system

Abstract

The system according to this embodiment aims to ensure the security of websites and protect users with low internet literacy. [Solution] The system according to the embodiment comprises a patrol unit, a detection unit, an exclusion unit, a monitoring unit, and a scoring unit. The patrol unit patrols websites. The detection unit analyzes the content of websites patrolled by the patrol unit and detects suspicious content and harmful advertisements. The exclusion unit excludes suspicious sites detected by the detection unit from search results. The monitoring unit monitors payment processing and the input of personal information. The scoring unit scores the risk level of each website.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, users with low digital literacy are at high risk of encountering phishing and harmful content, and there is room for improvement.

[0005] The system according to the embodiment aims to ensure the security of a website and protect users with low digital literacy.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a patrol unit, a detection unit, an exclusion unit, a monitoring unit, and a scoring unit. The patrol unit patrols websites. The detection unit analyzes the content of websites patrolled by the patrol unit and detects suspicious content and harmful advertisements. The exclusion unit excludes suspicious sites detected by the detection unit from search results. The monitoring unit monitors payment processing and the input of personal information. The scoring unit assigns a score to the risk level of each website. [Effects of the Invention]

[0007] The system according to this embodiment can ensure the security of websites and protect users with low internet literacy. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

[0019] The smart device 14 comprises a computer 36, a 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) An internet patrol agent system according to an embodiment of the present invention is an AI crawler agent system that protects children and the elderly with low internet literacy from phishing and viruses by patrolling websites and ensuring their safety. This internet patrol agent system crawls websites and detects sites containing suspicious content or harmful advertisements. Next, it excludes the detected sites from search results to prevent users from accessing them. It also monitors payment processing and the input of personal information to prevent problems before they occur. Furthermore, it can be combined with child-friendly filtering services to further enhance safety. By scoring the level of risk, control can be made according to age and literacy level. For example, in the internet patrol agent system, the AI ​​crawler crawls websites and detects sites containing suspicious content or harmful advertisements. In this process, the AI ​​analyzes the content of the website and identifies phishing and virus tactics. For example, phishing sites often contain fake login pages or forms that prompt users to enter personal information. The AI ​​detects these characteristics and marks the site as suspicious. Next, the internet patrol agent system excludes the detected sites from search results. This reduces the risk of users accessing suspicious sites. For example, by excluding suspicious sites from links displayed on search engine results pages, it prevents users from accidentally accessing them. The internet patrol agent system also monitors payment processing and personal information input. AI monitors the content of payments and personal information inputs made by users on websites. For example, it detects forms where personal information such as credit card information and addresses are entered and verifies their security. If input on a suspicious site is detected, a warning is displayed to the user, preventing problems before they occur. Furthermore, the internet patrol agent system can be combined with child-friendly filtering services to enhance security. Child-friendly filtering services are filtering services that provide safe content for children.By adding suspicious websites detected by an AI crawler to the filtering list of a child-friendly filtering service, the system provides a safe environment for children to use the internet. Finally, the Internet Patrol Agent system can assign a score to the level of danger, enabling control tailored to age and literacy level. The AI ​​scores the danger level of each website and restricts access based on that score. For example, it can restrict access to high-risk sites for children and the elderly with low internet literacy, ensuring they can use the internet safely. In this way, the Internet Patrol Agent system can protect children and the elderly with low internet literacy from phishing and viruses.

[0029] The internet patrol agent system according to this embodiment comprises a patrol unit, a detection unit, an exclusion unit, a monitoring unit, and a scoring unit. The patrol unit patrols websites. The patrol unit automatically patrols websites, for example, using an AI crawler. The patrol unit can periodically patrol websites based on a list of website URLs. For example, the patrol unit patrols websites at a fixed time each day to collect the latest information. The patrol unit can also patrol websites based on specific conditions. For example, the patrol unit prioritizes patrolling websites that contain specific keywords. The detection unit analyzes the content of websites patrolled by the patrol unit and detects suspicious content and harmful advertisements. The detection unit analyzes the content of websites, for example, using AI. The detection unit can identify phishing sites and sites containing malware. For example, the detection unit can detect sites containing fake login pages or forms that prompt users to enter personal information. The detection unit can also identify sites containing harmful advertisements. For example, the detection unit can detect fraudulent advertisements and advertisements containing malware. The exclusion unit removes suspicious sites detected by the detection unit from search results. For example, the exclusion unit removes suspicious sites from links displayed on the search engine results page. The exclusion unit can reduce the risk of users accessing suspicious sites. For example, the exclusion unit removes phishing sites and sites containing malware from search results. The monitoring unit monitors payment processing and the input of personal information. For example, the monitoring unit uses AI to monitor payment processing and the input of personal information that users perform on websites. The monitoring unit can detect forms into which personal information such as credit card information and addresses are entered and verify their security. For example, if input is detected on a suspicious site, the monitoring unit displays a warning to the user. The scoring unit scores the risk level of each website. For example, the scoring unit uses AI to evaluate the risk level of each website. The scoring unit can score the risk level of phishing sites and sites containing malware. For example, the scoring unit scores the risk level of each website on a scale from 0 to 100. The scoring unit can also implement controls based on age and literacy level.For example, the scoring unit restricts access to high-risk sites for children and the elderly who have low internet literacy. This allows the internet patrol agent system according to this embodiment to ensure safety through website patrolling, detection, exclusion, monitoring, and scoring.

[0030] The crawling unit crawls websites. For example, the crawling unit automatically crawls websites using an AI crawler. The AI ​​crawler crawls a list of website URLs based on a pre-configured algorithm and collects the latest information. Specifically, the crawling unit analyzes the HTML structure of a website and crawls pages one after another by following links within the pages. This allows for the efficient collection of website updates and new content. The crawling unit can crawl websites regularly. For example, the crawling unit can crawl websites at a fixed time every day to collect the latest information. This ensures that the information is always up-to-date and enables quick responses. The crawling unit can also crawl websites based on specific conditions. For example, the crawling unit can prioritize crawling websites containing specific keywords. This enables quick responses to specific topics and risks. Furthermore, the crawling unit can detect changes in the structure and content of websites and issue alerts if there are any abnormal changes. This allows for the early detection of website security risks and the implementation of countermeasures. The patrol department stores the collected data in a central database, making it accessible to other departments. This strengthens information sharing and collaboration throughout the system, enabling more efficient operation.

[0031] The detection unit analyzes the content of websites crawled by the crawling unit to detect suspicious content and harmful advertisements. For example, the detection unit uses AI to analyze website content. The AI ​​utilizes natural language processing and image recognition technologies to analyze website text and images, identifying suspicious content. Specifically, the detection unit can identify phishing sites and sites containing malware. For example, it can detect sites containing fake login pages or forms prompting users to enter personal information. This reduces the risk of users falling victim to phishing scams. The detection unit can also identify sites containing harmful advertisements. For example, it can detect fraudulent advertisements and advertisements containing malware. This reduces the risk of users clicking on harmful advertisements. The detection unit analyzes the collected data and learns rules and patterns for identifying suspicious content and harmful advertisements. This improves detection accuracy and enables more effective detection. Furthermore, the detection unit analyzes data in real time, enabling rapid response. For example, the detection unit immediately analyzes the data collected by the crawling unit to detect suspicious content and harmful advertisements. This allows appropriate measures to be taken before users access dangerous websites.

[0032] The exclusion unit removes suspicious websites detected by the detection unit from search results. For example, the exclusion unit removes suspicious websites from links displayed on the search engine results page. Specifically, the exclusion unit intervenes in the search engine's algorithm and removes links to detected suspicious websites from the search results. This reduces the risk of users accessing suspicious websites. For example, the exclusion unit excludes phishing sites and sites containing malware from search results. This reduces the risk of users accessing dangerous sites through search results. Based on the information provided by the detection unit, the exclusion unit creates a list of suspicious websites and sends an exclusion request to the search engine. This allows the search engine to remove links to suspicious websites from the search results and provide users with safe search results. Furthermore, the exclusion unit can collect user feedback and improve the accuracy of the exclusion list. For example, if a user accesses a suspicious website, the exclusion unit collects that information and reflects it in the exclusion list. This allows the exclusion unit to always maintain an exclusion list based on the latest information and ensure user safety.

[0033] The monitoring unit monitors payment processing and personal information input. For example, the monitoring unit uses AI to monitor payment processing and personal information input performed by users on websites. Specifically, the monitoring unit can detect forms where personal information such as credit card information and addresses are entered and verify their security. The monitoring unit uses AI to analyze the contents of forms and displays a warning to the user if input on a suspicious site is detected. For example, the monitoring unit can detect forms where credit card information is entered on phishing sites and display a warning to the user. This reduces the risk of users falling victim to phishing scams. Furthermore, the monitoring unit monitors the security of payment gateways to verify the security of payment processing. For example, the monitoring unit verifies the validity of the payment gateway's SSL certificate and monitors whether secure communication is taking place. This allows users to make payments safely. The monitoring unit can analyze data in real time and respond quickly. For example, the monitoring unit immediately verifies the security of personal information entered by users and displays a warning immediately if input on a suspicious site is detected. This allows appropriate measures to be taken before users enter personal information on dangerous sites.

[0034] The scoring unit assigns a score to the risk level of each website. For example, the scoring unit uses AI to evaluate the risk level of each website. Specifically, the scoring unit can assign a score to phishing sites and sites containing malware. The scoring unit uses an algorithm to evaluate risk based on the website's content, structure, and history. For example, the scoring unit assigns a score to each website on a scale from 0 to 100. This allows users to grasp the risk level of each website at a glance. Furthermore, the scoring unit can implement controls based on age and literacy level. For example, the scoring unit restricts access to high-risk sites for children and the elderly with low internet literacy. This allows for appropriate security measures to be taken for specific user groups. In addition, the scoring unit can collect user feedback to improve the accuracy of its evaluation algorithm. For example, if a user accesses a dangerous site, that information is collected and reflected in the evaluation algorithm. This allows the scoring unit to always provide highly accurate risk assessments based on the latest information. The scoring unit analyzes data in real time, enabling rapid responses. For example, it instantly reflects changes in the content and structure of a website and updates the risk assessment. This ensures that users always receive a risk assessment based on the latest information.

[0035] The monitoring unit monitors payment processing and personal information input, and can display a warning to the user if suspicious input is detected on a suspicious site. For example, the monitoring unit monitors the input of credit card information during payment processing. For example, the monitoring unit detects forms where credit card information is entered and verifies their security. The monitoring unit can also monitor the input of addresses and phone numbers when personal information is entered. For example, the monitoring unit detects forms where addresses and phone numbers are entered and verifies their security. The monitoring unit can also display a warning to the user if suspicious input is detected on a suspicious site. For example, if input is detected on a suspicious site, the monitoring unit displays a warning message to alert the user. This prevents problems by detecting input on suspicious sites and displaying warnings to the user. The content and display method of the warning include, for example, the content of the warning message and the timing of its display. Some or all of the above processes in the monitoring unit may be performed using AI, or not using AI. For example, the monitoring unit can input payment processing and personal information input into AI, which can verify its security and display a warning.

