system

Abstract

The system according to this embodiment aims to analyze online postings, detect and report problematic posts, and predict social problems that are likely to occur in the future. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a detection unit, a reporting unit, a prediction unit, a simulation unit, and a learning unit. The collection unit collects online postings. The analysis unit analyzes the data collected by the collection unit. The detection unit detects problematic posts based on the data analyzed by the analysis unit. The reporting unit reports the problematic posts detected by the detection unit. The prediction unit predicts likely future social problems based on past data analyzed by the analysis unit. The simulation unit performs simulations based on the social problems predicted by the prediction unit. The learning unit learns new trends and slang collected by the collection 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, problems in online writings are not sufficiently detected or predicted, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze online writings, detect and report problematic posts, and predict social problems likely to occur next.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an analysis unit, a detection unit, a reporting unit, a prediction unit, a simulation unit, and a learning unit. The collection unit collects online postings. The analysis unit analyzes the data collected by the collection unit. The detection unit detects problematic posts based on the data analyzed by the analysis unit. The reporting unit reports the problematic posts detected by the detection unit. The prediction unit predicts likely future social problems based on past data analyzed by the analysis unit. The simulation unit performs simulations based on the social problems predicted by the prediction unit. The learning unit learns new trends and slang collected by the collection unit. [Effects of the Invention]

[0007] The system according to this embodiment can analyze online postings, detect and report problematic posts, and predict social problems that are likely to occur next. [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 tagged storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. 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 tagged communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), 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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by the contact of an indicator (such as a pen or a finger) by detecting the contact of the indicator. The microphone 38B receives user input by voice by detecting the voice of the user. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, a specific processing unit 290 (see FIG. 2) acquires 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 online patrol system according to an embodiment of the present invention is a system that implements plans and comprehensive patrols to prevent problems from occurring in response to online postings. This online patrol system collects online postings and analyzes them using AI. Next, based on the analysis results, it detects and reports problematic posts. Furthermore, it predicts social problems that are likely to occur in the future based on past data and performs simulations to provide information for taking countermeasures in advance. In addition to text, it also analyzes the content of images and videos to detect problematic content. Furthermore, it continuously learns new trends and slang to maintain an up-to-date state. This realizes a safer and more reliable online environment through the early detection and response to crimes and problematic postings. For example, by monitoring online postings in real time and quickly reporting problematic posts, it can contribute to the prevention of social problems. The online patrol system collects online postings. In this process, it collects not only text but also the content of images and videos. For example, it collects posts from SNS and bulletin boards. Next, the collected data is analyzed by AI. The AI ​​performs text analysis, image recognition, and video analysis to detect problematic posts. For example, it detects posts that address social issues such as illegal part-time jobs and suicides. Furthermore, it predicts future social problems based on past data. The AI ​​analyzes past posting data to predict future problems. For example, it analyzes specific keywords and trends to predict problematic posts that are likely to occur next. The AI ​​also performs simulations and provides information to help take preventative measures. For example, it simulates the impact of a specific problem occurring and provides information to help take countermeasures. In addition, the AI ​​continuously learns new trends and slang, staying up-to-date at all times. This allows for patrols to be conducted based on the latest information. Through this system, a safer and more reliable online environment can be created by the early detection and response to crimes and problematic posts. For example, by monitoring online postings in real time and quickly reporting problematic posts, it can contribute to preventing social problems before they occur.This allows the internet patrol system to collect, analyze, detect, report, predict, simulate, and learn from online postings, enabling early detection and response to problems.

[0029] The internet patrol system according to this embodiment comprises a collection unit, an analysis unit, a detection unit, a reporting unit, a prediction unit, a simulation unit, and a learning unit. The collection unit collects online postings. The collection unit collects posts from, for example, social networking services (SNS) and bulletin boards. The collection unit can collect not only text but also image and video content. The collection unit collects, for example, SNS posts. The collection unit can also collect postings on bulletin boards. The collection unit can also collect image and video content. The analysis unit analyzes the data collected by the collection unit. The analysis unit performs, for example, text analysis. The analysis unit can also perform image recognition. The analysis unit can also perform video analysis. The analysis unit performs, for example, text analysis to analyze the content of postings. The analysis unit can also perform image recognition to analyze image content. The analysis unit can also perform video analysis to analyze video content. The detection unit detects problematic posts based on the data analyzed by the analysis unit. The detection unit detects, for example, problematic posts. The detection unit detects posts that are social problems, such as illegal part-time jobs or suicides. The detection unit can also detect illegal posts, for example. The detection unit can also detect defamatory posts, for example. The reporting unit reports problematic posts detected by the detection unit. The reporting unit reports problematic posts, for example. The reporting unit can also report problematic posts to administrators, for example. The reporting unit can also report problematic posts to relevant organizations, for example. The prediction unit predicts social problems that are likely to occur next based on past data analyzed by the analysis unit. The prediction unit predicts social problems that are likely to occur next, for example. The prediction unit analyzes specific keywords and trends to predict problematic posts that are likely to occur next, for example. The prediction unit can also analyze past data to predict problems that are likely to occur next, for example. The simulation unit performs simulations based on the social problems predicted by the prediction unit. The simulation unit simulates the impact of a specific problem occurring, for example. The simulation unit performs simulations and provides information for taking countermeasures, for example.The simulation unit can, for example, simulate the impact of a particular problem and provide information for taking countermeasures. The learning unit learns new trends and slang collected by the collection unit. The learning unit can, for example, learn new trends and slang, and keep itself up-to-date. The learning unit can, for example, learn new trends and slang, and keep itself up-to-date. This enables the internet patrol system to collect, analyze, detect, report, predict, simulate, and learn from online postings, allowing for early detection and response to problems.

[0030] The data collection unit collects online postings. For example, it collects posts from social networking services (SNS) and message boards. Specifically, the unit automatically crawls data from multiple SNS platforms and message board sites, collecting content such as text, images, and videos. The unit can retrieve data in real time using APIs and filter based on specific keywords and hashtags. For example, it can collect posts with specific hashtags and monitor posts from specific users or groups. Furthermore, the unit can collect metadata for images and videos, obtaining additional information such as the date, time, and location of posts. This allows the data collection unit to efficiently collect a wide range of online data and provide it to the analysis unit. The data collection unit centrally manages the collected data and stores it in a database. The database has indexes for efficiently searching, filtering, and classifying the collected data, allowing the analysis unit and other departments to access it quickly. The data collection unit can flexibly set the frequency and scope of data collection and change the collection targets according to specific events or trends. This allows the data collection unit to always collect the latest information and improve the accuracy and effectiveness of the entire online patrol system.

[0031] The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit performs text analysis. Specifically, it uses natural language processing (NLP) techniques to analyze the collected text data and understand the content and sentiment of posts. Text analysis includes morphological analysis, grammatical analysis, and sentiment analysis, which can identify the intent and topic of posts. For example, morphological analysis is used to break down the words in a post, and grammatical analysis is performed to understand the structure of the sentence. Sentiment analysis can determine whether a post has a positive, negative, or neutral sentiment. The analysis unit can also perform image recognition. Image recognition includes image classification and object detection using deep learning techniques, which can identify specific objects and scenes within an image. For example, image recognition can be used to detect illegal content or inappropriate images. The analysis unit can also perform video analysis. Video analysis includes frame-by-frame image analysis and motion detection, which can identify important scenes and events within a video. For example, video analysis can be used to detect violent scenes or illegal activities. In this way, the analysis unit can analyze the collected data from multiple angles and quickly and accurately grasp problems on the internet. Furthermore, the analysis unit saves the analysis results to a database, making them available to other departments. The analysis unit also establishes a feedback loop to continuously improve the accuracy of its analysis algorithms, providing the analysis results to the learning unit. This allows the analysis unit to improve the overall performance of the network patrol system.

[0032] The detection unit detects problematic posts based on data analyzed by the analysis unit. For example, the detection unit detects problematic posts. Specifically, the detection unit identifies problematic posts according to specific rules and criteria based on the analysis results provided by the analysis unit. For example, the detection unit detects posts containing specific keywords or phrases and determines whether these posts are related to illegal activities or social issues. For example, the detection unit detects posts that are social issues such as illegal part-time jobs or suicide. This involves filtering posts containing specific keywords or phrases and further analyzing the content and context of the posts to identify problematic posts. The detection unit can also detect illegal posts, for example. This involves identifying posts containing keywords or images related to illegal activities and determining whether these posts are legally problematic. The detection unit can also detect defamatory posts, for example. This involves identifying posts containing offensive words or phrases directed at specific individuals or groups and determining whether these posts constitute defamation. The detection unit stores the detected problematic posts in a database and makes them available to the reporting unit and other departments. The detection unit builds a feedback loop to continuously improve the accuracy of the detection algorithm and provides the detection results to the learning unit. This allows the detection unit to quickly and accurately identify problems on the internet and improve the overall performance of the network patrol system.

[0033] The reporting department reports problematic posts detected by the detection department. Specifically, the reporting department reports problematic posts provided by the detection department to administrators and relevant organizations. The reporting department can also report problematic posts to administrators, for example, by providing detailed information and analysis results of the problematic posts to enable administrators to respond quickly. The reporting department can also report problematic posts to relevant organizations, for example, by providing detailed information and evidence of the problematic posts to relevant organizations if legal action is required. The reporting department can flexibly configure the content and format of reports and change reporting methods depending on the specific problem or situation. For example, the reporting department can report to administrators via email or notification systems, and can create and submit official reports to relevant organizations. The reporting department stores a history of reports in a database and manages past reports and response status. This allows the reporting department to support quick and appropriate responses to problematic posts and improve the reliability and effectiveness of the overall internet patrol system. Furthermore, the reporting department will establish a feedback loop to continuously improve the accuracy and effectiveness of its reports, and will provide the reporting results to the learning department. This will enable the reporting department to strengthen its ability to respond to online issues and improve the overall performance of the online patrol system.

[0034] The prediction unit predicts likely future social problems based on historical data analyzed by the analysis unit. Specifically, the prediction unit analyzes historical data and extracts specific keywords and trends. This involves using time series analysis and trend analysis to predict future trends from historical data. For example, if a particular keyword is rapidly increasing, it can be predicted that there is a high probability that a social problem related to that keyword will occur. The prediction unit analyzes specific keywords and trends to predict likely future problem posts. This involves using natural language processing techniques to analyze the content and sentiment of posts and predict future problems. The prediction unit can also analyze historical data to predict likely future problems. This involves analyzing patterns and trends in past problem posts and predicting future problems. The prediction unit stores the prediction results in a database so that the simulation unit and other departments can use them. The prediction unit builds a feedback loop to continuously improve the accuracy of the prediction algorithm and provides the prediction results to the learning unit. This allows the prediction unit to predict online problems in advance and improve the overall performance of the online patrol system. Furthermore, the prediction unit, in collaboration with the simulation unit, uses the prediction results to formulate countermeasures against future problems. This allows the prediction unit to strengthen its proactive response to online problems and improve the reliability and effectiveness of the entire online patrol system.

