system

Abstract

The system according to this embodiment aims to efficiently identify illegal content in job advertisements and posts and issue warnings. [Solution] The system according to the embodiment comprises a monitoring unit, an analysis unit, an identification unit, and a warning unit. The monitoring unit monitors job advertisements and posts. The analysis unit analyzes the information monitored by the monitoring unit. The identification unit identifies illegal content based on the information analyzed by the analysis unit. The warning unit issues a warning based on the illegal content identified by the identification unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to efficiently identify illegal content in job advertisements and posts and issue warnings.

[0005] The system according to the embodiment aims to efficiently identify illegal content in job advertisements and posts and issue warnings.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a monitoring unit, an analysis unit, an identification unit, and a warning unit. The monitoring unit monitors job advertisements and posts. The analysis unit analyzes the information monitored by the monitoring unit. The identification unit identifies illegal content based on the information analyzed by the analysis unit. The warning unit issues a warning based on the illegal content identified by the identification unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently identify illegal content in job advertisements and posts and issue warnings. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

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

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

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

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example of form 1) The AI ​​agent system according to an embodiment of the present invention is designed to prevent the recruitment and application of illegal part-time jobs (illegal part-time jobs). This system monitors job platforms and social media, uses generative AI and data analysis technology to identify illegal activities, and issues warnings to authorities and platform administrators. It also issues warnings when someone who sees a job posting attempts to apply. For example, the AI ​​agent system monitors job advertisements and posts on job platforms and social media. Using generative AI and natural language processing (NLP), it analyzes the content of job advertisements and posts and automatically detects illegal content and suspicious language. For example, it analyzes posts containing keywords such as "high pay," "easy work," and "no experience necessary" to determine if they are potentially illegal. Next, it uses data analysis tools to process large amounts of job data in real time and detect anomaly patterns. For example, it analyzes job advertisements that are rapidly increasing in specific regions or industries to identify signs of illegal activity. It also monitors social media and bulletin board posts to identify illegal recruitment. If an illegal job posting is discovered, the warning system is activated and immediately notifies platform administrators and relevant authorities. For example, if an illegal job advertisement is discovered, the information is notified to the platform administrator, who is urged to remove the advertisement. Information is also provided to law enforcement agencies to support swift investigation and response. Furthermore, warnings are issued when someone attempts to apply for a job posting. For instance, if a job seeker attempts to apply for an illegal job, a warning message is displayed, urging them to avoid suspicious postings. This significantly reduces the risk of job seekers becoming involved in illegal employment. This mechanism improves the safety and reliability of job platforms and social media, creating a safer environment for users. It also contributes to the eradication of illegal employment by providing information to law enforcement agencies. In this way, the AI ​​agent system can prevent illegal job postings and applications.

[0029] The AI ​​agent system according to this embodiment comprises a monitoring unit, an analysis unit, an identification unit, and a warning unit. The monitoring unit monitors job advertisements and posts. The monitoring unit can, for example, monitor job advertisements and posts on job platforms and social media in real time. The monitoring unit can also perform periodic scans to detect illegal activities early. For example, the monitoring unit can analyze the frequency of occurrence of specific keywords and phrases in real time and detect abnormal patterns. The analysis unit analyzes the information monitored by the monitoring unit using generative AI and natural language processing. The analysis unit can, for example, analyze the content of job advertisements and posts using text analysis and data mining techniques. The analysis unit can also summarize the content of job advertisements and posts using generative AI and identify illegal content and suspicious language. The identification unit identifies illegal content based on the information analyzed by the analysis unit. The identification unit can, for example, automatically detect fraudulent job postings and false information. The identification unit can also detect suspicious language and assess the possibility of illegal activity. The warning unit issues warnings based on the illegal content identified by the identification unit. The warning unit can, for example, send email notifications or pop-up messages to platform administrators or relevant authorities. The warning unit can also display warning messages to job seekers to reduce the risk of becoming involved in illegal job postings. As a result, the AI ​​agent system according to the embodiment can monitor job advertisements and posts, identify illegal content, and issue warnings.

[0030] The monitoring unit monitors job advertisements and posts. For example, the monitoring unit can monitor job advertisements and posts on job platforms and social media in real time. Specifically, the monitoring unit accesses multiple job sites and social media platforms on the internet and collects data regularly. This includes methods such as using web scraping techniques and APIs to obtain text data of job advertisements and posts. The monitoring unit analyzes the collected data in real time and monitors the frequency of occurrence of specific keywords and phrases. For example, if keywords such as "high salary," "no experience necessary," and "immediate start" appear frequently, it may indicate an illegal job advertisement. Furthermore, the monitoring unit can identify anomalies by comparing them with historical data to detect unusual patterns. For example, a sudden increase in job advertisements in a particular region or industry may be a sign of fraudulent activity. The monitoring unit detects these anomalies early and provides the data to the analysis unit, which is the next step. This allows the monitoring unit to monitor job advertisements and posts efficiently and effectively and detect illegal activity early.

[0031] The Analysis Department analyzes information monitored by the Monitoring Department using generative AI and natural language processing. Specifically, the Analysis Department analyzes the content of job advertisements and posts using text analysis and data mining techniques. Generative AI, for example, uses large-scale language models to summarize the content of job advertisements and posts and extract important information. Natural language processing techniques are used to understand the meaning of the text and identify illegal content or suspicious language. For example, generative AI analyzes the text of job advertisements to check if keywords such as "high income," "no experience necessary," and "immediate start" are included. Generative AI can also understand the context of job advertisements and identify fraudulent or false information. Furthermore, the Analysis Department uses data mining techniques to analyze patterns in job advertisements and posts and detect anomaly patterns. For example, a sudden increase in job advertisements in a particular region or industry may be a sign of fraudulent activity. The Analysis Department identifies these anomalies and provides the data to the Identification Department, which is the next step. This allows the Analysis Department to analyze the content of job advertisements and posts in detail and identify illegal content or suspicious language.

[0032] The Identification Department identifies illegal content based on information analyzed by the Analysis Department. Specifically, the Identification Department can automatically detect fraudulent job postings and false information. For example, the Identification Department can identify fraudulent job postings based on the content of job postings analyzed by the Generating AI. Fraudulent job postings often attract job seekers by offering attractive conditions such as excessive pay or immediate start. The Identification Department automatically detects job postings containing these conditions and assesses the possibility of illegal activity. The Identification Department can also detect suspicious language and assess the possibility of illegal activity. For example, if keywords such as "high income," "no experience necessary," and "immediate start" appear frequently, it may be an illegal job posting. The Identification Department automatically detects job postings containing these keywords and assesses the possibility of illegal activity. Furthermore, the Identification Department can utilize historical data and statistical information to conduct long-term risk assessments and trend analyses. For example, based on past data on fraudulent job postings, it can predict fluctuations in risk in specific regions or industries and formulate future countermeasures. This allows the relevant department to analyze the content of job advertisements and posts in detail and identify illegal content or suspicious language.

[0033] The warning unit issues warnings based on illegal content identified by the identification unit. Specifically, the warning unit can send email notifications and pop-up messages to platform administrators and relevant authorities. For example, if the identification unit identifies a fraudulent job advertisement, the warning unit will send an email notification to the platform administrator instructing them to remove the advertisement. The warning unit can also send pop-up messages to relevant authorities reporting the possibility of illegal activity. Furthermore, the warning unit can display warning messages to job seekers to reduce the risk of becoming involved in illegal job postings. For example, if a job seeker attempts to apply for a fraudulent job advertisement, the warning unit will display a warning message to the job seeker, informing them of the potential fraud. The warning message will be displayed on the job seeker's smartphone or computer and can be alerted through voice guidance or vibration notifications. This allows the warning unit to quickly provide appropriate warnings to each user, minimizing the risk of becoming involved in illegal job postings. In addition, the warning unit can collect user feedback and continuously improve the accuracy and effectiveness of its warnings. For example, it can review and improve warning content based on feedback from users who have received warning messages. Furthermore, the warning unit can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information not only through email notifications but also through voice calls, SMS, and email. This allows the warning unit to provide users with prompt and reliable warnings, minimizing the risk of becoming involved in illegal recruitment schemes.

[0034] The AI ​​agent system includes an anomaly detection unit that detects anomalous patterns using data analysis tools. The anomaly detection unit can process large amounts of job posting data in real time and detect anomalous patterns, for example, using machine learning tools or statistical analysis tools. For instance, the anomaly detection unit can analyze job postings that are rapidly increasing in a specific region or industry to identify signs of illegal activity. The anomaly detection unit can also monitor social media and message board posts and detect anomalous posting patterns. For example, it can analyze the frequency of occurrence of specific keywords or phrases in real time to detect anomalous patterns. This allows the anomaly detection unit to detect illegal activity at an early stage. Some or all of the above-described processes in the anomaly detection unit may be performed using AI, for example, or without AI. For example, the anomaly detection unit can detect anomalous patterns using machine learning models.

[0035] The AI ​​agent system includes a provisioning unit that provides information to law enforcement agencies. For example, the provisioning unit can provide information to law enforcement agencies when it discovers illegal job advertisements or postings. The provisioning unit can, for example, send reports and provide real-time notifications. For instance, the provisioning unit can create a report containing detailed information about an illegal job advertisement and send it to law enforcement agencies. It can also notify law enforcement agencies in real time when illegal activity is discovered. This allows the provisioning unit to support law enforcement agencies in conducting swift investigations and responses. Some or all of the above processes in the provisioning unit may be performed using AI, for example, or not. For example, the provisioning unit can automatically collect information on illegal job advertisements and provide it to law enforcement agencies.