[0036] The scoring unit assigns a score to the risk level of each website and can restrict access based on that score. For example, the scoring unit assigns a score to each website on a scale from 0 to 100. For example, the scoring unit assigns a higher score to phishing sites and sites containing malware. The scoring unit can also restrict access based on the risk score. For example, the scoring unit restricts access to sites with a high risk level. This ensures user safety by restricting access based on risk level. The methods and criteria for access restriction include, for example, the level of restriction and the criteria for selecting sites to restrict. Some or all of the above processing in the scoring unit may be performed using AI, or not using AI. For example, the scoring unit can input the risk level of each website into an AI, which can then assign a score to that risk level and restrict access.

[0037] The detection unit can detect the characteristics of phishing sites and mark them as suspicious sites. For example, the detection unit can identify the characteristics of phishing sites. For example, the detection unit can detect sites that contain fake login pages or forms that prompt users to enter personal information. The detection unit can also mark sites as suspicious based on the characteristics of phishing sites. For example, the detection unit can analyze the URL patterns and content of phishing sites and mark them as suspicious sites. This allows for the identification of phishing sites and the protection of users. The definition and criteria for the characteristics of phishing sites include, for example, URL patterns and site content. Some or all of the above processing in the detection unit may be performed using AI, for example, or not using AI. For example, the detection unit can input the characteristics of phishing sites into AI, and the AI ​​can mark them as suspicious sites based on those characteristics.

[0038] The exclusion function can exclude suspicious sites from links displayed on search engine results pages. For example, the exclusion function can exclude phishing sites and sites containing malware from links displayed on search engine results pages. For example, by excluding suspicious sites from search results, the exclusion function can prevent users from accidentally accessing them. This prevents users from accidentally accessing suspicious sites by excluding them from search results. The scope and target of the search engine results pages include, for example, specific search engines and the display format of the results pages. Some or all of the above processing in the exclusion function may be performed using AI, for example, or without AI. For example, the exclusion function can input the links displayed on the search engine results pages into AI, and the AI ​​can exclude suspicious sites.

[0039] The scoring unit can perform controls according to age and literacy level. For example, the scoring unit scores the risk level of each website and restricts access according to age and literacy level based on that score. For example, the scoring unit restricts access to high-risk sites for children and the elderly who have low internet literacy. In addition, the scoring unit can ensure user safety by performing controls according to age and literacy level. The definitions and criteria for age and literacy level include, for example, age group classifications and methods for evaluating literacy levels. Some or all of the above processing in the scoring unit may be performed using AI, or not using AI. For example, the scoring unit can input the risk level of each website into AI, the AI ​​can score that risk level, and perform controls according to age and literacy level.

[0040] The patrolling unit can analyze past patrolling history and select the optimal patrolling route. For example, the patrolling unit can prioritize patrolling routes where many suspicious sites have been detected in the past. For example, the patrolling unit can select routes with many suspicious sites based on past patrolling history. The patrolling unit can also select routes with many suspicious sites at specific time periods based on past patrolling history. For example, the patrolling unit can select routes with many suspicious sites at specific time periods based on past patrolling history. The patrolling unit can also plan efficient patrolling routes based on past patrolling history. For example, the patrolling unit can plan efficient patrolling routes based on past patrolling history. This makes efficient patrolling possible by selecting the optimal patrolling route based on past patrolling history. The criteria and methods for selecting the optimal patrolling route include, for example, evaluation criteria and selection algorithms for patrolling routes. Some or all of the above processing in the patrolling unit may be performed using, for example, AI, or not using AI. For example, the patrol unit can input past patrol history data into the AI, which can then select the optimal patrol route.

[0041] The crawling unit can prioritize crawling websites of specific categories. For example, it can prioritize crawling websites of categories that contain a high number of phishing sites. It can also prioritize crawling websites of categories that contain a high number of harmful advertisements. It can also prioritize crawling websites of categories that frequently require users to enter personal information. This allows for efficient crawling by prioritizing websites of specific categories. The definition and criteria for specific categories include, for example, the type of category and how to set priorities. Some or all of the above processing in the crawling unit may be performed using AI, for example, or not using AI. For example, the crawling unit can input data from websites of specific categories into AI, and the AI ​​can select websites to prioritize crawling.

[0042] The crawling unit can prioritize visiting highly relevant websites by considering the user's geographical location. For example, the crawling unit can prioritize visiting region-specific phishing sites based on the user's geographical location. The crawling unit can also prioritize visiting local news sites by considering the user's geographical location. For example, the crawling unit can prioritize visiting local news sites by considering the user's geographical location. The crawling unit can also prioritize visiting local commercial sites by considering the user's geographical location. For example, the crawling unit can prioritize visiting local commercial sites by considering the user's geographical location. This allows for more appropriate crawling by prioritizing highly relevant websites by considering the user's geographical location. The method of acquiring and using geographical location information includes, for example, the means of acquiring location information and the scope of its use. Some or all of the above processing in the crawling unit may be performed using, for example, AI, or not using AI. For example, the patrolling unit can input the user's geographical location information into the AI, which can then prioritize visiting websites that are highly relevant to the user.

[0043] The crawling unit can analyze a user's social media activity and crawl relevant websites. For example, the crawling unit can prioritize crawling social media links that the user frequently accesses. The crawling unit can also crawl relevant news sites based on the user's social media activity. The crawling unit can also crawl websites in categories of interest based on the user's social media activity. This allows for more appropriate crawling by analyzing the user's social media activity and crawling relevant websites. Methods for analyzing and using social media activity include, for example, methods for collecting activity data and analysis algorithms. Some or all of the above processing in the crawling unit may be performed using, for example, AI, or not using AI. For example, the patrol unit can input user social media activity data into the AI, which can then patrol relevant websites.

[0044] The detection unit can analyze the content of a website in real time and identify suspicious content. For example, the detection unit can analyze the text content of a website in real time and identify phishing techniques. The detection unit can also analyze the image content of a website in real time and identify harmful advertisements. The detection unit can also analyze the destinations of links on a website in real time and identify suspicious sites. This allows for the rapid identification of suspicious content by analyzing the content of a website in real time. The methods and criteria for real-time analysis include, for example, the timing of the analysis and the technology used. Some or all of the above-described processes in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input the content of a website into AI, which can analyze it in real time and identify suspicious content.

[0045] The detection unit can identify suspicious content by referring to the website's update history. For example, the detection unit can analyze the website's update history and determine that content that is frequently changed is suspicious. The detection unit can also determine that content updated during specific time periods is suspicious based on the website's update history. The detection unit can also identify sites that have previously contained suspicious content based on the website's update history. This allows for the identification of suspicious content by referring to the website's update history. Methods for obtaining and using the update history include, for example, methods for collecting historical data and analysis algorithms. Some or all of the above-described processes in the detection unit may be performed using AI, or not. For example, the detection unit can input website update history data into AI, which can then identify suspicious content.

[0046] The detection unit can identify suspicious content by considering the geographical distribution of websites. For example, the detection unit can prioritize the detection of phishing sites that are prevalent in a particular area. The detection unit can also identify websites in areas with a high concentration of harmful advertisements based on geographical distribution. The detection unit can also detect region-specific suspicious content by considering geographical distribution. For example, the detection unit can detect region-specific suspicious content by considering geographical distribution. This makes it possible to identify region-specific suspicious content by considering the geographical distribution of websites. Methods for obtaining and using geographical distribution include, for example, methods for collecting distribution data and analysis algorithms. Some or all of the above-described processes in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input geographical distribution data of websites into AI, which can then identify suspicious content.

[0047] The detection unit can identify suspicious content by referring to relevant literature on a website. For example, the detection unit can analyze relevant literature on a website to identify phishing techniques. The detection unit can also identify the characteristics of harmful advertisements based on relevant literature on a website. The detection unit can also identify suspicious links by referring to relevant literature on a website. This allows for the identification of suspicious content by referring to relevant literature on a website. Methods for referring to and using relevant literature include, for example, methods for collecting literature data and analysis algorithms. Some or all of the above-described processes in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input relevant literature data from a website into an AI, which can then identify suspicious content.

[0048] The exclusion unit can improve the accuracy of exclusion by evaluating the reliability of websites. For example, the exclusion unit can evaluate the reliability of websites and prioritize the exclusion of unreliable sites. For example, the exclusion unit can evaluate the reliability of websites and prioritize the exclusion of unreliable sites. The exclusion unit can also identify and exclude suspicious sites based on the reliability of websites. For example, the exclusion unit can identify and exclude suspicious sites based on the reliability of websites. The exclusion unit can also evaluate the reliability of websites and exclude highly reliable sites from exclusion. For example, the exclusion unit can evaluate the reliability of websites and exclude highly reliable sites from exclusion. This improves the accuracy of exclusion by evaluating the reliability of websites. Reliability evaluation criteria and methods include, for example, reliability evaluation metrics and evaluation algorithms. Some or all of the above processing in the exclusion unit may be performed using, for example, AI, or not using AI. For example, the exclusion unit can input website reliability data into AI, which can evaluate reliability and improve the accuracy of exclusion.

[0049] The exclusion unit can perform exclusions by referring to the past evaluation history of websites. For example, the exclusion unit can analyze the past evaluation history of websites and prioritize the exclusion of sites with low ratings. The exclusion unit can also identify and exclude suspicious sites based on the past evaluation history of websites. The exclusion unit can also exclude unreliable sites by referring to the past evaluation history of websites. This improves the accuracy of exclusions by referring to the past evaluation history of websites. The methods for obtaining and using past evaluation history include, for example, methods for collecting historical data and analysis algorithms. Some or all of the above processing in the exclusion unit may be performed using, for example, AI, or not using AI. For example, the exclusion unit can input the past evaluation history data of websites into AI, and the AI ​​can perform the exclusions.

[0050] The exclusion function can exclude websites while considering their geographical distribution. For example, it can prioritize the exclusion of phishing sites that are prevalent in a particular region. The exclusion function can also exclude websites in areas with a high concentration of harmful advertisements, based on their geographical distribution. The exclusion function can also exclude suspicious content specific to a particular region, taking geographical distribution into consideration. This allows for the exclusion of suspicious content specific to a particular region by considering the geographical distribution of websites. Methods for obtaining and using geographical distribution include, for example, methods for collecting distribution data and analysis algorithms. Some or all of the above-described processes in the exclusion function may be performed using, for example, AI, or not. For example, the exclusion function can input the geographical distribution data of websites into an AI, which can then perform the exclusions.