[0035] The Simulation Department performs simulations based on social problems predicted by the Prediction Department. For example, the Simulation Department simulates the impact of a specific problem if it occurs. Specifically, the Simulation Department simulates the impact of a specific problem if it occurs, based on the prediction results provided by the Prediction Department. This involves modeling the occurrence and impact of the problem using simulation techniques such as system dynamics and agent-based modeling. For example, if a specific keyword suddenly increases, the Simulation Department can simulate how posts related to that keyword will spread and what impact they will have on society. For example, the Simulation Department performs simulations and provides information for taking countermeasures. This involves formulating countermeasures to prevent the occurrence of problems and response measures if problems occur, based on the simulation results. For example, the Simulation Department can simulate the impact of a specific problem if it occurs and provide information for taking countermeasures. This involves proposing specific countermeasures to relevant organizations and administrators based on the simulation results. The Simulation Department stores the simulation results in a database so that other departments can use them. The Simulation Department builds a feedback loop to continuously improve the accuracy of the simulation algorithm and provides the simulation results to the Learning Department. This allows the simulation unit to strengthen its proactive response to online issues and improve the overall performance of the online patrol system. Furthermore, based on the simulation results, the simulation unit reviews and optimizes the overall strategy of the online patrol system. This allows the simulation unit to strengthen its ability to respond to online issues and improve the reliability and effectiveness of the overall online patrol system.

[0036] The learning unit learns new trends and slang collected by the collection unit. Specifically, the learning unit automatically learns new trends and slang based on data provided by the collection unit. This involves using natural language processing techniques to extract new words and phrases from the collected text data and understanding their meaning and usage. For example, the learning unit analyzes new slang and trend words and understands their background and context. The learning unit continuously learns new trends and slang, keeping itself up-to-date. This involves regularly updating the data and incorporating new information to always grasp the latest trends and slang. The learning unit can also continuously learn new trends and slang and keep itself up-to-date. This involves continuously improving the learning algorithm and quickly incorporating new information to improve the accuracy and speed of learning. The learning unit stores the learning results in a database so that other units can use them. The learning unit builds a feedback loop to continuously improve the accuracy of the learning algorithm and provides the learning results to the analysis and detection units. This allows the learning unit to improve the overall performance of the network patrol system. Furthermore, based on the learning results, the learning unit can improve the algorithms of the analysis and detection units, enabling it to more accurately identify problems on the network. This allows the learning unit to improve the reliability and effectiveness of the entire network patrol system.

[0037] The analysis unit can perform text analysis, image recognition, and video analysis. For example, the analysis unit can perform text analysis. For example, the analysis unit can perform morphological analysis to analyze the structure of a text. For example, the analysis unit can perform grammatical analysis to analyze the grammatical structure of a text. For example, the analysis unit can perform semantic analysis to analyze the meaning of a text. For example, the analysis unit can perform image recognition. For example, the analysis unit can use a CNN (Convolutional Neural Network) to analyze the content of an image. For example, the analysis unit can use an object detection algorithm to detect objects in an image. For example, the analysis unit can perform video analysis. For example, the analysis unit can perform motion detection to analyze the motion in a video. For example, the analysis unit can perform frame analysis to analyze each frame of a video. For example, the analysis unit can perform action recognition to analyze actions in a video. In this way, the analysis unit can detect problematic posts from multiple angles by analyzing text, images, and videos. Some or all of the above-described processes in the analysis unit may be performed using a generation AI, for example, or without a generation AI. For example, the analysis unit can input text data into a generation AI, and the generation AI can perform text analysis. The analysis unit can input image data into a generation AI, and the generation AI can perform image recognition. The analysis unit can input video data into a generation AI, and the generation AI can perform video analysis.

[0038] The detection unit can detect posts that are social problems, such as illegal part-time jobs or suicides. For example, the detection unit can detect posts about illegal part-time jobs. For example, the detection unit can detect posts about illegal part-time jobs. For example, the detection unit can also detect posts about part-time jobs that are involved in crimes. For example, the detection unit can detect posts about suicide. For example, the detection unit can detect posts that are suicide threats. For example, the detection unit can also detect posts that are suicide-related. In this way, by detecting posts that are social problems, the detection unit can enable early detection and response to problems. 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 post data into a generating AI, and the generating AI can detect problematic posts.

[0039] The prediction unit can analyze specific keywords and trends to predict the next likely problem post. For example, the prediction unit can analyze specific keywords. For example, the prediction unit can analyze popular buzzwords to predict the next likely problem post. For example, the prediction unit can analyze keywords related to social issues to predict the next likely problem post. For example, the prediction unit can analyze trends. For example, the prediction unit can analyze specific trends to predict the next likely problem post. For example, the prediction unit can analyze specific trends to predict the next likely problem post. This allows the prediction unit to take countermeasures in advance by predicting the next likely problem post. Some or all of the above processing in the prediction unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the prediction unit can input keyword data into a generative AI, and the generative AI can predict the next likely problem post.

[0040] The simulation unit can simulate the impact of a specific problem occurring and provide information for taking countermeasures. For example, the simulation unit simulates the impact of a specific problem occurring. The simulation unit can simulate the impact of a specific problem occurring and provide information for taking countermeasures. The simulation unit can also simulate the impact of a specific problem occurring and provide information for taking countermeasures. This allows the simulation unit to take appropriate countermeasures by simulating the impact of a problem occurring. Some or all of the above processing in the simulation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the simulation unit can input problem data into a generative AI, which can then perform the simulation.

[0041] The learning unit can learn new trends and slang and stay up-to-date at all times. The learning unit can learn new trends and slang, for example. The learning unit can learn the latest trending words, for example. The learning unit can also learn internet memes, for example. The learning unit can continue to learn new trends and slang and stay up-to-date at all times. The learning unit can also learn new trends and slang and stay up-to-date at all times. This allows the learning unit to always conduct patrols based on the latest information by learning new trends and slang. Some or all of the above processing 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 trend data into a generative AI, which can learn new trends and slang.

[0042] The collection unit can filter online postings based on specific keywords or phrases. For example, the collection unit can prioritize collecting postings containing specific keywords. For example, the collection unit can prioritize collecting postings containing keywords such as "illegal part-time jobs" or "suicide." The collection unit can filter and collect postings containing specific phrases. For example, the collection unit can filter and collect postings containing phrases such as "help me" or "I want to die." The collection unit can collect postings related to specific topics. For example, the collection unit can also collect postings related to crime or violence. This allows the collection unit to prioritize collecting important postings by filtering based on specific keywords or phrases. Some or all of the above processing in the collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the collection unit can input keyword data into a generative AI, which can then perform the filtering.

[0043] The collection unit can analyze a user's past posting history and select data to collect when collecting posts. For example, the collection unit can analyze a user's past posting history. For example, the collection unit can analyze a user's past posting history for the past year and select data to collect. For example, the collection unit can analyze a user's posting history on a specific topic and select data to collect. For example, the collection unit can prioritize the collection of problematic posts. For example, the collection unit can collect posts related to a specific topic. For example, the collection unit can select data to collect based on a user's past posting history and collect data efficiently. This allows the collection unit to efficiently collect highly relevant posts by analyzing a user's past posting history. Some or all of the above processing in the collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the collection unit can input posting history data into a generative AI, which can then select data to collect.

[0044] The collection unit can prioritize collecting posts that are highly relevant by considering the user's geographical location information when collecting posts. For example, the collection unit can prioritize collecting posts related to the user's current location. For example, the collection unit can collect posts related to problems occurring in a specific region. The collection unit can also select and collect posts that are highly relevant based on the user's geographical location information. In this way, the collection unit can prioritize collecting posts that are highly relevant by considering the user's geographical location information. Some or all of the above processing in the collection unit may be performed using, for example, a generation AI, or without a generation AI. For example, the collection unit can input geographical location data into a generation AI, and the generation AI can select posts that are highly relevant.

[0045] The collection unit can analyze a user's social media activity and collect relevant posts when collecting posts. For example, the collection unit can analyze a user's social media activity. For example, the collection unit can analyze a user's posting frequency and collect relevant posts. For example, the collection unit can analyze a user's number of followers and collect relevant posts. For example, the collection unit can analyze a user's number of likes and collect relevant posts. For example, the collection unit can collect posts from accounts that a user follows. For example, the collection unit can select and collect highly relevant posts based on a user's social media activity. In this way, the collection unit can efficiently collect highly relevant posts by analyzing a user's social media activity. Some or all of the above processing in the collection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the collection unit can input social media data into a generative AI, which can then select highly relevant posts.

[0046] The analysis unit can adjust the level of detail of the analysis based on the importance of the writes during the analysis. For example, the analysis unit performs a detailed analysis for high-importance writes. For example, the analysis unit performs a simplified analysis for low-importance writes. The analysis unit can also adjust the level of detail of the analysis according to the importance of the writes. This allows the analysis unit to perform efficient analysis by adjusting the level of detail of the analysis based on the importance of the writes. Some or all of the above processing in the analysis unit may be performed using a generation AI, for example, or without a generation AI. For example, the analysis unit can input the write data into a generation AI, and the generation AI can adjust the level of detail of the analysis based on importance.

[0047] The analysis unit can apply different analysis algorithms depending on the category of the post during analysis. For example, the analysis unit may apply a specific analysis algorithm to crime-related posts. For example, the analysis unit may apply a different analysis algorithm to health-related posts. The analysis unit can also select and apply the most suitable analysis algorithm depending on the category of the post. This improves the accuracy of the analysis by allowing the analysis unit to apply the most suitable analysis algorithm according to the category of the post. 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 category data into a generative AI, which can then apply the most suitable analysis algorithm.

[0048] The analysis unit can determine the priority of analysis based on the posting date of the posts during the analysis. For example, the analysis unit may prioritize analyzing recent posts. For example, the analysis unit may prioritize analyzing posts that were concentrated within a specific period. The analysis unit can also adjust the priority of analysis based on the posting date. This allows the analysis unit to perform efficient analysis by determining the priority of analysis based on the posting date of the posts. Some or all of the above processing in the analysis unit may be performed using a generation AI, for example, or without a generation AI. For example, the analysis unit can input posting date data into a generation AI, and the generation AI can determine the priority of analysis.

[0049] The analysis unit can adjust the order of analysis based on the relevance of the writes during analysis. For example, the analysis unit may prioritize the analysis of highly relevant writes. For example, the analysis unit may postpone the analysis of less relevant writes. The analysis unit can also adjust the order of analysis based on the relevance of the writes. This allows the analysis unit to perform efficient analysis by adjusting the order of analysis based on the relevance of the writes. Some or all of the above processing in the analysis unit may be performed using a generation AI, for example, or without a generation AI. For example, the analysis unit may input relevance data into a generation AI, and the generation AI may adjust the order of analysis.

