system

Abstract

An object of the system according to the embodiment is to automatically perform warning and countermeasures against phishing sites and false information.SOLUTION: A system according to an embodiment includes a reception unit, a filter unit, a warning unit, an access warning unit, an information distribution unit, and a takedown unit. A reception part receives regular transmission information and official site information from a company. The filter unit filters the information received by the receiving unit to determine whether it is legitimate. The warning unit issues a warning when it is determined by the filter unit that the CS window is not legitimate, and displays a legitimate CS window. The access warning unit issues a warning when the phishing site is accessed. The information distribution unit automatically transmits information to the company when the warning is issued by the warning unit and the access warning unit. The takedown unit performs takedown based on the information transmitted by the information distribution unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies do not provide sufficient countermeasures against phishing sites and false information, leaving users at risk of being harmed.

[0005] The system according to the embodiment aims to automatically warn against and take measures against phishing sites and false information. [Means for solving the problem]

[0006] The system according to the embodiment includes a receiving unit, a filtering unit, a warning unit, an access warning unit, an information distribution unit, and a takedown unit. The receiving unit receives legitimate information and official website information from companies. The filtering unit filters the information received by the receiving unit to determine whether it is legitimate. The warning unit issues a warning if the filtering unit determines that the information is not legitimate, and displays the legitimate customer service contact point. The access warning unit issues a warning if a phishing site is accessed. The information distribution unit automatically sends information to the company when a warning is issued by the warning unit and the access warning unit. The takedown unit performs takedown based on the information sent by the information distribution unit. [Effects of the Invention]

[0007] The system according to the embodiment can automatically warn against and take measures against phishing sites and false information. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A system according to an embodiment of the present invention receives legitimate information from companies and official website information, filters it, and issues a warning if the information is not legitimate. Furthermore, a similar warning is issued when a phishing site is accessed, and the legitimate customer service contact point is displayed. It also includes a mechanism for automatically sending information distribution to companies and taking down the information when the information is received or the site is accessed. This allows the system to receive legitimate information from companies and official website information, filter it, and issue a warning if the information is not legitimate. Furthermore, a similar warning is issued when a phishing site is accessed, and the legitimate customer service contact point is displayed. Furthermore, a mechanism for automatically sending information distribution to companies and taking down the information when the information is received or the site is accessed.

[0029] An information filtering system according to an embodiment includes a receiving unit, a filtering unit, a warning unit, an access warning unit, an information distribution unit, and a takedown unit. The receiving unit receives legitimate information and official website information from a company. For example, the receiving unit can receive information from a company's official website or information from an authenticated third-party site. The filtering unit filters the information received by the receiving unit to determine whether the information is legitimate. For example, the filtering unit analyzes the information using keyword filtering or blacklist filtering to determine whether it is legitimate. The warning unit issues a warning and displays a legitimate customer support hotline when the filtering unit determines that the information is not legitimate. For example, the warning unit issues a warning using a pop-up message or an email notification and displays the company's official customer support hotline. The access warning unit issues a warning when a phishing site is accessed. For example, the access warning unit detects phishing sites using URL pattern matching or blacklist reference and issues a warning. The information distribution unit automatically sends information to a company when a warning is issued by the warning unit and the access warning unit. For example, the information distribution unit automatically sends information to a company using an API. The takedown unit performs takedown based on the information transmitted by the information distribution unit. For example, the takedown unit deletes phishing sites through legal procedures. As a result, the information filtering system according to the embodiment receives legitimate information transmitted by companies and official website information, applies filters, issues a warning if the information is not legitimate, and displays the legitimate customer service contact point. Furthermore, if a phishing site is accessed, a similar warning is issued, and information distribution is automatically sent to the company to perform takedown.

[0030] The receiving unit evaluates the trustworthiness of a company and determines the priority of receiving information based on the trustworthiness. The receiving unit evaluates the trustworthiness based on, for example, the company's past transaction history. For example, the receiving unit retrieves the company's transaction history from a database and calculates a trustworthiness score. The receiving unit can also evaluate the trustworthiness based on ratings from a third-party rating agency. For example, the receiving unit retrieves rating data from the rating agency and calculates a trustworthiness score. The receiving unit also determines the priority of receiving information based on the trustworthiness of the company. For example, the receiving unit prioritizes receiving information from highly trustworthy companies and postpones receiving information from less trustworthy companies. The receiving unit can also set trustworthiness evaluation criteria and receive only information from companies that meet the criteria. The receiving unit can also save information from less trustworthy companies in a separate folder so that the user can manually check it. In this way, by determining the priority of receiving information based on the trustworthiness of the company, highly reliable information can be preferentially received. Some or all of the above-described processing in the receiving unit may be performed using, for example, AI, or may be performed without using AI.

