system

Abstract

The system according to this embodiment aims to detect problems occurring in the classroom at an early stage and propose appropriate countermeasures. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a detection unit, and a provision unit. The collection unit collects data from within the classroom. The analysis unit analyzes the data collected by the collection unit. The detection unit detects signs of a problem based on the data analyzed by the analysis unit. The provision unit provides alerts and suggestions to teachers and parents based on the signs of a problem detected by the detection 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 conventional technology, there is a problem that it is difficult to detect early problems occurring in a classroom and take appropriate measures.

[0005] The system according to the embodiment aims to detect early problems occurring in a classroom and propose appropriate measures.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, an analysis unit, a detection unit, and a data provision unit. The data collection unit collects data from within the classroom. The analysis unit analyzes the data collected by the data collection unit. The detection unit detects signs of problems based on the data analyzed by the analysis unit. The data provision unit provides alerts and suggestions to teachers and parents based on the signs of problems detected by the detection unit. [Effects of the Invention]

[0007] The system according to this embodiment can detect problems occurring in the classroom at an early stage and propose appropriate countermeasures. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applicable 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 ​​agent system according to an embodiment of the present invention is a system that detects and analyzes problems occurring among students in schools and classrooms at an early stage and proposes appropriate countermeasures to teachers and parents. This AI agent system collects and analyzes classroom data (student behavior, speech, facial expressions, etc.) in real time, detects signs of problems, and provides alerts and suggestions to teachers and parents. For example, the AI ​​agent system uses natural language processing (NLP) to analyze the content of students' conversations and detect signs of bullying or stress. The AI ​​agent system also uses computer vision to analyze students' facial expressions and behavior and detect decreased motivation to learn or abnormal behavior. As a result, the AI ​​agent system can catch signs of problems at an early stage. Furthermore, based on the detected signs of problems, the AI ​​agent system provides alerts and suggestions to teachers and parents at an appropriate time. For example, if signs of bullying are detected, the AI ​​agent system proposes specific countermeasures to teachers. Also, if decreased motivation to learn is detected, the AI ​​agent system proposes learning support to parents. In this way, the AI ​​agent system supports teachers and parents in taking quick and accurate countermeasures. This provides a safe and secure learning environment and enables students to realize their maximum potential. Furthermore, the AI ​​agent system can support teachers and parents in taking quick and accurate measures, thereby improving the efficiency and quality of education. This allows the AI ​​agent system to detect and analyze problems occurring among students in schools and classrooms at an early stage and propose appropriate solutions to teachers and parents.

[0029] The AI ​​agent system according to this embodiment comprises a collection unit, an analysis unit, a detection unit, and a provision unit. The collection unit collects data from within the classroom. Classroom data includes, but is not limited to, student behavior data, speech data, and facial expression data. The collection unit collects data using, for example, sensors and cameras installed in the classroom. The collection unit can also collect students' speech using a microphone and save it as audio data. Furthermore, the collection unit can film students' behavior with a camera and save it as video data. For example, the collection unit monitors students' behavior in real time using multiple cameras in the classroom and collects behavior data. The collection unit records students' speech using a microphone and saves it as audio data. The collection unit collects temperature data in the classroom using, for example, a temperature sensor. The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the content of students' speech using, for example, natural language processing (NLP) technology. The analysis unit analyzes students' facial expressions and behavior using, for example, computer vision technology. The analysis unit analyzes collected data using, for example, machine learning algorithms to detect signs of problems. For example, the analysis unit analyzes students' statements using NLP technology to detect signs of bullying or stress. The analysis unit analyzes students' facial expressions and behavior using, for example, computer vision technology to detect decreased motivation to learn or abnormal behavior. The analysis unit analyzes collected data using, for example, machine learning algorithms to detect signs of problems. The detection unit detects signs of problems based on the data analyzed by the analysis unit. For example, the detection unit detects signs of bullying. For example, the detection unit detects decreased motivation to learn. For example, the detection unit detects abnormal behavior based on the data analyzed by the analysis unit. For example, the detection unit detects signs of bullying based on the data analyzed by the analysis unit. For example, the detection unit detects decreased motivation to learn based on the data analyzed by the analysis unit. For example, the detection unit detects abnormal behavior based on the data analyzed by the analysis unit. The provision unit provides alerts and suggestions to teachers and parents based on the signs of problems detected by the detection unit. For example, if signs of bullying are detected, the provision unit proposes specific countermeasures to teachers.For example, if a decline in motivation to learn is detected, the service provider will suggest learning support to the parents. For example, if abnormal behavior is detected, the service provider will suggest specific countermeasures to the teacher. For example, if signs of bullying are detected, the service provider will suggest counseling to the teacher. For example, if a decline in motivation to learn is detected, the service provider will provide advice on home learning to the parents. For example, if abnormal behavior is detected, the service provider will suggest behavioral improvement to the teacher. In this way, the AI ​​agent system according to the embodiment can collect, analyze, detect, and provide data from within the classroom, thereby enabling early detection of signs of problems and the suggestion of appropriate countermeasures.

[0030] The data collection unit collects data from within the classroom. This data includes, but is not limited to, student behavior data, speech data, and facial expression data. The data collection unit uses sensors and cameras installed in the classroom to collect data. Specifically, it uses multiple cameras in the classroom to monitor student behavior in real time and collect behavioral data. This allows the unit to understand what kind of behavior students are exhibiting, for example, whether they are concentrating during class, talking to other students, or engaging in inappropriate behavior. The data collection unit also uses microphones to record students' speech and saves it as audio data. This allows the unit to understand what students are saying during class, for example, whether they are asking questions, talking to other students, or talking about things unrelated to the lesson. Furthermore, the data collection unit uses temperature sensors to collect temperature data within the classroom. This allows the unit to understand whether the classroom environment is suitable for student learning, for example, whether the temperature and humidity are appropriate. The data collection unit centrally manages this data and can collaborate with other systems and departments as needed. For example, the collected data can be stored on a cloud server and made accessible to the analysis and detection units. Furthermore, by adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions become possible. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0031] The analysis unit analyzes the data collected by the collection unit. The analysis unit uses natural language processing (NLP) technology to analyze the content of students' statements. Specifically, it uses NLP technology to convert students' statements into text data and analyzes its content. This allows it to understand what students are saying in class, for example, whether they are asking questions, talking to other students, or talking about things unrelated to the lesson. The analysis unit also uses computer vision technology to analyze students' facial expressions and behavior. Specifically, it analyzes camera footage to recognize students' facial expressions and behavior. This allows it to understand what kind of expressions students have in class, for example, whether they are concentrating, tired, or unhappy. Furthermore, the analysis unit uses machine learning algorithms to analyze the collected data and detect signs of problems. Specifically, it uses models trained on past data to analyze newly collected data and detect signs of bullying and stress. This allows the analysis unit to quickly and accurately analyze the collected data and understand the surrounding risk situation in real time. Furthermore, the analysis unit can also utilize past data and statistical information to perform long-term risk assessments and trend analyses. For example, based on past data, it can predict fluctuations in risk for specific students or classes and formulate future countermeasures. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns or abnormal data, issuing early warnings. This allows the analysis unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, improving the overall reliability and safety of the system.

[0032] The detection unit detects signs of a problem based on data analyzed by the analysis unit. Specifically, to detect signs of bullying, it uses NLP technology to analyze students' statements and detect keywords and phrases related to bullying. It also uses computer vision technology to analyze students' facial expressions and behavior to detect signs of bullying. For example, it can detect when a student is acting aggressively towards other students or when a particular student is isolated. Furthermore, it uses machine learning algorithms to analyze the collected data and detect decreased motivation to learn or abnormal behavior. For example, it can detect when a student is not concentrating during class or has lost interest in the lessons. As a result, the detection unit can quickly and accurately detect signs of bullying, decreased motivation to learn, and abnormal behavior based on data analyzed by the analysis unit. In addition, the detection unit can utilize historical data and statistical information to perform long-term risk assessments and trend analyses. For example, it can predict fluctuations in risk for specific students or classes based on historical data and formulate future countermeasures. Furthermore, the detection unit can use anomaly detection algorithms to detect unusual patterns or abnormal data and issue warnings early. This allows the detection unit to not only grasp the situation in real time, but also to handle long-term risk management and anomaly detection, thereby improving the reliability and safety of the entire system.

[0033] The service provider provides alerts and suggestions to teachers and parents based on the signs of problems detected by the detection unit. Specifically, if signs of bullying are detected, the service provider will propose specific countermeasures to teachers. For example, if signs of bullying are detected, the service provider will suggest counseling to teachers. Also, if a decline in motivation to learn is detected, the service provider will suggest learning support to parents. For example, if a decline in motivation to learn is detected, the service provider will provide advice on home learning to parents. Furthermore, if abnormal behavior is detected, the service provider will propose specific countermeasures to teachers. For example, if abnormal behavior is detected, the service provider will suggest behavioral improvement to teachers. The service provider can use multiple communication methods to deliver these alerts and suggestions quickly and accurately. For example, it can use email, SMS, and app notifications to deliver alerts and suggestions to teachers and parents. The service provider can also collect user feedback and continuously improve the accuracy and effectiveness of the content provided. For example, it can review and improve the content based on feedback from teachers and parents who have received alerts and suggestions. This allows the service provider to provide alerts and suggestions to teachers and parents quickly and accurately, supporting the early detection and countermeasures of problems. In addition, the service provider can utilize historical data and statistical information to conduct long-term risk assessments and trend analyses. For example, based on past data, the system can predict fluctuations in risk for specific students or classes and formulate future countermeasures. This allows the service provider to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, thereby improving the reliability and security of the entire system.