[0051] The exclusion unit can improve the accuracy of exclusion by referring to relevant literature on the website during the exclusion process. For example, the exclusion unit can analyze relevant literature on the website to identify and exclude phishing techniques. The exclusion unit can also identify and exclude characteristics of harmful advertisements based on relevant literature on the website. The exclusion unit can also identify and exclude suspicious links by referring to relevant literature on the website. This improves the accuracy of exclusion by referring to relevant literature on the website. The methods for referring to and using relevant literature include, for example, methods for collecting literature data and analysis algorithms. Some or all of the above processing in the exclusion unit may be performed using, for example, AI, or not using AI. For example, the exclusion unit can input relevant literature data from the website into AI, and the AI ​​can perform the exclusion.

[0052] The monitoring unit can analyze payment processing and personal information input in real time during monitoring. For example, the monitoring unit can analyze credit card information input in real time during payment processing. For example, the monitoring unit can analyze credit card information input in real time during payment processing. The monitoring unit can also analyze address and phone number input in real time during personal information input. For example, the monitoring unit can analyze address and phone number input in real time during personal information input. The monitoring unit can also analyze payment processing and personal information input in real time to identify suspicious sites. For example, the monitoring unit can analyze payment processing and personal information input in real time to identify suspicious sites. This allows for the rapid identification of suspicious sites by analyzing payment processing and personal information input in real time. The methods and criteria for real-time analysis include, for example, the timing of the analysis and the technology used. Some or all of the above-described processes in the monitoring unit may be performed using, for example, AI, or not using AI. For example, the monitoring unit can input payment processing and personal information input into AI, which can analyze it in real time and identify suspicious sites.

[0053] The monitoring unit can select the optimal monitoring method by referring to past monitoring history during monitoring. For example, the monitoring unit can prioritize monitoring sites where problems frequently occur based on past monitoring history. The monitoring unit can also select and monitor sites that have a high number of problems during specific time periods based on past monitoring history. The monitoring unit can also plan efficient monitoring methods by referring to past monitoring history. This allows the optimal monitoring method to be selected by referring to past monitoring history. Methods for acquiring and using past monitoring history include, for example, methods for collecting historical data and analysis algorithms. Some or all of the above-described processes in the monitoring unit may be performed using, for example, AI, or not using AI. For example, the monitoring unit can input past monitoring history data into AI, and the AI ​​can select the optimal monitoring method.

[0054] The monitoring unit can perform highly relevant monitoring by considering the user's geographical location information during monitoring. For example, the monitoring unit can prioritize monitoring region-specific phishing sites based on the user's geographical location information. The monitoring unit can also monitor local commercial sites by considering the user's geographical location information. The monitoring unit can also monitor local news sites by considering the user's geographical location information. This enables more appropriate monitoring by performing highly relevant monitoring by considering the user's geographical location information. The method of acquiring and using geographical location information includes, for example, the means of acquiring location information and the scope of use. Some or all of the above processing in the monitoring unit may be performed using, for example, AI, or without AI. For example, the monitoring unit can input the user's geographical location information into AI, and the AI ​​can perform highly relevant monitoring.

[0055] The monitoring unit can analyze a user's social media activity and perform relevant monitoring during monitoring. For example, the monitoring unit can prioritize monitoring the destinations of social media links that the user frequently accesses. The monitoring unit can also monitor relevant news sites based on the user's social media activity. The monitoring unit can also monitor websites in categories of interest based on the user's social media activity. This allows for more appropriate monitoring by analyzing the user's social media activity and performing relevant monitoring. Methods for analyzing and using social media activity include, for example, methods for collecting activity data and analysis algorithms. 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 user's social media activity data into AI, which can then perform relevant monitoring.

[0056] The scoring unit can analyze the content of a website in real time and assign a score to its level of risk. For example, the scoring unit can analyze the text content of a website in real time and assign a score to phishing tactics. The scoring unit can also analyze the image content of a website in real time and assign a score to the level of risk of harmful advertisements. The scoring unit can also analyze the destinations of links on a website in real time and assign a score to the level of risk of suspicious sites. This allows for rapid scoring of risk by analyzing the content of a website in real time. The methods and criteria for real-time analysis include, for example, the timing of the analysis and the technologies used. Some or all of the above-described processes in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input the content of a website into AI, which can analyze it in real time and assign a score to the level of risk.

[0057] The scoring unit can perform scoring by referring to the past evaluation history of a website. For example, the scoring unit can analyze the past evaluation history of a website and assign a higher score to sites with low ratings. The scoring unit can also assign a score to suspicious sites based on the past evaluation history of a website. For example, the scoring unit can assign a score to suspicious sites based on the past evaluation history of a website. The scoring unit can also assign a score to unreliable sites by referring to the past evaluation history of a website. For example, the scoring unit can assign a score to unreliable sites by referring to the past evaluation history of a website. This improves the accuracy of scoring by referring to the past evaluation history of a website. The methods for obtaining and using past evaluation history include, for example, the methods for collecting historical data and the analysis algorithms. Some or all of the above-described processes in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input past evaluation history data of a website into AI, and the AI ​​can perform the scoring.

[0058] The scoring unit can consider the geographical distribution of websites when scoring them. For example, the scoring unit can assign a higher score to phishing sites that are frequently found in a particular area. The scoring unit can also assign a higher score to websites in areas with a high concentration of harmful advertisements, based on geographical distribution. The scoring unit can also assign a score to suspicious content specific to a particular area, taking geographical distribution into consideration. This allows for the scoring of suspicious content specific to a particular area by considering the geographical distribution of websites. Methods for obtaining and using geographical distribution include, for example, methods for collecting distribution data and analysis algorithms. Some or all of the above-described processes in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input geographical distribution data of websites into AI, which can then perform the scoring.

[0059] The scoring unit can improve the accuracy of scoring by referring to relevant literature on the website during the scoring process. For example, the scoring unit can analyze relevant literature on the website and score the risk level of phishing tactics. For example, the scoring unit can analyze relevant literature on the website and score the risk level of phishing tactics. The scoring unit can also score the characteristics of harmful advertisements based on relevant literature on the website. For example, the scoring unit can score the characteristics of harmful advertisements based on relevant literature on the website. The scoring unit can also score the risk level of suspicious links by referring to relevant literature on the website. For example, the scoring unit can score the risk level of suspicious links by referring to relevant literature on the website. This improves the accuracy of scoring by referring to relevant literature on the website. The methods for referring to and using relevant literature include, for example, methods for collecting literature data and analysis algorithms. Some or all of the above-described processes in the scoring unit may be performed using, for example, AI, or not using AI. For example, the scoring unit can input relevant literature data from a website into the AI, which then performs the scoring.

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

[0061] The Internet Patrol Agent System can score the risk level of websites, taking into account the user's geographical location. For example, it can score the risk level of phishing sites that are prevalent in a particular area, thereby imposing stricter restrictions on users in that area. It can also score the risk level of websites in areas with a high concentration of harmful advertisements, based on geographical distribution. Furthermore, it can score the risk level of suspicious content specific to a particular region, allowing for appropriate restrictions on users in that region. This enables scoring that addresses region-specific risks, providing a safer internet environment. The method of acquiring and using geographical distribution includes the means of acquiring location information and the scope of its use. The scoring unit inputs the geographical distribution data of websites into an AI, which then performs the scoring.

[0062] The Internet Patrol Agent System can analyze a user's social media activity and score the risk level of related websites. For example, it can score the risk level of links on social media frequently accessed by the user, thereby imposing stricter restrictions. It can also score the risk level of related news sites based on the user's social media activity and impose appropriate restrictions. Furthermore, it can score the risk level of websites in categories of interest based on the user's social media activity and impose appropriate restrictions. This enables scoring based on the user's social media activity, providing a more appropriate internet usage environment. The methods for analyzing and using social media activity include methods for collecting activity data and analysis algorithms. The scoring unit inputs the user's social media activity data into an AI, which then performs the scoring.

[0063] The Internet Patrol Agent System can score the risk level of websites by referring to their update history. For example, it can analyze a website's update history and assign a higher risk level to content that is frequently changed. It can also score the risk level of content updated during specific time periods and impose appropriate restrictions on users accessing those sites. Furthermore, it can score the risk level of sites that have previously contained suspicious content and impose appropriate restrictions. This enables scoring based on website update history, providing a safer internet environment. The methods for obtaining and using update history include data collection methods and analysis algorithms. The scoring unit inputs website update history data into an AI, which then performs the scoring.

[0064] The Internet Patrol Agent System can score the risk level of websites by referring to relevant literature. For example, it can analyze relevant literature on a website and score the risk level of phishing tactics. It can also score the characteristics of harmful advertisements based on relevant literature and set appropriate restrictions. Furthermore, it can score the risk level of suspicious links by referring to relevant literature and set appropriate restrictions. This enables scoring based on relevant literature on websites, providing a safer internet environment. The methods for referring to and using relevant literature include methods for collecting literature data and analysis algorithms. The scoring unit inputs the relevant literature data from websites into an AI, which then performs the scoring.

[0065] The internet patrol agent system can adjust the monitoring frequency based on the user's geographical location. For example, it can prioritize monitoring phishing sites that are prevalent in a particular area, and provide stricter monitoring to users in that area. It can also prioritize monitoring websites in areas with a high concentration of harmful advertisements based on geographical distribution. Furthermore, it can prioritize monitoring suspicious content specific to a particular region, providing appropriate monitoring to users in that region. This enables monitoring that addresses region-specific risks, providing a safer internet environment. The method of acquiring and using geographical distribution includes the means of acquiring location information and the scope of its use. The monitoring unit inputs the user's geographical location information into the AI, which can then adjust the monitoring frequency.

[0066] The Internet Patrol Agent System can analyze a user's social media activity and adjust the frequency of monitoring relevant websites. For example, it can prioritize monitoring of social media links frequently accessed by the user, enabling stricter surveillance. It can also prioritize monitoring of news sites related to the user's social media activity. Furthermore, it can prioritize monitoring of websites in categories of interest based on the user's social media activity. This enables monitoring based on the user's social media activity, providing a more appropriate internet usage environment. The methods for analyzing and using social media activity include methods for collecting activity data and analysis algorithms. The monitoring unit inputs the user's social media activity data into the AI, which can then adjust the monitoring frequency.