[0031] The receiving unit selects an appropriate receiving means depending on the type of information when receiving the information. For example, the receiving unit receives text information via email and images and videos via a dedicated app. For example, the receiving unit obtains text information from an email server and displays it on the user's email client. The receiving unit can also receive images and videos via a dedicated app and display them on the user's device. The receiving unit can also store large videos in cloud storage and receive a link to the videos. For example, the receiving unit uploads videos to cloud storage and sends the link to the user. The receiving unit can also receive important text information via push notification so that the information can be viewed immediately. For example, the receiving unit obtains important text information from a push notification server and notifies the user's device. This allows efficient information reception by selecting the optimal receiving means depending on the type of information. Some or all of the above-described processing in the receiving unit may be performed using, for example, AI, or may be performed without using AI.

[0032] Upon reception, the receiving unit analyzes the user's past reception history and selects an appropriate reception method. For example, the receiving unit retrieves the user's past reception history from a database and analyzes it using data mining technology. For example, the receiving unit analyzes the format of information the user frequently received in the past and receives the information in a similar format. The receiving unit can also prioritize receiving the type of information the user has previously preferred. For example, the receiving unit prioritizes receiving a specific type of information based on the user's past reception history. The receiving unit can also optimize information to be received during a specific time period based on the user's past reception history. For example, the receiving unit receives information during a specific time period based on the user's past reception history. By analyzing the user's past reception history, the receiving unit can select the optimal reception method and improve user convenience. Some or all of the above-described processing in the receiving unit may be performed using, for example, AI, or may be performed without AI.

[0033] The filter unit evaluates the reliability of information during filtering and improves the accuracy of filtering based on the reliability. The filter unit evaluates the reliability of information based on, for example, the reliability of the information source. For example, the filter unit obtains the reliability of the information source from a database and calculates a reliability score. The filter unit can also evaluate the reliability of information based on past evaluation history. For example, the filter unit obtains the evaluation history from a database and calculates a reliability score. The filter unit also improves the accuracy of filtering based on the reliability of the information. For example, the filter unit preferentially filters information with high reliability and excludes information with low reliability. The filter unit can also set reliability evaluation criteria and filter only information that meets the criteria. The filter unit can also save information with low reliability in a separate folder so that the user can manually check it. In this way, by improving the accuracy of filtering based on the reliability of the information, it is possible to preferentially receive information with high reliability. Some or all of the above-mentioned processing in the filter unit may be performed, for example, using AI or without AI.

[0034] During filtering, the filter unit applies an appropriate filtering algorithm depending on the category of information. For example, the filter unit applies a text analysis algorithm to text information and an image analysis algorithm to image information. For example, the filter unit analyzes and filters text information using natural language processing technology. The filter unit can also analyze and filter image information using image recognition technology. The filter unit can also apply a video analysis algorithm to video information and an audio analysis algorithm to audio information. For example, the filter unit analyzes and filters video information using video analysis technology. The filter unit can also analyze and filter audio information using audio analysis technology. This allows for applying an optimal filtering algorithm depending on the category of information, thereby improving the accuracy of filtering. Some or all of the above-described processing in the filter unit may be performed using, for example, AI, or may be performed without using AI.

[0035] The filter unit improves the accuracy of filtering by referring to the user's past filtering results. For example, the filter unit obtains the user's past filtering results from a database and analyzes them using data mining technology. For example, the filter unit analyzes the results of information previously filtered by the user and filters similar information. The filter unit can also adjust the filtering criteria based on the user's past filtering results. For example, the filter unit changes the filtering criteria based on the user's past filtering results. The filter unit can also optimize the filtering algorithm based on the user's past filtering results. For example, the filter unit adjusts the filtering algorithm based on the past filtering results. In this way, the accuracy of filtering can be improved by referring to the user's past filtering results. Some or all of the above-described processing in the filter unit may be performed using, for example, AI, or may be performed without using AI.