[0050] The detection unit can improve the accuracy of detection by considering the interrelationships of posts during detection. For example, the detection unit groups related posts and performs detection while considering their interrelationships. For example, the detection unit analyzes the interrelationships of posts to perform highly accurate detection. For example, the detection unit can also detect problematic posts based on the interrelationships of posts. In this way, the detection unit can perform highly accurate detection by considering the interrelationships of posts. 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 interrelationship data into a generating AI, which can then improve the accuracy of detection.

[0051] The detection unit can perform detection while considering the attribute information of the poster of the post. For example, the detection unit can perform detection while considering attribute information such as the poster's age and gender. For example, the detection unit can perform detection based on the poster's past posting history. For example, the detection unit can also detect problematic posts based on the poster's attribute information. In this way, the detection unit can perform appropriate detection by considering the poster'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 using a generating AI. For example, the detection unit can input attribute information data into a generating AI, and the generating AI can perform detection.

[0052] The detection unit can perform detection while considering the geographical distribution of posts. For example, the detection unit can prioritize the detection of posts concentrated in a specific area. For example, the detection unit can detect problematic posts based on geographical distribution. The detection unit can also perform highly accurate detection by considering the geographical distribution of posts. As a result, the detection unit can perform highly accurate detection by considering the geographical distribution of posts. 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 geographical distribution data into a generative AI, and the generative AI can perform the detection.

[0053] The detection unit can improve the accuracy of detection by referring to related literature during detection. For example, the detection unit performs detection by referring to related academic papers. For example, the detection unit performs detection based on related news articles. The detection unit can also perform highly accurate detection by referring to related literature. This enables the detection unit to perform highly accurate detection by referring to related 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 related literature data into a generating AI, and the generating AI can perform detection.

[0054] The reporting unit can adjust the level of detail in its reports based on the importance of the entries. For example, the reporting unit can provide detailed reports for high-importance entries, or simplified reports for low-importance entries. The reporting unit can also adjust the level of detail in its reports according to the importance of the entries. This allows the reporting unit to provide efficient reports by adjusting the level of detail based on the importance of the entries. Some or all of the above processing in the reporting unit may be performed using, for example, a generating AI, or without a generating AI. For example, the reporting unit can input the entry data into a generating AI, which can then adjust the level of detail in its reports based on importance.

[0055] The reporting unit can apply different reporting algorithms depending on the category of the post when reporting. For example, the reporting unit may apply a specific reporting algorithm to crime-related posts. For example, the reporting unit may apply a different reporting algorithm to health-related posts. The reporting unit can also select and apply the most suitable reporting algorithm depending on the category of the post. This improves the accuracy of the report by allowing the reporting unit to apply the most suitable reporting algorithm according to the category of the post. Some or all of the above processing in the reporting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reporting unit can input category data into a generative AI, which can then apply the most suitable reporting algorithm.

[0056] The reporting unit can determine the priority of reports based on the posting date of the entries. For example, the reporting unit may prioritize reporting recent entries. For example, the reporting unit may prioritize reporting entries that were concentrated within a specific period. The reporting unit can also adjust the priority of reports based on the posting date. This allows the reporting unit to perform efficient reporting by determining the priority of reports based on the posting date of the entries. Some or all of the above processing in the reporting unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reporting unit can input posting date data into a generative AI, and the generative AI can determine the priority of reports.

[0057] The reporting unit can adjust the order of reports based on the relevance of the entries when reporting. For example, the reporting unit may prioritize reporting highly relevant entries. For example, the reporting unit may postpone reporting less relevant entries. The reporting unit can also adjust the order of reports based on the relevance of the entries. This allows the reporting unit to perform efficient reporting by adjusting the order of reports based on the relevance of the entries. Some or all of the above processing in the reporting unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reporting unit can input relevance data into a generative AI, and the generative AI can adjust the order of reports.

[0058] The prediction unit can optimize the current prediction by referring to past data during the prediction process. For example, the prediction unit optimizes the current prediction based on past posting data. For example, the prediction unit analyzes past trends and reflects them in the current prediction. The prediction unit can also make highly accurate predictions by referring to past data. As a result, the prediction unit can make highly accurate predictions by optimizing the current prediction by referring to past data. Some or all of the above processes in the prediction unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the prediction unit can input past data into a generative AI, and the generative AI can optimize the current prediction.

[0059] The prediction unit can apply different prediction methods to each category of post during prediction. For example, the prediction unit may apply a specific prediction method to crime-related posts. For example, it may apply a different prediction method to health-related posts. The prediction unit can also select and apply the optimal prediction method according to the category of post. This improves the accuracy of predictions by applying the optimal prediction method to each category of post. Some or all of the above processing in the prediction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the prediction unit can input category data into a generative AI, which can then apply the optimal prediction method.

[0060] The prediction unit can analyze changes in predictions based on the posting time of the posts during the prediction process. For example, the prediction unit analyzes changes in predictions based on the posting time. For example, the prediction unit makes predictions based on posts that were concentrated during a specific period. For example, the prediction unit can analyze changes in predictions according to the posting time and make the optimal prediction. This enables the prediction unit to make highly accurate predictions by analyzing changes in predictions based on the posting time of the posts. Some or all of the above processing in the prediction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the prediction unit can input posting time data into a generative AI, and the generative AI can analyze changes in predictions.

[0061] The prediction unit can analyze its predictions by referring to relevant market data for writing during the prediction process. For example, the prediction unit makes predictions based on relevant market data. For example, the prediction unit makes highly accurate predictions by referring to relevant market data. For example, the prediction unit can also analyze relevant market data for writing and make optimal predictions. This enables the prediction unit to make highly accurate predictions by referring to relevant market data. Some or all of the above processing in the prediction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the prediction unit can input market data into a generative AI, and the generative AI can make predictions.

[0062] The simulation unit can optimize the simulation algorithm by referring to past data during the simulation. For example, the simulation unit optimizes the simulation algorithm based on past posting data. For example, the simulation unit analyzes past trends and reflects them in the simulation. For example, the simulation unit can perform highly accurate simulations by referring to past data. This enables the simulation unit to perform highly accurate simulations by optimizing the simulation algorithm by referring to past data. Some or all of the above processes in the simulation unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the simulation unit can input past data into a generative AI, and the generative AI can optimize the simulation algorithm.

[0063] The simulation unit can apply different simulation methods to each category of writing during the simulation. For example, the simulation unit can apply a specific simulation method to crime-related writings. For example, the simulation unit can apply a different simulation method to health-related writings. The simulation unit can also select and apply the optimal simulation method according to the category of writing. This improves the accuracy of the simulation by applying the optimal simulation method to each category of writing. Some or all of the above processing in the simulation unit may be performed using a generative AI, for example, or without a generative AI. For example, the simulation unit can input category data into a generative AI, which can then apply the optimal simulation method.

[0064] The simulation unit can perform simulations while considering the geographical distribution of posts. For example, the simulation unit can perform simulations based on posts concentrated in a specific area. For example, the simulation unit can simulate problematic posts based on geographical distribution. The simulation unit can also perform highly accurate simulations by considering the geographical distribution of posts. This enables the simulation unit to perform highly accurate simulations by considering the geographical distribution of posts. Some or all of the above processing in the simulation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the simulation unit can input geographical distribution data into a generative AI, and the generative AI can perform the simulation.

[0065] The simulation unit can improve the accuracy of the simulation by referring to relevant literature during the simulation. For example, the simulation unit performs simulations by referring to relevant academic papers. For example, the simulation unit performs simulations based on relevant news articles. For example, the simulation unit can also perform highly accurate simulations by referring to relevant literature. In this way, the simulation unit can perform highly accurate simulations by referring to relevant literature. Some or all of the above processing in the simulation unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the simulation unit can input relevant literature data into a generative AI, and the generative AI can perform the simulation.

[0066] The learning unit can optimize its learning algorithm by referring to past learning data during the learning process. For example, the learning unit optimizes the learning algorithm based on past learning data. For example, the learning unit analyzes past trends and reflects them in the learning process. For example, the learning unit can perform highly accurate learning by referring to past data. This enables highly accurate learning by optimizing the learning algorithm 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 data into a generative AI, and the generative AI can optimize the learning algorithm.

[0067] The learning unit can build a feedback loop to quickly incorporate new trends and slang during the learning process. For example, the learning unit can extract new trends and slang from user posts and reflect them in the learning data. The learning unit can also learn new trends and slang in real time and always maintain an up-to-date state. This allows the learning unit to always maintain an up-to-date state by quickly incorporating new trends and slang. 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 trend data into a generative AI, which can then learn new trends and slang.

[0068] The learning unit can weight the training data based on the posting date of the posts during training. For example, the learning unit can weight the training data by giving more emphasis to recent posts. For example, the learning unit can weight the training data by giving more emphasis to posts that were concentrated in a specific period. The learning unit can also adjust the weighting of the training data based on the posting date. This enables the learning unit to perform highly accurate training by weighting the training data based on the posting date of the posts. Some or all of the above processing in the learning unit may be performed using a generative AI, for example, or without a generative AI. For example, the learning unit can input posting date data into a generative AI, and the generative AI can perform the weighting of the training data.

[0069] The learning unit can improve the accuracy of its learning by referring to relevant market data during the learning process. For example, the learning unit performs learning based on relevant market data. For example, the learning unit performs highly accurate learning by referring to relevant market data. The learning unit can also perform optimal learning by analyzing relevant market data for writing. This enables the learning unit to perform highly accurate learning by referring to relevant market data. Some or all of the above processing 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 market data into a generative AI, and the generative AI can perform learning.

[0070] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0071] The internet patrol system may also include a behavioral analysis unit that analyzes the user's behavioral history. The behavioral analysis unit, for example, analyzes the user's past browsing and click history to provide auxiliary information for detecting problematic posts. For example, the behavioral analysis unit can analyze the frequency of visits to specific sites or pages to improve the accuracy of problematic post detection. The behavioral analysis unit can also analyze the user's click patterns to aid in the detection of problematic posts. In this way, the behavioral analysis unit can improve the accuracy of problematic post detection by analyzing the user's behavioral history.

[0072] The detection unit can further improve the accuracy of detecting problematic posts by analyzing the user's social network. For example, the detection unit can analyze the user's friendships and follower relationships to assess the risk of problematic posts spreading. The detection unit can also analyze the user's influence within their social network to assess the impact of problematic posts. For example, the detection unit can analyze the relationships between posts within the user's social network to improve the accuracy of detecting problematic posts. In this way, the detection unit can improve the accuracy of detecting problematic posts by analyzing the user's social network.