[0067] The Internet Patrol Agent System can adjust how monitoring results are displayed, taking into account the user's geographical location. For example, it can display detailed monitoring results for phishing sites that are prevalent in a specific area, allowing for stricter warnings to users in that area. It can also display detailed monitoring results for websites in areas with a high concentration of harmful advertisements, based on geographical distribution. Furthermore, it can display detailed monitoring results for suspicious content specific to a particular area, allowing for appropriate warnings to users in that area. This enables the display of monitoring results that address region-specific risks, providing a safer internet environment. The method of acquiring and using geographical distribution includes the means of acquiring location information and the scope of its use. The monitoring unit inputs the user's geographical location information into the AI, which can then adjust how the monitoring results are displayed.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The crawling unit crawls websites. The crawling unit automatically crawls websites, for example, using an AI crawler. The crawling unit can periodically crawl websites based on a list of website URLs. For example, the crawling unit can crawl websites at a set time each day to collect the latest information. The crawling unit can also crawl websites based on specific conditions. For example, the crawling unit can prioritize crawling websites that contain specific keywords. Step 2: The detection unit analyzes the content of websites crawled by the crawling unit to detect suspicious content and harmful advertisements. The detection unit can analyze website content using, for example, AI. The detection unit can identify phishing sites and sites containing malware. For example, the detection unit can detect sites containing fake login pages or forms that prompt users to enter personal information. The detection unit can also identify sites containing harmful advertisements. For example, the detection unit can detect fraudulent advertisements and advertisements containing malware. Step 3: The exclusion unit removes suspicious sites detected by the detection unit from the search results. For example, the exclusion unit removes suspicious sites from links displayed on the search engine results page. The exclusion unit can reduce the risk of users accessing suspicious sites. For example, the exclusion unit removes phishing sites and sites containing malware from the search results. Step 4: The monitoring unit monitors payment processing and personal information entry. The monitoring unit uses AI, for example, to monitor payment processing and personal information entry that users make on websites. The monitoring unit can detect forms where personal information such as credit card information and addresses are entered and verify their security. For example, if the monitoring unit detects input on a suspicious site, it will display a warning to the user. Step 5: The scoring unit assigns a score to the risk level of each website. The scoring unit uses, for example, AI to evaluate the risk level of each website. The scoring unit can assign a score to phishing sites and sites containing malware. For example, the scoring unit assigns a score to each website on a scale from 0 to 100. The scoring unit can also implement controls based on age and literacy level. For example, the scoring unit can restrict access to high-risk sites for children and the elderly with low internet literacy.

[0070] (Example of form 2) An internet patrol agent system according to an embodiment of the present invention is an AI crawler agent system that protects children and the elderly with low internet literacy from phishing and viruses by patrolling websites and ensuring their safety. This internet patrol agent system crawls websites and detects sites containing suspicious content or harmful advertisements. Next, it excludes the detected sites from search results to prevent users from accessing them. It also monitors payment processing and the input of personal information to prevent problems before they occur. Furthermore, it can be combined with child-friendly filtering services to further enhance safety. By scoring the level of risk, control can be made according to age and literacy level. For example, in the internet patrol agent system, the AI ​​crawler crawls websites and detects sites containing suspicious content or harmful advertisements. In this process, the AI ​​analyzes the content of the website and identifies phishing and virus tactics. For example, phishing sites often contain fake login pages or forms that prompt users to enter personal information. The AI ​​detects these characteristics and marks the site as suspicious. Next, the internet patrol agent system excludes the detected sites from search results. This reduces the risk of users accessing suspicious sites. For example, by excluding suspicious sites from links displayed on search engine results pages, it prevents users from accidentally accessing them. The internet patrol agent system also monitors payment processing and personal information input. AI monitors the content of payments and personal information inputs made by users on websites. For example, it detects forms where personal information such as credit card information and addresses are entered and verifies their security. If input on a suspicious site is detected, a warning is displayed to the user, preventing problems before they occur. Furthermore, the internet patrol agent system can be combined with child-friendly filtering services to enhance security. Child-friendly filtering services are filtering services that provide safe content for children.By adding suspicious websites detected by an AI crawler to the filtering list of a child-friendly filtering service, the system provides a safe environment for children to use the internet. Finally, the Internet Patrol Agent system can assign a score to the level of danger, enabling control tailored to age and literacy level. The AI ​​scores the danger level of each website and restricts access based on that score. For example, it can restrict access to high-risk sites for children and the elderly with low internet literacy, ensuring they can use the internet safely. In this way, the Internet Patrol Agent system can protect children and the elderly with low internet literacy from phishing and viruses.

[0071] The internet patrol agent system according to this embodiment comprises a patrol unit, a detection unit, an exclusion unit, a monitoring unit, and a scoring unit. The patrol unit patrols websites. The patrol unit automatically patrols websites, for example, using an AI crawler. The patrol unit can periodically patrol websites based on a list of website URLs. For example, the patrol unit patrols websites at a fixed time each day to collect the latest information. The patrol unit can also patrol websites based on specific conditions. For example, the patrol unit prioritizes patrolling websites that contain specific keywords. The detection unit analyzes the content of websites patrolled by the patrol unit and detects suspicious content and harmful advertisements. The detection unit analyzes the content of websites, for example, using AI. The detection unit can identify phishing sites and sites containing malware. For example, the detection unit can detect sites containing fake login pages or forms that prompt users to enter personal information. The detection unit can also identify sites containing harmful advertisements. For example, the detection unit can detect fraudulent advertisements and advertisements containing malware. The exclusion unit removes suspicious sites detected by the detection unit from search results. For example, the exclusion unit removes suspicious sites from links displayed on the search engine results page. The exclusion unit can reduce the risk of users accessing suspicious sites. For example, the exclusion unit removes phishing sites and sites containing malware from search results. The monitoring unit monitors payment processing and the input of personal information. For example, the monitoring unit uses AI to monitor payment processing and the input of personal information that users perform on websites. The monitoring unit can detect forms into which personal information such as credit card information and addresses are entered and verify their security. For example, if input is detected on a suspicious site, the monitoring unit displays a warning to the user. The scoring unit scores the risk level of each website. For example, the scoring unit uses AI to evaluate the risk level of each website. The scoring unit can score the risk level of phishing sites and sites containing malware. For example, the scoring unit scores the risk level of each website on a scale from 0 to 100. The scoring unit can also implement controls based on age and literacy level.For example, the scoring unit restricts access to high-risk sites for children and the elderly who have low internet literacy. This allows the internet patrol agent system according to this embodiment to ensure safety through website patrolling, detection, exclusion, monitoring, and scoring.

[0072] The crawling unit crawls websites. For example, the crawling unit automatically crawls websites using an AI crawler. The AI ​​crawler crawls a list of website URLs based on a pre-configured algorithm and collects the latest information. Specifically, the crawling unit analyzes the HTML structure of a website and crawls pages one after another by following links within the pages. This allows for the efficient collection of website updates and new content. The crawling unit can crawl websites regularly. For example, the crawling unit can crawl websites at a fixed time every day to collect the latest information. This ensures that the information is always up-to-date and enables quick responses. The crawling unit can also crawl websites based on specific conditions. For example, the crawling unit can prioritize crawling websites containing specific keywords. This enables quick responses to specific topics and risks. Furthermore, the crawling unit can detect changes in the structure and content of websites and issue alerts if there are any abnormal changes. This allows for the early detection of website security risks and the implementation of countermeasures. The patrol department stores the collected data in a central database, making it accessible to other departments. This strengthens information sharing and collaboration throughout the system, enabling more efficient operation.

[0073] The detection unit analyzes the content of websites crawled by the crawling unit to detect suspicious content and harmful advertisements. For example, the detection unit uses AI to analyze website content. The AI ​​utilizes natural language processing and image recognition technologies to analyze website text and images, identifying suspicious content. Specifically, the detection unit can identify phishing sites and sites containing malware. For example, it can detect sites containing fake login pages or forms prompting users to enter personal information. This reduces the risk of users falling victim to phishing scams. The detection unit can also identify sites containing harmful advertisements. For example, it can detect fraudulent advertisements and advertisements containing malware. This reduces the risk of users clicking on harmful advertisements. The detection unit analyzes the collected data and learns rules and patterns for identifying suspicious content and harmful advertisements. This improves detection accuracy and enables more effective detection. Furthermore, the detection unit analyzes data in real time, enabling rapid response. For example, the detection unit immediately analyzes the data collected by the crawling unit to detect suspicious content and harmful advertisements. This allows appropriate measures to be taken before users access dangerous websites.

[0074] The exclusion unit removes suspicious websites detected by the detection unit from search results. For example, the exclusion unit removes suspicious websites from links displayed on the search engine results page. Specifically, the exclusion unit intervenes in the search engine's algorithm and removes links to detected suspicious websites from the search results. This reduces the risk of users accessing suspicious websites. For example, the exclusion unit excludes phishing sites and sites containing malware from search results. This reduces the risk of users accessing dangerous sites through search results. Based on the information provided by the detection unit, the exclusion unit creates a list of suspicious websites and sends an exclusion request to the search engine. This allows the search engine to remove links to suspicious websites from the search results and provide users with safe search results. Furthermore, the exclusion unit can collect user feedback and improve the accuracy of the exclusion list. For example, if a user accesses a suspicious website, the exclusion unit collects that information and reflects it in the exclusion list. This allows the exclusion unit to always maintain an exclusion list based on the latest information and ensure user safety.

[0075] The monitoring unit monitors payment processing and personal information input. For example, the monitoring unit uses AI to monitor payment processing and personal information input performed by users on websites. Specifically, the monitoring unit can detect forms where personal information such as credit card information and addresses are entered and verify their security. The monitoring unit uses AI to analyze the contents of forms and displays a warning to the user if input on a suspicious site is detected. For example, the monitoring unit can detect forms where credit card information is entered on phishing sites and display a warning to the user. This reduces the risk of users falling victim to phishing scams. Furthermore, the monitoring unit monitors the security of payment gateways to verify the security of payment processing. For example, the monitoring unit verifies the validity of the payment gateway's SSL certificate and monitors whether secure communication is taking place. This allows users to make payments safely. The monitoring unit can analyze data in real time and respond quickly. For example, the monitoring unit immediately verifies the security of personal information entered by users and displays a warning immediately if input on a suspicious site is detected. This allows appropriate measures to be taken before users enter personal information on dangerous sites.

[0076] The scoring unit assigns a score to the risk level of each website. For example, the scoring unit uses AI to evaluate the risk level of each website. Specifically, the scoring unit can assign a score to phishing sites and sites containing malware. The scoring unit uses an algorithm to evaluate risk based on the website's content, structure, and history. For example, the scoring unit assigns a score to each website on a scale from 0 to 100. This allows users to grasp the risk level of each website at a glance. Furthermore, the scoring unit can implement controls based on age and literacy level. For example, the scoring unit restricts access to high-risk sites for children and the elderly with low internet literacy. This allows for appropriate security measures to be taken for specific user groups. In addition, the scoring unit can collect user feedback to improve the accuracy of its evaluation algorithm. For example, if a user accesses a dangerous site, that information is collected and reflected in the evaluation algorithm. This allows the scoring unit to always provide highly accurate risk assessments based on the latest information. The scoring unit analyzes data in real time, enabling rapid responses. For example, it instantly reflects changes in the content and structure of a website and updates the risk assessment. This ensures that users always receive a risk assessment based on the latest information.