[0036] The AI ​​agent system includes a warning display unit that displays warning messages to job seekers. The warning display unit can, for example, display a warning message if a job seeker attempts to apply for an illegal job. The warning display unit can, for example, set the wording and display format of the warning and display it to the job seeker. For example, the warning display unit can issue a warning to the job seeker using a pop-up message or email notification. Furthermore, the warning display unit can customize the content of the warning message to provide appropriate warnings to job seekers. This allows the warning display unit to reduce the risk of job seekers becoming involved in illegal job postings. Some or all of the above processing in the warning display unit may be performed using AI, for example, or without AI. For example, the warning display unit can monitor the job seeker's behavior in real time and display a warning message if they attempt to apply for an illegal job.

[0037] The monitoring unit monitors job advertisements and posts on job platforms and social media. For example, the monitoring unit can monitor job advertisements and posts on job platforms and social media in real time. The monitoring unit can also perform periodic scans to detect illegal activity early. For example, the monitoring unit can analyze the frequency of occurrence of specific keywords and phrases in real time to detect abnormal patterns. This allows the monitoring unit to detect illegal activity on job platforms and social media early. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can use machine learning models to detect abnormal patterns.

[0038] The analysis department analyzes the content of job advertisements and posts using generative AI and natural language processing. For example, the analysis department can analyze the content of job advertisements and posts using text analysis and data mining techniques. The analysis department can also use generative AI to summarize the content of job advertisements and posts and identify illegal content or suspicious language. For example, the analysis department can use generative AI to summarize the content of job advertisements and posts and identify illegal content or suspicious language. This allows the analysis department to accurately analyze the content of job advertisements and posts. Some or all of the above processing in the analysis department may be performed using generative AI, or not. For example, the analysis department can use generative AI to summarize the content of job advertisements and posts and identify illegal content or suspicious language.

[0039] The identification unit automatically detects illegal content and suspicious language. For example, the identification unit can automatically detect fraudulent job postings and false information. The identification unit can also detect suspicious language and assess the possibility of illegal activity. For example, the identification unit analyzes the frequency of occurrence of specific keywords and phrases in real time to identify illegal content and suspicious language. This allows the identification unit to identify illegal content and suspicious language at an early stage. Some or all of the above processing in the identification unit may be performed using AI, for example, or not using AI. For example, the identification unit can use machine learning models to identify illegal content and suspicious language.

[0040] The warning unit notifies platform administrators and relevant authorities when it discovers illegal job postings. For example, if an illegal job advertisement is found, the warning unit will notify the platform administrator and urge them to remove the advertisement. The warning unit can also provide information to law enforcement agencies to support swift investigation and response. For example, the warning unit can create a report containing detailed information about the illegal job advertisement and send it to law enforcement agencies. The warning unit can also notify law enforcement agencies in real time when illegal activity is discovered. This allows the warning unit to take swift action when it discovers illegal job postings. Some or all of the above processes by the warning unit may be performed using AI, for example, or not. For example, the warning unit can automatically collect information on illegal job advertisements and provide it to platform administrators and law enforcement agencies.

[0041] The monitoring unit analyzes the frequency of occurrence of specific keywords and phrases in real time. For example, the monitoring unit can analyze the frequency of occurrence of keywords such as "high income" and "easy work" in real time. The monitoring unit can also detect anomalies if there is a sudden surge in the occurrence of a particular phrase. Furthermore, the monitoring unit can evaluate the likelihood of illegal posts based on the frequency of keyword occurrences. Thus, the monitoring unit can evaluate the likelihood of illegal posts by analyzing the frequency of occurrence of specific keywords and phrases. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the frequency of occurrence of specific keywords and phrases into a generating AI and have the generating AI perform the analysis in real time.

[0042] The monitoring unit detects abnormal patterns early by referring to past monitoring data. For example, the monitoring unit can detect abnormal posting patterns early based on past monitoring data. The monitoring unit can also detect posts that are rapidly increasing in number as abnormal by comparing them with past data. Furthermore, the monitoring unit can detect abnormal behavior of a specific poster by referring to past data. In this way, the monitoring unit can detect abnormal patterns early by referring to past monitoring data. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input past monitoring data into a generating AI and have the generating AI perform the detection of abnormal patterns.

[0043] The monitoring unit can intensify its surveillance by focusing on specific regions or time periods. For example, the monitoring unit can focus its monitoring on posts in a particular region. It can also intensify its surveillance during times when there is a surge in posts. Furthermore, the monitoring unit can set different monitoring criteria for each region or time period. This allows the monitoring unit to efficiently detect illegal activity by intensifying its surveillance by focusing on specific regions or time periods. Some or all of the above processes in the monitoring unit may be performed using AI, for example, or not using AI. For example, the monitoring unit can input data for specific regions or time periods into a generating AI and have the generating AI perform the intensified surveillance.

[0044] The monitoring unit focuses its monitoring on specific groups and forums on social media. For example, it can focus its monitoring on groups where illegal activity is frequent. It can also monitor posts on specific forums in real time. Furthermore, the monitoring unit can set different monitoring criteria for each group or forum. This allows the monitoring unit to efficiently detect illegal activity by focusing its monitoring on specific groups and forums. Some or all of the above processes in the monitoring unit may be performed using AI, for example, or not. For example, the monitoring unit can input data from specific groups or forums into a generating AI and have the generating AI perform enhanced monitoring.

[0045] The analysis unit makes a determination of illegality by considering the context of the posted content. For example, the analysis unit can analyze the context of the posted content and determine whether or not it is illegal. The analysis unit can also evaluate the likelihood of an illegal post based on the context. Furthermore, the analysis unit can make a determination of illegality by considering the context of the posted content. In this way, the analysis unit can improve the accuracy of its determination of illegality by considering the context of the posted content. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input contextual data of the posted content into a generative AI and have the generative AI perform the determination of illegality.

[0046] The analysis unit includes images and videos from posts in its analysis. For example, the analysis unit can analyze images from posts and determine whether they are illegal. It can also analyze videos from posts and determine whether they are illegal. Furthermore, the analysis unit can analyze the content of images and videos and evaluate the possibility of them being illegal posts. By including images and videos from posts in its analysis, the analysis unit can improve the accuracy of its illegality determination. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input image and video data from posts into a generative AI and have the generative AI perform the analysis.

[0047] The analysis unit applies different analysis algorithms depending on the language and region of the post. For example, the analysis unit can apply an appropriate analysis algorithm depending on the language of the post. It can also apply an appropriate analysis algorithm depending on the region of the post. Furthermore, the analysis unit can apply different analysis algorithms for each language and region. This allows the analysis unit to improve analysis accuracy by applying different analysis algorithms depending on the language and region of the post. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input language and region data of the post into a generative AI and have the generative AI apply different analysis algorithms.

[0048] The analysis unit also considers the metadata of the post (such as the poster's information and the posting time). For example, the analysis unit can analyze the poster's information to determine whether it is illegal. It can also analyze the posting time to determine whether it is illegal. Furthermore, the analysis unit can consider the metadata to evaluate the likelihood of an illegal post. In this way, the analysis unit can improve the accuracy of its illegality determination by considering the metadata of the post. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the metadata of the post into a generative AI and have the generative AI perform the analysis.

[0049] The identification unit improves the accuracy of identification by referring to past illegal posting data. The identification unit can improve the accuracy of identification based on past illegal posting data, for example. The identification unit can also improve the accuracy of identifying illegal posts by referring to past data. Furthermore, the identification unit can improve the accuracy of identification by utilizing past illegal posting data. Thus, the identification unit can improve the accuracy of identification by referring to past illegal posting data. Some or all of the above processing in the identification unit may be performed using AI, for example, or without using AI. For example, the identification unit can input past illegal posting data into a generating AI and have the generating AI perform the improvement of identification accuracy.

[0050] The identification unit considers not only the content of the post but also the poster's past behavioral history. For example, the identification unit can analyze the poster's past behavioral history to determine whether or not it is illegal. The identification unit can also comprehensively evaluate the content of the post and the poster's behavioral history. Furthermore, the identification unit can improve the accuracy of identifying illegal posts by considering the poster's past behavioral history. In this way, the identification unit can improve the accuracy of identifying illegal posts by considering not only the content of the post but also the poster's past behavioral history. Some or all of the above processing in the identification unit may be performed using AI, for example, or without using AI. For example, the identification unit can input the poster's past behavioral history data into a generating AI and have the generating AI perform the task of improving the accuracy of identification.

[0051] The identification unit determines the illegality of a post by considering its geographical distribution. For example, the identification unit can analyze the geographical distribution of posts and determine whether or not they are illegal. The identification unit can also evaluate the likelihood of a post being illegal based on its geographical distribution. Furthermore, the identification unit can make a determination of illegality by considering the geographical distribution of posts. This allows the identification unit to improve the accuracy of its determination of illegality by considering the geographical distribution of posts. Some or all of the above processing in the identification unit may be performed using AI, for example, or without AI. For example, the identification unit can input geographical distribution data of posts into a generating AI and have the generating AI perform the determination of illegality.

