. The answer provider can also use a supervised learning algorithm to provide the optimal answer based on labeled data. Furthermore, the answer provider can use an unsupervised learning algorithm to perform clustering and dimensionality reduction and provide answers based on user interests. This makes it possible to provide the optimal answer for the user by applying the optimal answer method according to the learning algorithm of the generative AI. For example, the answer provider can select the optimal answer method based on the learning algorithm of the generative AI. Furthermore, the answer provider can provide answers based on user interests according to the learning algorithm of the generative AI. Furthermore, the answer provider can provide the optimal answer to the user's search query, taking into account the learning algorithm of the generative AI. Some or all of the above processing in the answer provider may be performed using a generative AI, for example, or without using a generative AI. For example, the response provision unit can input the learning algorithm data of the generating AI into the generating AI, and have the generating AI select and apply a response method.

[0109] The response provider can estimate the user's emotions and prioritize responses based on those emotions. For example, the response provider can use techniques such as facial expression analysis, voice analysis, and text analysis to estimate the user's emotions. For instance, the response provider can capture the user's facial expressions with a camera and estimate their emotions using a facial expression analysis algorithm. It can also record the user's voice and estimate their emotions using voice analysis technology. Furthermore, it can analyze the user's text data and estimate their emotions using text analysis technology. This allows for the provision of optimal responses by prioritizing responses based on the user's emotions. For example, if the user is relaxed, responses containing detailed information can be prioritized. If the user is in a hurry, concise and to-the-point responses can be prioritized. Furthermore, if the user is excited, responses with visually stimulating effects can be prioritized. Some or all of the above processing in the response provider may be performed using, for example, generative AI, or without generative AI. For example, the response provision unit can input user emotion data into a generating AI, which can then perform emotion estimation and prioritize responses.

[0110] The response provider can provide responses while considering the geographical distribution of the generating AI. For example, the response provider can analyze the access patterns of geographically different users and provide responses while considering the characteristics of each region. Geographical distribution includes access data by region and user location information. For example, the response provider can analyze access data by region and identify responses that are popular in a particular region. The response provider can also analyze user location information and understand the interests of users in each region. This makes it possible to provide responses that reflect the characteristics of each region by considering geographical distribution. For example, the response provider can prioritize providing responses that are popular in a particular region based on geographical distribution. The response provider can also provide responses that reflect the interests of users in each region based on geographical data. Some or all of the above processing in the response provider may be performed using, for example, a generating AI, or without using a generating AI. For example, the response provider can input geographical distribution data into a generating AI and have the generating AI perform data analysis and reflect the characteristics of each region.

[0111] The answer-providing unit can improve the accuracy of its answers by referring to relevant literature generated by the AI ​​when providing answers. For example, the answer-providing unit improves the accuracy of its answers based on the latest information obtained from relevant literature. Relevant literature includes academic papers, technical reports, and patent documents. For example, the answer-providing unit can refer to academic papers and reflect in-depth knowledge on a specific topic in its answers. It can also refer to technical reports and reflect in the latest technical information in its answers. Furthermore, it can refer to patent documents and reflect in-depth information on a specific technology in its answers. As a result, the accuracy of the answers is improved by referring to relevant literature. For example, the answer-providing unit can extract keywords that will interest the user based on the relevant literature and reflect them in its answers. It can also reflect in-depth knowledge on a specific topic in its answers based on the relevant literature. Some or all of the above processing in the answer-providing unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the answer-providing unit can input relevant literature data into a generating AI, and have the generating AI perform data referencing and improve the accuracy of the answers. === Hard Collateral 1-1 === Each of the multiple elements described above, including the analysis unit, conversion unit, provision unit, monitoring unit, readjustment unit, and answer provision unit, is implemented, for example, in at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The conversion unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The provision unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The monitoring unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The readjustment unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The answer provision unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements described above, including the analysis unit, conversion unit, provision unit, monitoring unit, readjustment unit, and answer provision unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The conversion unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The provision unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The monitoring unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The readjustment unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The answer provision unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements described above, including the analysis unit, conversion unit, provision unit, monitoring unit, readjustment unit, and response provision unit, is implemented, for example, in at least one of the headset terminal 314 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The conversion unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The provision unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The monitoring unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The readjustment unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The response provision unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements described above, including the analysis unit, conversion unit, provision unit, monitoring unit, readjustment unit, and answer provision unit, is implemented, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The conversion unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The provision unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The monitoring unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The readjustment unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The answer provision unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] The analysis unit can estimate the user's emotions and prioritize analysis based on those emotions. For example, if the user is excited, important content can be prioritized for analysis. If the user is relaxed, all content can be analyzed evenly. Furthermore, if the user is stressed, simple and easy-to-understand content can be prioritized for analysis. By determining analysis priorities based on the user's emotions, more effective analysis becomes possible.

[0114] The translation unit can estimate the user's emotions and change the way the translation is presented based on those emotions. For example, if the user is relaxed, the translation can include detailed explanations. If the user is in a hurry, the translation can be concise and to the point. Furthermore, if the user is excited, the translation can include visually stimulating effects. By adjusting the way the translation is presented based on the user's emotions, it becomes possible to create translations that are easy for the user to understand.

[0115] The information delivery system can estimate the user's emotions and adjust the timing of the delivery based on those emotions. For example, if the user is relaxed, it can deliver information with detailed details. If the user is in a hurry, it can deliver information concisely and to the point. Furthermore, if the user is excited, it can deliver information with visually stimulating effects. By adjusting the timing of the delivery based on the user's emotions, information can be delivered at the optimal time for the user.