[0077] The monitoring unit monitors payment processing and personal information input, and can display a warning to the user if suspicious input is detected on a suspicious site. For example, the monitoring unit monitors the input of credit card information during payment processing. For example, the monitoring unit detects forms where credit card information is entered and verifies their security. The monitoring unit can also monitor the input of addresses and phone numbers when personal information is entered. For example, the monitoring unit detects forms where addresses and phone numbers are entered and verifies their security. The monitoring unit can also display a warning to the user if suspicious input is detected on a suspicious site. For example, if input is detected on a suspicious site, the monitoring unit displays a warning message to alert the user. This prevents problems by detecting input on suspicious sites and displaying warnings to the user. The content and display method of the warning include, for example, the content of the warning message and the timing of its display. Some or all of the above processes in the monitoring unit may be performed using AI, or not using AI. For example, the monitoring unit can input payment processing and personal information input into AI, which can verify its security and display a warning.

[0078] The scoring unit assigns a score to the risk level of each website and can restrict access based on that score. For example, the scoring unit assigns a score to each website on a scale from 0 to 100. For example, the scoring unit assigns a higher score to phishing sites and sites containing malware. The scoring unit can also restrict access based on the risk score. For example, the scoring unit restricts access to sites with a high risk level. This ensures user safety by restricting access based on risk level. The methods and criteria for access restriction include, for example, the level of restriction and the criteria for selecting sites to restrict. Some or all of the above processing in the scoring unit may be performed using AI, or not using AI. For example, the scoring unit can input the risk level of each website into an AI, which can then assign a score to that risk level and restrict access.

[0079] The detection unit can detect the characteristics of phishing sites and mark them as suspicious sites. For example, the detection unit can identify the characteristics of phishing sites. For example, the detection unit can detect sites that contain fake login pages or forms that prompt users to enter personal information. The detection unit can also mark sites as suspicious based on the characteristics of phishing sites. For example, the detection unit can analyze the URL patterns and content of phishing sites and mark them as suspicious sites. This allows for the identification of phishing sites and the protection of users. The definition and criteria for the characteristics of phishing sites include, for example, URL patterns and site content. Some or all of the above processing in the detection unit may be performed using AI, for example, or not using AI. For example, the detection unit can input the characteristics of phishing sites into AI, and the AI ​​can mark them as suspicious sites based on those characteristics.

[0080] The exclusion function can exclude suspicious sites from links displayed on search engine results pages. For example, the exclusion function can exclude phishing sites and sites containing malware from links displayed on search engine results pages. For example, by excluding suspicious sites from search results, the exclusion function can prevent users from accidentally accessing them. This prevents users from accidentally accessing suspicious sites by excluding them from search results. The scope and target of the search engine results pages include, for example, specific search engines and the display format of the results pages. Some or all of the above processing in the exclusion function may be performed using AI, for example, or without AI. For example, the exclusion function can input the links displayed on the search engine results pages into AI, and the AI ​​can exclude suspicious sites.

[0081] The scoring unit can perform controls according to age and literacy level. For example, the scoring unit scores the risk level of each website and restricts access according to age and literacy level based on that score. For example, the scoring unit restricts access to high-risk sites for children and the elderly who have low internet literacy. In addition, the scoring unit can ensure user safety by performing controls according to age and literacy level. The definitions and criteria for age and literacy level include, for example, age group classifications and methods for evaluating literacy levels. Some or all of the above processing in the scoring unit may be performed using AI, or not using AI. For example, the scoring unit can input the risk level of each website into AI, the AI ​​can score that risk level, and perform controls according to age and literacy level.

[0082] The patrol unit can estimate the user's emotions and adjust the patrol frequency based on the estimated emotions. For example, if the user is feeling anxious, the patrol unit can increase the patrol frequency to ensure safety. For example, if the user is feeling anxious, the patrol unit can set the patrol frequency higher than usual. The patrol unit can also return the patrol frequency to normal if the user is relaxed. For example, if the user is relaxed, the patrol unit can return the patrol frequency to normal. The patrol unit can also temporarily decrease the patrol frequency if the user is in a hurry. For example, if the patrol unit is in a hurry, the patrol unit can temporarily lower the patrol frequency. This allows for more appropriate patrols by adjusting the patrol frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a 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 patrol unit may be performed using AI, for example, or without AI. For example, the patrol unit can input user emotion data into a generating AI, which can then estimate the emotion and adjust the frequency of patrols.

[0083] The patrolling unit can analyze past patrolling history and select the optimal patrolling route. For example, the patrolling unit can prioritize patrolling routes where many suspicious sites have been detected in the past. For example, the patrolling unit can select routes with many suspicious sites based on past patrolling history. The patrolling unit can also select routes with many suspicious sites at specific time periods based on past patrolling history. For example, the patrolling unit can select routes with many suspicious sites at specific time periods based on past patrolling history. The patrolling unit can also plan efficient patrolling routes based on past patrolling history. For example, the patrolling unit can plan efficient patrolling routes based on past patrolling history. This makes efficient patrolling possible by selecting the optimal patrolling route based on past patrolling history. The criteria and methods for selecting the optimal patrolling route include, for example, evaluation criteria and selection algorithms for patrolling routes. Some or all of the above processing in the patrolling unit may be performed using, for example, AI, or not using AI. For example, the patrol unit can input past patrol history data into the AI, which can then select the optimal patrol route.

[0084] The crawling unit can prioritize crawling websites of specific categories. For example, it can prioritize crawling websites of categories that contain a high number of phishing sites. It can also prioritize crawling websites of categories that contain a high number of harmful advertisements. It can also prioritize crawling websites of categories that frequently require users to enter personal information. This allows for efficient crawling by prioritizing websites of specific categories. The definition and criteria for specific categories include, for example, the type of category and how to set priorities. Some or all of the above processing in the crawling unit may be performed using AI, for example, or not using AI. For example, the crawling unit can input data from websites of specific categories into AI, and the AI ​​can select websites to prioritize crawling.

[0085] The crawling unit can estimate the user's emotions and determine the priority of websites to visit based on the estimated emotions. For example, if the user is feeling anxious, the crawling unit may prioritize visiting phishing sites. For example, if the user is feeling anxious, the crawling unit may prioritize visiting phishing sites. The crawling unit may also maintain the normal crawling order if the user is relaxed. For example, if the crawling unit is relaxed, the crawling unit may maintain the normal crawling order. The crawling unit may also prioritize visiting important sites if the user is in a hurry. For example, if the crawling unit is in a hurry, the crawling unit may prioritize visiting important sites. This allows for a more appropriate crawl by determining the priority of websites to visit according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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 crawling unit may be performed using AI, for example, or without AI. For example, the browsing unit can input user emotion data into a generating AI, which can then estimate the emotion and determine the priority of the websites to visit.

[0086] The crawling unit can prioritize visiting highly relevant websites by considering the user's geographical location. For example, the crawling unit can prioritize visiting region-specific phishing sites based on the user's geographical location. The crawling unit can also prioritize visiting local news sites by considering the user's geographical location. For example, the crawling unit can prioritize visiting local news sites by considering the user's geographical location. The crawling unit can also prioritize visiting local commercial sites by considering the user's geographical location. For example, the crawling unit can prioritize visiting local commercial sites by considering the user's geographical location. This allows for more appropriate crawling by prioritizing highly relevant websites by considering the user's geographical location. The method of acquiring and using geographical location information includes, for example, the means of acquiring location information and the scope of its use. Some or all of the above processing in the crawling unit may be performed using, for example, AI, or not using AI. For example, the patrolling unit can input the user's geographical location information into the AI, which can then prioritize visiting websites that are highly relevant to the user.

[0087] The crawling unit can analyze a user's social media activity and crawl relevant websites. For example, the crawling unit can prioritize crawling social media links that the user frequently accesses. The crawling unit can also crawl relevant news sites based on the user's social media activity. The crawling unit can also crawl websites in categories of interest based on the user's social media activity. This allows for more appropriate crawling by analyzing the user's social media activity and crawling relevant websites. Methods for analyzing and using social media activity include, for example, methods for collecting activity data and analysis algorithms. Some or all of the above processing in the crawling unit may be performed using, for example, AI, or not using AI. For example, the patrol unit can input user social media activity data into the AI, which can then patrol relevant websites.

[0088] The detection unit can estimate the user's emotions and adjust the detection accuracy based on the estimated emotions. For example, if the user is feeling anxious, the detection unit can increase the detection accuracy to more rigorously detect suspicious content. For example, if the user is feeling anxious, the detection unit can set the detection accuracy higher than usual. The detection unit can also maintain normal detection accuracy if the user is relaxed. For example, if the user is relaxed, the detection unit can maintain normal detection accuracy. The detection unit can also temporarily decrease the detection accuracy if the user is in a hurry. For example, if the user is in a hurry, the detection unit can temporarily set the detection accuracy lower. By adjusting the detection accuracy according to the user's emotions, more appropriate detection becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input user emotion data into a generating AI, which can then estimate the emotion and adjust the detection accuracy.

[0089] The detection unit can analyze the content of a website in real time and identify suspicious content. For example, the detection unit can analyze the text content of a website in real time and identify phishing techniques. The detection unit can also analyze the image content of a website in real time and identify harmful advertisements. The detection unit can also analyze the destinations of links on a website in real time and identify suspicious sites. This allows for the rapid identification of suspicious content by analyzing the content of a website in real time. The methods and criteria for real-time analysis include, for example, the timing of the analysis and the technology used. Some or all of the above-described processes in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input the content of a website into AI, which can analyze it in real time and identify suspicious content.

[0090] The detection unit can identify suspicious content by referring to the website's update history. For example, the detection unit can analyze the website's update history and determine that content that is frequently changed is suspicious. The detection unit can also determine that content updated during specific time periods is suspicious based on the website's update history. The detection unit can also identify sites that have previously contained suspicious content based on the website's update history. This allows for the identification of suspicious content by referring to the website's update history. Methods for obtaining and using the update history include, for example, methods for collecting historical data and analysis algorithms. Some or all of the above-described processes in the detection unit may be performed using AI, or not. For example, the detection unit can input website update history data into AI, which can then identify suspicious content.