[0052] The identification unit also includes related links and sources cited in the post as part of its analysis. For example, the identification unit can analyze related links to a post and determine whether or not they are illegal. It can also analyze sources cited in a post and determine whether or not they are illegal. Furthermore, the identification unit can consider related links and sources to evaluate the likelihood of an illegal post. In this way, the identification unit can improve the accuracy of its illegality determination by including related links and sources cited in the analysis. Some or all of the above processing in the identification unit may be performed using AI, for example, or without AI. For example, the identification unit can input related links and source data of a post into a generating AI and have the generating AI perform the analysis.

[0053] The warning unit varies the intensity of the warning according to the degree of illegality. For example, the warning unit can issue a strong warning if the degree of illegality is high. It can also issue a mild warning if the degree of illegality is low. Furthermore, the warning unit can adjust the intensity of the warning according to the degree of illegality. In this way, the warning unit can provide an appropriate warning by changing the intensity of the warning according to the degree of illegality. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the degree of illegality into a generating AI and have the generating AI adjust the intensity of the warning.

[0054] The warning unit optimizes the effectiveness of warnings by referring to past warning history. For example, the warning unit can optimize the effectiveness of warnings based on past warning history. The warning unit can also adjust the content of warnings by referring to past warning history. Furthermore, the warning unit can optimize the effectiveness of warnings by utilizing past warning history. In this way, the warning unit can optimize the effectiveness of warnings by referring to past warning history. Some or all of the above processing in the warning unit may be performed using AI, for example, or without using AI. For example, the warning unit can input past warning history data into a generating AI and have the generating AI perform the optimization of the effectiveness of warnings.

[0055] The warning unit optimizes the display method of warning messages according to the user's device. For example, if a smartphone is being used, the warning unit can display a warning message that is adapted to the screen size. If a tablet is being used, the warning unit can also display a warning message optimized for a larger screen. Furthermore, if a smartwatch is being used, the warning unit can display a concise and highly visible warning message. In this way, the warning unit can improve visibility by optimizing the display method of warning messages according to the user's device. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's device information into a generating AI and have the generating AI perform the optimization of the warning message display method.

[0056] The warning unit displays warning messages in multiple languages. For example, the warning unit can automatically configure warning messages based on the user's device language settings. The warning unit can also provide a language switching function if the user uses multiple languages. Furthermore, the warning unit can display warning messages in a specific language if the user selects that language. This allows the warning unit to accommodate users who use different languages ​​by displaying warning messages in multiple languages. Some or all of the above processing in the warning unit may be performed using AI, or not. For example, the warning unit can input the user's language setting information into a generating AI and have the generating AI configure the language settings for the warning messages.

[0057] The anomaly detection unit improves the accuracy of detection by referring to past anomaly data when an anomaly is detected. For example, the anomaly detection unit can improve the accuracy of anomaly detection based on past anomaly data. The anomaly detection unit can also improve the accuracy of anomaly detection by referring to past data. Furthermore, the anomaly detection unit can improve the accuracy of anomaly detection by utilizing past anomaly data. In this way, the anomaly detection unit can improve the accuracy of anomaly detection by referring to past anomaly data. Some or all of the above processing in the anomaly detection unit may be performed using AI, for example, or without using AI. For example, the anomaly detection unit can input past anomaly data into a generating AI and have the generating AI perform the improvement of anomaly detection accuracy.

[0058] The anomaly detection unit enhances detection by focusing on specific regions or time periods when an anomaly is detected. For example, the anomaly detection unit can focus on detecting anomalies in specific regions. Furthermore, if anomalies increase sharply during a particular time period, the anomaly detection unit can enhance detection during that time period. In addition, the anomaly detection unit can set different anomaly detection criteria for each region and time period. This allows the anomaly detection unit to efficiently detect anomalies by enhancing detection by focusing on specific regions and time periods. Some or all of the above-described processes in the anomaly detection unit may be performed using AI, for example, or without AI. For example, the anomaly detection unit can input data for specific regions and time periods into a generating AI and have the generating AI perform enhanced anomaly detection.

[0059] The service provider optimizes the effectiveness of the service by referring to past service history at the time of service provision. For example, the service provider can optimize the effectiveness of the service based on past service history. The service provider can also adjust the content of the service by referring to past service history. Furthermore, the service provider can optimize the effectiveness of the service by utilizing past service history. In this way, the service provider can optimize the effectiveness of the service by referring to past service history. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI. For example, the service provider can input past service history data into a generating AI and have the generating AI perform the optimization of the service effectiveness.

[0060] The information provider displays the information in multiple languages. The information provider can, for example, automatically configure the information based on the user's device language settings. The information provider can also provide a language switching function if the user uses multiple languages. Furthermore, the information provider can provide information in a specific language if the user selects that language. In this way, the information provider can accommodate users who use different languages ​​by displaying the information in multiple languages. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the information provider can input the user's language setting information into a generating AI and have the generating AI configure the language settings of the information.

[0061] The warning display unit optimizes the display effect by referring to past warning display history when displaying a warning. For example, the warning display unit can optimize the display effect based on past warning display history. The warning display unit can also adjust the content of the display by referring to past warning display history. Furthermore, the warning display unit can optimize the display effect by utilizing past warning display history. In this way, the warning display unit can optimize the display effect by referring to past warning display history. Some or all of the above processing in the warning display unit may be performed using AI, for example, or without using AI. For example, the warning display unit can input past warning display history data into a generating AI and have the generating AI perform the optimization of the display effect.

[0062] The warning display unit optimizes warning messages according to the user's device. For example, if a smartphone is being used, the warning display unit can display a warning message that is adapted to the screen size. If a tablet is being used, the warning display unit can also display a warning message optimized for a larger screen. Furthermore, if a smartwatch is being used, the warning display unit can display a concise and highly visible warning message. In this way, the warning display unit can improve visibility by optimizing the display method of warning messages according to the user's device. Some or all of the above processing in the warning display unit may be performed using AI, for example, or without AI. For example, the warning display unit can input user device information into a generating AI and have the generating AI optimize the display method of warning messages.

[0063] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0064] The AI ​​agent system includes an anomaly detection unit, which can improve the accuracy of detection by referring to past anomaly data. For example, it can improve the accuracy of anomaly detection based on past anomaly data. It can also improve the accuracy of anomaly detection by referring to past data. Furthermore, it can improve the accuracy of anomaly detection by utilizing past anomaly data. Thus, the anomaly detection unit can improve the accuracy of anomaly detection by referring to past anomaly data. Some or all of the above processing in the anomaly detection unit may be performed using AI, for example, or without using AI. For example, the anomaly detection unit can input past anomaly data into a generating AI and cause the generating AI to perform an improvement in the accuracy of anomaly detection.

[0065] The AI ​​agent system includes an anomaly detection unit, which can enhance detection by focusing on specific regions or time periods. For example, it can focus on detecting anomalies in specific regions. It can also enhance detection during times when anomalies surge. Furthermore, it can set different anomaly detection criteria for each region and time period. This allows the anomaly detection unit to efficiently detect anomalies by enhancing detection by focusing on specific regions and time periods. Some or all of the above-described processes in the anomaly detection unit may be performed using AI, for example, or without AI. For example, the anomaly detection unit can input data for specific regions and time periods into a generating AI and have the generating AI perform enhanced anomaly detection.

[0066] The AI ​​agent system includes a delivery unit that can optimize the effectiveness of a delivery by referring to past delivery history at the time of delivery. For example, it can optimize the effectiveness of a delivery based on past delivery history. It can also adjust the content of the delivery by referring to past delivery history. Furthermore, it can optimize the effectiveness of a delivery by utilizing past delivery history. In this way, the delivery unit can optimize the effectiveness of a delivery by referring to past delivery history. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without using AI. For example, the delivery unit can input past delivery history data into a generating AI and have the generating AI perform the optimization of the effectiveness of the delivery.

[0067] The AI ​​agent system includes a service provider that can display the information it provides in multiple languages. For example, it can automatically set the information based on the language settings of the user's device. It can also provide a language switching function if the user uses multiple languages. Furthermore, if the user selects a specific language, it can provide the information in that language. In this way, the service provider can accommodate users who use different languages ​​by displaying the information it provides in multiple languages. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can input the user's language setting information into a generating AI and have the generating AI perform the language setting of the information.

[0068] The AI ​​agent system includes a warning display unit that can optimize warning messages according to the user's device. For example, when using a smartphone, it can display a warning message that is sized to fit the screen. When using a tablet, it can display a warning message optimized for a larger screen. Furthermore, when using a smartwatch, it can display a concise and highly visible warning message. In this way, the warning display unit can improve visibility by optimizing how warning messages are displayed according to the user's device. Some or all of the above processing in the warning display unit may be performed using AI, for example, or without AI. For example, the warning display unit can input user device information into a generating AI and have the generating AI perform the optimization of how warning messages are displayed.

[0069] The following briefly describes the processing flow for example form 1.

[0070] Step 1: The monitoring unit monitors job advertisements and posts. For example, it monitors job advertisements and posts on job platforms and social media in real time and conducts regular scans to detect illegal activity early. It analyzes the frequency of occurrence of specific keywords and phrases in real time and detects abnormal patterns. Step 2: The analysis unit uses generative AI and natural language processing to analyze the information monitored by the monitoring unit. For example, it analyzes the content of job advertisements and posts using text analysis and data mining techniques, summarizes the content using generative AI, and identifies illegal content or suspicious language. Step 3: The Identification Department identifies illegal content based on the information analyzed by the Analysis Department. For example, it automatically detects fraudulent job postings and false information, and assesses the possibility of illegal activity by detecting suspicious language. Step 4: The warning unit issues warnings based on the illegal content identified by the identification unit. For example, it sends email notifications or pop-up messages to platform administrators and relevant authorities, and displays warning messages to job seekers to reduce the risk of them becoming involved in illegal job postings.