[0034] The NLP unit analyzes the content of students' conversations using natural language processing. For example, the NLP unit uses morphological analysis to divide students' statements into individual words and analyzes the meaning of each word. For example, the NLP unit uses grammatical analysis to analyze the grammatical structure of students' statements and understand the meaning of sentences. For example, the NLP unit uses semantic analysis to analyze the meaning of students' statements and detect signs of bullying or stress. For example, the NLP unit can use morphological analysis to divide students' statements into individual words and analyze the meaning of each word. For example, the NLP unit can use grammatical analysis to analyze the grammatical structure of students' statements and understand the meaning of sentences. For example, the NLP unit can use semantic analysis to analyze the meaning of students' statements and detect signs of bullying or stress. In this way, the NLP unit can detect signs of bullying or stress by analyzing the content of students' conversations. Some or all of the above processing in the NLP unit may be performed using, for example, generative AI, or without using generative AI. For example, the NLP department can input student speech data into a generating AI, which then analyzes the content of the speech to detect signs of bullying or stress.

[0035] The CV unit analyzes students' facial expressions and behavior using computer vision. The CV unit, for example, analyzes students' facial expressions using facial recognition technology and detects changes in emotion. The CV unit, for example, analyzes students' behavior using motion analysis technology and detects abnormal behavior. The CV unit, for example, analyzes students' facial expressions and behavior using machine learning algorithms and detects decreased motivation to learn or abnormal behavior. For example, the CV unit can analyze students' facial expressions using facial recognition technology and detect changes in emotion. The CV unit, for example, can analyze students' behavior using motion analysis technology and detect abnormal behavior. The CV unit, for example, can analyze students' facial expressions and behavior using machine learning algorithms and detect decreased motivation to learn or abnormal behavior. As a result, the CV unit can detect decreased motivation to learn or abnormal behavior by analyzing students' facial expressions and behavior. Some or all of the above processing in the CV unit may be performed using, for example, a generative AI, or without a generative AI. For example, the CV unit can input student facial expression data into a generative AI, which can analyze the facial expressions and detect changes in emotion.

[0036] The learning unit learns the tendencies of individual students and generates custom suggestions. The learning unit, for example, uses machine learning algorithms to learn student behavior data and generates individually customized suggestions. The learning unit, for example, analyzes students' past behavior data and predicts future behavior. The learning unit, for example, analyzes students' learning history and proposes an optimal learning plan. For example, the learning unit can use machine learning algorithms to learn student behavior data and generate individually customized suggestions. The learning unit, for example, can analyze students' past behavior data and predict future behavior. The learning unit, for example, can analyze students' learning history and propose an optimal learning plan. In this way, the learning unit can generate individually customized suggestions by learning student tendencies. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input student behavior data into a generative AI, which can learn the behavior data and generate custom suggestions.

[0037] The service provider can propose specific measures to teachers when signs of bullying are detected. For example, the service provider can suggest counseling to teachers when signs of bullying are detected. For example, the service provider can also suggest contacting parents to teachers when signs of bullying are detected. For example, the service provider can also suggest measures to be taken within the school to teachers when signs of bullying are detected. This enables a swift response by proposing specific measures to teachers when signs of bullying are detected. 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 bullying sign data into a generating AI, and the generating AI can propose specific measures.

[0038] The service provider can offer learning support suggestions to parents if a decline in learning motivation is detected. For example, if a decline in learning motivation is detected, the service provider can offer advice on home learning to parents. For example, if a decline in learning motivation is detected, the service provider can also offer supplementary lessons to parents. For example, if a decline in learning motivation is detected, the service provider can also offer improvements to the learning environment to parents. This allows for appropriate support by offering learning support suggestions to parents when a decline in learning motivation is detected. 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 data on the decline in learning motivation into a generating AI, and the generating AI can make suggestions for learning support.

[0039] The data collection unit can analyze students' past behavioral history and select the optimal data collection method. For example, the data collection unit can determine the target of data collection based on actions that students have frequently performed in the past. The data collection unit can also analyze students' past behavioral patterns and collect data at specific time periods. For example, the data collection unit can select a data collection method based on specific events or situations from students' past behavioral history. This allows for the selection of the optimal data collection method by analyzing students' past behavioral history. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input student behavioral history data into a generative AI, which can then select the optimal data collection method.

[0040] The data collection unit can filter data based on the student's current lesson content and areas of interest during data collection. For example, the data collection unit can prioritize collecting data related to the lesson content the student is currently taking. The data collection unit can also filter and collect highly relevant data based on the student's areas of interest. The data collection unit can also collect only the necessary data according to the student's current learning situation. This allows for the collection of highly relevant data by filtering the data based on the student's lesson content and areas of interest. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input student lesson content data into a generative AI, which can then filter and collect highly relevant data.

[0041] The data collection unit can prioritize the collection of highly relevant data by considering the students' seating position information during data collection. For example, the data collection unit can prioritize the collection of conversations with nearby students based on the students' seating position. The data collection unit can also prioritize the collection of actions within the students' field of vision based on the students' seating position. The data collection unit can also prioritize the collection of ambient sounds based on the students' seating position. In this way, by considering the students' seating position information, highly relevant data can be prioritized. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input student seating position data into a generative AI, which can then prioritize the collection of highly relevant data.

[0042] The data collection unit can analyze students' social media activities and collect relevant data during data collection. For example, the data collection unit can analyze the content of students' social media posts and collect relevant data. The data collection unit can also analyze students' social media friendships and collect relevant data. The data collection unit can also analyze students' social media activity time and determine the optimal timing for data collection. This allows for the collection of relevant data by analyzing students' social media activities. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input students' social media data into a generative AI, which can then collect relevant data.

[0043] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during the analysis. For example, the analysis unit can perform a detailed analysis on data with high importance. For example, the analysis unit can also perform a simplified analysis on data with low importance. The analysis unit can also determine the priority of the analysis according to the importance of the data. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data. 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 importance of the data into the generative AI, and the generative AI can adjust the level of detail of the analysis based on the importance.

[0044] The analysis unit can apply different analysis algorithms depending on the data category during analysis. For example, the analysis unit can apply a behavioral analysis algorithm to student behavioral data. For example, the analysis unit can also apply a natural language processing algorithm to student speech data. For example, the analysis unit can also apply a facial expression analysis algorithm to student facial expression data. By applying different analysis algorithms depending on the data category, highly accurate analysis becomes possible. 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 student behavioral data into a generative AI, and the generative AI can apply a behavioral analysis algorithm.

[0045] The analysis unit can determine the priority of analysis based on the data collection period during analysis. For example, the analysis unit may prioritize the analysis of recently collected data. The analysis unit can also analyze current data while referring to past data. The analysis unit can also adjust the priority of analysis according to the data collection period. This enables efficient analysis by determining the priority of analysis based on the data collection period. 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 data collection period into the generative AI, and the generative AI can determine the priority of analysis based on the collection period.

[0046] The analysis unit can adjust the order of analysis based on the relevance of the data during analysis. For example, the analysis unit may prioritize the analysis of highly relevant data. For example, the analysis unit may also postpone the analysis of less relevant data. The analysis unit can also adjust the order of analysis according to the relevance of the data. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the data. Some or all of the above-described processes 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 relevance of the data into a generative AI, and the generative AI can adjust the order of analysis based on the relevance.

[0047] The detection unit can improve detection accuracy by considering the interrelationships between data during detection. For example, the detection unit can improve detection accuracy by combining student behavior data and speech data. The detection unit can also improve detection accuracy by combining student facial expression data and behavior data. The detection unit can also improve detection accuracy by combining student speech data and facial expression data. In this way, detection accuracy can be improved by considering the interrelationships between data. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input multiple data into a generative AI, and the generative AI can improve detection accuracy by considering the interrelationships between the data.

[0048] The detection unit can perform detection while considering the student's attribute information. For example, the detection unit can adjust the detection criteria based on the student's age and gender. The detection unit can also adjust the detection criteria based on the student's grade and class. The detection unit can also adjust the detection criteria based on the student's past behavioral history. This makes it possible to perform more appropriate detection by considering the student's attribute information. Some or all of the above processing in the detection unit may be performed using, for example, a generating AI, or without a generating AI. For example, the detection unit can input the student's attribute information into a generating AI, and the generating AI can adjust the detection criteria based on the attribute information.

[0049] The detection unit can perform detection while considering the geographical distribution of the data. For example, the detection unit can detect problems in a specific area based on the student's seating position. The detection unit can also detect problems in a specific location based on the student's movement path. The detection unit can also detect problems in a specific region based on the student's activity range. In this way, problems in a specific area can be detected by considering the geographical distribution of the data. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input the student's geographical data into a generative AI, and the generative AI can detect problems while considering the geographical distribution.

[0050] The detection unit can improve the accuracy of detection by referring to relevant literature during detection. For example, the detection unit can detect signs of bullying by referring to literature on bullying. The detection unit can also detect a decline in motivation to learn by referring to literature on a decline in motivation to learn. The detection unit can also detect abnormal behavior by referring to literature on abnormal behavior. In this way, the accuracy of detection can be improved by referring to relevant literature. Some or all of the above processing in the detection unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the detection unit can input relevant literature data into a generating AI, and the generating AI can improve the accuracy of detection by referring to the literature.

[0051] The service provider can adjust the level of detail of alerts and suggestions based on the severity of the issue at the time of delivery. For example, the service provider can provide detailed alerts and suggestions for high-severity issues. For example, the service provider can also provide simplified alerts and suggestions for low-severity issues. The service provider can also prioritize alerts and suggestions according to the severity of the issue. This enables efficient information delivery by adjusting the level of detail of alerts and suggestions based on the severity of the issue. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the service provider can input issue severity data into a generative AI, and the generative AI can adjust the level of detail of alerts and suggestions based on the severity.