[0116] The monitoring unit can estimate the user's emotions and adjust the monitoring criteria based on those estimates. For example, if the user is stressed, it can provide simple and easily visible monitoring criteria. If the user is relaxed, it can provide monitoring criteria that include more detailed information. Furthermore, if the user is in a hurry, it can provide concise monitoring criteria. By adjusting the monitoring criteria based on the user's emotions, optimal monitoring becomes possible for the user.

[0117] The readjustment unit can estimate the user's emotions and modify the readjustment method based on those estimates. For example, if the user is relaxed, it can perform a readjustment that includes detailed information. If the user is in a hurry, it can perform a concise and to-the-point readjustment. Furthermore, if the user is excited, it can perform a readjustment that includes visually stimulating effects. By adjusting the readjustment method based on the user's emotions, it becomes possible to perform the optimal readjustment for the user.

[0118] The analysis unit can improve the accuracy of its analysis by referring to past website access data during the analysis process. For example, it can identify pages that users frequently visit from past access data and focus its analysis on those pages. It can also extract keywords that users are interested in based on past access data and incorporate them into the analysis. Furthermore, by analyzing past access data, it can understand user behavior patterns and improve the accuracy of the analysis. In short, referring to past access data improves the accuracy of the analysis.

[0119] The conversion unit can adjust the level of detail in the conversion based on the importance of the content. For example, content with a high number of views can be converted with detailed explanations. Content with high user ratings can be converted with visual effects. Furthermore, highly relevant content can be converted with important keywords highlighted. This allows for the emphasis of important information by adjusting the level of detail in the conversion based on the importance of the content.

[0120] The delivery unit can improve the accuracy of its deliveries by referring to the generative AI's past training data. For example, it can refer to the generative AI's training dataset to provide the best possible answers to users' search queries. It can also refer to the generative AI's learning history to provide content based on the user's interests. In this way, the accuracy of deliveries is improved by referring to the generative AI's past training data.

[0121] The monitoring unit can perform monitoring while considering the attribute information of the training data of the generated AI. For example, it can perform monitoring related to specific attributes by considering user attributes. It can also perform monitoring related to specific data by considering data attributes. As a result, the accuracy of monitoring is improved by considering the attribute information of the training data.

[0122] The readjustment unit can apply different readjustment methods depending on the learning algorithm of the generative AI during readjustment. For example, it can use a reinforcement learning algorithm to perform optimal readjustment based on user behavior. It can also use a supervised learning algorithm to perform optimal readjustment based on labeled data. Furthermore, it can use an unsupervised learning algorithm to perform clustering and dimensionality reduction and readjustment based on user interests. By applying the optimal readjustment method according to the learning algorithm of the generative AI, the accuracy of readjustment is improved.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The analysis unit analyzes the website content. The analysis unit uses natural language processing algorithms to analyze the content structure and keywords in detail using techniques such as morphological analysis, grammatical analysis, and semantic analysis. For example, it divides sentences into individual words, identifies the part of speech of each word, analyzes the sentence structure, clarifies the relationships between subjects, predicates, objects, etc., and extracts important keywords. Step 2: The conversion unit converts the content analyzed by the analysis unit into a format that the generating AI can efficiently learn from. The conversion unit performs keyword highlighting and sentence simplification. For example, important keywords are made bold or their color is changed to make them easier for the generating AI to recognize, long sentences are shortened, and technical terms are replaced with simpler language to make the content easier for the generating AI to understand. Step 3: The provider provides the converted content to the generation AI. The provider can provide the content via API, or as a text file or JSON file. Step 4: The Monitoring Unit monitors the learning outcomes of the Generative AI based on the content provided by the Provider Unit. The Monitoring Unit performs real-time monitoring and periodic data collection to monitor the process of the Generative AI learning the content in real time and understand the progress of learning. It also periodically evaluates the accuracy and coverage of the data learned by the Generative AI and monitors the effectiveness of the learning. Step 5: The readjustment unit readjusts the content based on the data monitored by the monitoring unit. The readjustment unit adjusts parameters and reanalyzes the data. For example, it adjusts the learning rate and batch size of the generative AI to improve learning efficiency. Also, if there are errors in the data that the generative AI has learned, it corrects that data and trains the generative AI again.

[0125] 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.

[0126] 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 the following. 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 (for example, 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. 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 a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0127] 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.

[0128] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.).

[0141] 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.

[0142] 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. 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.

[0143] 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.

[0144] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.).

[0157] 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.

[0158] 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. 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.

[0159] 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.

[0160] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.).

[0174] 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.

[0175] 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. 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.

[0176] 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.

[0177] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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."

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] [Explanation of symbols]

[0197] 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 content of the website, A conversion unit converts the content analyzed by the analysis unit into a format that the generating AI can efficiently learn from, A providing unit that provides the content converted by the conversion unit to the generating AI, A monitoring unit monitors the learning results of the generating AI based on the content provided by the aforementioned provisioning unit, A readjustment unit that readjusts the content based on the data monitored by the monitoring unit, Equipped with A system characterized by the following features.

2. The aforementioned analysis unit, Analyze website content using natural language processing algorithms. The system according to feature 1.

3. The conversion unit is Highlight keywords and simplify sentences. The system according to feature 1.

4. The aforementioned supply unit is, Provide the converted content to the generation AI. The system according to feature 1.

5. The monitoring unit, Monitor the effectiveness of the learning process of the generative AI. The system according to feature 1.

6. The readjustment unit is, Readjust content based on monitored data. The system according to feature 1.

7. The aforementioned supply unit is, It includes an answer provision unit that provides appropriate answers to the user based on the content learned by the generating AI. The system according to feature 1.

8. The aforementioned analysis unit, It estimates the user's emotions and sets analysis priorities based on the estimated user emotions. The system according to feature 1.

9. The aforementioned analysis unit, During analysis, we improve the accuracy of the analysis by referring to the website's past access data. The system according to feature 1.

Images