[0071] (Example of form 2) The AI ​​agent system according to an embodiment of the present invention is designed to prevent the recruitment and application of illegal part-time jobs (illegal part-time jobs). This system monitors job platforms and social media, uses generative AI and data analysis technology to identify illegal activities, and issues warnings to authorities and platform administrators. It also issues warnings when someone who sees a job posting attempts to apply. For example, the AI ​​agent system monitors job advertisements and posts on job platforms and social media. Using generative AI and natural language processing (NLP), it analyzes the content of job advertisements and posts and automatically detects illegal content and suspicious language. For example, it analyzes posts containing keywords such as "high pay," "easy work," and "no experience necessary" to determine if they are potentially illegal. Next, it uses data analysis tools to process large amounts of job data in real time and detect anomaly patterns. For example, it analyzes job advertisements that are rapidly increasing in specific regions or industries to identify signs of illegal activity. It also monitors social media and bulletin board posts to identify illegal recruitment. If an illegal job posting is discovered, the warning system is activated and immediately notifies platform administrators and relevant authorities. For example, if an illegal job advertisement is discovered, the information is notified to the platform administrator, who is urged to remove the advertisement. Information is also provided to law enforcement agencies to support swift investigation and response. Furthermore, warnings are issued when someone attempts to apply for a job posting. For instance, if a job seeker attempts to apply for an illegal job, a warning message is displayed, urging them to avoid suspicious postings. This significantly reduces the risk of job seekers becoming involved in illegal employment. This mechanism improves the safety and reliability of job platforms and social media, creating a safer environment for users. It also contributes to the eradication of illegal employment by providing information to law enforcement agencies. In this way, the AI ​​agent system can prevent illegal job postings and applications.

[0072] The AI ​​agent system according to this embodiment comprises a monitoring unit, an analysis unit, an identification unit, and a warning unit. The monitoring unit monitors job advertisements and posts. The monitoring unit can, for example, monitor job advertisements and posts on job platforms and social media in real time. The monitoring unit can also perform periodic scans to detect illegal activities early. For example, the monitoring unit can analyze the frequency of occurrence of specific keywords and phrases in real time and detect abnormal patterns. The analysis unit analyzes the information monitored by the monitoring unit using generative AI and natural language processing. The analysis unit can, for example, analyze the content of job advertisements and posts using text analysis and data mining techniques. The analysis unit can also summarize the content of job advertisements and posts using generative AI and identify illegal content and suspicious language. The identification unit identifies illegal content based on the information analyzed by the analysis unit. The identification unit can, for example, automatically detect fraudulent job postings and false information. The identification unit can also detect suspicious language and assess the possibility of illegal activity. The warning unit issues warnings based on the illegal content identified by the identification unit. The warning unit can, for example, send email notifications or pop-up messages to platform administrators or relevant authorities. The warning unit can also display warning messages to job seekers to reduce the risk of becoming involved in illegal job postings. As a result, the AI ​​agent system according to the embodiment can monitor job advertisements and posts, identify illegal content, and issue warnings.

[0073] The monitoring unit monitors job advertisements and posts. For example, the monitoring unit can monitor job advertisements and posts on job platforms and social media in real time. Specifically, the monitoring unit accesses multiple job sites and social media platforms on the internet and collects data regularly. This includes methods such as using web scraping techniques and APIs to obtain text data of job advertisements and posts. The monitoring unit analyzes the collected data in real time and monitors the frequency of occurrence of specific keywords and phrases. For example, if keywords such as "high salary," "no experience necessary," and "immediate start" appear frequently, it may indicate an illegal job advertisement. Furthermore, the monitoring unit can identify anomalies by comparing them with historical data to detect unusual patterns. For example, a sudden increase in job advertisements in a particular region or industry may be a sign of fraudulent activity. The monitoring unit detects these anomalies early and provides the data to the analysis unit, which is the next step. This allows the monitoring unit to monitor job advertisements and posts efficiently and effectively and detect illegal activity early.

[0074] The Analysis Department analyzes information monitored by the Monitoring Department using generative AI and natural language processing. Specifically, the Analysis Department analyzes the content of job advertisements and posts using text analysis and data mining techniques. Generative AI, for example, uses large-scale language models to summarize the content of job advertisements and posts and extract important information. Natural language processing techniques are used to understand the meaning of the text and identify illegal content or suspicious language. For example, generative AI analyzes the text of job advertisements to check if keywords such as "high income," "no experience necessary," and "immediate start" are included. Generative AI can also understand the context of job advertisements and identify fraudulent or false information. Furthermore, the Analysis Department uses data mining techniques to analyze patterns in job advertisements and posts and detect anomaly patterns. For example, a sudden increase in job advertisements in a particular region or industry may be a sign of fraudulent activity. The Analysis Department identifies these anomalies and provides the data to the Identification Department, which is the next step. This allows the Analysis Department to analyze the content of job advertisements and posts in detail and identify illegal content or suspicious language.

[0075] The Identification Department identifies illegal content based on information analyzed by the Analysis Department. Specifically, the Identification Department can automatically detect fraudulent job postings and false information. For example, the Identification Department can identify fraudulent job postings based on the content of job postings analyzed by the Generating AI. Fraudulent job postings often attract job seekers by offering attractive conditions such as excessive pay or immediate start. The Identification Department automatically detects job postings containing these conditions and assesses the possibility of illegal activity. The Identification Department can also detect suspicious language and assess the possibility of illegal activity. For example, if keywords such as "high income," "no experience necessary," and "immediate start" appear frequently, it may be an illegal job posting. The Identification Department automatically detects job postings containing these keywords and assesses the possibility of illegal activity. Furthermore, the Identification Department can utilize historical data and statistical information to conduct long-term risk assessments and trend analyses. For example, based on past data on fraudulent job postings, it can predict fluctuations in risk in specific regions or industries and formulate future countermeasures. This allows the relevant department to analyze the content of job advertisements and posts in detail and identify illegal content or suspicious language.

[0076] The warning unit issues warnings based on illegal content identified by the identification unit. Specifically, the warning unit can send email notifications and pop-up messages to platform administrators and relevant authorities. For example, if the identification unit identifies a fraudulent job advertisement, the warning unit will send an email notification to the platform administrator instructing them to remove the advertisement. The warning unit can also send pop-up messages to relevant authorities reporting the possibility of illegal activity. Furthermore, the warning unit can display warning messages to job seekers to reduce the risk of becoming involved in illegal job postings. For example, if a job seeker attempts to apply for a fraudulent job advertisement, the warning unit will display a warning message to the job seeker, informing them of the potential fraud. The warning message will be displayed on the job seeker's smartphone or computer and can be alerted through voice guidance or vibration notifications. This allows the warning unit to quickly provide appropriate warnings to each user, minimizing the risk of becoming involved in illegal job postings. In addition, the warning unit can collect user feedback and continuously improve the accuracy and effectiveness of its warnings. For example, it can review and improve warning content based on feedback from users who have received warning messages. Furthermore, the warning unit can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information not only through email notifications but also through voice calls, SMS, and email. This allows the warning unit to provide users with prompt and reliable warnings, minimizing the risk of becoming involved in illegal recruitment schemes.

[0077] The AI ​​agent system includes an anomaly detection unit that detects anomalous patterns using data analysis tools. The anomaly detection unit can process large amounts of job posting data in real time and detect anomalous patterns, for example, using machine learning tools or statistical analysis tools. For instance, the anomaly detection unit can analyze job postings that are rapidly increasing in a specific region or industry to identify signs of illegal activity. The anomaly detection unit can also monitor social media and message board posts and detect anomalous posting patterns. For example, it can analyze the frequency of occurrence of specific keywords or phrases in real time to detect anomalous patterns. This allows the anomaly detection unit to detect illegal activity at an early stage. Some or all of the above-described processes in the anomaly detection unit may be performed using AI, for example, or without AI. For example, the anomaly detection unit can detect anomalous patterns using machine learning models.

[0078] The AI ​​agent system includes a provisioning unit that provides information to law enforcement agencies. For example, the provisioning unit can provide information to law enforcement agencies when it discovers illegal job advertisements or postings. The provisioning unit can, for example, send reports and provide real-time notifications. For instance, the provisioning unit can create a report containing detailed information about an illegal job advertisement and send it to law enforcement agencies. It can also notify law enforcement agencies in real time when illegal activity is discovered. This allows the provisioning unit to support law enforcement agencies in conducting swift investigations and responses. Some or all of the above processes in the provisioning unit may be performed using AI, for example, or not. For example, the provisioning unit can automatically collect information on illegal job advertisements and provide it to law enforcement agencies.