[0052] The service provider can apply different suggestion algorithms depending on the category of the problem at the time of provision. For example, the service provider can apply an anti-bullying suggestion algorithm to signs of bullying. For example, the service provider can apply a learning support suggestion algorithm to decreased motivation to learn. For example, the service provider can apply a behavior improvement suggestion algorithm to abnormal behavior. By applying different suggestion algorithms depending on the category of the problem, highly accurate suggestions become possible. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input problem category data into a generative AI, and the generative AI can apply a suggestion algorithm according to the category.

[0053] The service provider can prioritize alerts and suggestions based on when the problem occurred. For example, the service provider will prioritize alerts and suggestions for recently occurring problems. The service provider can also provide alerts and suggestions for current problems by referring to past problems. The service provider can also adjust the priority of alerts and suggestions according to when the problem occurred. This enables efficient information provision by prioritizing alerts and suggestions based on when the problem occurred. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the service provider can input problem occurrence data into a generative AI, and the generative AI can determine the priority of alerts and suggestions based on the occurrence date.

[0054] The service provider can adjust the order of alerts and suggestions based on the relevance of the issues at the time of delivery. For example, the service provider can prioritize providing alerts and suggestions for highly relevant issues. For example, the service provider can also postpone providing alerts and suggestions for less relevant issues. The service provider can also adjust the order of alerts and suggestions according to the relevance of the issues. This allows for efficient information delivery by adjusting the order of alerts and suggestions based on the relevance of the issues. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the service provider can input issue relevance data into a generative AI, and the generative AI can adjust the order of alerts and suggestions based on relevance.

[0055] The NLP unit can adjust the level of detail of its analysis based on specific keywords when analyzing conversation content. For example, the NLP unit will perform a detailed analysis for keywords related to bullying. For example, the NLP unit can perform a simplified analysis for keywords related to motivation to learn. The NLP unit can also determine the priority of analysis based on specific keywords. This allows for efficient analysis by adjusting the level of detail based on specific keywords. Some or all of the above processing in the NLP unit may be performed using, for example, a generative AI, or without a generative AI. For example, the NLP unit can input specific keyword data into a generative AI, which can then adjust the level of detail of its analysis based on the keywords.

[0056] The NLP unit can apply different analysis algorithms depending on the category of the conversation when analyzing the content of the conversation. For example, the NLP unit can apply a bullying analysis algorithm to a conversation related to bullying. For example, the NLP unit can apply a learning motivation analysis algorithm to a conversation related to learning motivation. For example, the NLP unit can apply an abnormal behavior analysis algorithm to a conversation related to abnormal behavior. By applying different analysis algorithms depending on the category of the conversation, highly accurate analysis becomes possible. Some or all of the above processing in the NLP unit may be performed using, for example, a generative AI, or without a generative AI. For example, the NLP unit can input conversation category data into a generative AI, and the generative AI can apply an analysis algorithm according to the category.

[0057] The NLP unit can determine the priority of analysis based on when the conversation occurred when analyzing conversation content. For example, the NLP unit may prioritize the analysis of recent conversation content. The NLP unit can also analyze current conversation content while referring to past conversation content. The NLP unit can also adjust the priority of analysis according to when the conversation occurred. This enables efficient analysis by determining the priority of analysis based on when the conversation occurred. Some or all of the above processing in the NLP unit may be performed using, for example, a generative AI, or without a generative AI. For example, the NLP unit can input conversation occurrence data into a generative AI, and the generative AI can determine the priority of analysis based on the occurrence time.

[0058] The NLP unit can adjust the order of analysis based on the relevance of the conversation content. For example, the NLP unit may prioritize the analysis of highly relevant conversation content. The NLP unit may also postpone the analysis of less relevant conversation content. The NLP unit can adjust the order of analysis according to the relevance of the conversation. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the conversation. Some or all of the above processing in the NLP unit may be performed using, for example, a generative AI, or without a generative AI. For example, the NLP unit can input conversation relevance data into a generative AI, which can then adjust the order of analysis based on the relevance.

[0059] The CV unit can adjust the level of detail of its analysis based on specific actions when analyzing facial expressions and behaviors. For example, the CV unit performs a detailed analysis of actions related to bullying. For example, the CV unit can perform a simplified analysis of actions related to motivation to learn. The CV unit can also determine the priority of analysis based on specific actions. This allows for efficient analysis by adjusting the level of detail based on specific actions. Some or all of the above processing in the CV unit may be performed using, for example, a generative AI, or without a generative AI. For example, the CV unit can input specific action data into a generative AI, which can then adjust the level of detail of its analysis based on the action.

[0060] The CV unit can apply different analysis algorithms depending on the category of behavior when analyzing facial expressions and actions. For example, the CV unit can apply a bullying analysis algorithm to behaviors related to bullying. For example, the CV unit can apply a learning motivation analysis algorithm to behaviors related to learning motivation. For example, the CV unit can apply an abnormal behavior analysis algorithm to behaviors related to abnormal behavior. By applying different analysis algorithms depending on the category of behavior, highly accurate analysis becomes possible. Some or all of the above processing in the CV unit may be performed using, for example, a generative AI, or without a generative AI. For example, the CV unit can input behavior category data into a generative AI, and the generative AI can apply an analysis algorithm according to the category.

[0061] The CV unit can determine the priority of analysis based on the timing of the actions when analyzing facial expressions and actions. For example, the CV unit may prioritize the analysis of recent actions. The CV unit can also analyze current actions while referring to past actions. The CV unit can also adjust the priority of analysis according to the timing of the actions. This enables efficient analysis by determining the priority of analysis based on the timing of the actions. Some or all of the above processing in the CV unit may be performed using, for example, a generative AI, or without a generative AI. For example, the CV unit can input action timing data into a generative AI, which can then determine the priority of analysis based on the timing.

[0062] The CV unit can adjust the order of analysis based on the relevance of actions when analyzing facial expressions and actions. For example, the CV unit can prioritize the analysis of highly relevant actions. For example, the CV unit can also postpone the analysis of less relevant actions. For example, the CV unit can adjust the order of analysis according to the relevance of actions. This allows for efficient analysis by adjusting the order of analysis based on the relevance of actions. Some or all of the above processing in the CV unit may be performed using, for example, a generative AI, or without a generative AI. For example, the CV unit can input action relevance data into a generative AI, and the generative AI can adjust the order of analysis based on the relevance.

[0063] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also adjust the parameters of the learning algorithm by referring to past learning data. The learning unit can also improve the accuracy of the learning algorithm by analyzing past learning data. In this way, the learning algorithm can be optimized and its accuracy improved by referring to past learning data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input past learning data into a generative AI, and the generative AI can optimize the learning algorithm by referring to the data.

[0064] The learning unit can weight the training data based on when the data was collected during training. For example, the learning unit can assign higher weights to recently collected data. For example, the learning unit can assign lower weights to older data. The learning unit can also adjust the weighting of the training data according to when the data was collected. This enables efficient training by weighting the training data based on when the data was collected. Some or all of the above processing in the learning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the learning unit can input data collection time data into a generative AI, and the generative AI can weight the training data based on the collection time.

[0065] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0066] The analysis unit can apply different analysis methods depending on the type of data when analyzing data provided by the collection unit. For example, it can analyze the content of speech using speech recognition technology for audio data, and analyze behavioral patterns using motion analysis technology for behavioral data. The analysis unit can also evaluate the reliability of the collected data and exclude unreliable data. Furthermore, the analysis unit can analyze long-term trends by considering the temporal changes in the collected data. This enables the analysis unit to perform advanced analysis that takes into account the type of data, reliability, and temporal changes.

[0067] The NLP (Neuro-Linguistic Programming) component can improve the accuracy of its analysis of students' conversations by considering the context of the conversation. For example, it can more accurately understand the meaning of a particular statement by referring to the preceding and following statements. The NLP component can also estimate the intent behind a statement by analyzing the tone and emotion of the conversation. Furthermore, the NLP component can recognize and appropriately analyze jargon and slang used in conversations. This enables the NLP component to perform advanced conversation analysis that takes context, emotion, and jargon into account.

[0068] The video conferencing (CV) unit can improve the accuracy of its analysis of students' facial expressions and behavior by integrating video data from multiple cameras. For example, it can combine footage shot from different angles to perform a more detailed analysis of facial expressions and behavior. The CV unit can also automatically extract specific actions or facial expressions from the video data and use them for analysis. Furthermore, the CV unit can track specific students within the video data and analyze changes in their behavior over time. This enables the CV unit to perform advanced video analysis by integrating multiple camera feeds, extracting specific actions and facial expressions, and analyzing them over time.

[0069] The learning department can analyze students' learning history to evaluate their learning progress and achievements. For example, it can analyze past test results and assignment submission status to assess learning progress. Furthermore, the learning department can analyze students' learning styles and strengths and weaknesses to propose individually optimized learning plans. In addition, based on students' learning history, the learning department can predict future learning outcomes and provide necessary support. This enables the learning department to provide advanced learning support by evaluating learning progress and achievements, proposing individually optimized learning plans, and predicting future learning outcomes.

[0070] When signs of bullying are detected, the service provider can improve the accuracy of its suggestions when proposing specific countermeasures to teachers by referring to past cases and successful examples. For example, it can refer to past cases where similar signs of bullying were detected and propose effective countermeasures. The service provider can also adjust the content and urgency of the suggestions according to the severity of the signs of bullying. Furthermore, the service provider can propose customized countermeasures that take into account the individual circumstances of the student in whom signs of bullying were detected. This allows the service provider to refer to past cases and successful examples, adjust the content of the suggestions according to the severity, and provide sophisticated countermeasures that take individual circumstances into account.