[0091] The detection unit can estimate the user's emotions and adjust the display method of the detection results based on the estimated user emotions. For example, if the user is feeling anxious, the detection unit can display detailed detection results to provide reassurance. For example, if the user is feeling anxious, the detection unit can display detailed detection results to provide reassurance. The detection unit can also display concise detection results if the user is relaxed. For example, if the user is relaxed, the detection unit can display concise detection results. The detection unit can also display concise detection results if the user is in a hurry. For example, if the user is in a hurry, the detection unit can display concise detection results. By adjusting the display method of the detection results according to the user's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input user emotion data into a generating AI, which can then estimate the emotion and adjust how the detection results are displayed.

[0092] The detection unit can identify suspicious content by considering the geographical distribution of websites. For example, the detection unit can prioritize the detection of phishing sites that are prevalent in a particular area. The detection unit can also identify websites in areas with a high concentration of harmful advertisements based on geographical distribution. The detection unit can also detect region-specific suspicious content by considering geographical distribution. For example, the detection unit can detect region-specific suspicious content by considering geographical distribution. This makes it possible to identify region-specific suspicious content by considering the geographical distribution of websites. Methods for obtaining and using geographical distribution include, for example, methods for collecting distribution data and analysis algorithms. Some or all of the above-described processes in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input geographical distribution data of websites into AI, which can then identify suspicious content.

[0093] The detection unit can identify suspicious content by referring to relevant literature on a website. For example, the detection unit can analyze relevant literature on a website to identify phishing techniques. The detection unit can also identify the characteristics of harmful advertisements based on relevant literature on a website. The detection unit can also identify suspicious links by referring to relevant literature on a website. This allows for the identification of suspicious content by referring to relevant literature on a website. Methods for referring to and using relevant literature include, for example, methods for collecting literature data and analysis algorithms. Some or all of the above-described processes in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input relevant literature data from a website into an AI, which can then identify suspicious content.

[0094] The exclusion section can estimate the user's emotions and adjust the exclusion criteria based on the estimated emotions. For example, if the user is feeling anxious, the exclusion section can tighten the exclusion criteria and exclude more suspicious sites. For example, if the user is feeling anxious, the exclusion section can set the exclusion criteria stricter than usual. The exclusion section can also maintain the normal exclusion criteria if the user is relaxed. For example, if the user is relaxed, the exclusion section can maintain the normal exclusion criteria. The exclusion section can also temporarily relax the exclusion criteria if the user is in a hurry. For example, if the user is in a hurry, the exclusion section can temporarily loosen the exclusion criteria. This allows for more appropriate exclusion by adjusting the exclusion criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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 exclusion section may be performed using AI, for example, or without AI. For example, the exclusion unit can input user emotion data into a generating AI, which can then estimate the emotion and adjust the exclusion criteria.

[0095] The exclusion unit can improve the accuracy of exclusion by evaluating the reliability of websites. For example, the exclusion unit can evaluate the reliability of websites and prioritize the exclusion of unreliable sites. For example, the exclusion unit can evaluate the reliability of websites and prioritize the exclusion of unreliable sites. The exclusion unit can also identify and exclude suspicious sites based on the reliability of websites. For example, the exclusion unit can identify and exclude suspicious sites based on the reliability of websites. The exclusion unit can also evaluate the reliability of websites and exclude highly reliable sites from exclusion. For example, the exclusion unit can evaluate the reliability of websites and exclude highly reliable sites from exclusion. This improves the accuracy of exclusion by evaluating the reliability of websites. Reliability evaluation criteria and methods include, for example, reliability evaluation metrics and evaluation algorithms. Some or all of the above processing in the exclusion unit may be performed using, for example, AI, or not using AI. For example, the exclusion unit can input website reliability data into AI, which can evaluate reliability and improve the accuracy of exclusion.

[0096] The exclusion unit can perform exclusions by referring to the past evaluation history of websites. For example, the exclusion unit can analyze the past evaluation history of websites and prioritize the exclusion of sites with low ratings. The exclusion unit can also identify and exclude suspicious sites based on the past evaluation history of websites. The exclusion unit can also exclude unreliable sites by referring to the past evaluation history of websites. This improves the accuracy of exclusions by referring to the past evaluation history of websites. The methods for obtaining and using past evaluation history include, for example, methods for collecting historical data and analysis algorithms. Some or all of the above processing in the exclusion unit may be performed using, for example, AI, or not using AI. For example, the exclusion unit can input the past evaluation history data of websites into AI, and the AI ​​can perform the exclusions.

[0097] The exclusion section can estimate the user's emotions and adjust how the exclusion results are displayed based on the estimated emotions. For example, if the user is feeling anxious, the exclusion section can display detailed exclusion results to provide reassurance. For example, if the user is feeling anxious, the exclusion section can display detailed exclusion results to provide reassurance. The exclusion section can also display concise exclusion results if the user is relaxed. For example, if the user is relaxed, the exclusion section can display concise exclusion results. The exclusion section can also display concise exclusion results if the user is in a hurry. For example, if the user is in a hurry, the exclusion section can display concise exclusion results. By adjusting how the exclusion results are displayed according to the user's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a 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 exclusion section may be performed using AI, for example, or without AI. For example, the exclusion unit can input user emotion data into a generating AI, which can then estimate the emotion and adjust how the exclusion results are displayed.

[0098] The exclusion function can exclude websites while considering their geographical distribution. For example, it can prioritize the exclusion of phishing sites that are prevalent in a particular region. The exclusion function can also exclude websites in areas with a high concentration of harmful advertisements, based on their geographical distribution. The exclusion function can also exclude suspicious content specific to a particular region, taking geographical distribution into consideration. This allows for the exclusion of suspicious content specific to a particular region by considering the geographical distribution of websites. Methods for obtaining and using geographical distribution include, for example, methods for collecting distribution data and analysis algorithms. Some or all of the above-described processes in the exclusion function may be performed using, for example, AI, or not. For example, the exclusion function can input the geographical distribution data of websites into an AI, which can then perform the exclusions.

[0099] The exclusion unit can improve the accuracy of exclusion by referring to relevant literature on the website during the exclusion process. For example, the exclusion unit can analyze relevant literature on the website to identify and exclude phishing techniques. The exclusion unit can also identify and exclude characteristics of harmful advertisements based on relevant literature on the website. The exclusion unit can also identify and exclude suspicious links by referring to relevant literature on the website. This improves the accuracy of exclusion by referring to relevant literature on the website. The methods for referring to and using relevant literature include, for example, methods for collecting literature data and analysis algorithms. Some or all of the above processing in the exclusion unit may be performed using, for example, AI, or not using AI. For example, the exclusion unit can input relevant literature data from the website into AI, and the AI ​​can perform the exclusion.

[0100] The monitoring unit can estimate the user's emotions and adjust the monitoring frequency based on the estimated emotions. For example, if the user is feeling anxious, the monitoring unit can increase the monitoring frequency to ensure safety. For example, if the user is feeling anxious, the monitoring unit can set the monitoring frequency higher than usual. The monitoring unit can also return the monitoring frequency to normal if the user is relaxed. For example, if the user is relaxed, the monitoring unit can return the monitoring frequency to normal. The monitoring unit can also temporarily decrease the monitoring frequency if the user is in a hurry. For example, if the monitoring unit is in a hurry, the monitoring unit can temporarily lower the monitoring frequency. This allows for more appropriate monitoring 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 without AI. For example, the monitoring unit can input user emotion data into a generating AI, which can then estimate the emotion and adjust the monitoring frequency.

[0101] The monitoring unit can analyze payment processing and personal information input in real time during monitoring. For example, the monitoring unit can analyze credit card information input in real time during payment processing. For example, the monitoring unit can analyze credit card information input in real time during payment processing. The monitoring unit can also analyze address and phone number input in real time during personal information input. For example, the monitoring unit can analyze address and phone number input in real time during personal information input. The monitoring unit can also analyze payment processing and personal information input in real time to identify suspicious sites. For example, the monitoring unit can analyze payment processing and personal information input in real time to identify suspicious sites. This allows for the rapid identification of suspicious sites by analyzing payment processing and personal information input in real time. The methods and criteria for real-time analysis include, for example, the timing of the analysis and the technology used. Some or all of the above-described processes in the monitoring unit may be performed using, for example, AI, or not using AI. For example, the monitoring unit can input payment processing and personal information input into AI, which can analyze it in real time and identify suspicious sites.

[0102] The monitoring unit can select the optimal monitoring method by referring to past monitoring history during monitoring. For example, the monitoring unit can prioritize monitoring sites where problems frequently occur based on past monitoring history. The monitoring unit can also select and monitor sites that have a high number of problems during specific time periods based on past monitoring history. The monitoring unit can also plan efficient monitoring methods by referring to past monitoring history. This allows the optimal monitoring method to be selected by referring to past monitoring history. Methods for acquiring and using past monitoring history include, for example, methods for collecting historical data and analysis algorithms. Some or all of the above-described processes in the monitoring unit may be performed using, for example, AI, or not using AI. For example, the monitoring unit can input past monitoring history data into AI, and the AI ​​can select the optimal monitoring method.

[0103] The monitoring unit can estimate the user's emotions and adjust the display method of the monitoring results based on the estimated user emotions. For example, if the user is feeling anxious, the monitoring unit can display detailed monitoring results to provide reassurance. For example, if the user is feeling anxious, the monitoring unit can display detailed monitoring results to provide reassurance. The monitoring unit can also display concise monitoring results if the user is relaxed. For example, if the user is relaxed, the monitoring unit can display concise monitoring results. The monitoring unit can also display concise monitoring results if the user is in a hurry. For example, if the user is in a hurry, the monitoring unit can display concise monitoring results. By adjusting the display method of the monitoring results according to the user's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a 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 monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input user emotion data into a generating AI, which can then estimate the emotion and adjust how the monitoring results are displayed.

[0104] The monitoring unit can perform highly relevant monitoring by considering the user's geographical location information during monitoring. For example, the monitoring unit can prioritize monitoring region-specific phishing sites based on the user's geographical location information. The monitoring unit can also monitor local commercial sites by considering the user's geographical location information. The monitoring unit can also monitor local news sites by considering the user's geographical location information. This enables more appropriate monitoring by performing highly relevant monitoring by considering the user's geographical location information. The method of acquiring and using geographical location information includes, for example, the means of acquiring location information and the scope of use. Some or all of the above processing in the monitoring unit may be performed using, for example, AI, or without AI. For example, the monitoring unit can input the user's geographical location information into AI, and the AI ​​can perform highly relevant monitoring.

[0105] The monitoring unit can analyze a user's social media activity and perform relevant monitoring during monitoring. For example, the monitoring unit can prioritize monitoring the destinations of social media links that the user frequently accesses. The monitoring unit can also monitor relevant news sites based on the user's social media activity. The monitoring unit can also monitor websites in categories of interest based on the user's social media activity. This allows for more appropriate monitoring by analyzing the user's social media activity and performing relevant monitoring. Methods for analyzing and using social media activity include, for example, methods for collecting activity data and analysis algorithms. 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 user's social media activity data into AI, which can then perform relevant monitoring.