[0079] The AI ​​agent system includes a warning display unit that displays warning messages to job seekers. The warning display unit can, for example, display a warning message if a job seeker attempts to apply for an illegal job. The warning display unit can, for example, set the wording and display format of the warning and display it to the job seeker. For example, the warning display unit can issue a warning to the job seeker using a pop-up message or email notification. Furthermore, the warning display unit can customize the content of the warning message to provide appropriate warnings to job seekers. This allows the warning display unit to reduce the risk of job seekers becoming involved in illegal job postings. Some or all of the above processing in the warning display unit may be performed using AI, for example, or without AI. For example, the warning display unit can monitor the job seeker's behavior in real time and display a warning message if they attempt to apply for an illegal job.

[0080] The monitoring unit monitors job advertisements and posts on job platforms and social media. For example, the monitoring unit can monitor job advertisements and posts on job platforms and social media in real time. The monitoring unit can also perform periodic scans to detect illegal activity early. For example, the monitoring unit can analyze the frequency of occurrence of specific keywords and phrases in real time to detect abnormal patterns. This allows the monitoring unit to detect illegal activity on job platforms and social media early. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can use machine learning models to detect abnormal patterns.

[0081] The analysis department analyzes the content of job advertisements and posts using generative AI and natural language processing. For example, the analysis department can analyze the content of job advertisements and posts using text analysis and data mining techniques. The analysis department can also use generative AI to summarize the content of job advertisements and posts and identify illegal content or suspicious language. For example, the analysis department can use generative AI to summarize the content of job advertisements and posts and identify illegal content or suspicious language. This allows the analysis department to accurately analyze the content of job advertisements and posts. Some or all of the above processing in the analysis department may be performed using generative AI, or not. For example, the analysis department can use generative AI to summarize the content of job advertisements and posts and identify illegal content or suspicious language.

[0082] The identification unit automatically detects illegal content and suspicious language. For example, the identification unit can automatically detect fraudulent job postings and false information. The identification unit can also detect suspicious language and assess the possibility of illegal activity. For example, the identification unit analyzes the frequency of occurrence of specific keywords and phrases in real time to identify illegal content and suspicious language. This allows the identification unit to identify illegal content and suspicious language at an early stage. Some or all of the above processing in the identification unit may be performed using AI, for example, or not using AI. For example, the identification unit can use machine learning models to identify illegal content and suspicious language.

[0083] The warning unit notifies platform administrators and relevant authorities when it discovers illegal job postings. For example, if an illegal job advertisement is found, the warning unit will notify the platform administrator and urge them to remove the advertisement. The warning unit can also provide information to law enforcement agencies to support swift investigation and response. For example, the warning unit can create a report containing detailed information about the illegal job advertisement and send it to law enforcement agencies. The warning unit can also notify law enforcement agencies in real time when illegal activity is discovered. This allows the warning unit to take swift action when it discovers illegal job postings. Some or all of the above processes by the warning unit may be performed using AI, for example, or not. For example, the warning unit can automatically collect information on illegal job advertisements and provide it to platform administrators and law enforcement agencies.

[0084] The monitoring unit estimates the user's emotions and adjusts the monitoring frequency based on the estimated emotions. For example, if the user is stressed, the monitoring unit can increase the monitoring frequency to provide reassurance. Conversely, if the user is relaxed, the monitoring unit can decrease the monitoring frequency to reduce the system load. Furthermore, if the user is in a hurry, the monitoring unit can increase the monitoring frequency to provide a quick response. In this way, the monitoring unit can optimize the system load by adjusting the monitoring frequency 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 monitoring unit may be performed using AI, for example, or not using AI. For example, the monitoring unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0085] The monitoring unit analyzes the frequency of occurrence of specific keywords and phrases in real time. For example, the monitoring unit can analyze the frequency of occurrence of keywords such as "high income" and "easy work" in real time. The monitoring unit can also detect anomalies if there is a sudden surge in the occurrence of a particular phrase. Furthermore, the monitoring unit can evaluate the likelihood of illegal posts based on the frequency of keyword occurrences. Thus, the monitoring unit can evaluate the likelihood of illegal posts by analyzing the frequency of occurrence of specific keywords and phrases. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the frequency of occurrence of specific keywords and phrases into a generating AI and have the generating AI perform the analysis in real time.

[0086] The monitoring unit detects abnormal patterns early by referring to past monitoring data. For example, the monitoring unit can detect abnormal posting patterns early based on past monitoring data. The monitoring unit can also detect posts that are rapidly increasing in number as abnormal by comparing them with past data. Furthermore, the monitoring unit can detect abnormal behavior of a specific poster by referring to past data. In this way, the monitoring unit can detect abnormal patterns early by referring to past monitoring data. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input past monitoring data into a generating AI and have the generating AI perform the detection of abnormal patterns.

[0087] The monitoring unit estimates the user's emotions and determines the priority of monitored items based on the estimated emotions. For example, if the user is feeling anxious, the monitoring unit can prioritize important monitored items. If the user is relaxed, the monitoring unit can also prioritize normal monitored items. Furthermore, if the user is in a hurry, the monitoring unit can prioritize highly urgent monitored items. In this way, the monitoring unit can prioritize important monitored items by determining the priority of monitored items 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 monitoring unit may be performed using AI, or not using AI. For example, the monitoring unit can input user emotion data into a generative AI and have the generative AI perform the determination of the priority of monitored items.

[0088] The monitoring unit can intensify its surveillance by focusing on specific regions or time periods. For example, the monitoring unit can focus its monitoring on posts in a particular region. It can also intensify its surveillance during times when there is a surge in posts. Furthermore, the monitoring unit can set different monitoring criteria for each region or time period. This allows the monitoring unit to efficiently detect illegal activity by intensifying its surveillance by focusing on specific regions or time periods. Some or all of the above processes in the monitoring unit may be performed using AI, for example, or not using AI. For example, the monitoring unit can input data for specific regions or time periods into a generating AI and have the generating AI perform the intensified surveillance.

[0089] The monitoring unit focuses its monitoring on specific groups and forums on social media. For example, it can focus its monitoring on groups where illegal activity is frequent. It can also monitor posts on specific forums in real time. Furthermore, the monitoring unit can set different monitoring criteria for each group or forum. This allows the monitoring unit to efficiently detect illegal activity by focusing its monitoring on specific groups and forums. Some or all of the above processes in the monitoring unit may be performed using AI, for example, or not. For example, the monitoring unit can input data from specific groups or forums into a generating AI and have the generating AI perform enhanced monitoring.

[0090] The analysis unit estimates the user's emotions and adjusts the level of detail of the analysis based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit can provide detailed analysis results. If the user is relaxed, the analysis unit can provide concise analysis results. Furthermore, if the user is in a hurry, the analysis unit can provide rapid analysis results. In this way, the analysis unit can provide appropriate analysis results by adjusting the level of detail 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. 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, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the level of detail of the analysis.

[0091] The analysis unit makes a determination of illegality by considering the context of the posted content. For example, the analysis unit can analyze the context of the posted content and determine whether or not it is illegal. The analysis unit can also evaluate the likelihood of an illegal post based on the context. Furthermore, the analysis unit can make a determination of illegality by considering the context of the posted content. In this way, the analysis unit can improve the accuracy of its determination of illegality by considering the context of the posted content. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input contextual data of the posted content into a generative AI and have the generative AI perform the determination of illegality.

[0092] The analysis unit includes images and videos from posts in its analysis. For example, the analysis unit can analyze images from posts and determine whether they are illegal. It can also analyze videos from posts and determine whether they are illegal. Furthermore, the analysis unit can analyze the content of images and videos and evaluate the possibility of them being illegal posts. By including images and videos from posts in its analysis, the analysis unit can improve the accuracy of its illegality determination. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input image and video data from posts into a generative AI and have the generative AI perform the analysis.

[0093] The analysis unit estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit can display detailed analysis results. If the user is relaxed, the analysis unit can display concise analysis results. Furthermore, if the user is in a hurry, the analysis unit can display rapid analysis results. In this way, the analysis unit can provide appropriate information by adjusting how the analysis results are displayed 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 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 have the generative AI adjust how the analysis results are displayed.

[0094] The analysis unit applies different analysis algorithms depending on the language and region of the post. For example, the analysis unit can apply an appropriate analysis algorithm depending on the language of the post. It can also apply an appropriate analysis algorithm depending on the region of the post. Furthermore, the analysis unit can apply different analysis algorithms for each language and region. This allows the analysis unit to improve analysis accuracy by applying different analysis algorithms depending on the language and region of the post. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input language and region data of the post into a generative AI and have the generative AI apply different analysis algorithms.

[0095] The analysis unit also considers the metadata of the post (such as the poster's information and the posting time). For example, the analysis unit can analyze the poster's information to determine whether it is illegal. It can also analyze the posting time to determine whether it is illegal. Furthermore, the analysis unit can consider the metadata to evaluate the likelihood of an illegal post. In this way, the analysis unit can improve the accuracy of its illegality determination by considering the metadata of the post. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the metadata of the post into a generative AI and have the generative AI perform the analysis.

[0096] The identification unit estimates the user's emotions and adjusts specific criteria based on the estimated emotions. For example, if the user is feeling anxious, the identification unit can apply strict criteria. If the user is relaxed, the identification unit can apply normal criteria. Furthermore, if the user is in a hurry, the identification unit can apply rapid criteria. In this way, the identification unit can perform appropriate identification by adjusting specific 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 identification unit may be performed using AI or not using AI. For example, the identification unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of specific criteria.