[0071] The following briefly describes the processing flow for example form 1.

[0072] Step 1: The data collection unit collects data from within the classroom. This data includes student behavior data, speech data, and facial expression data. The data collection unit uses sensors and cameras installed in the classroom to collect data. It can also collect student speech using microphones and save it as audio data. Furthermore, it can film student behavior with cameras and save it as video data. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit uses natural language processing (NLP) technology to analyze the content of students' statements and computer vision technology to analyze students' facial expressions and behavior. Furthermore, it uses machine learning algorithms to analyze the collected data and detect signs of problems. Step 3: The detection unit detects signs of a problem based on the data analyzed by the analysis unit. For example, it may detect signs of bullying, decreased motivation to learn, or abnormal behavior. Step 4: The provisioning unit provides alerts and suggestions to teachers and parents based on the signs of problems detected by the detection unit. For example, if signs of bullying are detected, specific measures are suggested to the teacher, and if a decline in motivation to learn is detected, suggestions for learning support are made to the parents.

[0073] (Example of form 2) The AI ​​agent system according to an embodiment of the present invention is a system that detects and analyzes problems occurring among students in schools and classrooms at an early stage and proposes appropriate countermeasures to teachers and parents. This AI agent system collects and analyzes classroom data (student behavior, speech, facial expressions, etc.) in real time, detects signs of problems, and provides alerts and suggestions to teachers and parents. For example, the AI ​​agent system uses natural language processing (NLP) to analyze the content of students' conversations and detect signs of bullying or stress. The AI ​​agent system also uses computer vision to analyze students' facial expressions and behavior and detect decreased motivation to learn or abnormal behavior. As a result, the AI ​​agent system can catch signs of problems at an early stage. Furthermore, based on the detected signs of problems, the AI ​​agent system provides alerts and suggestions to teachers and parents at an appropriate time. For example, if signs of bullying are detected, the AI ​​agent system proposes specific countermeasures to teachers. Also, if decreased motivation to learn is detected, the AI ​​agent system proposes learning support to parents. In this way, the AI ​​agent system supports teachers and parents in taking quick and accurate countermeasures. This provides a safe and secure learning environment and enables students to realize their maximum potential. Furthermore, the AI ​​agent system can support teachers and parents in taking quick and accurate measures, thereby improving the efficiency and quality of education. This allows the AI ​​agent system to detect and analyze problems occurring among students in schools and classrooms at an early stage and propose appropriate solutions to teachers and parents.

[0074] The AI ​​agent system according to this embodiment comprises a collection unit, an analysis unit, a detection unit, and a provision unit. The collection unit collects data from within the classroom. Classroom data includes, but is not limited to, student behavior data, speech data, and facial expression data. The collection unit collects data using, for example, sensors and cameras installed in the classroom. The collection unit can also collect students' speech using a microphone and save it as audio data. Furthermore, the collection unit can film students' behavior with a camera and save it as video data. For example, the collection unit monitors students' behavior in real time using multiple cameras in the classroom and collects behavior data. The collection unit records students' speech using a microphone and saves it as audio data. The collection unit collects temperature data in the classroom using, for example, a temperature sensor. The analysis unit analyzes the data collected by the collection unit. The analysis unit analyzes the content of students' speech using, for example, natural language processing (NLP) technology. The analysis unit analyzes students' facial expressions and behavior using, for example, computer vision technology. The analysis unit analyzes collected data using, for example, machine learning algorithms to detect signs of problems. For example, the analysis unit analyzes students' statements using NLP technology to detect signs of bullying or stress. The analysis unit analyzes students' facial expressions and behavior using, for example, computer vision technology to detect decreased motivation to learn or abnormal behavior. The analysis unit analyzes collected data using, for example, machine learning algorithms to detect signs of problems. The detection unit detects signs of problems based on the data analyzed by the analysis unit. For example, the detection unit detects signs of bullying. For example, the detection unit detects decreased motivation to learn. For example, the detection unit detects abnormal behavior based on the data analyzed by the analysis unit. For example, the detection unit detects signs of bullying based on the data analyzed by the analysis unit. For example, the detection unit detects decreased motivation to learn based on the data analyzed by the analysis unit. For example, the detection unit detects abnormal behavior based on the data analyzed by the analysis unit. The provision unit provides alerts and suggestions to teachers and parents based on the signs of problems detected by the detection unit. For example, if signs of bullying are detected, the provision unit proposes specific countermeasures to teachers.For example, if a decline in motivation to learn is detected, the service provider will suggest learning support to the parents. For example, if abnormal behavior is detected, the service provider will suggest specific countermeasures to the teacher. For example, if signs of bullying are detected, the service provider will suggest counseling to the teacher. For example, if a decline in motivation to learn is detected, the service provider will provide advice on home learning to the parents. For example, if abnormal behavior is detected, the service provider will suggest behavioral improvement to the teacher. In this way, the AI ​​agent system according to the embodiment can collect, analyze, detect, and provide data from within the classroom, thereby enabling early detection of signs of problems and the suggestion of appropriate countermeasures.

[0075] The data collection unit collects data from within the classroom. This data includes, but is not limited to, student behavior data, speech data, and facial expression data. The data collection unit uses sensors and cameras installed in the classroom to collect data. Specifically, it uses multiple cameras in the classroom to monitor student behavior in real time and collect behavioral data. This allows the unit to understand what kind of behavior students are exhibiting, for example, whether they are concentrating during class, talking to other students, or engaging in inappropriate behavior. The data collection unit also uses microphones to record students' speech and saves it as audio data. This allows the unit to understand what students are saying during class, for example, whether they are asking questions, talking to other students, or talking about things unrelated to the lesson. Furthermore, the data collection unit uses temperature sensors to collect temperature data within the classroom. This allows the unit to understand whether the classroom environment is suitable for student learning, for example, whether the temperature and humidity are appropriate. The data collection unit centrally manages this data and can collaborate with other systems and departments as needed. For example, the collected data can be stored on a cloud server and made accessible to the analysis and detection units. Furthermore, by adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions become possible. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0076] The analysis unit analyzes the data collected by the collection unit. The analysis unit uses natural language processing (NLP) technology to analyze the content of students' statements. Specifically, it uses NLP technology to convert students' statements into text data and analyzes its content. This allows it to understand what students are saying in class, for example, whether they are asking questions, talking to other students, or talking about things unrelated to the lesson. The analysis unit also uses computer vision technology to analyze students' facial expressions and behavior. Specifically, it analyzes camera footage to recognize students' facial expressions and behavior. This allows it to understand what kind of expressions students have in class, for example, whether they are concentrating, tired, or unhappy. Furthermore, the analysis unit uses machine learning algorithms to analyze the collected data and detect signs of problems. Specifically, it uses models trained on past data to analyze newly collected data and detect signs of bullying and stress. This allows the analysis unit to quickly and accurately analyze the collected data and understand the surrounding risk situation in real time. Furthermore, the analysis unit can also utilize past data and statistical information to perform long-term risk assessments and trend analyses. For example, based on past data, it can predict fluctuations in risk for specific students or classes and formulate future countermeasures. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns or abnormal data, issuing early warnings. This allows the analysis unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, improving the overall reliability and safety of the system.

[0077] The detection unit detects signs of a problem based on data analyzed by the analysis unit. Specifically, to detect signs of bullying, it uses NLP technology to analyze students' statements and detect keywords and phrases related to bullying. It also uses computer vision technology to analyze students' facial expressions and behavior to detect signs of bullying. For example, it can detect when a student is acting aggressively towards other students or when a particular student is isolated. Furthermore, it uses machine learning algorithms to analyze the collected data and detect decreased motivation to learn or abnormal behavior. For example, it can detect when a student is not concentrating during class or has lost interest in the lessons. As a result, the detection unit can quickly and accurately detect signs of bullying, decreased motivation to learn, and abnormal behavior based on data analyzed by the analysis unit. In addition, the detection unit can utilize historical data and statistical information to perform long-term risk assessments and trend analyses. For example, it can predict fluctuations in risk for specific students or classes based on historical data and formulate future countermeasures. Furthermore, the detection unit can use anomaly detection algorithms to detect unusual patterns or abnormal data and issue warnings early. This allows the detection unit to not only grasp the situation in real time, but also to handle long-term risk management and anomaly detection, thereby improving the reliability and safety of the entire system.

[0078] The service provider provides alerts and suggestions to teachers and parents based on the signs of problems detected by the detection unit. Specifically, if signs of bullying are detected, the service provider will propose specific countermeasures to teachers. For example, if signs of bullying are detected, the service provider will suggest counseling to teachers. Also, if a decline in motivation to learn is detected, the service provider will suggest learning support to parents. For example, if a decline in motivation to learn is detected, the service provider will provide advice on home learning to parents. Furthermore, if abnormal behavior is detected, the service provider will propose specific countermeasures to teachers. For example, if abnormal behavior is detected, the service provider will suggest behavioral improvement to teachers. The service provider can use multiple communication methods to deliver these alerts and suggestions quickly and accurately. For example, it can use email, SMS, and app notifications to deliver alerts and suggestions to teachers and parents. The service provider can also collect user feedback and continuously improve the accuracy and effectiveness of the content provided. For example, it can review and improve the content based on feedback from teachers and parents who have received alerts and suggestions. This allows the service provider to provide alerts and suggestions to teachers and parents quickly and accurately, supporting the early detection and countermeasures of problems. In addition, the service provider can utilize historical data and statistical information to conduct long-term risk assessments and trend analyses. For example, based on past data, the system can predict fluctuations in risk for specific students or classes and formulate future countermeasures. This allows the service provider to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, thereby improving the reliability and security of the entire system.