[0036] The warning unit adjusts the level of detail of the warning based on the importance of the information when issuing a warning. The warning unit evaluates the importance of the information based on, for example, the urgency of the information. For example, the warning unit obtains the urgency of the information from a database and calculates an importance score. The warning unit can also evaluate the importance of the information based on the scope of impact of the information. For example, the warning unit obtains the scope of impact from a database and calculates an importance score. The warning unit also adjusts the level of detail of the warning based on the importance of the information. For example, the warning unit displays a detailed warning for information of high importance and a brief warning for information of low importance. The warning unit can also set importance evaluation criteria and provide a detailed warning only for information that meets the criteria. The warning unit can also display a brief warning for information of low importance so that the user can manually check the details. By adjusting the level of detail of the warning based on the importance of the information, it is possible to provide an optimal warning for the user. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI.

[0037] When issuing a warning, the warning unit applies an appropriate warning algorithm depending on the category of information. For example, the warning unit applies a text analysis algorithm to text information and an image analysis algorithm to image information. For example, the warning unit analyzes the text information using natural language processing technology and issues a warning. The warning unit can also analyze the image information using image recognition technology and issue a warning. The warning unit can also apply a video analysis algorithm to video information and an audio analysis algorithm to audio information. For example, the warning unit analyzes the video information using video analysis technology and issues a warning. The warning unit can also analyze the audio information using audio analysis technology and issue a warning. In this way, by applying the optimal warning algorithm depending on the category of information, the accuracy of the warning can be improved. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI.

[0038] When issuing a warning, the warning unit improves the accuracy of the warning by referring to the user's past warning results. The warning unit, for example, obtains the user's past warning results from a database and analyzes them using data mining technology. For example, the warning unit analyzes the results of warnings the user has received in the past and issues a warning for similar information. The warning unit can also adjust the warning criteria based on the user's past warning results. For example, the warning unit changes the warning criteria based on the user's past warning results. The warning unit can also optimize the warning algorithm based on the user's past warning results. For example, the warning unit adjusts the warning algorithm based on the user's past warning results. In this way, the accuracy of the warning can be improved by referring to the user's past warning results. Some or all of the above-mentioned processing in the warning unit may be performed, for example, using AI or without AI.

[0039] When issuing an access warning, the access warning unit evaluates the reliability of the phishing site and adjusts the level of detail of the warning based on the reliability. The access warning unit evaluates the reliability based on, for example, the phishing site's past report history. For example, the access warning unit retrieves the report history from a database and calculates a reliability score. The access warning unit can also evaluate the reliability based on ratings from a third-party rating agency. For example, the access warning unit retrieves rating data from the rating agency and calculates a reliability score. The access warning unit adjusts the level of detail of the warning based on the reliability of the phishing site. For example, the access warning unit displays a detailed warning for low-reliability phishing sites and a concise warning for high-reliability sites. The access warning unit can also set reliability evaluation criteria and provide a detailed warning only for sites that meet the criteria. The access warning unit can also display a concise warning for low-reliability sites and allow the user to manually check the details. By adjusting the level of detail of the warning based on the reliability of the phishing site, it is possible to provide an optimal warning for the user. Some or all of the above-described processing in the access warning unit may be performed using, for example, AI, or without AI.

[0040] When issuing an access warning, the access warning unit applies an appropriate warning algorithm depending on the category of the phishing site. For example, the access warning unit applies a text analysis algorithm to text information and an image analysis algorithm to image information. For example, the access warning unit analyzes the text information using natural language processing technology and issues a warning. The access warning unit can also analyze the image information using image recognition technology and issue a warning. The access warning unit can also apply a video analysis algorithm to video information and an audio analysis algorithm to audio information. For example, the access warning unit analyzes the video information using video analysis technology and issues a warning. The access warning unit can also analyze the audio information using audio analysis technology and issue a warning. This allows the application of an optimal warning algorithm depending on the category of the phishing site, thereby improving the accuracy of the warning. Some or all of the above-mentioned processing in the access warning unit may be performed using, for example, AI, or may be performed without using AI.