[0097] The identification unit improves the accuracy of identification by referring to past illegal posting data. The identification unit can improve the accuracy of identification based on past illegal posting data, for example. The identification unit can also improve the accuracy of identifying illegal posts by referring to past data. Furthermore, the identification unit can improve the accuracy of identification by utilizing past illegal posting data. Thus, the identification unit can improve the accuracy of identification by referring to past illegal posting data. Some or all of the above processing in the identification unit may be performed using AI, for example, or without using AI. For example, the identification unit can input past illegal posting data into a generating AI and have the generating AI perform the improvement of identification accuracy.

[0098] The identification unit considers not only the content of the post but also the poster's past behavioral history. For example, the identification unit can analyze the poster's past behavioral history to determine whether or not it is illegal. The identification unit can also comprehensively evaluate the content of the post and the poster's behavioral history. Furthermore, the identification unit can improve the accuracy of identifying illegal posts by considering the poster's past behavioral history. In this way, the identification unit can improve the accuracy of identifying illegal posts by considering not only the content of the post but also the poster's past behavioral history. Some or all of the above processing in the identification unit may be performed using AI, for example, or without using AI. For example, the identification unit can input the poster's past behavioral history data into a generating AI and have the generating AI perform the task of improving the accuracy of identification.

[0099] The identification unit estimates the user's emotions and adjusts the display method of the identification results based on the estimated user emotions. For example, if the user is feeling anxious, the identification unit can display detailed identification results. If the user is relaxed, the identification unit can also display concise identification results. Furthermore, if the user is in a hurry, the identification unit can display rapid identification results. In this way, the identification unit can provide appropriate information by adjusting the display method of the identification results 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 identification unit may be performed using AI, for example, or not using AI. For example, the identification unit can input user emotion data into the generative AI and have the generative AI adjust the display method of the identification results.

[0100] The identification unit determines the illegality of a post by considering its geographical distribution. For example, the identification unit can analyze the geographical distribution of posts and determine whether or not they are illegal. The identification unit can also evaluate the likelihood of a post being illegal based on its geographical distribution. Furthermore, the identification unit can make a determination of illegality by considering the geographical distribution of posts. This allows the identification unit to improve the accuracy of its determination of illegality by considering the geographical distribution of posts. Some or all of the above processing in the identification unit may be performed using AI, for example, or without AI. For example, the identification unit can input geographical distribution data of posts into a generating AI and have the generating AI perform the determination of illegality.

[0101] The identification unit also includes related links and sources cited in the post as part of its analysis. For example, the identification unit can analyze related links to a post and determine whether or not they are illegal. It can also analyze sources cited in a post and determine whether or not they are illegal. Furthermore, the identification unit can consider related links and sources to evaluate the likelihood of an illegal post. In this way, the identification unit can improve the accuracy of its illegality determination by including related links and sources cited in the analysis. Some or all of the above processing in the identification unit may be performed using AI, for example, or without AI. For example, the identification unit can input related links and source data of a post into a generating AI and have the generating AI perform the analysis.

[0102] The warning unit estimates the user's emotions and adjusts the content of the warning based on the estimated emotions. For example, if the user is feeling anxious, the warning unit can provide a detailed warning. If the user is relaxed, the warning unit can provide a concise warning. Furthermore, if the user is in a hurry, the warning unit can provide a quick warning. In this way, the warning unit can provide appropriate warnings by adjusting the content of the warning 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 warning unit may be performed using AI, or not using AI. For example, the warning unit can input user emotion data into a generative AI and have the generative AI adjust the content of the warning.

[0103] The warning unit varies the intensity of the warning according to the degree of illegality. For example, the warning unit can issue a strong warning if the degree of illegality is high. It can also issue a mild warning if the degree of illegality is low. Furthermore, the warning unit can adjust the intensity of the warning according to the degree of illegality. In this way, the warning unit can provide an appropriate warning by changing the intensity of the warning according to the degree of illegality. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the degree of illegality into a generating AI and have the generating AI adjust the intensity of the warning.

[0104] The warning unit optimizes the effectiveness of warnings by referring to past warning history. For example, the warning unit can optimize the effectiveness of warnings based on past warning history. The warning unit can also adjust the content of warnings by referring to past warning history. Furthermore, the warning unit can optimize the effectiveness of warnings by utilizing past warning history. In this way, the warning unit can optimize the effectiveness of warnings by referring to past warning history. Some or all of the above processing in the warning unit may be performed using AI, for example, or without using AI. For example, the warning unit can input past warning history data into a generating AI and have the generating AI perform the optimization of the effectiveness of warnings.

[0105] The warning unit estimates the user's emotions and adjusts the timing of warnings based on the estimated emotions. For example, if the user is feeling anxious, the warning unit can issue a warning earlier. If the user is relaxed, the warning unit can issue a warning at the normal time. Furthermore, if the user is in a hurry, the warning unit can issue a warning quickly. In this way, the warning unit can provide warnings at the appropriate time by adjusting the timing of warnings 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 warning unit may be performed using AI, for example, or not using AI. For example, the warning unit can input user emotion data into a generative AI and have the generative AI adjust the timing of warnings.

[0106] The warning unit optimizes the display method of warning messages according to the user's device. For example, if a smartphone is being used, the warning unit can display a warning message that is adapted to the screen size. If a tablet is being used, the warning unit can also display a warning message optimized for a larger screen. Furthermore, if a smartwatch is being used, the warning unit can display a concise and highly visible warning message. In this way, the warning unit can improve visibility by optimizing the display method of warning messages according to the user's device. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's device information into a generating AI and have the generating AI perform the optimization of the warning message display method.

[0107] The warning unit displays warning messages in multiple languages. For example, the warning unit can automatically configure warning messages based on the user's device language settings. The warning unit can also provide a language switching function if the user uses multiple languages. Furthermore, the warning unit can display warning messages in a specific language if the user selects that language. This allows the warning unit to accommodate users who use different languages ​​by displaying warning messages in multiple languages. Some or all of the above processing in the warning unit may be performed using AI, or not. For example, the warning unit can input the user's language setting information into a generating AI and have the generating AI configure the language settings for the warning messages.

[0108] The anomaly detection unit estimates the user's emotions and adjusts the anomaly detection criteria based on the estimated emotions. For example, if the user is feeling anxious, the anomaly detection unit can apply strict anomaly detection criteria. If the user is relaxed, the anomaly detection unit can apply normal anomaly detection criteria. Furthermore, if the user is in a hurry, the anomaly detection unit can apply rapid anomaly detection criteria. In this way, the anomaly detection unit can perform appropriate anomaly detection by adjusting the anomaly 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 anomaly detection unit may be performed using AI, for example, or without AI. For example, the anomaly detection unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the anomaly detection criteria.

[0109] The anomaly detection unit improves the accuracy of detection by referring to past anomaly data when an anomaly is detected. For example, the anomaly detection unit can improve the accuracy of anomaly detection based on past anomaly data. The anomaly detection unit can also improve the accuracy of anomaly detection by referring to past data. Furthermore, the anomaly detection unit can improve the accuracy of anomaly detection by utilizing past anomaly data. In this way, the anomaly detection unit can improve the accuracy of anomaly detection by referring to past anomaly data. Some or all of the above processing in the anomaly detection unit may be performed using AI, for example, or without using AI. For example, the anomaly detection unit can input past anomaly data into a generating AI and have the generating AI perform the improvement of anomaly detection accuracy.

[0110] The anomaly detection unit estimates the user's emotions and adjusts the frequency of anomaly detection based on the estimated emotions. For example, if the user is feeling anxious, the anomaly detection unit can increase the frequency of anomaly detection. Conversely, if the user is relaxed, the anomaly detection unit can decrease the frequency of anomaly detection. Furthermore, if the user is in a hurry, the anomaly detection unit can increase the frequency of anomaly detection. In this way, the anomaly detection unit can optimize the system load by adjusting the frequency of anomaly detection 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 anomaly detection unit may be performed using AI, for example, or without AI. For example, the anomaly detection unit can input user emotion data into the generative AI and have the generative AI adjust the frequency of anomaly detection.

[0111] The anomaly detection unit enhances detection by focusing on specific regions or time periods when an anomaly is detected. For example, the anomaly detection unit can focus on detecting anomalies in specific regions. Furthermore, if anomalies increase sharply during a particular time period, the anomaly detection unit can enhance detection during that time period. In addition, the anomaly detection unit can set different anomaly detection criteria for each region and time period. This allows the anomaly detection unit to efficiently detect anomalies by enhancing detection by focusing on specific regions and time periods. Some or all of the above-described processes in the anomaly detection unit may be performed using AI, for example, or without AI. For example, the anomaly detection unit can input data for specific regions and time periods into a generating AI and have the generating AI perform enhanced anomaly detection.

[0112] The service provider estimates the user's emotions and adjusts the level of detail of the information provided based on the estimated emotions. For example, if the user is feeling anxious, the service provider can provide detailed information. If the user is relaxed, the service provider can provide concise information. Furthermore, if the user is in a hurry, the service provider can provide quick information. In this way, the service provider can provide appropriate information by adjusting the level of detail of the information provided 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 service provider may be performed using AI, for example, or not using AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI perform the adjustment of the level of detail of the information.

[0113] The service provider optimizes the effectiveness of the service by referring to past service history at the time of service provision. For example, the service provider can optimize the effectiveness of the service based on past service history. The service provider can also adjust the content of the service by referring to past service history. Furthermore, the service provider can optimize the effectiveness of the service by utilizing past service history. In this way, the service provider can optimize the effectiveness of the service by referring to past service history. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI. For example, the service provider can input past service history data into a generating AI and have the generating AI perform the optimization of the service effectiveness.