[0079] The NLP unit analyzes the content of students' conversations using natural language processing. For example, the NLP unit uses morphological analysis to divide students' statements into individual words and analyzes the meaning of each word. For example, the NLP unit uses grammatical analysis to analyze the grammatical structure of students' statements and understand the meaning of sentences. For example, the NLP unit uses semantic analysis to analyze the meaning of students' statements and detect signs of bullying or stress. For example, the NLP unit can use morphological analysis to divide students' statements into individual words and analyze the meaning of each word. For example, the NLP unit can use grammatical analysis to analyze the grammatical structure of students' statements and understand the meaning of sentences. For example, the NLP unit can use semantic analysis to analyze the meaning of students' statements and detect signs of bullying or stress. In this way, the NLP unit can detect signs of bullying or stress by analyzing the content of students' conversations. Some or all of the above processing in the NLP unit may be performed using, for example, generative AI, or without using generative AI. For example, the NLP department can input student speech data into a generating AI, which then analyzes the content of the speech to detect signs of bullying or stress.

[0080] The CV unit analyzes students' facial expressions and behavior using computer vision. The CV unit, for example, analyzes students' facial expressions using facial recognition technology and detects changes in emotion. The CV unit, for example, analyzes students' behavior using motion analysis technology and detects abnormal behavior. The CV unit, for example, analyzes students' facial expressions and behavior using machine learning algorithms and detects decreased motivation to learn or abnormal behavior. For example, the CV unit can analyze students' facial expressions using facial recognition technology and detect changes in emotion. The CV unit, for example, can analyze students' behavior using motion analysis technology and detect abnormal behavior. The CV unit, for example, can analyze students' facial expressions and behavior using machine learning algorithms and detect decreased motivation to learn or abnormal behavior. As a result, the CV unit can detect decreased motivation to learn or abnormal behavior by analyzing students' facial expressions and behavior. Some or all of the above processing in the CV unit may be performed using, for example, a generative AI, or without a generative AI. For example, the CV unit can input student facial expression data into a generative AI, which can analyze the facial expressions and detect changes in emotion.

[0081] The learning unit learns the tendencies of individual students and generates custom suggestions. The learning unit, for example, uses machine learning algorithms to learn student behavior data and generates individually customized suggestions. The learning unit, for example, analyzes students' past behavior data and predicts future behavior. The learning unit, for example, analyzes students' learning history and proposes an optimal learning plan. For example, the learning unit can use machine learning algorithms to learn student behavior data and generate individually customized suggestions. The learning unit, for example, can analyze students' past behavior data and predict future behavior. The learning unit, for example, can analyze students' learning history and propose an optimal learning plan. In this way, the learning unit can generate individually customized suggestions by learning student tendencies. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input student behavior data into a generative AI, which can learn the behavior data and generate custom suggestions.

[0082] The service provider can propose specific measures to teachers when signs of bullying are detected. For example, the service provider can suggest counseling to teachers when signs of bullying are detected. For example, the service provider can also suggest contacting parents to teachers when signs of bullying are detected. For example, the service provider can also suggest measures to be taken within the school to teachers when signs of bullying are detected. This enables a swift response by proposing specific measures to teachers when signs of bullying are detected. 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 bullying sign data into a generating AI, and the generating AI can propose specific measures.

[0083] The service provider can offer learning support suggestions to parents if a decline in learning motivation is detected. For example, if a decline in learning motivation is detected, the service provider can offer advice on home learning to parents. For example, if a decline in learning motivation is detected, the service provider can also offer supplementary lessons to parents. For example, if a decline in learning motivation is detected, the service provider can also offer improvements to the learning environment to parents. This allows for appropriate support by offering learning support suggestions to parents when a decline in learning motivation is detected. 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 data on the decline in learning motivation into a generating AI, and the generating AI can make suggestions for learning support.

[0084] The data collection unit can estimate students' emotions and adjust the timing of data collection based on the estimated emotions. For example, if a student is stressed, the data collection unit can increase the frequency of data collection and collect more detailed data. For example, if a student is relaxed, the data collection unit can decrease the frequency of data collection and collect only the minimum necessary data. For example, if a student is excited, the data collection unit can focus on specific behaviors or statements to collect data. This allows for more appropriate data collection by adjusting the timing of data collection based on students' emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can input student emotion data into a generative AI, which can estimate emotions and adjust the timing of data collection.

[0085] The data collection unit can analyze students' past behavioral history and select the optimal data collection method. For example, the data collection unit can determine the target of data collection based on actions that students have frequently performed in the past. The data collection unit can also analyze students' past behavioral patterns and collect data at specific time periods. For example, the data collection unit can select a data collection method based on specific events or situations from students' past behavioral history. This allows for the selection of the optimal data collection method by analyzing students' past behavioral history. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input student behavioral history data into a generative AI, which can then select the optimal data collection method.

[0086] The data collection unit can filter data based on the student's current lesson content and areas of interest during data collection. For example, the data collection unit can prioritize collecting data related to the lesson content the student is currently taking. The data collection unit can also filter and collect highly relevant data based on the student's areas of interest. The data collection unit can also collect only the necessary data according to the student's current learning situation. This allows for the collection of highly relevant data by filtering the data based on the student's lesson content and areas of interest. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input student lesson content data into a generative AI, which can then filter and collect highly relevant data.

[0087] The data collection unit can estimate students' emotions and prioritize the data to collect based on the estimated emotions. For example, if a student is stressed, the data collection unit will prioritize collecting data related to stress. For example, if a student is relaxed, the data collection unit may prioritize collecting data related to motivation to learn. For example, if a student is excited, the data collection unit may prioritize collecting data related to behavior and speech. This allows for the priority collection of important data by prioritizing data based on students' emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can input student emotion data into a generative AI, which can estimate emotions and determine the priority of the data to collect.

[0088] The data collection unit can prioritize the collection of highly relevant data by considering the students' seating position information during data collection. For example, the data collection unit can prioritize the collection of conversations with nearby students based on the students' seating position. The data collection unit can also prioritize the collection of actions within the students' field of vision based on the students' seating position. The data collection unit can also prioritize the collection of ambient sounds based on the students' seating position. In this way, by considering the students' seating position information, highly relevant data can be prioritized. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input student seating position data into a generative AI, which can then prioritize the collection of highly relevant data.

[0089] The data collection unit can analyze students' social media activities and collect relevant data during data collection. For example, the data collection unit can analyze the content of students' social media posts and collect relevant data. The data collection unit can also analyze students' social media friendships and collect relevant data. The data collection unit can also analyze students' social media activity time and determine the optimal timing for data collection. This allows for the collection of relevant data by analyzing students' social media activities. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input students' social media data into a generative AI, which can then collect relevant data.

[0090] The analysis unit can estimate the student's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the student is stressed, the analysis unit can display the analysis results in a simple and easy-to-understand format. For example, if the student is relaxed, the analysis unit can also display detailed analysis results. For example, if the student is excited, the analysis unit can also display the analysis results in a visually stimulating format. This allows for the provision of more appropriate analysis results by adjusting the presentation of the analysis based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit can input student emotion data into a generative AI, which can estimate emotions and adjust the presentation of the analysis.

[0091] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during the analysis. For example, the analysis unit can perform a detailed analysis on data with high importance. For example, the analysis unit can also perform a simplified analysis on data with low importance. The analysis unit can also determine the priority of the analysis according to the importance of the data. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data. 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 importance of the data into the generative AI, and the generative AI can adjust the level of detail of the analysis based on the importance.

[0092] The analysis unit can apply different analysis algorithms depending on the data category during analysis. For example, the analysis unit can apply a behavioral analysis algorithm to student behavioral data. For example, the analysis unit can also apply a natural language processing algorithm to student speech data. For example, the analysis unit can also apply a facial expression analysis algorithm to student facial expression data. By applying different analysis algorithms depending on the data category, highly accurate analysis becomes possible. 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 student behavioral data into a generative AI, and the generative AI can apply a behavioral analysis algorithm.

[0093] The analysis unit can estimate the student's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the student is stressed, the analysis unit can perform a short, concise analysis. If the student is relaxed, the analysis unit can perform a detailed analysis. If the student is excited, the analysis unit can perform an analysis in a visually stimulating format. By adjusting the length of the analysis based on the student's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input student emotion data into a generative AI, which can estimate the emotions and adjust the length of the analysis.

[0094] The analysis unit can determine the priority of analysis based on the data collection period during analysis. For example, the analysis unit may prioritize the analysis of recently collected data. The analysis unit can also analyze current data while referring to past data. The analysis unit can also adjust the priority of analysis according to the data collection period. This enables efficient analysis by determining the priority of analysis based on the data collection period. 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 data collection period into the generative AI, and the generative AI can determine the priority of analysis based on the collection period.

[0095] The analysis unit can adjust the order of analysis based on the relevance of the data during analysis. For example, the analysis unit may prioritize the analysis of highly relevant data. For example, the analysis unit may also postpone the analysis of less relevant data. The analysis unit can also adjust the order of analysis according to the relevance of the data. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the data. Some or all of the above-described processes 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 relevance of the data into a generative AI, and the generative AI can adjust the order of analysis based on the relevance.

[0096] The detection unit can estimate a student's emotions and adjust the detection criteria for signs of problems based on the estimated emotions. For example, if a student is stressed, the detection unit will prioritize detecting signs related to stress. For example, if a student is relaxed, the detection unit may also prioritize detecting signs related to motivation to learn. For example, if a student is excited, the detection unit may also prioritize detecting signs related to behavior or speech. By adjusting the detection criteria based on the student's emotions, more appropriate signs of problems can be detected. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input student emotion data into a generative AI, which can estimate emotions and adjust the detection criteria.