[0073] The simulation unit can further incorporate user behavior patterns into the simulation. For example, the simulation unit can simulate a user's reaction when a specific problem occurs, based on the user's past behavior data. The simulation unit can also analyze user behavior patterns and simulate the impact of a problem when it occurs. For example, the simulation unit can simulate countermeasures when a problem occurs, based on user behavior patterns. In this way, the simulation unit can perform more realistic simulations by incorporating user behavior patterns into the simulation.

[0074] The data collection unit can further consider the user's geographical information and prioritize the collection of posts related to a specific region. For example, the data collection unit can prioritize the collection of posts related to the user's current location. The data collection unit can also, for example, collect posts related to problems occurring in a specific region. The data collection unit can also, for example, select and collect highly relevant posts based on the user's geographical information. In this way, the data collection unit can prioritize the collection of highly relevant posts by considering the user's geographical information.

[0075] The detection unit can further analyze the user's behavior history to improve the accuracy of detecting problematic posts. For example, the detection unit can analyze the user's past posting history to provide auxiliary information for detecting problematic posts. The detection unit can also analyze the user's browsing history to improve the accuracy of detecting problematic posts. For example, the detection unit can analyze the user's click history to help detect problematic posts. In this way, the detection unit can improve the accuracy of detecting problematic posts by analyzing the user's behavior history.

[0076] The following briefly describes the processing flow for example form 1.

[0077] Step 1: The collection unit collects online postings. For example, the collection unit collects posts from social media and message boards. The collection unit can collect not only text but also images and videos. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit can perform, for example, text analysis, image recognition, and video analysis. Step 3: The detection unit detects problematic posts based on the data analyzed by the analysis unit. The detection unit can detect posts that are social problems, such as illegal part-time jobs or suicides, illegal posts, and defamatory posts. Step 4: The reporting unit reports the problematic posts detected by the detection unit. The reporting unit may, for example, report the problematic posts to administrators or relevant organizations. Step 5: The prediction unit predicts the next social problem that is likely to occur based on the historical data analyzed by the analysis unit. For example, the prediction unit analyzes specific keywords or trends to predict the next problem post. Step 6: The simulation unit performs simulations based on the social problems predicted by the prediction unit. For example, the simulation unit simulates the impact of a specific problem occurring and provides information for taking countermeasures. Step 7: The learning unit learns new trends and slang collected by the collection unit. The learning unit, for example, continues to learn new trends and slang to stay up-to-date.

[0078] (Example of form 2) The online patrol system according to an embodiment of the present invention is a system that implements plans and comprehensive patrols to prevent problems from occurring in response to online postings. This online patrol system collects online postings and analyzes them using AI. Next, based on the analysis results, it detects and reports problematic posts. Furthermore, it predicts social problems that are likely to occur in the future based on past data and performs simulations to provide information for taking countermeasures in advance. In addition to text, it also analyzes the content of images and videos to detect problematic content. Furthermore, it continuously learns new trends and slang to maintain an up-to-date state. This realizes a safer and more reliable online environment through the early detection and response to crimes and problematic postings. For example, by monitoring online postings in real time and quickly reporting problematic posts, it can contribute to the prevention of social problems. The online patrol system collects online postings. In this process, it collects not only text but also the content of images and videos. For example, it collects posts from SNS and bulletin boards. Next, the collected data is analyzed by AI. The AI ​​performs text analysis, image recognition, and video analysis to detect problematic posts. For example, it detects posts that address social issues such as illegal part-time jobs and suicides. Furthermore, it predicts future social problems based on past data. The AI ​​analyzes past posting data to predict future problems. For example, it analyzes specific keywords and trends to predict problematic posts that are likely to occur next. The AI ​​also performs simulations and provides information to help take preventative measures. For example, it simulates the impact of a specific problem occurring and provides information to help take countermeasures. In addition, the AI ​​continuously learns new trends and slang, staying up-to-date at all times. This allows for patrols to be conducted based on the latest information. Through this system, a safer and more reliable online environment can be created by the early detection and response to crimes and problematic posts. For example, by monitoring online postings in real time and quickly reporting problematic posts, it can contribute to preventing social problems before they occur.This allows the internet patrol system to collect, analyze, detect, report, predict, simulate, and learn from online postings, enabling early detection and response to problems.

[0079] The internet patrol system according to this embodiment comprises a collection unit, an analysis unit, a detection unit, a reporting unit, a prediction unit, a simulation unit, and a learning unit. The collection unit collects online postings. The collection unit collects posts from, for example, social networking services (SNS) and bulletin boards. The collection unit can collect not only text but also image and video content. The collection unit collects, for example, SNS posts. The collection unit can also collect postings on bulletin boards. The collection unit can also collect image and video content. The analysis unit analyzes the data collected by the collection unit. The analysis unit performs, for example, text analysis. The analysis unit can also perform image recognition. The analysis unit can also perform video analysis. The analysis unit performs, for example, text analysis to analyze the content of postings. The analysis unit can also perform image recognition to analyze image content. The analysis unit can also perform video analysis to analyze video content. The detection unit detects problematic posts based on the data analyzed by the analysis unit. The detection unit detects, for example, problematic posts. The detection unit detects posts that are social problems, such as illegal part-time jobs or suicides. The detection unit can also detect illegal posts, for example. The detection unit can also detect defamatory posts, for example. The reporting unit reports problematic posts detected by the detection unit. The reporting unit reports problematic posts, for example. The reporting unit can also report problematic posts to administrators, for example. The reporting unit can also report problematic posts to relevant organizations, for example. The prediction unit predicts social problems that are likely to occur next based on past data analyzed by the analysis unit. The prediction unit predicts social problems that are likely to occur next, for example. The prediction unit analyzes specific keywords and trends to predict problematic posts that are likely to occur next, for example. The prediction unit can also analyze past data to predict problems that are likely to occur next, for example. The simulation unit performs simulations based on the social problems predicted by the prediction unit. The simulation unit simulates the impact of a specific problem occurring, for example. The simulation unit performs simulations and provides information for taking countermeasures, for example.The simulation unit can, for example, simulate the impact of a particular problem and provide information for taking countermeasures. The learning unit learns new trends and slang collected by the collection unit. The learning unit can, for example, learn new trends and slang, and keep itself up-to-date. The learning unit can, for example, learn new trends and slang, and keep itself up-to-date. This enables the internet patrol system to collect, analyze, detect, report, predict, simulate, and learn from online postings, allowing for early detection and response to problems.

[0080] The data collection unit collects online postings. For example, it collects posts from social networking services (SNS) and message boards. Specifically, the unit automatically crawls data from multiple SNS platforms and message board sites, collecting content such as text, images, and videos. The unit can retrieve data in real time using APIs and filter based on specific keywords and hashtags. For example, it can collect posts with specific hashtags and monitor posts from specific users or groups. Furthermore, the unit can collect metadata for images and videos, obtaining additional information such as the date, time, and location of posts. This allows the data collection unit to efficiently collect a wide range of online data and provide it to the analysis unit. The data collection unit centrally manages the collected data and stores it in a database. The database has indexes for efficiently searching, filtering, and classifying the collected data, allowing the analysis unit and other departments to access it quickly. The data collection unit can flexibly set the frequency and scope of data collection and change the collection targets according to specific events or trends. This allows the data collection unit to always collect the latest information and improve the accuracy and effectiveness of the entire online patrol system.

[0081] The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit performs text analysis. Specifically, it uses natural language processing (NLP) techniques to analyze the collected text data and understand the content and sentiment of posts. Text analysis includes morphological analysis, grammatical analysis, and sentiment analysis, which can identify the intent and topic of posts. For example, morphological analysis is used to break down the words in a post, and grammatical analysis is performed to understand the structure of the sentence. Sentiment analysis can determine whether a post has a positive, negative, or neutral sentiment. The analysis unit can also perform image recognition. Image recognition includes image classification and object detection using deep learning techniques, which can identify specific objects and scenes within an image. For example, image recognition can be used to detect illegal content or inappropriate images. The analysis unit can also perform video analysis. Video analysis includes frame-by-frame image analysis and motion detection, which can identify important scenes and events within a video. For example, video analysis can be used to detect violent scenes or illegal activities. In this way, the analysis unit can analyze the collected data from multiple angles and quickly and accurately grasp problems on the internet. Furthermore, the analysis unit saves the analysis results to a database, making them available to other departments. The analysis unit also establishes a feedback loop to continuously improve the accuracy of its analysis algorithms, providing the analysis results to the learning unit. This allows the analysis unit to improve the overall performance of the network patrol system.

[0082] The detection unit detects problematic posts based on data analyzed by the analysis unit. For example, the detection unit detects problematic posts. Specifically, the detection unit identifies problematic posts according to specific rules and criteria based on the analysis results provided by the analysis unit. For example, the detection unit detects posts containing specific keywords or phrases and determines whether these posts are related to illegal activities or social issues. For example, the detection unit detects posts that are social issues such as illegal part-time jobs or suicide. This involves filtering posts containing specific keywords or phrases and further analyzing the content and context of the posts to identify problematic posts. The detection unit can also detect illegal posts, for example. This involves identifying posts containing keywords or images related to illegal activities and determining whether these posts are legally problematic. The detection unit can also detect defamatory posts, for example. This involves identifying posts containing offensive words or phrases directed at specific individuals or groups and determining whether these posts constitute defamation. The detection unit stores the detected problematic posts in a database and makes them available to the reporting unit and other departments. The detection unit builds a feedback loop to continuously improve the accuracy of the detection algorithm and provides the detection results to the learning unit. This allows the detection unit to quickly and accurately identify problems on the internet and improve the overall performance of the network patrol system.

[0083] The reporting department reports problematic posts detected by the detection department. Specifically, the reporting department reports problematic posts provided by the detection department to administrators and relevant organizations. The reporting department can also report problematic posts to administrators, for example, by providing detailed information and analysis results of the problematic posts to enable administrators to respond quickly. The reporting department can also report problematic posts to relevant organizations, for example, by providing detailed information and evidence of the problematic posts to relevant organizations if legal action is required. The reporting department can flexibly configure the content and format of reports and change reporting methods depending on the specific problem or situation. For example, the reporting department can report to administrators via email or notification systems, and can create and submit official reports to relevant organizations. The reporting department stores a history of reports in a database and manages past reports and response status. This allows the reporting department to support quick and appropriate responses to problematic posts and improve the reliability and effectiveness of the overall internet patrol system. Furthermore, the reporting department will establish a feedback loop to continuously improve the accuracy and effectiveness of its reports, and will provide the reporting results to the learning department. This will enable the reporting department to strengthen its ability to respond to online issues and improve the overall performance of the online patrol system.