[0114] The information delivery unit estimates the user's emotions and adjusts the timing of delivery based on the estimated emotions. For example, if the user is feeling anxious, the information delivery unit can provide information earlier. If the user is relaxed, the information delivery unit can provide information at the normal time. Furthermore, if the user is in a hurry, the information delivery unit can provide information quickly. In this way, the information delivery unit can provide information at the appropriate time by adjusting the timing of delivery 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 information delivery unit may be performed using AI, for example, or not using AI. For example, the information delivery unit can input user emotion data into a generative AI and have the generative AI adjust the timing of delivery.

[0115] The information provider displays the information in multiple languages. The information provider can, for example, automatically configure the information based on the user's device language settings. The information provider can also provide a language switching function if the user uses multiple languages. Furthermore, the information provider can provide information in a specific language if the user selects that language. In this way, the information provider can accommodate users who use different languages ​​by displaying the information in multiple languages. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the information provider can input the user's language setting information into a generating AI and have the generating AI configure the language settings of the information.

[0116] The warning display unit estimates the user's emotions and adjusts the content of the warning message based on the estimated emotions. For example, if the user is feeling anxious, the warning display unit can display a detailed warning message. If the user is relaxed, the warning display unit can display a concise warning message. Furthermore, if the user is in a hurry, the warning display unit can display a quick warning message. In this way, the warning display unit can provide appropriate warnings by adjusting the content of the warning message 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 warning display unit may be performed using AI, or not using AI. For example, the warning display unit can input user emotion data into the generative AI and have the generative AI adjust the content of the warning message.

[0117] The warning display unit optimizes the display effect by referring to past warning display history when displaying a warning. For example, the warning display unit can optimize the display effect based on past warning display history. The warning display unit can also adjust the content of the display by referring to past warning display history. Furthermore, the warning display unit can optimize the display effect by utilizing past warning display history. In this way, the warning display unit can optimize the display effect by referring to past warning display history. Some or all of the above processing in the warning display unit may be performed using AI, for example, or without using AI. For example, the warning display unit can input past warning display history data into a generating AI and have the generating AI perform the optimization of the display effect.

[0118] The warning display unit estimates the user's emotions and adjusts the timing of the warning message display based on the estimated emotions. For example, if the user is feeling anxious, the warning display unit can display the warning message earlier. If the user is relaxed, the warning display unit can display the warning message at the normal timing. Furthermore, if the user is in a hurry, the warning display unit can display the warning message quickly. In this way, the warning display unit can provide warnings at the appropriate time by adjusting the timing of the warning message display 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 a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the warning display unit may be performed using AI, for example, or without AI. For example, the warning display unit can input user emotion data into the generative AI and have the generative AI adjust the timing of the warning message display.

[0119] The warning display unit optimizes warning messages according to the user's device. For example, if a smartphone is being used, the warning display unit can display a warning message that is adapted to the screen size. If a tablet is being used, the warning display unit can also display a warning message optimized for a larger screen. Furthermore, if a smartwatch is being used, the warning display unit can display a concise and highly visible warning message. In this way, the warning display unit can improve visibility by optimizing the display method of warning messages according to the user's device. Some or all of the above processing in the warning display unit may be performed using AI, for example, or without AI. For example, the warning display unit can input user device information into a generating AI and have the generating AI optimize the display method of warning messages.

[0120] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0121] The AI ​​agent system can estimate the user's emotions and adjust the content of warning messages based on the estimated emotions. For example, if the user is feeling anxious, it can provide a detailed warning. If the user is relaxed, it can provide a concise warning. Furthermore, if the user is in a hurry, it can provide a quick warning. In this way, the warning unit can provide appropriate warnings by adjusting the content of the warning 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 warning unit may be performed using AI, or not using AI. For example, the warning unit can input user emotion data into the generative AI and have the generative AI adjust the content of the warning.

[0122] The AI ​​agent system can estimate the user's emotions and adjust the monitoring frequency based on the estimated emotions. For example, if the user is stressed, the monitoring frequency can be increased to provide reassurance. Conversely, if the user is relaxed, the monitoring frequency can be decreased to reduce the system load. Furthermore, if the user is in a hurry, the monitoring frequency can be increased to provide a quick response. In this way, the monitoring unit can optimize the system load by adjusting the monitoring frequency 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 monitoring unit may be performed using AI, or not using AI. For example, the monitoring unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0123] The AI ​​agent system can estimate the user's emotions and adjust the level of detail of the analysis based on the estimated emotions. For example, if the user is feeling anxious, it can provide detailed analysis results. If the user is relaxed, it can provide concise analysis results. Furthermore, if the user is in a hurry, it can provide rapid analysis results. In this way, the analysis unit can provide appropriate analysis results by adjusting the level of detail 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. 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 have the generative AI perform the adjustment of the level of detail of the analysis.

[0124] The AI ​​agent system can estimate the user's emotions and adjust the level of detail of the information provided based on the estimated emotions. For example, if the user is feeling anxious, detailed information can be provided. If the user is relaxed, concise information can be provided. Furthermore, if the user is in a hurry, quick information can be provided. In this way, the service provider can provide appropriate information by adjusting the level of detail of the information provided 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 service provider may be performed using AI or not using AI. For example, the service provider can input user emotion data into the generative AI and have the generative AI perform the adjustment of the level of detail of the information.

[0125] The AI ​​agent system can estimate the user's emotions and adjust the timing of warnings based on the estimated emotions. For example, if the user is feeling anxious, a warning can be issued earlier. If the user is relaxed, a warning can be issued at the normal time. Furthermore, if the user is in a hurry, a warning can be issued quickly. In this way, the warning unit can provide warnings at the appropriate time by adjusting the timing of warnings 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 warning unit may be performed using AI or not using AI. For example, the warning unit can input user emotion data into the generative AI and have the generative AI adjust the timing of warnings.

[0126] The AI ​​agent system includes an anomaly detection unit, which can improve the accuracy of detection by referring to past anomaly data. For example, it can improve the accuracy of anomaly detection based on past anomaly data. It can also improve the accuracy of anomaly detection by referring to past data. Furthermore, it can improve the accuracy of anomaly detection by utilizing past anomaly data. Thus, the anomaly detection unit can improve the accuracy of anomaly detection by referring to past anomaly data. Some or all of the above processing in the anomaly detection unit may be performed using AI, for example, or without using AI. For example, the anomaly detection unit can input past anomaly data into a generating AI and cause the generating AI to perform an improvement in the accuracy of anomaly detection.

[0127] The AI ​​agent system includes an anomaly detection unit, which can enhance detection by focusing on specific regions or time periods. For example, it can focus on detecting anomalies in specific regions. It can also enhance detection during times when anomalies surge. Furthermore, it can set different anomaly detection criteria for each region and time period. This allows the anomaly detection unit to efficiently detect anomalies by enhancing detection by focusing on specific regions and time periods. Some or all of the above-described processes in the anomaly detection unit may be performed using AI, for example, or without AI. For example, the anomaly detection unit can input data for specific regions and time periods into a generating AI and have the generating AI perform enhanced anomaly detection.

[0128] The AI ​​agent system includes a delivery unit that can optimize the effectiveness of a delivery by referring to past delivery history at the time of delivery. For example, it can optimize the effectiveness of a delivery based on past delivery history. It can also adjust the content of the delivery by referring to past delivery history. Furthermore, it can optimize the effectiveness of a delivery by utilizing past delivery history. In this way, the delivery unit can optimize the effectiveness of a delivery by referring to past delivery history. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without using AI. For example, the delivery unit can input past delivery history data into a generating AI and have the generating AI perform the optimization of the effectiveness of the delivery.

[0129] The AI ​​agent system includes a service provider that can display the information it provides in multiple languages. For example, it can automatically set the information based on the language settings of the user's device. It can also provide a language switching function if the user uses multiple languages. Furthermore, if the user selects a specific language, it can provide the information in that language. In this way, the service provider can accommodate users who use different languages ​​by displaying the information it provides in multiple languages. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can input the user's language setting information into a generating AI and have the generating AI perform the language setting of the information.

[0130] The AI ​​agent system includes a warning display unit that can optimize warning messages according to the user's device. For example, when using a smartphone, it can display a warning message that is sized to fit the screen. When using a tablet, it can display a warning message optimized for a larger screen. Furthermore, when using a smartwatch, it can display a concise and highly visible warning message. In this way, the warning display unit can improve visibility by optimizing how warning messages are displayed according to the user's device. Some or all of the above processing in the warning display unit may be performed using AI, for example, or without AI. For example, the warning display unit can input user device information into a generating AI and have the generating AI perform the optimization of how warning messages are displayed.

[0131] The following briefly describes the processing flow for example form 2.