[0097] The detection unit can improve detection accuracy by considering the interrelationships between data during detection. For example, the detection unit can improve detection accuracy by combining student behavior data and speech data. The detection unit can also improve detection accuracy by combining student facial expression data and behavior data. The detection unit can also improve detection accuracy by combining student speech data and facial expression data. In this way, detection accuracy can be improved by considering the interrelationships between data. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input multiple data into a generative AI, and the generative AI can improve detection accuracy by considering the interrelationships between the data.

[0098] The detection unit can perform detection while considering the student's attribute information. For example, the detection unit can adjust the detection criteria based on the student's age and gender. The detection unit can also adjust the detection criteria based on the student's grade and class. The detection unit can also adjust the detection criteria based on the student's past behavioral history. This makes it possible to perform more appropriate detection by considering the student's attribute information. Some or all of the above processing in the detection unit may be performed using, for example, a generating AI, or without a generating AI. For example, the detection unit can input the student's attribute information into a generating AI, and the generating AI can adjust the detection criteria based on the attribute information.

[0099] The detection unit can estimate a student's emotions and adjust the display order of the detection results based on the estimated emotions. For example, if a student is feeling stressed, the detection unit can prioritize displaying detection results related to stress. For example, if a student is relaxed, the detection unit can prioritize displaying detection results related to motivation to learn. For example, if a student is excited, the detection unit can prioritize displaying detection results related to behavior or speech. By adjusting the display order of detection results based on the student's emotions, more appropriate information can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input student emotion data into a generative AI, which can estimate emotions and adjust the display order of the detection results.

[0100] The detection unit can perform detection while considering the geographical distribution of the data. For example, the detection unit can detect problems in a specific area based on the student's seating position. The detection unit can also detect problems in a specific location based on the student's movement path. The detection unit can also detect problems in a specific region based on the student's activity range. In this way, problems in a specific area can be detected by considering the geographical distribution of the data. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input the student's geographical data into a generative AI, and the generative AI can detect problems while considering the geographical distribution.

[0101] The detection unit can improve the accuracy of detection by referring to relevant literature during detection. For example, the detection unit can detect signs of bullying by referring to literature on bullying. The detection unit can also detect a decline in motivation to learn by referring to literature on a decline in motivation to learn. The detection unit can also detect abnormal behavior by referring to literature on abnormal behavior. In this way, the accuracy of detection can be improved by referring to relevant literature. Some or all of the above processing in the detection unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the detection unit can input relevant literature data into a generating AI, and the generating AI can improve the accuracy of detection by referring to the literature.

[0102] The service provider can estimate a student's emotions and adjust the way alerts and suggestions are presented based on the estimated emotions. For example, if a student is stressed, the service provider can provide a simple and easy-to-understand alert. If a student is relaxed, the service provider can also provide detailed suggestions. If a student is excited, the service provider can also provide a visually stimulating alert. This allows for more appropriate information to be provided by adjusting the way alerts and suggestions are presented based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the service provider may be performed using AI or not. For example, the service provider can input student emotion data into a generative AI, which can estimate the emotions and adjust the way alerts and suggestions are presented.

[0103] The service provider can adjust the level of detail of alerts and suggestions based on the severity of the issue at the time of delivery. For example, the service provider can provide detailed alerts and suggestions for high-severity issues. For example, the service provider can also provide simplified alerts and suggestions for low-severity issues. The service provider can also prioritize alerts and suggestions according to the severity of the issue. This enables efficient information delivery by adjusting the level of detail of alerts and suggestions based on the severity of the issue. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the service provider can input issue severity data into a generative AI, and the generative AI can adjust the level of detail of alerts and suggestions based on the severity.

[0104] The service provider can apply different suggestion algorithms depending on the category of the problem at the time of provision. For example, the service provider can apply an anti-bullying suggestion algorithm to signs of bullying. For example, the service provider can apply a learning support suggestion algorithm to decreased motivation to learn. For example, the service provider can apply a behavior improvement suggestion algorithm to abnormal behavior. By applying different suggestion algorithms depending on the category of the problem, highly accurate suggestions become possible. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input problem category data into a generative AI, and the generative AI can apply a suggestion algorithm according to the category.

[0105] The service provider can estimate a student's emotions and adjust the length of alerts and suggestions based on the estimated emotions. For example, if a student is stressed, the service provider can provide a short, concise alert. If a student is relaxed, the service provider can also provide a detailed suggestion. If a student is excited, the service provider can also provide a visually stimulating alert. By adjusting the length of alerts and suggestions based on the student's emotions, more appropriate information can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the service provider may be performed using AI or not. For example, the service provider can input student emotion data into a generative AI, which can estimate the emotions and adjust the length of alerts and suggestions.

[0106] The service provider can prioritize alerts and suggestions based on when the problem occurred. For example, the service provider will prioritize alerts and suggestions for recently occurring problems. The service provider can also provide alerts and suggestions for current problems by referring to past problems. The service provider can also adjust the priority of alerts and suggestions according to when the problem occurred. This enables efficient information provision by prioritizing alerts and suggestions based on when the problem occurred. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the service provider can input problem occurrence data into a generative AI, and the generative AI can determine the priority of alerts and suggestions based on the occurrence date.

[0107] The service provider can adjust the order of alerts and suggestions based on the relevance of the issues at the time of delivery. For example, the service provider can prioritize providing alerts and suggestions for highly relevant issues. For example, the service provider can also postpone providing alerts and suggestions for less relevant issues. The service provider can also adjust the order of alerts and suggestions according to the relevance of the issues. This allows for efficient information delivery by adjusting the order of alerts and suggestions based on the relevance of the issues. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the service provider can input issue relevance data into a generative AI, and the generative AI can adjust the order of alerts and suggestions based on relevance.

[0108] The NLP unit can estimate a student's emotions and adjust the analysis method of the conversation content based on the estimated emotions. For example, if a student is stressed, the NLP unit will prioritize analyzing keywords related to stress. For example, if a student is relaxed, the NLP unit can also analyze detailed conversation content. For example, if a student is excited, the NLP unit can also prioritize analyzing keywords related to behavior and speech. By adjusting the analysis method of the conversation content based on the student's emotions, a more appropriate analysis becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the NLP unit may be performed using AI, for example, or without AI. For example, the NLP unit can input student emotion data into a generative AI, which can estimate emotions and adjust the analysis method of the conversation content.

[0109] The NLP unit can adjust the level of detail of its analysis based on specific keywords when analyzing conversation content. For example, the NLP unit will perform a detailed analysis for keywords related to bullying. For example, the NLP unit can perform a simplified analysis for keywords related to motivation to learn. The NLP unit can also determine the priority of analysis based on specific keywords. This allows for efficient analysis by adjusting the level of detail based on specific keywords. Some or all of the above processing in the NLP unit may be performed using, for example, a generative AI, or without a generative AI. For example, the NLP unit can input specific keyword data into a generative AI, which can then adjust the level of detail of its analysis based on the keywords.

[0110] The NLP unit can apply different analysis algorithms depending on the category of the conversation when analyzing the content of the conversation. For example, the NLP unit can apply a bullying analysis algorithm to a conversation related to bullying. For example, the NLP unit can apply a learning motivation analysis algorithm to a conversation related to learning motivation. For example, the NLP unit can apply an abnormal behavior analysis algorithm to a conversation related to abnormal behavior. By applying different analysis algorithms depending on the category of the conversation, highly accurate analysis becomes possible. Some or all of the above processing in the NLP unit may be performed using, for example, a generative AI, or without a generative AI. For example, the NLP unit can input conversation category data into a generative AI, and the generative AI can apply an analysis algorithm according to the category.

[0111] The NLP unit can estimate a student's emotions and prioritize the analysis of conversation content based on the estimated emotions. For example, if a student is stressed, the NLP unit will prioritize analyzing conversation content related to stress. If a student is relaxed, the NLP unit can also analyze detailed conversation content. If a student is excited, the NLP unit can also prioritize analyzing conversation content related to behavior or speech. This allows for more appropriate analysis by prioritizing the analysis of conversation content based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the NLP unit may be performed using AI or not. For example, the NLP unit can input student emotion data into a generative AI, which can estimate emotions and determine the priority of conversation content analysis.

[0112] The NLP unit can determine the priority of analysis based on when the conversation occurred when analyzing conversation content. For example, the NLP unit may prioritize the analysis of recent conversation content. The NLP unit can also analyze current conversation content while referring to past conversation content. The NLP unit can also adjust the priority of analysis according to when the conversation occurred. This enables efficient analysis by determining the priority of analysis based on when the conversation occurred. Some or all of the above processing in the NLP unit may be performed using, for example, a generative AI, or without a generative AI. For example, the NLP unit can input conversation occurrence data into a generative AI, and the generative AI can determine the priority of analysis based on the occurrence time.

[0113] The NLP unit can adjust the order of analysis based on the relevance of the conversation content. For example, the NLP unit may prioritize the analysis of highly relevant conversation content. The NLP unit may also postpone the analysis of less relevant conversation content. The NLP unit can adjust the order of analysis according to the relevance of the conversation. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the conversation. Some or all of the above processing in the NLP unit may be performed using, for example, a generative AI, or without a generative AI. For example, the NLP unit can input conversation relevance data into a generative AI, which can then adjust the order of analysis based on the relevance.