[0041] When issuing an access warning, the access warning unit improves the accuracy of the warning by referring to the user's past access warning results. The access warning unit, for example, retrieves the user's past access warning results from a database and analyzes them using data mining technology. For example, the access warning unit analyzes the results of access warnings the user has received in the past and issues a warning for similar information. The access warning unit can also adjust the warning criteria based on the user's past access warning results. For example, the access warning unit changes the warning criteria based on the user's past access warning results. The access warning unit can also optimize the warning algorithm based on the user's past access warning results. For example, the access warning unit adjusts the warning algorithm based on the user's past access warning results. This allows the accuracy of the warning to be improved by referring to the user's past access warning results. Some or all of the above-described processing in the access warning unit may be performed using, for example, AI, or may be performed without using AI.

[0042] The information distribution unit evaluates the trustworthiness of a company when distributing information and determines the priority of information distribution based on the trustworthiness. The information distribution unit evaluates the trustworthiness based on, for example, the company's past transaction history. For example, the information distribution unit retrieves the company's transaction history from a database and calculates a trustworthiness score. The information distribution unit can also evaluate the trustworthiness based on ratings from a third-party rating agency. For example, the information distribution unit retrieves rating data from the rating agency and calculates a trustworthiness score. The information distribution unit also determines the priority of information distribution based on the trustworthiness of the company. For example, the information distribution unit prioritizes information from highly trustworthy companies and postpones information from less trustworthy companies. The information distribution unit can also set trustworthiness evaluation criteria and distribute only information from companies that meet the criteria. The information distribution unit can also save information from less trustworthy companies in a separate folder so that the user can manually check it. In this way, by determining the priority of information distribution based on the trustworthiness of the company, highly reliable information can be preferentially distributed. Some or all of the above-described processing in the information distribution unit may be performed using, for example, AI, or may be performed without using AI.

[0043] When distributing information, the information distribution unit selects an appropriate distribution means depending on the type of information. For example, the information distribution unit distributes text information via email and images and videos via a dedicated app. For example, the information distribution unit may obtain text information from an email server and display it on the user's email client. The information distribution unit may also distribute images and videos via a dedicated app and display them on the user's device. The information distribution unit may also store large videos in cloud storage and distribute links to them. For example, the information distribution unit may upload videos to cloud storage and send the links to the user. The information distribution unit may also distribute important text information via push notifications so that the information can be viewed immediately. For example, the information distribution unit may obtain important text information from a push notification server and notify the user's device. This allows for efficient information distribution by selecting the optimal distribution means depending on the type of information. Some or all of the above-described processing in the information distribution unit may be performed using AI, for example, or without AI.

[0044] When distributing information, the information distribution unit analyzes the user's past information distribution history and selects the optimal distribution method. For example, the information distribution unit retrieves the user's past information distribution history from a database and analyzes it using data mining technology. For example, the information distribution unit analyzes the format of information the user frequently received in the past and distributes the information in a similar format. The information distribution unit can also prioritize the type of information the user has previously preferred. For example, the information distribution unit prioritizes the distribution of specific types of information based on the user's past information distribution history. The information distribution unit can also optimize the information to be distributed during specific time periods based on the user's past information distribution history. For example, the information distribution unit distributes information during specific time periods based on the user's past information distribution history. By analyzing the user's past information distribution history, the optimal distribution method can be selected, improving user convenience. Some or all of the above-described processing in the information distribution unit may be performed using, for example, AI, or may be performed without AI.

[0045] The takedown unit evaluates the reliability of a phishing site during takedown and determines the priority of takedown based on the reliability. The takedown unit evaluates the reliability based on, for example, the phishing site's past reporting history. For example, the takedown unit obtains the reporting history from a database and calculates a reliability score. The takedown unit can also evaluate the reliability based on ratings from a third-party rating agency. For example, the takedown unit obtains rating data from the rating agency and calculates a reliability score. The takedown unit also determines the priority of takedown based on the reliability of the phishing site. For example, the takedown unit prioritizes takedown of phishing sites with low reliability and postpones takedown of sites with high reliability. The takedown unit can also set reliability evaluation criteria and prioritize takedown of only sites that meet the criteria. The takedown unit can also quickly take down low-reliability sites to ensure user safety. Thus, by determining the priority of takedown based on the reliability of phishing sites, user safety can be ensured. Some or all of the above-described processing in the takedown section may be performed using AI, for example, or may be performed without using AI.