[0106] The scoring unit can estimate the user's emotions and adjust the scoring criteria based on the estimated emotions. For example, if the user is feeling anxious, the scoring unit will tighten the scoring criteria and rate the level of danger higher. For example, if the user is feeling anxious, the scoring unit will set the scoring criteria stricter than usual. The scoring unit can also maintain the normal scoring criteria if the user is relaxed. For example, if the user is relaxed, the scoring unit will maintain the normal scoring criteria. The scoring unit can also temporarily relax the scoring criteria if the user is in a hurry. For example, if the user is in a hurry, the scoring unit will temporarily loosen the scoring criteria. By adjusting the scoring criteria according to the user's emotions, more appropriate scoring becomes possible. 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-described processes in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input user emotion data into a generating AI, which can then estimate the emotion and adjust the scoring criteria.

[0107] The scoring unit can analyze the content of a website in real time and assign a score to its level of risk. For example, the scoring unit can analyze the text content of a website in real time and assign a score to phishing tactics. The scoring unit can also analyze the image content of a website in real time and assign a score to the level of risk of harmful advertisements. The scoring unit can also analyze the destinations of links on a website in real time and assign a score to the level of risk of suspicious sites. This allows for rapid scoring of risk by analyzing the content of a website in real time. The methods and criteria for real-time analysis include, for example, the timing of the analysis and the technologies used. Some or all of the above-described processes in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input the content of a website into AI, which can analyze it in real time and assign a score to the level of risk.

[0108] The scoring unit can perform scoring by referring to the past evaluation history of a website. For example, the scoring unit can analyze the past evaluation history of a website and assign a higher score to sites with low ratings. The scoring unit can also assign a score to suspicious sites based on the past evaluation history of a website. For example, the scoring unit can assign a score to suspicious sites based on the past evaluation history of a website. The scoring unit can also assign a score to unreliable sites by referring to the past evaluation history of a website. For example, the scoring unit can assign a score to unreliable sites by referring to the past evaluation history of a website. This improves the accuracy of scoring by referring to the past evaluation history of a website. The methods for obtaining and using past evaluation history include, for example, the methods for collecting historical data and the analysis algorithms. Some or all of the above-described processes in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input past evaluation history data of a website into AI, and the AI ​​can perform the scoring.

[0109] The scoring unit can estimate the user's emotions and adjust the display method of the scoring results based on the estimated emotions. For example, if the user is feeling anxious, the scoring unit can display the scoring results in detail to provide reassurance. For example, if the user is feeling anxious, the scoring unit can display the scoring results in detail to provide reassurance. The scoring unit can also display concise scoring results if the user is relaxed. For example, if the user is relaxed, the scoring unit can display concise scoring results. For example, if the user is in a hurry, the scoring unit can display scoring results that get straight to the point. For example, if the user is in a hurry, the scoring unit can display scoring results that get straight to the point. In this way, by adjusting the display method of the scoring results according to the user's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. 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-described processes in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input user emotion data into a generating AI, the generating AI can estimate the emotion, and the method of displaying the scoring result can be adjusted.

[0110] The scoring unit can consider the geographical distribution of websites when scoring them. For example, the scoring unit can assign a higher score to phishing sites that are frequently found in a particular area. The scoring unit can also assign a higher score to websites in areas with a high concentration of harmful advertisements, based on geographical distribution. The scoring unit can also assign a score to suspicious content specific to a particular area, taking geographical distribution into consideration. This allows for the scoring of suspicious content specific to a particular area by considering the geographical distribution of websites. Methods for obtaining and using geographical distribution include, for example, methods for collecting distribution data and analysis algorithms. Some or all of the above-described processes in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input geographical distribution data of websites into AI, which can then perform the scoring.

[0111] The scoring unit can improve the accuracy of scoring by referring to relevant literature on the website during the scoring process. For example, the scoring unit can analyze relevant literature on the website and score the risk level of phishing tactics. For example, the scoring unit can analyze relevant literature on the website and score the risk level of phishing tactics. The scoring unit can also score the characteristics of harmful advertisements based on relevant literature on the website. For example, the scoring unit can score the characteristics of harmful advertisements based on relevant literature on the website. The scoring unit can also score the risk level of suspicious links by referring to relevant literature on the website. For example, the scoring unit can score the risk level of suspicious links by referring to relevant literature on the website. This improves the accuracy of scoring by referring to relevant literature on the website. The methods for referring to and using relevant literature include, for example, methods for collecting literature data and analysis algorithms. Some or all of the above-described processes in the scoring unit may be performed using, for example, AI, or not using AI. For example, the scoring unit can input relevant literature data from a website into the AI, which then performs the scoring.

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

[0113] The Internet Patrol Agent System can estimate a user's emotions and score the risk level of a website based on those emotions. For example, if a user is feeling anxious, the scoring unit will rate the risk higher and impose stricter restrictions. If the user is relaxed, the normal scoring criteria will be applied, and standard restrictions will be imposed. Furthermore, if the user is in a hurry, the scoring unit can temporarily relax the criteria to allow for quick access. This enables flexible scoring that responds to the user's emotions, providing a more appropriate internet usage environment. Emotion estimation is performed using an emotion engine or generative AI. For example, the generative AI may include, but is not limited to, text generation AI or multimodal generation AI. The scoring unit inputs the user's emotion data into the generative AI, which estimates the emotions and adjusts the scoring criteria.

[0114] The Internet Patrol Agent System can score the risk level of websites, taking into account the user's geographical location. For example, it can score the risk level of phishing sites that are prevalent in a particular area, thereby imposing stricter restrictions on users in that area. It can also score the risk level of websites in areas with a high concentration of harmful advertisements, based on geographical distribution. Furthermore, it can score the risk level of suspicious content specific to a particular region, allowing for appropriate restrictions on users in that region. This enables scoring that addresses region-specific risks, providing a safer internet environment. The method of acquiring and using geographical distribution includes the means of acquiring location information and the scope of its use. The scoring unit inputs the geographical distribution data of websites into an AI, which then performs the scoring.

[0115] The Internet Patrol Agent System can analyze a user's social media activity and score the risk level of related websites. For example, it can score the risk level of links on social media frequently accessed by the user, thereby imposing stricter restrictions. It can also score the risk level of related news sites based on the user's social media activity and impose appropriate restrictions. Furthermore, it can score the risk level of websites in categories of interest based on the user's social media activity and impose appropriate restrictions. This enables scoring based on the user's social media activity, providing a more appropriate internet usage environment. The methods for analyzing and using social media activity include methods for collecting activity data and analysis algorithms. The scoring unit inputs the user's social media activity data into an AI, which then performs the scoring.

[0116] The Internet Patrol Agent System can score the risk level of websites by referring to their update history. For example, it can analyze a website's update history and assign a higher risk level to content that is frequently changed. It can also score the risk level of content updated during specific time periods and impose appropriate restrictions on users accessing those sites. Furthermore, it can score the risk level of sites that have previously contained suspicious content and impose appropriate restrictions. This enables scoring based on website update history, providing a safer internet environment. The methods for obtaining and using update history include data collection methods and analysis algorithms. The scoring unit inputs website update history data into an AI, which then performs the scoring.

[0117] The Internet Patrol Agent System can score the risk level of websites by referring to relevant literature. For example, it can analyze relevant literature on a website and score the risk level of phishing tactics. It can also score the characteristics of harmful advertisements based on relevant literature and set appropriate restrictions. Furthermore, it can score the risk level of suspicious links by referring to relevant literature and set appropriate restrictions. This enables scoring based on relevant literature on websites, providing a safer internet environment. The methods for referring to and using relevant literature include methods for collecting literature data and analysis algorithms. The scoring unit inputs the relevant literature data from websites into an AI, which then performs the scoring.

[0118] The internet patrol agent system can estimate a user's emotions and adjust the monitoring frequency based on the estimated emotions. For example, if a user is feeling anxious, the monitoring unit can increase the monitoring frequency to ensure safety. Conversely, if the user is relaxed, the monitoring frequency can be returned to normal. Furthermore, if the user is in a hurry, the monitoring frequency can be temporarily reduced. This enables flexible monitoring in response to the user's emotions, providing a more appropriate internet usage environment. Emotion estimation is performed using an emotion engine or generative AI. For example, the generative AI may include, but is not limited to, text generation AI or multimodal generation AI. The monitoring unit inputs the user's emotion data into the generative AI, which estimates the emotions and adjusts the monitoring frequency.

[0119] The internet patrol agent system can adjust the monitoring frequency based on the user's geographical location. For example, it can prioritize monitoring phishing sites that are prevalent in a particular area, and provide stricter monitoring to users in that area. It can also prioritize monitoring websites in areas with a high concentration of harmful advertisements based on geographical distribution. Furthermore, it can prioritize monitoring suspicious content specific to a particular region, providing appropriate monitoring to users in that region. This enables monitoring that addresses region-specific risks, providing a safer internet environment. The method of acquiring and using geographical distribution includes the means of acquiring location information and the scope of its use. The monitoring unit inputs the user's geographical location information into the AI, which can then adjust the monitoring frequency.

[0120] The Internet Patrol Agent System can analyze a user's social media activity and adjust the frequency of monitoring relevant websites. For example, it can prioritize monitoring of social media links frequently accessed by the user, enabling stricter surveillance. It can also prioritize monitoring of news sites related to the user's social media activity. Furthermore, it can prioritize monitoring of websites in categories of interest based on the user's social media activity. This enables monitoring based on the user's social media activity, providing a more appropriate internet usage environment. The methods for analyzing and using social media activity include methods for collecting activity data and analysis algorithms. The monitoring unit inputs the user's social media activity data into the AI, which can then adjust the monitoring frequency.

[0121] The internet patrol agent system can estimate a user's emotions and adjust the display method of monitoring results based on the estimated emotions. For example, if a user is feeling anxious, the monitoring unit can display detailed monitoring results to provide reassurance. If the user is relaxed, it can display concise monitoring results. Furthermore, if the user is in a hurry, it can display monitoring results that get straight to the point. This enables flexible display according to the user's emotions, providing a more appropriate internet usage environment. Emotion estimation is performed using an emotion engine or generative AI. For example, the generative AI may include, but is not limited to, text generation AI or multimodal generation AI. The monitoring unit inputs user emotion data into the generative AI, which estimates the emotions and adjusts the display method of the monitoring results.