[0084] The prediction unit predicts likely future social problems based on historical data analyzed by the analysis unit. Specifically, the prediction unit analyzes historical data and extracts specific keywords and trends. This involves using time series analysis and trend analysis to predict future trends from historical data. For example, if a particular keyword is rapidly increasing, it can be predicted that there is a high probability that a social problem related to that keyword will occur. The prediction unit analyzes specific keywords and trends to predict likely future problem posts. This involves using natural language processing techniques to analyze the content and sentiment of posts and predict future problems. The prediction unit can also analyze historical data to predict likely future problems. This involves analyzing patterns and trends in past problem posts and predicting future problems. The prediction unit stores the prediction results in a database so that the simulation unit and other departments can use them. The prediction unit builds a feedback loop to continuously improve the accuracy of the prediction algorithm and provides the prediction results to the learning unit. This allows the prediction unit to predict online problems in advance and improve the overall performance of the online patrol system. Furthermore, the prediction unit, in collaboration with the simulation unit, uses the prediction results to formulate countermeasures against future problems. This allows the prediction unit to strengthen its proactive response to online problems and improve the reliability and effectiveness of the entire online patrol system.

[0085] The Simulation Department performs simulations based on social problems predicted by the Prediction Department. For example, the Simulation Department simulates the impact of a specific problem if it occurs. Specifically, the Simulation Department simulates the impact of a specific problem if it occurs, based on the prediction results provided by the Prediction Department. This involves modeling the occurrence and impact of the problem using simulation techniques such as system dynamics and agent-based modeling. For example, if a specific keyword suddenly increases, the Simulation Department can simulate how posts related to that keyword will spread and what impact they will have on society. For example, the Simulation Department performs simulations and provides information for taking countermeasures. This involves formulating countermeasures to prevent the occurrence of problems and response measures if problems occur, based on the simulation results. For example, the Simulation Department can simulate the impact of a specific problem if it occurs and provide information for taking countermeasures. This involves proposing specific countermeasures to relevant organizations and administrators based on the simulation results. The Simulation Department stores the simulation results in a database so that other departments can use them. The Simulation Department builds a feedback loop to continuously improve the accuracy of the simulation algorithm and provides the simulation results to the Learning Department. This allows the simulation unit to strengthen its proactive response to online issues and improve the overall performance of the online patrol system. Furthermore, based on the simulation results, the simulation unit reviews and optimizes the overall strategy of the online patrol system. This allows the simulation unit to strengthen its ability to respond to online issues and improve the reliability and effectiveness of the overall online patrol system.

[0086] The learning unit learns new trends and slang collected by the collection unit. Specifically, the learning unit automatically learns new trends and slang based on data provided by the collection unit. This involves using natural language processing techniques to extract new words and phrases from the collected text data and understanding their meaning and usage. For example, the learning unit analyzes new slang and trend words and understands their background and context. The learning unit continuously learns new trends and slang, keeping itself up-to-date. This involves regularly updating the data and incorporating new information to always grasp the latest trends and slang. The learning unit can also continuously learn new trends and slang and keep itself up-to-date. This involves continuously improving the learning algorithm and quickly incorporating new information to improve the accuracy and speed of learning. The learning unit stores the learning results in a database so that other units can use them. The learning unit builds a feedback loop to continuously improve the accuracy of the learning algorithm and provides the learning results to the analysis and detection units. This allows the learning unit to improve the overall performance of the network patrol system. Furthermore, based on the learning results, the learning unit can improve the algorithms of the analysis and detection units, enabling it to more accurately identify problems on the network. This allows the learning unit to improve the reliability and effectiveness of the entire network patrol system.

[0087] The analysis unit can perform text analysis, image recognition, and video analysis. For example, the analysis unit can perform text analysis. For example, the analysis unit can perform morphological analysis to analyze the structure of a text. For example, the analysis unit can perform grammatical analysis to analyze the grammatical structure of a text. For example, the analysis unit can perform semantic analysis to analyze the meaning of a text. For example, the analysis unit can perform image recognition. For example, the analysis unit can use a CNN (Convolutional Neural Network) to analyze the content of an image. For example, the analysis unit can use an object detection algorithm to detect objects in an image. For example, the analysis unit can perform video analysis. For example, the analysis unit can perform motion detection to analyze the motion in a video. For example, the analysis unit can perform frame analysis to analyze each frame of a video. For example, the analysis unit can perform action recognition to analyze actions in a video. In this way, the analysis unit can detect problematic posts from multiple angles by analyzing text, images, and videos. Some or all of the above-described processes in the analysis unit may be performed using a generation AI, for example, or without a generation AI. For example, the analysis unit can input text data into a generation AI, and the generation AI can perform text analysis. The analysis unit can input image data into a generation AI, and the generation AI can perform image recognition. The analysis unit can input video data into a generation AI, and the generation AI can perform video analysis.

[0088] The detection unit can detect posts that are social problems, such as illegal part-time jobs or suicides. For example, the detection unit can detect posts about illegal part-time jobs. For example, the detection unit can detect posts about illegal part-time jobs. For example, the detection unit can also detect posts about part-time jobs that are involved in crimes. For example, the detection unit can detect posts about suicide. For example, the detection unit can detect posts that are suicide threats. For example, the detection unit can also detect posts that are suicide-related. In this way, by detecting posts that are social problems, the detection unit can enable early detection and response to problems. 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 post data into a generating AI, and the generating AI can detect problematic posts.

[0089] The prediction unit can analyze specific keywords and trends to predict the next likely problem post. For example, the prediction unit can analyze specific keywords. For example, the prediction unit can analyze popular buzzwords to predict the next likely problem post. For example, the prediction unit can analyze keywords related to social issues to predict the next likely problem post. For example, the prediction unit can analyze trends. For example, the prediction unit can analyze specific trends to predict the next likely problem post. For example, the prediction unit can analyze specific trends to predict the next likely problem post. This allows the prediction unit to take countermeasures in advance by predicting the next likely problem post. Some or all of the above processing in the prediction unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the prediction unit can input keyword data into a generative AI, and the generative AI can predict the next likely problem post.

[0090] The simulation unit can simulate the impact of a specific problem occurring and provide information for taking countermeasures. For example, the simulation unit simulates the impact of a specific problem occurring. The simulation unit can simulate the impact of a specific problem occurring and provide information for taking countermeasures. The simulation unit can also simulate the impact of a specific problem occurring and provide information for taking countermeasures. This allows the simulation unit to take appropriate countermeasures by simulating the impact of a problem occurring. Some or all of the above processing in the simulation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the simulation unit can input problem data into a generative AI, which can then perform the simulation.

[0091] The learning unit can learn new trends and slang and stay up-to-date at all times. The learning unit can learn new trends and slang, for example. The learning unit can learn the latest trending words, for example. The learning unit can also learn internet memes, for example. The learning unit can continue to learn new trends and slang and stay up-to-date at all times. The learning unit can also learn new trends and slang and stay up-to-date at all times. This allows the learning unit to always conduct patrols based on the latest information by learning new trends and slang. Some or all of the above processing 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 trend data into a generative AI, which can learn new trends and slang.

[0092] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. For example, if the user is excited, the data collection unit can immediately collect data and perform rapid analysis. If the user is relaxed, the data collection unit can periodically collect data and adjust the frequency of analysis. If the user is stressed, the data collection unit can temporarily stop collecting data and wait for the user's emotions to calm down. This allows the data collection unit to collect data at the appropriate time by adjusting the timing according to the user'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 processing in the data collection unit may be performed using a generative AI, or not. For example, the data collection unit can input user emotion data into a generative AI, which can then estimate the emotions.

[0093] The collection unit can filter online postings based on specific keywords or phrases. For example, the collection unit can prioritize collecting postings containing specific keywords. For example, the collection unit can prioritize collecting postings containing keywords such as "illegal part-time jobs" or "suicide." The collection unit can filter and collect postings containing specific phrases. For example, the collection unit can filter and collect postings containing phrases such as "help me" or "I want to die." The collection unit can collect postings related to specific topics. For example, the collection unit can also collect postings related to crime or violence. This allows the collection unit to prioritize collecting important postings by filtering based on specific keywords or phrases. Some or all of the above processing in the collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the collection unit can input keyword data into a generative AI, which can then perform the filtering.

[0094] The collection unit can analyze a user's past posting history and select data to collect when collecting posts. For example, the collection unit can analyze a user's past posting history. For example, the collection unit can analyze a user's past posting history for the past year and select data to collect. For example, the collection unit can analyze a user's posting history on a specific topic and select data to collect. For example, the collection unit can prioritize the collection of problematic posts. For example, the collection unit can collect posts related to a specific topic. For example, the collection unit can select data to collect based on a user's past posting history and collect data efficiently. This allows the collection unit to efficiently collect highly relevant posts by analyzing a user's past posting history. Some or all of the above processing in the collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the collection unit can input posting history data into a generative AI, which can then select data to collect.

[0095] The data collection unit can estimate the user's emotions and determine the priority of posts to collect based on the estimated user emotions. For example, if the user is excited, the data collection unit will prioritize collecting urgent posts. For example, if the user is relaxed, the data collection unit will collect posts periodically and adjust the priority. For example, if the user is stressed, the data collection unit will prioritize collecting posts related to those emotions. In this way, the data collection unit can prioritize collecting important posts by determining the priority of posts to collect according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using a generative AI, or not using a generative AI. For example, the data collection unit can input user emotion data into a generative AI, which can estimate the emotions.

[0096] The collection unit can prioritize collecting posts that are highly relevant by considering the user's geographical location information when collecting posts. For example, the collection unit can prioritize collecting posts related to the user's current location. For example, the collection unit can collect posts related to problems occurring in a specific region. The collection unit can also select and collect posts that are highly relevant based on the user's geographical location information. In this way, the collection unit can prioritize collecting posts that are highly relevant by considering the user's geographical location information. Some or all of the above processing in the collection unit may be performed using, for example, a generation AI, or without a generation AI. For example, the collection unit can input geographical location data into a generation AI, and the generation AI can select posts that are highly relevant.

[0097] The collection unit can analyze a user's social media activity and collect relevant posts when collecting posts. For example, the collection unit can analyze a user's social media activity. For example, the collection unit can analyze a user's posting frequency and collect relevant posts. For example, the collection unit can analyze a user's number of followers and collect relevant posts. For example, the collection unit can analyze a user's number of likes and collect relevant posts. For example, the collection unit can collect posts from accounts that a user follows. For example, the collection unit can select and collect highly relevant posts based on a user's social media activity. In this way, the collection unit can efficiently collect highly relevant posts by analyzing a user's social media activity. Some or all of the above processing in the collection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the collection unit can input social media data into a generative AI, which can then select highly relevant posts.

[0098] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the user is excited, the analysis unit provides a concise and visually easy-to-understand presentation. For example, if the user is relaxed, the analysis unit provides detailed analysis results. For example, if the user is stressed, the analysis unit provides a simple and intuitive presentation. In this way, the analysis unit can provide appropriate analysis results by adjusting the presentation of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using a generative AI, or not using a generative AI. For example, the analysis unit can input user emotion data into a generative AI, and the generative AI can estimate the emotions.