[0114] The CV unit can estimate a student's emotions and adjust the analysis method of facial expressions and behaviors based on the estimated emotions. For example, if a student is stressed, the CV unit will prioritize analyzing stress-related facial expressions and behaviors. For example, if a student is relaxed, the CV unit can also analyze detailed facial expressions and behaviors. For example, if a student is excited, the CV unit can also prioritize analyzing facial expressions and behaviors related to their actions and statements. This allows for more appropriate analysis by adjusting the analysis method of facial expressions and behaviors based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the CV unit may be performed using AI, or not using AI. For example, the CV unit can input student emotion data into a generative AI, which can estimate emotions and adjust the analysis method of facial expressions and behaviors.

[0115] The CV unit can adjust the level of detail of its analysis based on specific actions when analyzing facial expressions and behaviors. For example, the CV unit performs a detailed analysis of actions related to bullying. For example, the CV unit can perform a simplified analysis of actions related to motivation to learn. The CV unit can also determine the priority of analysis based on specific actions. This allows for efficient analysis by adjusting the level of detail based on specific actions. Some or all of the above processing in the CV unit may be performed using, for example, a generative AI, or without a generative AI. For example, the CV unit can input specific action data into a generative AI, which can then adjust the level of detail of its analysis based on the action.

[0116] The CV unit can apply different analysis algorithms depending on the category of behavior when analyzing facial expressions and actions. For example, the CV unit can apply a bullying analysis algorithm to behaviors related to bullying. For example, the CV unit can apply a learning motivation analysis algorithm to behaviors related to learning motivation. For example, the CV unit can apply an abnormal behavior analysis algorithm to behaviors related to abnormal behavior. By applying different analysis algorithms depending on the category of behavior, highly accurate analysis becomes possible. Some or all of the above processing in the CV unit may be performed using, for example, a generative AI, or without a generative AI. For example, the CV unit can input behavior category data into a generative AI, and the generative AI can apply an analysis algorithm according to the category.

[0117] The CV unit can estimate a student's emotions and determine the priority of facial expression and behavior analysis based on the estimated emotions. For example, if a student is stressed, the CV unit will prioritize analyzing stress-related facial expressions and behaviors. For example, if a student is relaxed, the CV unit can also analyze detailed facial expressions and behaviors. For example, if a student is excited, the CV unit can also prioritize analyzing facial expressions and behaviors related to their actions and statements. This allows for more appropriate analysis by prioritizing the analysis of facial expressions and behaviors based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the CV unit may be performed using AI, or not using AI. For example, the CV unit can input student emotion data into a generative AI, which can estimate emotions and determine the priority of facial expression and behavior analysis.

[0118] The CV unit can determine the priority of analysis based on the timing of the actions when analyzing facial expressions and actions. For example, the CV unit may prioritize the analysis of recent actions. The CV unit can also analyze current actions while referring to past actions. The CV unit can also adjust the priority of analysis according to the timing of the actions. This enables efficient analysis by determining the priority of analysis based on the timing of the actions. Some or all of the above processing in the CV unit may be performed using, for example, a generative AI, or without a generative AI. For example, the CV unit can input action timing data into a generative AI, which can then determine the priority of analysis based on the timing.

[0119] The CV unit can adjust the order of analysis based on the relevance of actions when analyzing facial expressions and actions. For example, the CV unit can prioritize the analysis of highly relevant actions. For example, the CV unit can also postpone the analysis of less relevant actions. For example, the CV unit can adjust the order of analysis according to the relevance of actions. This allows for efficient analysis by adjusting the order of analysis based on the relevance of actions. Some or all of the above processing in the CV unit may be performed using, for example, a generative AI, or without a generative AI. For example, the CV unit can input action relevance data into a generative AI, and the generative AI can adjust the order of analysis based on the relevance.

[0120] The learning unit can estimate a student's emotions and select training data based on the estimated emotions. For example, if a student is stressed, the learning unit will prioritize learning data related to stress. For example, if a student is relaxed, the learning unit can also learn detailed data. For example, if a student is excited, the learning unit can also prioritize learning data related to behavior and speech. This allows for more appropriate learning by selecting training data based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input student emotion data into a generative AI, which can estimate emotions and select training data.

[0121] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also adjust the parameters of the learning algorithm by referring to past learning data. The learning unit can also improve the accuracy of the learning algorithm by analyzing past learning data. In this way, the learning algorithm can be optimized and its accuracy improved by referring to past learning data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input past learning data into a generative AI, and the generative AI can optimize the learning algorithm by referring to the data.

[0122] The learning unit can estimate a student's emotions and adjust the frequency of learning based on the estimated emotions. For example, if a student is stressed, the learning unit can reduce the frequency of learning. For example, if a student is relaxed, the learning unit can increase the frequency of learning. For example, if a student is excited, the learning unit can adjust the frequency of learning. This allows for more appropriate learning by adjusting the frequency of learning based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not using AI. For example, the learning unit can input student emotion data into a generative AI, which can estimate the emotions and adjust the frequency of learning.

[0123] The learning unit can weight the training data based on when the data was collected during training. For example, the learning unit can assign higher weights to recently collected data. For example, the learning unit can assign lower weights to older data. The learning unit can also adjust the weighting of the training data according to when the data was collected. This enables efficient training by weighting the training data based on when the data was collected. Some or all of the above processing in the learning unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the learning unit can input data collection time data into a generative AI, and the generative AI can weight the training data based on the collection time.

[0124] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0125] The analysis unit can apply different analysis methods depending on the type of data when analyzing data provided by the collection unit. For example, it can analyze the content of speech using speech recognition technology for audio data, and analyze behavioral patterns using motion analysis technology for behavioral data. The analysis unit can also evaluate the reliability of the collected data and exclude unreliable data. Furthermore, the analysis unit can analyze long-term trends by considering the temporal changes in the collected data. This enables the analysis unit to perform advanced analysis that takes into account the type of data, reliability, and temporal changes.

[0126] The NLP (Neuro-Linguistic Programming) component can improve the accuracy of its analysis of students' conversations by considering the context of the conversation. For example, it can more accurately understand the meaning of a particular statement by referring to the preceding and following statements. The NLP component can also estimate the intent behind a statement by analyzing the tone and emotion of the conversation. Furthermore, the NLP component can recognize and appropriately analyze jargon and slang used in conversations. This enables the NLP component to perform advanced conversation analysis that takes context, emotion, and jargon into account.

[0127] The video conferencing (CV) unit can improve the accuracy of its analysis of students' facial expressions and behavior by integrating video data from multiple cameras. For example, it can combine footage shot from different angles to perform a more detailed analysis of facial expressions and behavior. The CV unit can also automatically extract specific actions or facial expressions from the video data and use them for analysis. Furthermore, the CV unit can track specific students within the video data and analyze changes in their behavior over time. This enables the CV unit to perform advanced video analysis by integrating multiple camera feeds, extracting specific actions and facial expressions, and analyzing them over time.

[0128] The learning department can analyze students' learning history to evaluate their learning progress and achievements. For example, it can analyze past test results and assignment submission status to assess learning progress. Furthermore, the learning department can analyze students' learning styles and strengths and weaknesses to propose individually optimized learning plans. In addition, based on students' learning history, the learning department can predict future learning outcomes and provide necessary support. This enables the learning department to provide advanced learning support by evaluating learning progress and achievements, proposing individually optimized learning plans, and predicting future learning outcomes.

[0129] When signs of bullying are detected, the service provider can improve the accuracy of its suggestions when proposing specific countermeasures to teachers by referring to past cases and successful examples. For example, it can refer to past cases where similar signs of bullying were detected and propose effective countermeasures. The service provider can also adjust the content and urgency of the suggestions according to the severity of the signs of bullying. Furthermore, the service provider can propose customized countermeasures that take into account the individual circumstances of the student in whom signs of bullying were detected. This allows the service provider to refer to past cases and successful examples, adjust the content of the suggestions according to the severity, and provide sophisticated countermeasures that take individual circumstances into account.

[0130] The data collection unit can estimate students' emotions and adjust the timing of data collection based on those estimates. For example, if a student is stressed, the frequency of data collection can be increased to collect more detailed data. Conversely, if a student is relaxed, the frequency of data collection can be decreased to collect only the minimum necessary data. Furthermore, if a student is excited, data can be collected focusing on specific behaviors or statements. By adjusting the timing of data collection based on students' emotions, more appropriate data collection becomes possible.

[0131] The analysis unit can estimate the student's emotions and adjust the presentation of the analysis based on those emotions. For example, if a student is stressed, the analysis results can be displayed in a simple and easy-to-understand format. If the student is relaxed, detailed analysis results can be displayed. Furthermore, if the student is excited, the analysis results can be displayed in a visually stimulating format. By adjusting the presentation of the analysis based on the student's emotions, more appropriate analysis results can be provided.

[0132] The detection unit can estimate the student's emotions and adjust the detection criteria for signs of problems based on the estimated emotions. For example, if a student is stressed, it can prioritize detecting signs related to stress. If a student is relaxed, it can prioritize detecting signs related to motivation to learn. Furthermore, if a student is agitated, it can prioritize detecting signs related to behavior and speech. By adjusting the detection criteria based on the student's emotions, it is possible to detect more appropriate signs of problems.

[0133] The system can estimate a student's emotions and adjust the way alerts and suggestions are presented based on that estimation. For example, if a student is stressed, a simple and easy-to-understand alert can be provided. If the student is relaxed, a more detailed suggestion can be offered. Furthermore, if the student is excited, a visually stimulating alert can be provided. By adjusting the presentation of alerts and suggestions based on the student's emotions, more appropriate information can be provided.