[0122] The Internet Patrol Agent System can adjust how monitoring results are displayed, taking into account the user's geographical location. For example, it can display detailed monitoring results for phishing sites that are prevalent in a specific area, allowing for stricter warnings to users in that area. It can also display detailed monitoring results for websites in areas with a high concentration of harmful advertisements, based on geographical distribution. Furthermore, it can display detailed monitoring results for suspicious content specific to a particular area, allowing for appropriate warnings to users in that area. This enables the display of monitoring results that address region-specific risks, providing a safer internet environment. The method of acquiring and using geographical distribution includes the means of acquiring location information and the scope of its use. The monitoring unit inputs the user's geographical location information into the AI, which can then adjust how the monitoring results are displayed.

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

[0124] Step 1: The crawling unit crawls websites. The crawling unit automatically crawls websites, for example, using an AI crawler. The crawling unit can periodically crawl websites based on a list of website URLs. For example, the crawling unit can crawl websites at a set time each day to collect the latest information. The crawling unit can also crawl websites based on specific conditions. For example, the crawling unit can prioritize crawling websites that contain specific keywords. Step 2: The detection unit analyzes the content of websites crawled by the crawling unit to detect suspicious content and harmful advertisements. The detection unit can analyze website content using, for example, AI. The detection unit can identify phishing sites and sites containing malware. For example, the detection unit can detect sites containing fake login pages or forms that prompt users to enter personal information. The detection unit can also identify sites containing harmful advertisements. For example, the detection unit can detect fraudulent advertisements and advertisements containing malware. Step 3: The exclusion unit removes suspicious sites detected by the detection unit from the search results. For example, the exclusion unit removes suspicious sites from links displayed on the search engine results page. The exclusion unit can reduce the risk of users accessing suspicious sites. For example, the exclusion unit removes phishing sites and sites containing malware from the search results. Step 4: The monitoring unit monitors payment processing and personal information entry. The monitoring unit uses AI, for example, to monitor payment processing and personal information entry that users make on websites. The monitoring unit can detect forms where personal information such as credit card information and addresses are entered and verify their security. For example, if the monitoring unit detects input on a suspicious site, it will display a warning to the user. Step 5: The scoring unit assigns a score to the risk level of each website. The scoring unit uses, for example, AI to evaluate the risk level of each website. The scoring unit can assign a score to phishing sites and sites containing malware. For example, the scoring unit assigns a score to each website on a scale from 0 to 100. The scoring unit can also implement controls based on age and literacy level. For example, the scoring unit can restrict access to high-risk sites for children and the elderly with low internet literacy.

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include 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.

[0127] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements described above, including the crawling unit, detection unit, exclusion unit, monitoring unit, and scoring unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the crawling unit is implemented by the control unit 46A of the smart device 14 and automatically crawls websites using an AI crawler. The detection unit is implemented by the identification processing unit 290 of the data processing device 12 and analyzes the content of websites to detect suspicious content and harmful advertisements. The exclusion unit is implemented by the identification processing unit 290 of the data processing device 12 and excludes suspicious sites from search results. The monitoring unit is implemented by the control unit 46A of the smart device 14 and monitors payment processing and input of personal information. The scoring unit is implemented by the identification processing unit 290 of the data processing device 12 and scores the risk level of each website. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

[0130] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. 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.

[0143] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the crawling unit, detection unit, exclusion unit, monitoring unit, and scoring unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the crawling unit is implemented by the control unit 46A of the smart glasses 214 and automatically crawls websites using an AI crawler. The detection unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and analyzes the content of websites to detect suspicious content and harmful advertisements. The exclusion unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and excludes suspicious sites from search results. The monitoring unit is implemented, for example, by the control unit 46A of the smart glasses 214 and monitors payment processing and input of personal information. The scoring unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and scores the risk level of each website. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

[0146] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0148] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0152] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0153] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0154] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0155] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0156] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0157] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. 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.

[0159] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0160] Each of the multiple elements described above, including the crawling unit, detection unit, exclusion unit, monitoring unit, and scoring unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the crawling unit is implemented by the control unit 46A of the headset terminal 314 and automatically crawls websites using an AI crawler. The detection unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the content of websites to detect suspicious content and harmful advertisements. The exclusion unit is implemented by the identification processing unit 290 of the data processing unit 12 and excludes suspicious sites from search results. The monitoring unit is implemented by the control unit 46A of the headset terminal 314 and monitors payment processing and input of personal information. The scoring unit is implemented by the identification processing unit 290 of the data processing unit 12 and scores the risk level of each website. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

[0162] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0163] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0164] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0165] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0167] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0168] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0169] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0170] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0171] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0172] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0173] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0174] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0175] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. 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.

[0176] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0177] Each of the multiple elements described above, including the crawling unit, detection unit, exclusion unit, monitoring unit, and scoring unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the crawling unit is implemented by the control unit 46A of the robot 414 and automatically crawls websites using an AI crawler. The detection unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and analyzes the content of websites to detect suspicious content and harmful advertisements. The exclusion unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and excludes suspicious sites from search results. The monitoring unit is implemented by, for example, the control unit 46A of the robot 414 and monitors payment processing and input of personal information. The scoring unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and scores the risk level of each website. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0178] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0179] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0180] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0181] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0182] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0183] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0184] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0185] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0186] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0187] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0188] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0189] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0190] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0191] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0192] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0193] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0194] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0195] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0196] (Note 1) A crawling unit that visits websites, A detection unit analyzes the content of websites crawled by the aforementioned crawling unit and detects suspicious content and harmful advertisements. An exclusion unit that excludes suspicious sites detected by the detection unit from the search results, A monitoring department that monitors payment processing and personal information input, It comprises a scoring unit that assigns a score to the level of risk for each website. A system characterized by the following features. (Note 2) The aforementioned monitoring unit, The system monitors payment processing and personal information entry, and displays a warning to the user if suspicious entry is detected on a site. The system described in Appendix 1, characterized by the features described herein. (Note 3) The scoring unit is, The level of risk assigned to each website is scored, and access is restricted based on that score. The system described in Appendix 1, characterized by the features described herein. (Note 4) The detection unit is It detects the characteristics of phishing sites and marks them as suspicious sites. The system described in Appendix 1, characterized by the features described herein. (Note 5) The exclusion section is, Filter out suspicious sites from links displayed on search engine results pages. The system described in Appendix 1, characterized by the features described herein. (Note 6) The scoring unit is, Control is implemented according to age and literacy level. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned patrol unit is, It estimates the user's emotions and adjusts the frequency of visits based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned patrol unit is, Analyze past patrol history to select the optimal patrol route. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned patrol unit is, Prioritize browsing websites in specific categories. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned patrol unit is, It estimates user sentiment and prioritizes websites to visit based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned patrol unit is, The system prioritizes browsing relevant websites by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned patrol unit is, Analyze users' social media activity and crawl relevant websites. The system described in Appendix 1, characterized by the features described herein. (Note 13) The detection unit is It estimates the user's emotions and adjusts the accuracy of the detection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The detection unit is It analyzes website content in real time and identifies suspicious content. The system described in Appendix 1, characterized by the features described herein. (Note 15) The detection unit is Identify suspicious content by reviewing the website's update history. The system described in Appendix 1, characterized by the features described herein. (Note 16) The detection unit is It estimates the user's emotions and adjusts how the detection results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The detection unit is Identify suspicious content by considering the geographical distribution of websites. The system described in Appendix 1, characterized by the features described herein. (Note 18) The detection unit is Identify suspicious content by referring to relevant literature on the website. The system described in Appendix 1, characterized by the features described herein. (Note 19) The exclusion section is, We estimate the user's sentiment and adjust the exclusion criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The exclusion section is, Evaluate website reliability to improve the accuracy of exclusion. The system described in Appendix 1, characterized by the features described herein. (Note 21) The exclusion section is, When excluding a website, the website's past rating history is used to perform the exclusion. The system described in Appendix 1, characterized by the features described herein. (Note 22) The exclusion section is, It estimates the user's sentiment and adjusts how exclusion results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The exclusion section is, When excluding websites, consider their geographical distribution. The system described in Appendix 1, characterized by the features described herein. (Note 24) The exclusion section is, When excluding, we refer to relevant literature on the website to improve the accuracy of the exclusion. The system described in Appendix 1, characterized by the features described herein. (Note 25) 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 26) The aforementioned monitoring unit, During monitoring, payment processing and personal information input are analyzed in real time. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned monitoring unit, During monitoring, the optimal monitoring method is selected by referring to past monitoring history. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned monitoring unit, It estimates the user's emotions and adjusts how monitoring results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned monitoring unit, During monitoring, the system takes into account the user's geographical location to perform more relevant monitoring. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned monitoring unit, During monitoring, the system analyzes the user's social media activity and performs relevant monitoring. The system described in Appendix 1, characterized by the features described herein. (Note 31) The scoring unit is, The system estimates the user's emotions and adjusts the scoring criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The scoring unit is, During the scoring process, the website content is analyzed in real time to assign a score to its level of risk. The system described in Appendix 1, characterized by the features described herein. (Note 33) The scoring unit is, When assigning scores, the website's past rating history is referenced. The system described in Appendix 1, characterized by the features described herein. (Note 34) The scoring unit is, The system estimates the user's emotions and adjusts how the scoring results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The scoring unit is, When assigning scores, the geographical distribution of websites is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 36) The scoring unit is, When assigning scores, we refer to relevant literature on the website to improve the accuracy of the scoring. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0197] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A crawling unit that visits websites, A detection unit analyzes the content of websites crawled by the aforementioned crawling unit and detects suspicious content and harmful advertisements. An exclusion unit that excludes suspicious sites detected by the detection unit from the search results, A monitoring department that monitors payment processing and personal information input, It comprises a scoring unit that assigns a score to the level of risk for each website. A system characterized by the following features.

2. The aforementioned monitoring unit, The system monitors payment processing and personal information entry, and displays a warning to the user if suspicious entry is detected on a site. The system according to feature 1.

3. The scoring unit is, The level of risk assigned to each website is scored, and access is restricted based on that score. The system according to feature 1.

4. The detection unit is It detects the characteristics of phishing sites and marks them as suspicious sites. The system according to feature 1.

5. The exclusion section is, Filter out suspicious sites from links displayed on search engine results pages. The system according to feature 1.

6. The scoring unit is, Control is implemented according to age and literacy level. The system according to feature 1.

7. The aforementioned patrol unit is, It estimates the user's emotions and adjusts the frequency of visits based on the estimated emotions. The system according to feature 1.

8. The aforementioned patrol unit is, Analyze past patrol history to select the optimal patrol route. The system according to feature 1.

9. The aforementioned patrol unit is, Prioritize browsing websites in specific categories. The system according to feature 1.

10. The aforementioned patrol unit is, It estimates user sentiment and prioritizes websites to visit based on that estimated sentiment. The system according to feature 1.

Images