[0099] The analysis unit can adjust the level of detail of the analysis based on the importance of the writes during the analysis. For example, the analysis unit performs a detailed analysis for high-importance writes. For example, the analysis unit performs a simplified analysis for low-importance writes. The analysis unit can also adjust the level of detail of the analysis according to the importance of the writes. This allows the analysis unit to perform efficient analysis by adjusting the level of detail of the analysis based on the importance of the writes. Some or all of the above processing in the analysis unit may be performed using a generation AI, for example, or without a generation AI. For example, the analysis unit can input the write data into a generation AI, and the generation AI can adjust the level of detail of the analysis based on importance.

[0100] The analysis unit can apply different analysis algorithms depending on the category of the post during analysis. For example, the analysis unit may apply a specific analysis algorithm to crime-related posts. For example, the analysis unit may apply a different analysis algorithm to health-related posts. The analysis unit can also select and apply the most suitable analysis algorithm depending on the category of the post. This improves the accuracy of the analysis by allowing the analysis unit to apply the most suitable analysis algorithm according to the category of the post. 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 category data into a generative AI, which can then apply the most suitable analysis algorithm.

[0101] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the user is in a hurry, the analysis unit provides a short, concise analysis result. For example, if the user is relaxed, the analysis unit provides a detailed analysis result. For example, if the user is excited, the analysis unit provides a visually easy-to-understand analysis result. In this way, the analysis unit can provide appropriate analysis results by adjusting the length of the analysis according to the user's emotions. 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 analysis unit may be performed using a generative AI, or not using a generative AI. For example, the analysis unit can input user emotion data into a generative AI, and the generative AI can estimate the emotions.

[0102] The analysis unit can determine the priority of analysis based on the posting date of the posts during the analysis. For example, the analysis unit may prioritize analyzing recent posts. For example, the analysis unit may prioritize analyzing posts that were concentrated within a specific period. The analysis unit can also adjust the priority of analysis based on the posting date. This allows the analysis unit to perform efficient analysis by determining the priority of analysis based on the posting date of the posts. Some or all of the above processing in the analysis unit may be performed using a generation AI, for example, or without a generation AI. For example, the analysis unit can input posting date data into a generation AI, and the generation AI can determine the priority of analysis.

[0103] The analysis unit can adjust the order of analysis based on the relevance of the writes during analysis. For example, the analysis unit may prioritize the analysis of highly relevant writes. For example, the analysis unit may postpone the analysis of less relevant writes. The analysis unit can also adjust the order of analysis based on the relevance of the writes. This allows the analysis unit to perform efficient analysis by adjusting the order of analysis based on the relevance of the writes. Some or all of the above processing in the analysis unit may be performed using a generation AI, for example, or without a generation AI. For example, the analysis unit may input relevance data into a generation AI, and the generation AI may adjust the order of analysis.

[0104] The detection unit can estimate the user's emotions and adjust the detection criteria based on the estimated user emotions. For example, if the user is excited, the detection unit will use strict criteria for detection. For example, if the user is relaxed, the detection unit will use flexible criteria for detection. For example, if the user is stressed, the detection unit will apply emotion-related criteria for detection. This allows the detection unit to perform appropriate detection by adjusting the detection criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the detection unit may be performed using a generative AI, or not using a generative AI. For example, the detection unit can input user emotion data into a generative AI, which can then estimate the emotions.

[0105] The detection unit can improve the accuracy of detection by considering the interrelationships of posts during detection. For example, the detection unit groups related posts and performs detection while considering their interrelationships. For example, the detection unit analyzes the interrelationships of posts to perform highly accurate detection. For example, the detection unit can also detect problematic posts based on the interrelationships of posts. In this way, the detection unit can perform highly accurate detection by considering the interrelationships of posts. 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 interrelationship data into a generating AI, which can then improve the accuracy of detection.

[0106] The detection unit can perform detection while considering the attribute information of the poster of the post. For example, the detection unit can perform detection while considering attribute information such as the poster's age and gender. For example, the detection unit can perform detection based on the poster's past posting history. For example, the detection unit can also detect problematic posts based on the poster's attribute information. In this way, the detection unit can perform appropriate detection by considering the poster'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 using a generating AI. For example, the detection unit can input attribute information data into a generating AI, and the generating AI can perform detection.

[0107] The detection unit can estimate the user's emotions and adjust the order in which the detection results are displayed based on the estimated emotions. For example, if the user is excited, the detection unit will prioritize displaying important results. If the user is relaxed, the detection unit will prioritize displaying detailed results in order. If the user is stressed, the detection unit will prioritize displaying concise results. This allows the detection unit to provide appropriate information by adjusting the display order of detection results according to the user'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 processing in the detection unit may be performed using a generative AI, or not. For example, the detection unit can input user emotion data into a generative AI, which can then estimate the emotions.

[0108] The detection unit can perform detection while considering the geographical distribution of posts. For example, the detection unit can prioritize the detection of posts concentrated in a specific area. For example, the detection unit can detect problematic posts based on geographical distribution. The detection unit can also perform highly accurate detection by considering the geographical distribution of posts. As a result, the detection unit can perform highly accurate detection by considering the geographical distribution of posts. 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 geographical distribution data into a generative AI, and the generative AI can perform the detection.

[0109] The detection unit can improve the accuracy of detection by referring to related literature during detection. For example, the detection unit performs detection by referring to related academic papers. For example, the detection unit performs detection based on related news articles. The detection unit can also perform highly accurate detection by referring to related literature. This enables the detection unit to perform highly accurate detection by referring to related 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 related literature data into a generating AI, and the generating AI can perform detection.

[0110] The reporting unit can estimate the user's emotions and adjust the way the report is presented based on the estimated emotions. For example, if the user is excited, the reporting unit will provide a concise and visually easy-to-understand report. For example, if the user is relaxed, the reporting unit will provide a detailed report. For example, if the user is stressed, the reporting unit will provide a simple and intuitive report. This allows the reporting unit to provide appropriate reports by adjusting the way the report is presented according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reporting unit may be performed using a generative AI, or not using a generative AI. For example, the reporting unit can input user emotion data into a generative AI, which can then estimate the emotions.

[0111] The reporting unit can adjust the level of detail in its reports based on the importance of the entries. For example, the reporting unit can provide detailed reports for high-importance entries, or simplified reports for low-importance entries. The reporting unit can also adjust the level of detail in its reports according to the importance of the entries. This allows the reporting unit to provide efficient reports by adjusting the level of detail based on the importance of the entries. Some or all of the above processing in the reporting unit may be performed using, for example, a generating AI, or without a generating AI. For example, the reporting unit can input the entry data into a generating AI, which can then adjust the level of detail in its reports based on importance.

[0112] The reporting unit can apply different reporting algorithms depending on the category of the post when reporting. For example, the reporting unit may apply a specific reporting algorithm to crime-related posts. For example, the reporting unit may apply a different reporting algorithm to health-related posts. The reporting unit can also select and apply the most suitable reporting algorithm depending on the category of the post. This improves the accuracy of the report by allowing the reporting unit to apply the most suitable reporting algorithm according to the category of the post. Some or all of the above processing in the reporting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reporting unit can input category data into a generative AI, which can then apply the most suitable reporting algorithm.

[0113] The reporting unit can estimate the user's emotions and adjust the length of the report based on the estimated emotions. For example, if the user is in a hurry, the reporting unit will provide a short, concise report. If the user is relaxed, the reporting unit will provide a detailed report. If the user is excited, the reporting unit will provide a visually easy-to-understand report. This allows the reporting unit to provide an appropriate report by adjusting the length of the report according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reporting unit may be performed using a generative AI, or not using a generative AI. For example, the reporting unit can input user emotion data into a generative AI, which can then estimate the emotions.

[0114] The reporting unit can determine the priority of reports based on the posting date of the entries. For example, the reporting unit may prioritize reporting recent entries. For example, the reporting unit may prioritize reporting entries that were concentrated within a specific period. The reporting unit can also adjust the priority of reports based on the posting date. This allows the reporting unit to perform efficient reporting by determining the priority of reports based on the posting date of the entries. Some or all of the above processing in the reporting unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reporting unit can input posting date data into a generative AI, and the generative AI can determine the priority of reports.

[0115] The reporting unit can adjust the order of reports based on the relevance of the entries when reporting. For example, the reporting unit may prioritize reporting highly relevant entries. For example, the reporting unit may postpone reporting less relevant entries. The reporting unit can also adjust the order of reports based on the relevance of the entries. This allows the reporting unit to perform efficient reporting by adjusting the order of reports based on the relevance of the entries. Some or all of the above processing in the reporting unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reporting unit can input relevance data into a generative AI, and the generative AI can adjust the order of reports.

[0116] The prediction unit can estimate the user's emotions and adjust the display method of the prediction based on the estimated user emotions. For example, if the user is excited, the prediction unit provides a concise and visually easy-to-understand display method. For example, if the user is relaxed, the prediction unit provides detailed prediction results. For example, if the user is stressed, the prediction unit provides a simple and intuitive display method. In this way, the prediction unit can provide appropriate prediction results by adjusting the display method of the prediction according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI 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 prediction unit may be performed using a generative AI, or not using a generative AI. For example, the prediction unit can input user emotion data into a generative AI, and the generative AI can estimate the emotions.

[0117] The prediction unit can optimize the current prediction by referring to past data during the prediction process. For example, the prediction unit optimizes the current prediction based on past posting data. For example, the prediction unit analyzes past trends and reflects them in the current prediction. The prediction unit can also make highly accurate predictions by referring to past data. As a result, the prediction unit can make highly accurate predictions by optimizing the current prediction by referring to past data. Some or all of the above processes in the prediction unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the prediction unit can input past data into a generative AI, and the generative AI can optimize the current prediction.

[0118] The prediction unit can apply different prediction methods to each category of post during prediction. For example, the prediction unit may apply a specific prediction method to crime-related posts. For example, it may apply a different prediction method to health-related posts. The prediction unit can also select and apply the optimal prediction method according to the category of post. This improves the accuracy of predictions by applying the optimal prediction method to each category of post. Some or all of the above processing in the prediction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the prediction unit can input category data into a generative AI, which can then apply the optimal prediction method.

[0119] The prediction unit can estimate the user's emotions and adjust the importance of predictions based on the estimated emotions. For example, if the user is excited, the prediction unit will prioritize displaying important prediction results. For example, if the user is relaxed, the prediction unit will provide detailed prediction results. For example, if the user is stressed, the prediction unit will prioritize displaying concise prediction results. In this way, the prediction unit can provide appropriate prediction results by adjusting the importance of predictions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the prediction unit may be performed using a generative AI, or not using a generative AI. For example, the prediction unit can input user emotion data into a generative AI, which can then estimate the emotions.