[0134] The learning system can estimate students' emotions and adjust the frequency of learning based on those estimates. For example, if a student is stressed, the frequency of learning can be reduced. Conversely, if a student is relaxed, the frequency can be increased. Furthermore, if a student is agitated, the frequency can be adjusted. This allows for more appropriate learning by adjusting the frequency of learning based on students' emotions.

[0135] The following briefly describes the processing flow for example form 2.

[0136] Step 1: The data collection unit collects data from within the classroom. This data includes student behavior data, speech data, and facial expression data. The data collection unit uses sensors and cameras installed in the classroom to collect data. It can also collect student speech using microphones and save it as audio data. Furthermore, it can film student behavior with cameras and save it as video data. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit uses natural language processing (NLP) technology to analyze the content of students' statements and computer vision technology to analyze students' facial expressions and behavior. Furthermore, it uses machine learning algorithms to analyze the collected data and detect signs of problems. Step 3: The detection unit detects signs of a problem based on the data analyzed by the analysis unit. For example, it may detect signs of bullying, decreased motivation to learn, or abnormal behavior. Step 4: The provisioning unit provides alerts and suggestions to teachers and parents based on the signs of problems detected by the detection unit. For example, if signs of bullying are detected, specific measures are suggested to the teacher, and if a decline in motivation to learn is detected, suggestions for learning support are made to the parents.

[0137] 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.

[0138] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0139] 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.

[0140] Each of the multiple elements described above, including the collection unit, analysis unit, detection unit, provision unit, NLP unit, CV unit, and learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit collects data in the classroom using the camera 42 and microphone 38B of the smart device 14. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The detection unit is implemented in the specific processing unit 290 of the data processing unit 12 and detects signs of a problem based on the analyzed data. The provision unit is implemented in the specific processing unit 46A of the smart device 14 and provides alerts and suggestions to teachers and parents based on the detected signs of a problem. The NLP unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the content of students' conversations. The CV unit is implemented in the specific processing unit 290 of the smart device 14 and analyzes students' facial expressions and behavior using the camera 42 of the smart device 14. The learning unit is implemented in the specific processing unit 290 of the data processing unit 12 and learns students' tendencies and generates custom suggestions. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0141] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.).

[0153] 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.

[0154] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0155] 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.

[0156] Each of the multiple elements described above, including the collection unit, analysis unit, detection unit, provision unit, NLP unit, CV unit, and learning unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit collects data in the classroom using the camera 42 and microphone 238 of the smart glasses 214. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and analyzes the collected data. The detection unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and detects signs of a problem based on the analyzed data. The provision unit is implemented, for example, by the control unit 46A of the smart glasses 214, and provides alerts and suggestions to teachers and parents based on the detected signs of a problem. The NLP unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and analyzes the content of students' conversations. The CV unit analyzes students' facial expressions and behavior using the camera 42 of the smart glasses 214. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which learns the student's tendencies and generates custom suggestions. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0157] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.).

[0169] 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.

[0170] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0171] 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.

[0172] Each of the multiple elements described above, including the collection unit, analysis unit, detection unit, provision unit, NLP unit, CV unit, and learning unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit collects data in the classroom using the camera 42 and microphone 238 of the headset terminal 314. The analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the collected data. The detection unit is implemented in the identification processing unit 290 of the data processing unit 12 and detects signs of a problem based on the analyzed data. The provision unit is implemented in the control unit 46A of the headset terminal 314 and provides alerts and suggestions to teachers and parents based on the detected signs of a problem. The NLP unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the content of students' conversations. The CV unit analyzes students' facial expressions and behavior using the camera 42 of the headset terminal 314. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which learns the student's tendencies and generates custom suggestions. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0173] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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).

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.).

[0186] 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.

[0187] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0188] 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.

[0189] Each of the multiple elements described above, including the collection unit, analysis unit, detection unit, provision unit, NLP unit, CV unit, and learning unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the collection unit collects data in the classroom using the camera 42 and microphone 238 of the robot 414. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and analyzes the collected data. The detection unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and detects signs of a problem based on the analyzed data. The provision unit is implemented, for example, by the control unit 46A of the robot 414, and provides alerts and suggestions to teachers and parents based on the detected signs of a problem. The NLP unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and analyzes the content of students' conversations. The CV unit is implemented, for example, by the camera 42 of the robot 414, and analyzes students' facial expressions and behaviors. The learning unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and learns students' tendencies and generates custom suggestions. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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."

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] (Note 1) The data collection unit collects data from within the classroom, An analysis unit analyzes the data collected by the aforementioned collection unit, A detection unit that detects signs of a problem based on the data analyzed by the analysis unit, A providing unit that provides alerts and suggestions to teachers and parents based on the signs of the problem detected by the detection unit, Equipped with A system characterized by the following features. (Note 2) It includes an NLP (Neuro-Language Processing) unit that analyzes students' conversations using natural language processing. The system described in Appendix 1, characterized by the features described herein. (Note 3) It is equipped with a computer vision unit that analyzes students' facial expressions and behavior using computer vision. The system described in Appendix 1, characterized by the features described herein. (Note 4) It features a learning unit that learns the tendencies of individual students and generates customized suggestions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, If signs of bullying are detected, we will propose specific measures to the teachers. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned supply unit is, If a decline in motivation to learn is detected, we will propose learning support to the parents. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is We estimate students' emotions and adjust the timing of data collection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Analyze students' past behavioral history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting data, filtering is performed based on students' current lesson content and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is We estimate students' emotions and prioritize the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting data, the system prioritizes the collection of highly relevant data, taking into account students' seating locations. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is During data collection, analyze students' social media activity and collect relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, We estimate the students' emotions and adjust the representation of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, The system estimates the students' emotions and adjusts the length of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, the priority of the analysis is determined based on when the data was collected. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, adjust the order of analysis based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The detection unit is We estimate students' emotions and adjust the criteria for detecting signs of problems based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The detection unit is During detection, the accuracy of the detection is improved by considering the interrelationships between the data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The detection unit is During detection, the system takes student attribute information into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 22) The detection unit is The system estimates students' emotions and adjusts the display order of the detection results based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The detection unit is During detection, the geographical distribution of the data is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 24) The detection unit is During detection, we refer to relevant literature to improve detection accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, The system estimates students' emotions and adjusts the way alerts and suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing the information, the level of detail in alerts and suggestions will be adjusted based on the severity of the issue. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing the solution, different proposed algorithms will be applied depending on the problem category. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, The system estimates students' emotions and adjusts the length of alerts and suggestions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, When providing the solution, we prioritize alerts and suggestions based on when the problem occurred. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When providing updates, the order of alerts and suggestions will be adjusted based on the relevance of the issues. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned NLP unit is The system estimates the students' emotions and adjusts the conversation analysis method based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned NLP unit is When analyzing conversation content, adjust the level of detail based on specific keywords. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned NLP unit is When analyzing conversation content, different analysis algorithms are applied depending on the category of the conversation. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned NLP unit is The system estimates the students' emotions and prioritizes the analysis of conversation content based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned NLP unit is When analyzing conversation content, the priority of analysis is determined based on when the conversation occurred. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned NLP unit is When analyzing conversation content, the order of analysis is adjusted based on the relevance of the conversation. The system described in Appendix 2, characterized by the features described herein. (Note 37) The aforementioned CV section is The system estimates students' emotions and adjusts the analysis methods for facial expressions and behavior based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned CV section is When analyzing facial expressions and behavior, adjust the level of detail of the analysis based on specific actions. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned CV section is When analyzing facial expressions and behaviors, different analysis algorithms are applied depending on the category of the behavior. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned CV section is The system estimates the students' emotions and prioritizes the analysis of their facial expressions and behaviors based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 41) The aforementioned CV section is When analyzing facial expressions and behaviors, the priority of the analysis is determined based on when the behavior occurred. The system described in Appendix 3, characterized by the features described herein. (Note 42) The aforementioned CV section is When analyzing facial expressions and behaviors, the order of analysis is adjusted based on the relationships between the behaviors. The system described in Appendix 3, characterized by the features described herein. (Note 43) The aforementioned learning unit, The system estimates students' emotions and selects training data based on the estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 44) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 4, characterized by the features described herein. (Note 45) The aforementioned learning unit, The system estimates students' emotions and adjusts the frequency of learning based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 46) The aforementioned learning unit, During training, the training data is weighted based on when the data was collected. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0209] 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. The data collection unit collects data from within the classroom, An analysis unit analyzes the data collected by the aforementioned collection unit, A detection unit that detects signs of a problem based on the data analyzed by the analysis unit, A providing unit that provides alerts and suggestions to teachers and parents based on the signs of the problem detected by the detection unit, Equipped with A system characterized by the following features.

2. It includes an NLP (Neuro-Language Processing) unit that analyzes students' conversations using natural language processing. The system according to feature 1.

3. It is equipped with a computer vision unit that analyzes students' facial expressions and behavior using computer vision. The system according to feature 1.

4. It features a learning unit that learns the tendencies of individual students and generates customized suggestions. The system according to feature 1.

5. The aforementioned supply unit is, If signs of bullying are detected, we will propose specific measures to the teachers. The system according to feature 1.

6. The aforementioned supply unit is, If a decline in motivation to learn is detected, we will propose learning support to the parents. The system according to feature 1.

7. The aforementioned collection unit is We estimate students' emotions and adjust the timing of data collection based on the estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is Analyze students' past behavioral history and select the optimal data collection method. The system according to feature 1.

9. The aforementioned collection unit is When collecting data, filtering is performed based on students' current lesson content and areas of interest. The system according to feature 1.

10. The aforementioned collection unit is We estimate students' emotions and prioritize the data to collect based on those estimated emotions. The system according to feature 1.

Images