[0046] During takedown, the takedown unit applies an appropriate takedown method depending on the category of the phishing site. For example, the takedown unit applies a text analysis algorithm to text information and an image analysis algorithm to image information. For example, the takedown unit analyzes the text information using natural language processing technology and performs takedown. The takedown unit can also analyze the image information using image recognition technology and perform takedown. The takedown unit can also apply a video analysis algorithm to video information and an audio analysis algorithm to audio information. For example, the takedown unit analyzes the video information using video analysis technology and performs takedown. The takedown unit can also analyze the audio information using audio analysis technology and perform takedown. This allows the application of an optimal takedown method depending on the category of the phishing site, thereby improving the accuracy of the takedown. Some or all of the above-mentioned processing in the takedown unit may be performed using, for example, AI, or may be performed without using AI.

[0047] During takedown, the takedown unit improves the accuracy of the takedown by referring to the user's past takedown results. The takedown unit, for example, obtains the user's past takedown results from a database and analyzes them using data mining technology. For example, the takedown unit analyzes the results of takedowns previously performed by the user and performs takedowns on similar information. The takedown unit can also adjust the takedown criteria based on the user's past takedown results. For example, the takedown unit changes the takedown criteria based on the user's past takedown results. The takedown unit can also optimize the takedown algorithm based on the user's past takedown results. For example, the takedown unit adjusts the takedown algorithm based on the past takedown results. This allows the accuracy of the takedown to be improved by referring to the user's past takedown results. Some or all of the above-described processing in the takedown unit may be performed using, for example, AI, or may be performed without using AI.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The receiving unit can also acquire location information of the user and adjust the timing of receiving information based on the location information. For example, when the user is on the move, the receiving unit can delay the reception of important information. Furthermore, when the user is in a specific location, the receiving unit can prioritize receiving information related to that location. Furthermore, when the user is at home, the receiving unit can prioritize receiving private information. In this way, by adjusting the timing of receiving information based on the user's location information, it is possible to improve convenience for the user.

[0050] The receiving unit can also take into account social media ratings when evaluating a company's trustworthiness. For example, the receiving unit can collect ratings and comments on a company's social media and reflect them in the trustworthiness score. The receiving unit can also evaluate trustworthiness based on the number of followers and engagement rate of the company. Furthermore, the receiving unit can dynamically update the company's trustworthiness based on trend information on social media. In this way, by taking social media ratings into consideration, a more accurate trustworthiness evaluation can be performed.

[0051] The receiving unit can also take into consideration the state of the user's device when selecting an appropriate receiving means depending on the type of information. For example, when the user's device is low on battery, the receiving unit can prioritize receiving light text information. Also, when the user's device is connected to Wi-Fi, the receiving unit can receive large images and videos. Furthermore, when the user's device is in silent mode, the receiving unit can refrain from sending notifications. This allows for efficient information reception by selecting the optimal receiving means depending on the state of the user's device.

[0052] The receiving unit can also take the user's behavioral patterns into consideration when analyzing the user's past reception history. For example, if the user tends to preferentially receive specific information during a specific time period, the receiving unit can prioritize receiving similar information during that time period. Also, if the user tends to receive specific information on a specific day of the week, the receiving unit can prioritize receiving similar information on that day. Furthermore, if the user tends to receive specific information at a specific location, the receiving unit can prioritize receiving similar information at that location. This allows the optimal reception method to be selected based on the user's behavioral patterns, thereby improving user convenience.

[0053] The filter unit can also take into account the geographic location of the source of the information when evaluating the reliability of the information. For example, the filter unit can prioritize evaluation of information from a specific region. The filter unit can also reflect information from a specific region in the reliability score. Furthermore, the filter unit can dynamically update the reliability of the information based on the geographic location. This allows for a more accurate reliability evaluation by taking into account the geographic location of the source of the information.

[0054] The filter unit can also take into account the importance of the information when applying an appropriate filtering algorithm depending on the category of information. For example, the filter unit can apply a strict filtering algorithm to information with high importance. The filter unit can also apply a simple filtering algorithm to information with low importance. Furthermore, the filter unit can dynamically adjust the filtering algorithm based on the importance of the information. This allows for improved filtering accuracy by taking the importance of the information into account.