[0120] The prediction unit can analyze changes in predictions based on the posting time of the posts during the prediction process. For example, the prediction unit analyzes changes in predictions based on the posting time. For example, the prediction unit makes predictions based on posts that were concentrated during a specific period. For example, the prediction unit can analyze changes in predictions according to the posting time and make the optimal prediction. This enables the prediction unit to make highly accurate predictions by analyzing changes in predictions based on the posting time of the posts. Some or all of the above processing in the prediction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the prediction unit can input posting time data into a generative AI, and the generative AI can analyze changes in predictions.

[0121] The prediction unit can analyze its predictions by referring to relevant market data for writing during the prediction process. For example, the prediction unit makes predictions based on relevant market data. For example, the prediction unit makes highly accurate predictions by referring to relevant market data. For example, the prediction unit can also analyze relevant market data for writing and make optimal predictions. This enables the prediction unit to make highly accurate predictions by referring to relevant market data. Some or all of the above processing in the prediction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the prediction unit can input market data into a generative AI, and the generative AI can make predictions.

[0122] The simulation unit can estimate the user's emotions and adjust the simulation method based on the estimated user emotions. For example, if the user is excited, the simulation unit provides a concise and visually easy-to-understand simulation. For example, if the user is relaxed, the simulation unit provides detailed simulation results. For example, if the user is stressed, the simulation unit provides a simple and intuitive simulation. This allows the simulation unit to provide an appropriate simulation by adjusting the simulation method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the simulation unit may be performed using a generative AI, or not using a generative AI. For example, the simulation unit can input user emotion data into a generative AI, and the generative AI can estimate the emotions.

[0123] The simulation unit can optimize the simulation algorithm by referring to past data during the simulation. For example, the simulation unit optimizes the simulation algorithm based on past posting data. For example, the simulation unit analyzes past trends and reflects them in the simulation. For example, the simulation unit can perform highly accurate simulations by referring to past data. This enables the simulation unit to perform highly accurate simulations by optimizing the simulation algorithm by referring to past data. Some or all of the above processes in the simulation unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the simulation unit can input past data into a generative AI, and the generative AI can optimize the simulation algorithm.

[0124] The simulation unit can apply different simulation methods to each category of writing during the simulation. For example, the simulation unit can apply a specific simulation method to crime-related writings. For example, the simulation unit can apply a different simulation method to health-related writings. The simulation unit can also select and apply the optimal simulation method according to the category of writing. This improves the accuracy of the simulation by applying the optimal simulation method to each category of writing. Some or all of the above processing in the simulation unit may be performed using a generative AI, for example, or without a generative AI. For example, the simulation unit can input category data into a generative AI, which can then apply the optimal simulation method.

[0125] The simulation unit can estimate the user's emotions and determine the priority of simulations based on the estimated user emotions. For example, if the user is excited, the simulation unit will prioritize important simulations. For example, if the user is relaxed, the simulation unit will provide detailed simulations. For example, if the user is stressed, the simulation unit will prioritize concise simulations. In this way, the simulation unit can provide appropriate simulations by determining the priority of simulations according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the simulation unit may be performed using a generative AI, or not using a generative AI. For example, the simulation unit can input user emotion data into a generative AI, and the generative AI can estimate emotions.

[0126] The simulation unit can perform simulations while considering the geographical distribution of posts. For example, the simulation unit can perform simulations based on posts concentrated in a specific area. For example, the simulation unit can simulate problematic posts based on geographical distribution. The simulation unit can also perform highly accurate simulations by considering the geographical distribution of posts. This enables the simulation unit to perform highly accurate simulations by considering the geographical distribution of posts. Some or all of the above processing in the simulation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the simulation unit can input geographical distribution data into a generative AI, and the generative AI can perform the simulation.

[0127] The simulation unit can improve the accuracy of the simulation by referring to relevant literature during the simulation. For example, the simulation unit performs simulations by referring to relevant academic papers. For example, the simulation unit performs simulations based on relevant news articles. For example, the simulation unit can also perform highly accurate simulations by referring to relevant literature. In this way, the simulation unit can perform highly accurate simulations by referring to relevant literature. Some or all of the above processing in the simulation unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the simulation unit can input relevant literature data into a generative AI, and the generative AI can perform the simulation.

[0128] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is excited, the learning unit will prioritize learning important data. For example, if the user is relaxed, the learning unit will prioritize learning detailed data. For example, if the user is stressed, the learning unit will prioritize learning concise data. This allows the learning unit to perform appropriate learning by selecting training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using a generative AI, or not using a generative AI. For example, the learning unit can input user emotion data into a generative AI, and the generative AI can estimate the emotions.

[0129] The learning unit can optimize its learning algorithm by referring to past learning data during the learning process. For example, the learning unit optimizes the learning algorithm based on past learning data. For example, the learning unit analyzes past trends and reflects them in the learning process. For example, the learning unit can perform highly accurate learning by referring to past data. This enables highly accurate learning by optimizing the learning algorithm 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 data into a generative AI, and the generative AI can optimize the learning algorithm.

[0130] The learning unit can build a feedback loop to quickly incorporate new trends and slang during the learning process. For example, the learning unit can extract new trends and slang from user posts and reflect them in the learning data. The learning unit can also learn new trends and slang in real time and always maintain an up-to-date state. This allows the learning unit to always maintain an up-to-date state by quickly incorporating new trends and slang. 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 trend data into a generative AI, which can then learn new trends and slang.

[0131] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated emotions. For example, if the user is excited, the learning unit will learn frequently. For example, if the user is relaxed, the learning unit will learn regularly. For example, if the user is stressed, the learning unit will reduce the frequency of learning. This allows the learning unit to perform appropriate learning by adjusting the frequency of learning according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI 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 a generative AI, or not using a generative AI. For example, the learning unit can input user emotion data into a generative AI, and the generative AI can estimate emotions.

[0132] The learning unit can weight the training data based on the posting date of the posts during training. For example, the learning unit can weight the training data by giving more emphasis to recent posts. For example, the learning unit can weight the training data by giving more emphasis to posts that were concentrated in a specific period. The learning unit can also adjust the weighting of the training data based on the posting date. This enables the learning unit to perform highly accurate training by weighting the training data based on the posting date of the posts. Some or all of the above processing in the learning unit may be performed using a generative AI, for example, or without a generative AI. For example, the learning unit can input posting date data into a generative AI, and the generative AI can perform the weighting of the training data.

[0133] The learning unit can improve the accuracy of its learning by referring to relevant market data during the learning process. For example, the learning unit performs learning based on relevant market data. For example, the learning unit performs highly accurate learning by referring to relevant market data. The learning unit can also perform optimal learning by analyzing relevant market data for writing. This enables the learning unit to perform highly accurate learning by referring to relevant market data. Some or all of the above processing 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 market data into a generative AI, and the generative AI can perform learning.

[0134] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0135] The internet patrol system may also include a behavioral analysis unit that analyzes the user's behavioral history. The behavioral analysis unit, for example, analyzes the user's past browsing and click history to provide auxiliary information for detecting problematic posts. For example, the behavioral analysis unit can analyze the frequency of visits to specific sites or pages to improve the accuracy of problematic post detection. The behavioral analysis unit can also analyze the user's click patterns to aid in the detection of problematic posts. In this way, the behavioral analysis unit can improve the accuracy of problematic post detection by analyzing the user's behavioral history.

[0136] The analysis unit can further perform sentiment analysis of posts using natural language processing technology. For example, the analysis unit can classify posts into positive, negative, and neutral sentiments. The analysis unit can also calculate sentiment scores for posts and evaluate the intensity of those sentiments. For example, the analysis unit can track changes in sentiment over time and analyze sentiment trends. As a result, the analysis unit can improve the accuracy of detecting problematic posts by performing sentiment analysis on posts.

[0137] The detection unit can further improve the accuracy of detecting problematic posts by analyzing the user's social network. For example, the detection unit can analyze the user's friendships and follower relationships to assess the risk of problematic posts spreading. The detection unit can also analyze the user's influence within their social network to assess the impact of problematic posts. For example, the detection unit can analyze the relationships between posts within the user's social network to improve the accuracy of detecting problematic posts. In this way, the detection unit can improve the accuracy of detecting problematic posts by analyzing the user's social network.

[0138] The prediction unit can further estimate the user's emotions and improve the accuracy of its predictions based on the estimated emotions. For example, if the user is excited, the prediction unit can predict the next problem that is likely to occur based on changes in emotions. For example, if the user is relaxed, the prediction unit can also predict the next problem that is likely to occur based on emotional stability. For example, if the user is stressed, the prediction unit can also predict the next problem that is likely to occur based on emotional instability. In this way, the prediction unit can improve the accuracy of its predictions based on the user's emotions.

[0139] The simulation unit can further incorporate user behavior patterns into the simulation. For example, the simulation unit can simulate a user's reaction when a specific problem occurs, based on the user's past behavior data. The simulation unit can also analyze user behavior patterns and simulate the impact of a problem when it occurs. For example, the simulation unit can simulate countermeasures when a problem occurs, based on user behavior patterns. In this way, the simulation unit can perform more realistic simulations by incorporating user behavior patterns into the simulation.

[0140] The learning unit can further estimate the user's emotions and adjust the learning content based on the estimated emotions. For example, if the user is excited, the learning unit will prioritize learning emotion-related data. For example, if the user is relaxed, the learning unit can also learn detailed data. For example, if the user is stressed, the learning unit can also prioritize learning concise data. This allows the learning unit to perform appropriate learning by adjusting the learning content based on the user's emotions.

[0141] The data collection unit can further consider the user's geographical information and prioritize the collection of posts related to a specific region. For example, the data collection unit can prioritize the collection of posts related to the user's current location. The data collection unit can also, for example, collect posts related to problems occurring in a specific region. The data collection unit can also, for example, select and collect highly relevant posts based on the user's geographical information. In this way, the data collection unit can prioritize the collection of highly relevant posts by considering the user's geographical information.

[0142] The analysis unit can further estimate the user's emotions and determine the analysis priority based on the estimated emotions. For example, if the user is excited, the analysis unit will prioritize analyzing posts of high urgency. For example, if the user is relaxed, the analysis unit can also analyze posts at regular intervals. For example, if the user is stressed, the analysis unit can also prioritize analyzing posts related to emotions. In this way, the analysis unit can prioritize the analysis of important posts by determining the analysis priority based on the user's emotions.

[0143] The detection unit can further analyze the user's behavior history to improve the accuracy of detecting problematic posts. For example, the detection unit can analyze the user's past posting history to provide auxiliary information for detecting problematic posts. The detection unit can also analyze the user's browsing history to improve the accuracy of detecting problematic posts. For example, the detection unit can analyze the user's click history to help detect problematic posts. In this way, the detection unit can improve the accuracy of detecting problematic posts by analyzing the user's behavior history.

[0144] The reporting unit can further estimate the user's emotions and prioritize reports based on those emotions. For example, if the user is agitated, the reporting unit will prioritize urgent reports. If the user is relaxed, the reporting unit may also prioritize regular reports. If the user is stressed, the reporting unit may also prioritize reports related to emotions. This allows the reporting unit to prioritize important reports by determining their priority based on the user's emotions.