[0132] Step 1: The monitoring unit monitors job advertisements and posts. For example, it monitors job advertisements and posts on job platforms and social media in real time and conducts regular scans to detect illegal activity early. It analyzes the frequency of occurrence of specific keywords and phrases in real time and detects abnormal patterns. Step 2: The analysis unit uses generative AI and natural language processing to analyze the information monitored by the monitoring unit. For example, it analyzes the content of job advertisements and posts using text analysis and data mining techniques, summarizes the content using generative AI, and identifies illegal content or suspicious language. Step 3: The Identification Department identifies illegal content based on the information analyzed by the Analysis Department. For example, it automatically detects fraudulent job postings and false information, and assesses the possibility of illegal activity by detecting suspicious language. Step 4: The warning unit issues warnings based on the illegal content identified by the identification unit. For example, it sends email notifications or pop-up messages to platform administrators and relevant authorities, and displays warning messages to job seekers to reduce the risk of them becoming involved in illegal job postings.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] Each of the multiple elements described above, including the monitoring unit, analysis unit, identification unit, warning unit, anomaly detection unit, provision unit, and warning display unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the monitoring unit monitors job advertisements and posts using the camera 42 and communication I / F 44 of the smart device 14, and transmits the monitoring data to the data processing unit 12 via the control unit 46A. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and analyzes the monitoring data using generative AI and natural language processing. The identification unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and identifies illegal content based on the analysis results. The warning unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and issues a warning based on the identified illegal content. The anomaly detection unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and detects abnormal patterns using machine learning tools and statistical analysis tools. The provision unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides illegal job advertisements and posts to law enforcement agencies. The warning display unit is implemented, for example, by the control unit 46A of the smart device 14, and displays a warning message to job seekers. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various modifications are possible.

[0137] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] Each of the multiple elements described above, including the monitoring unit, analysis unit, identification unit, warning unit, anomaly detection unit, provision unit, and warning display unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the monitoring unit monitors job advertisements and posts using the camera 42 and communication I / F 44 of the smart glasses 214, and the control unit 46A transmits the monitoring data to the data processing unit 12. The analysis unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, and analyzes the monitoring data using generative AI and natural language processing. The identification unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, and identifies illegal content based on the analysis results. The warning unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, and issues a warning based on the identified illegal content. The anomaly detection unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, and detects abnormal patterns using machine learning tools and statistical analysis tools. The data provision unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides illegal job advertisements and posts to law enforcement agencies. The warning display unit is implemented, for example, by the control unit 46A of the smart glasses 214, and displays a warning message to job seekers. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various modifications are possible.

[0153] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] Each of the multiple elements described above, including the monitoring unit, analysis unit, identification unit, warning unit, anomaly detection unit, provision unit, and warning display unit, is implemented, for example, in at least one of the headset terminal 314 and the data processing unit 12. For example, the monitoring unit monitors job advertisements and posts using the camera 42 and communication I / F 44 of the headset terminal 314, and the control unit 46A transmits the monitoring data to the data processing unit 12. The analysis unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, and analyzes the monitoring data using generative AI and natural language processing. The identification unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, and identifies illegal content based on the analysis results. The warning unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, and issues a warning based on the identified illegal content. The anomaly detection unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, and detects abnormal patterns using machine learning tools and statistical analysis tools. The provision unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides illegal job advertisements and posts to law enforcement agencies. The warning display unit is implemented, for example, by the control unit 46A of the headset terminal 314, and displays a warning message to job seekers. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various modifications are possible.

[0169] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.).

[0182] 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.

[0183] 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.

[0184] 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.

[0185] Each of the multiple elements described above, including the monitoring unit, analysis unit, identification unit, warning unit, anomaly detection unit, provision unit, and warning display unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the monitoring unit monitors job advertisements and posts using the camera 42 and communication I / F 44 of the robot 414, and transmits the monitoring data to the data processing unit 12 via the control unit 46A. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and analyzes the monitoring data using generative AI and natural language processing. The identification unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and identifies illegal content based on the analysis results. The warning unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and issues a warning based on the identified illegal content. The anomaly detection unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and detects abnormal patterns using machine learning tools and statistical analysis tools. The provision unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides illegal job advertisements and posts to law enforcement agencies. The warning display unit is implemented, for example, by the control unit 46A of the robot 414, and displays a warning message to job seekers. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various modifications are possible.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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."

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] (Note 1) A monitoring department that monitors job advertisements and posts, An analysis unit analyzes the information monitored by the aforementioned monitoring unit, Based on the information analyzed by the aforementioned analysis unit, an identification unit identifies the illegal content, The system includes a warning unit that issues a warning based on the illegal content identified by the aforementioned identification unit. A system characterized by the following features. (Note 2) It includes an anomaly detection unit that detects abnormal patterns using a data analysis tool. The system described in Appendix 1, characterized by the features described herein. (Note 3) It has a department that provides information to law enforcement agencies. The system described in Appendix 1, characterized by the features described herein. (Note 4) It is equipped with a warning display unit that shows a warning message to job seekers. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned monitoring unit, Monitoring job postings and posts on job boards and social media. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit is We use generative AI and natural language processing to analyze the content of job advertisements and posts. The system described in Appendix 1, characterized by the features described herein. (Note 7) The specified part is, Automatically detects illegal content and suspicious language. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned warning unit is We will notify platform administrators and relevant authorities when we discover illegal job postings. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned monitoring unit, It estimates the user's emotions and adjusts the monitoring frequency based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned monitoring unit, Analyze the frequency of occurrence of specific keywords or phrases in real time. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned monitoring unit, By referring to past monitoring data, abnormal patterns can be detected early. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned monitoring unit, It estimates user sentiment and determines the priority of monitoring targets based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned monitoring unit, Strengthen monitoring by focusing on specific regions and time zones. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned monitoring unit, Focus on monitoring specific groups or forums on social media. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit is It estimates the user's emotions and adjusts the level of detail of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit is The legality of a post will be determined by considering the context of its content. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit is Images and videos in posts are also included in the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit is It estimates the user's emotions and adjusts how the analysis results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit is Different analysis algorithms are applied depending on the language and region of the post. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit is Consider the metadata of the post. The system described in Appendix 1, characterized by the features described herein. (Note 21) The specified part is, It estimates the user's emotions and adjusts certain criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The specified part is, Referencing past illegal posting data improves certain accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 23) The specified part is, We will consider not only the content of the post, but also the poster's past behavioral history. The system described in Appendix 1, characterized by the features described herein. (Note 24) The specified part is, It estimates the user's emotions and adjusts how specific results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The specified part is, The legality of a post is determined by considering its geographical distribution. The system described in Appendix 1, characterized by the features described herein. (Note 26) The specified part is, Related links and sources cited in the post will also be included in the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned warning unit is It estimates the user's emotions and adjusts the content of the warning based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned warning unit is The intensity of the warning will vary depending on the degree of illegality. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned warning unit is Optimize the effectiveness of warnings by referring to past warning history. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned warning unit is It estimates the user's emotions and adjusts the timing of warnings based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned warning unit is Optimize how warning messages are displayed according to the user's device. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned warning unit is Display warning messages in multiple languages The system described in Appendix 1, characterized by the features described herein. (Note 33) The abnormality detection unit, The system estimates the user's emotions and adjusts the anomaly detection criteria based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The abnormality detection unit, When an anomaly is detected, past anomaly data is referenced to improve the accuracy of the detection. The system described in Appendix 2, characterized by the features described herein. (Note 35) The abnormality detection unit, It estimates the user's emotions and adjusts the frequency of anomaly detection based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 36) The abnormality detection unit, When an anomaly is detected, the detection is strengthened by focusing on specific regions or time periods. The system described in Appendix 2, characterized by the features described herein. (Note 37) The aforementioned supply unit is, It estimates the user's emotions and adjusts the level of detail of the information provided based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned supply unit is, When providing a service, we optimize its effectiveness by referring to past service history. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned supply unit is, It estimates the user's emotions and adjusts the timing of service delivery based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned supply unit is, Display the information provided in multiple languages. The system described in Appendix 3, characterized by the features described herein. (Note 41) The aforementioned warning display unit is The system estimates the user's emotions and adjusts the content of warning messages based on those emotions. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned warning display unit is When a warning is displayed, the system optimizes the display effect by referring to the history of past warning displays. The system described in Appendix 4, characterized by the features described herein. (Note 43) The aforementioned warning display unit is The system estimates the user's emotions and adjusts the timing of warning messages based on those emotions. The system described in Appendix 4, characterized by the features described herein. (Note 44) The aforementioned warning display unit is Optimize warning messages according to the user's device. The system described in Appendix 4, characterized by the features described herein. [Explanation of symbols]

[0205] 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 monitoring department that monitors job advertisements and posts, An analysis unit analyzes the information monitored by the aforementioned monitoring unit, Based on the information analyzed by the aforementioned analysis unit, an identification unit identifies the illegal content, The system includes a warning unit that issues a warning based on the illegal content identified by the aforementioned identification unit. A system characterized by the following features.

2. It includes an anomaly detection unit that detects abnormal patterns using a data analysis tool. The system according to feature 1.

3. It has a department that provides information to law enforcement agencies. The system according to feature 1.

4. It is equipped with a warning display unit that shows a warning message to job seekers. The system according to feature 1.

5. The aforementioned monitoring unit, Monitoring job postings and posts on job boards and social media. The system according to feature 1.

6. The aforementioned analysis unit is We use generative AI and natural language processing to analyze the content of job advertisements and posts. The system according to feature 1.

7. The specified part is, Automatically detects illegal content and suspicious language. The system according to feature 1.

8. The aforementioned warning unit is We will notify platform administrators and relevant authorities when we discover illegal job postings. The system according to feature 1.

Images