[0055] The filter unit may also take user feedback into consideration when improving filtering accuracy by referring to the user's past filtering results. For example, the filter unit may adjust filtering criteria based on feedback provided by the user in the past. The filter unit may also collect user feedback in real time and reflect it in the filtering algorithm. Furthermore, the filter unit may dynamically update the filtering results based on the user's feedback. In this way, the accuracy of filtering can be improved by taking user feedback into consideration.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The receiving unit receives legitimate information and official website information from the company. For example, the receiving unit can receive information from the company's official website or information from an authenticated third-party site. Step 2: The filter unit filters the information received by the receiver to determine whether it is legitimate. For example, the filter unit analyzes the information using keyword filtering or blacklist filtering to determine whether it is legitimate. Step 3: The warning unit issues a warning if the filter unit determines that the request is not legitimate and displays the legitimate customer support contact point. For example, the warning unit issues a warning using a pop-up message or email notification and displays the company's official customer support contact point. Step 4: The access warning unit issues a warning when a phishing site is accessed. For example, the access warning unit detects phishing sites using URL pattern matching or blacklist reference, and issues a warning. Step 5: When a warning is issued by the warning unit and the access warning unit, the information distribution unit automatically transmits information to the company. For example, the information distribution unit automatically transmits information to the company using an API. Step 6: The takedown unit performs takedown based on the information sent by the information distribution unit. For example, the takedown unit removes the phishing site through legal procedures.

[0058] (Example 2) A system according to an embodiment of the present invention receives legitimate information from companies and official website information, filters it, and issues a warning if the information is not legitimate. Furthermore, a similar warning is issued when a phishing site is accessed, and the legitimate customer service contact point is displayed. It also includes a mechanism for automatically sending information distribution to companies and taking down the information when the information is received or the site is accessed. This allows the system to receive legitimate information from companies and official website information, filter it, and issue a warning if the information is not legitimate. Furthermore, a similar warning is issued when a phishing site is accessed, and the legitimate customer service contact point is displayed. Furthermore, a mechanism for automatically sending information distribution to companies and taking down the information when the information is received or the site is accessed.

[0059] An information filtering system according to an embodiment includes a receiving unit, a filtering unit, a warning unit, an access warning unit, an information distribution unit, and a takedown unit. The receiving unit receives legitimate information and official website information from a company. For example, the receiving unit can receive information from a company's official website or information from an authenticated third-party site. The filtering unit filters the information received by the receiving unit to determine whether the information is legitimate. For example, the filtering unit analyzes the information using keyword filtering or blacklist filtering to determine whether it is legitimate. The warning unit issues a warning and displays a legitimate customer support hotline when the filtering unit determines that the information is not legitimate. For example, the warning unit issues a warning using a pop-up message or an email notification and displays the company's official customer support hotline. The access warning unit issues a warning when a phishing site is accessed. For example, the access warning unit detects phishing sites using URL pattern matching or blacklist reference and issues a warning. The information distribution unit automatically sends information to a company when a warning is issued by the warning unit and the access warning unit. For example, the information distribution unit automatically sends information to a company using an API. The takedown unit performs takedown based on the information transmitted by the information distribution unit. For example, the takedown unit deletes phishing sites through legal procedures. As a result, the information filtering system according to the embodiment receives legitimate information transmitted by companies and official website information, applies filters, issues a warning if the information is not legitimate, and displays the legitimate customer service contact point. Furthermore, if a phishing site is accessed, a similar warning is issued, and information distribution is automatically sent to the company to perform takedown.

[0060] The receiving unit estimates the user's emotion and adjusts the timing of receiving information based on the estimated user emotion. For example, the receiving unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the receiving unit calculates an emotion score based on changes in facial expression. The receiving unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the receiving unit analyzes the tone and speed of the voice and calculates the emotion score. The receiving unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the receiving unit calculates the emotion score based on heart rate fluctuations. This allows the timing of receiving information to be adjusted according to the user's emotion, thereby reducing the user's stress and optimizing the reception of information. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the receiving unit may be performed using AI, for example, or may be performed without using AI.