[0145] The following briefly describes the processing flow for example form 2.

[0146] Step 1: The collection unit collects online postings. For example, the collection unit collects posts from social media and message boards. The collection unit can collect not only text but also images and videos. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit can perform, for example, text analysis, image recognition, and video analysis. Step 3: The detection unit detects problematic posts based on the data analyzed by the analysis unit. The detection unit can detect posts that are social problems, such as illegal part-time jobs or suicides, illegal posts, and defamatory posts. Step 4: The reporting unit reports the problematic posts detected by the detection unit. The reporting unit may, for example, report the problematic posts to administrators or relevant organizations. Step 5: The prediction unit predicts the next social problem that is likely to occur based on the historical data analyzed by the analysis unit. For example, the prediction unit analyzes specific keywords or trends to predict the next problem post. Step 6: The simulation unit performs simulations based on the social problems predicted by the prediction unit. For example, the simulation unit simulates the impact of a specific problem occurring and provides information for taking countermeasures. Step 7: The learning unit learns new trends and slang collected by the collection unit. The learning unit, for example, continues to learn new trends and slang to stay up-to-date.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] Each of the multiple elements described above, including the collection unit, analysis unit, detection unit, reporting unit, prediction unit, simulation 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 online postings using the camera 42 and communication I / F 44 of the smart device 14. The analysis unit analyzes the collected data using the identification processing unit 290 of the data processing unit 12. The detection unit detects problematic posts based on the analysis results using the identification processing unit 290 of the data processing unit 12. The reporting unit reports the detected problematic posts using the control unit 46A of the smart device 14. The prediction unit predicts likely social problems based on past data using the identification processing unit 290 of the data processing unit 12. The simulation unit performs simulations based on the social problems predicted by the identification processing unit 290 of the data processing unit 12. The learning unit learns new trends and slang using the control unit 46A of the smart device 14. 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.

[0151] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] Each of the multiple elements described above, including the collection unit, analysis unit, detection unit, reporting unit, prediction unit, simulation unit, and learning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit collects online postings using the camera 42 and communication I / F 44 of the smart glasses 214. The analysis unit analyzes the collected data using the identification processing unit 290 of the data processing unit 12. The detection unit detects problematic posts based on the analysis results using the identification processing unit 290 of the data processing unit 12. The reporting unit reports the detected problematic posts using the control unit 46A of the smart glasses 214. The prediction unit predicts likely social problems based on past data using the identification processing unit 290 of the data processing unit 12. The simulation unit performs simulations based on the social problems predicted by the identification processing unit 290 of the data processing unit 12. The learning unit learns new trends and slang using the control unit 46A of the smart glasses 214. 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.

[0167] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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).

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.).

[0179] 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.

[0180] 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.

[0181] 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.

[0182] Each of the multiple elements described above, including the collection unit, analysis unit, detection unit, reporting unit, prediction unit, simulation 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 online postings using the camera 42 and communication I / F 44 of the headset terminal 314. The analysis unit analyzes the collected data using the identification processing unit 290 of the data processing unit 12. The detection unit detects problematic posts based on the analysis results using the identification processing unit 290 of the data processing unit 12. The reporting unit reports the detected problematic posts using the control unit 46A of the headset terminal 314. The prediction unit predicts likely social problems based on past data using the identification processing unit 290 of the data processing unit 12. The simulation unit performs simulations based on the social problems predicted by the identification processing unit 290 of the data processing unit 12. The learning unit learns new trends and slang using the control unit 46A of the headset terminal 314. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0183] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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).

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.).

[0196] 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.

[0197] 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.

[0198] 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.

[0199] Each of the multiple elements described above, including the collection unit, analysis unit, detection unit, reporting unit, prediction unit, simulation unit, and learning unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the collection unit collects online postings using the camera 42 and communication I / F 44 of the robot 414. The analysis unit analyzes the collected data using the identification processing unit 290 of the data processing unit 12. The detection unit detects problematic posts based on the analysis results using the identification processing unit 290 of the data processing unit 12. The reporting unit reports the detected problematic posts using the control unit 46A of the robot 414. The prediction unit predicts likely social problems based on past data using the identification processing unit 290 of the data processing unit 12. The simulation unit performs simulations based on the social problems predicted by the identification processing unit 290 of the data processing unit 12. The learning unit learns new trends and slang using the control unit 46A of the robot 414. 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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."

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] (Note 1) A collection department that collects online postings, An analysis unit analyzes the data collected by the aforementioned collection unit, A detection unit detects problematic posts based on the data analyzed by the aforementioned analysis unit, A reporting unit reports problematic posts detected by the aforementioned detection unit, A prediction unit predicts the next social problem that is likely to occur based on past data analyzed by the aforementioned analysis unit, A simulation unit that performs simulations based on the social problems predicted by the prediction unit, The system includes a learning unit that learns new trends and slang collected by the aforementioned collection unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Performs text analysis, image recognition, and video analysis. The system described in Appendix 1, characterized by the features described herein. (Note 3) The detection unit is Posts related to illegal part-time jobs and suicides, which are causing social problems, were detected. The system described in Appendix 1, characterized by the features described herein. (Note 4) The prediction unit, By analyzing specific keywords and trends, we predict the next problematic posts that are likely to appear. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned simulation unit, It simulates the impact of a specific problem and provides information to help implement countermeasures. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned learning unit, Learn new trends and slang to stay up-to-date. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is The system estimates user sentiment and adjusts the timing of post collection based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is When collecting online postings, filtering is performed based on specific keywords or phrases. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting posts, the system analyzes the user's past posting history to select which posts to collect. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates user sentiment and determines the priority of posts to collect based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting posts, the system prioritizes collecting posts that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting posts, the system analyzes users' social media activity and collects relevant posts. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, The system estimates the user's emotions and adjusts 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, the level of detail of the analysis is adjusted based on the importance of the write. 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 category of the write. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts the length of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, the priority of analysis is determined based on the posting date of the comments. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the writes. The system described in Appendix 1, characterized by the features described herein. (Note 19) The detection unit is It estimates the user's emotions and adjusts the detection criteria based on the estimated user 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 of the write operations. The system described in Appendix 1, characterized by the features described herein. (Note 21) The detection unit is During detection, the attribute information of the poster of the post is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 22) The detection unit is It estimates the user's sentiment and adjusts the order in which the detection results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The detection unit is During detection, the geographical distribution of writes is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 24) The detection unit is During detection, the accuracy of the detection is improved by referring to related literature for the writing. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned reporting department, The system estimates the user's emotions and adjusts the way reports are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned reporting department, When reporting, adjust the level of detail in the report based on the importance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned reporting department, When reporting, different reporting algorithms are applied depending on the category of the post. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned reporting department, The system estimates the user's sentiment and adjusts the length of the report based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned reporting department, When reporting, prioritize reports based on when they were posted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned reporting department, When reporting, adjust the order of reports based on the relevance of the posts. The system described in Appendix 1, characterized by the features described herein. (Note 31) The prediction unit, It estimates the user's emotions and adjusts how predictions are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The prediction unit, When making predictions, we optimize the current prediction by referring to past data. The system described in Appendix 1, characterized by the features described herein. (Note 33) The prediction unit, When making predictions, different prediction methods are applied for each category of writes. The system described in Appendix 1, characterized by the features described herein. (Note 34) The prediction unit, It estimates the user's emotions and adjusts the importance of the prediction based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The prediction unit, When making predictions, we analyze how the predictions change based on when the posts were made. The system described in Appendix 1, characterized by the features described herein. (Note 36) The prediction unit, When making predictions, we analyze the forecast by referring to relevant market data for writing. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned simulation unit, It estimates the user's emotions and adjusts the simulation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned simulation unit, During simulation, the simulation algorithm is optimized by referring to past data. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned simulation unit, During simulation, different simulation methods are applied to each category of write operation. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned simulation unit, It estimates the user's emotions and determines the priority of simulations based on the estimated user emotions. The system according to Appendix 1, characterized in that... (Appendix 41) The simulation unit performs simulation considering the geographical distribution of writes during simulation The system according to Appendix 1, characterized in that... (Appendix 42) The simulation unit improves the accuracy of simulation by referring to relevant documents of writes during simulation The system according to Appendix 1, characterized in that... (Appendix 43) The learning unit [[ID=二十ー]] estimates the user's emotion and selects learning data based on the estimated user's emotion The system according to Appendix 1, characterized in that... (Appendix 44) The learning unit optimizes the learning algorithm by referring to past learning data during learning The system according to Appendix 1, characterized in that... (Appendix 45) The learning unit constructs a feedback loop for rapidly incorporating new trends and slang during learning The system according to Appendix 1, characterized in that... (Appendix 46) The learning unit estimates the user's emotion and adjusts the learning frequency based on the estimated user's emotion The system according to Appendix 1, characterized in that... (Appendix 47) The learning unit performs weighting of learning data based on the posting time of writes during learning ] The system according to Appendix 1, characterized in that... (Appendix 48) The learning unit improves the accuracy of learning by referring to relevant market data of writes during learning The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0219] 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. A collection department that collects online postings, An analysis unit analyzes the data collected by the aforementioned collection unit, A detection unit detects problematic posts based on the data analyzed by the aforementioned analysis unit, A reporting unit reports problematic posts detected by the aforementioned detection unit, A prediction unit predicts the next social problem that is likely to occur based on past data analyzed by the aforementioned analysis unit, A simulation unit that performs simulations based on the social problems predicted by the prediction unit, The system includes a learning unit that learns new trends and slang collected by the aforementioned collection unit. A system characterized by the following features.

2. The aforementioned analysis unit, Performs text analysis, image recognition, and video analysis. The system according to feature 1.

3. The detection unit is Posts related to illegal part-time jobs and suicides, which are causing social problems, were detected. The system according to feature 1.

4. The prediction unit, By analyzing specific keywords and trends, we predict the next problematic posts that are likely to appear. The system according to feature 1.

5. The aforementioned simulation unit, It simulates the impact of a specific problem and provides information to help implement countermeasures. The system according to feature 1.

6. The aforementioned learning unit, Learn new trends and slang to stay up-to-date. The system according to feature 1.

7. The aforementioned collection unit is The system estimates user sentiment and adjusts the timing of post collection based on the estimated user sentiment. The system according to feature 1.

8. The aforementioned collection unit is When collecting online postings, filtering is performed based on specific keywords or phrases. The system according to feature 1.

9. The aforementioned collection unit is When collecting posts, the system analyzes the user's past posting history to select which posts to collect. The system according to feature 1.

10. The aforementioned collection unit is It estimates user sentiment and determines the priority of posts to collect based on the estimated user sentiment. The system according to feature 1.

Images