[0061] The receiving unit evaluates the trustworthiness of a company and determines the priority of receiving information based on the trustworthiness. The receiving unit evaluates the trustworthiness based on, for example, the company's past transaction history. For example, the receiving unit retrieves the company's transaction history from a database and calculates a trustworthiness score. The receiving unit can also evaluate the trustworthiness based on ratings from a third-party rating agency. For example, the receiving unit retrieves rating data from the rating agency and calculates a trustworthiness score. The receiving unit also determines the priority of receiving information based on the trustworthiness of the company. For example, the receiving unit prioritizes receiving information from highly trustworthy companies and postpones receiving information from less trustworthy companies. The receiving unit can also set trustworthiness evaluation criteria and receive only information from companies that meet the criteria. The receiving unit can also save information from less trustworthy companies in a separate folder so that the user can manually check it. In this way, by determining the priority of receiving information based on the trustworthiness of the company, highly reliable information can be preferentially received. Some or all of the above-described processing in the receiving unit may be performed using, for example, AI, or may be performed without using AI.

[0062] The receiving unit selects an appropriate receiving means depending on the type of information when receiving the information. For example, the receiving unit receives text information via email and images and videos via a dedicated app. For example, the receiving unit obtains text information from an email server and displays it on the user's email client. The receiving unit can also receive images and videos via a dedicated app and display them on the user's device. The receiving unit can also store large videos in cloud storage and receive a link to the videos. For example, the receiving unit uploads videos to cloud storage and sends the link to the user. The receiving unit can also receive important text information via push notification so that the information can be viewed immediately. For example, the receiving unit obtains important text information from a push notification server and notifies the user's device. This allows efficient information reception by selecting the optimal receiving means depending on the type of information. Some or all of the above-described processing in the receiving unit may be performed using, for example, AI, or may be performed without using AI.

[0063] Upon reception, the receiving unit analyzes the user's past reception history and selects an appropriate reception method. For example, the receiving unit retrieves the user's past reception history from a database and analyzes it using data mining technology. For example, the receiving unit analyzes the format of information the user frequently received in the past and receives the information in a similar format. The receiving unit can also prioritize receiving the type of information the user has previously preferred. For example, the receiving unit prioritizes receiving a specific type of information based on the user's past reception history. The receiving unit can also optimize information to be received during a specific time period based on the user's past reception history. For example, the receiving unit receives information during a specific time period based on the user's past reception history. By analyzing the user's past reception history, the receiving unit can select the optimal reception method and improve user convenience. Some or all of the above-described processing in the receiving unit may be performed using, for example, AI, or may be performed without AI.

[0064] The filter unit estimates the user's emotions and adjusts filtering criteria based on the estimated user emotions. For example, the filter unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the filter unit calculates an emotion score based on changes in facial expressions. The filter unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the filter unit analyzes the tone and speed of the voice and calculates an emotion score. The filter unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the filter unit calculates an emotion score based on heart rate fluctuations. This allows the filtering criteria to be adjusted according to the user's emotions, thereby eliminating unnecessary information and efficiently receiving necessary information. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the filter section may be performed using AI, for example, or may be performed without using AI.

[0065] The filter unit evaluates the reliability of information during filtering and improves the accuracy of filtering based on the reliability. The filter unit evaluates the reliability of information based on, for example, the reliability of the information source. For example, the filter unit obtains the reliability of the information source from a database and calculates a reliability score. The filter unit can also evaluate the reliability of information based on past evaluation history. For example, the filter unit obtains the evaluation history from a database and calculates a reliability score. The filter unit also improves the accuracy of filtering based on the reliability of the information. For example, the filter unit preferentially filters information with high reliability and excludes information with low reliability. The filter unit can also set reliability evaluation criteria and filter only information that meets the criteria. The filter unit can also save information with low reliability in a separate folder so that the user can manually check it. In this way, by improving the accuracy of filtering based on the reliability of the information, it is possible to preferentially receive information with high reliability. Some or all of the above-mentioned processing in the filter unit may be performed, for example, using AI or without AI.

[0066] During filtering, the filter unit applies an appropriate filtering algorithm depending on the category of information. For example, the filter unit applies a text analysis algorithm to text information and an image analysis algorithm to image information. For example, the filter unit analyzes and filters text information using natural language processing technology. The filter unit can also analyze and filter image information using image recognition technology. The filter unit can also apply a video analysis algorithm to video information and an audio analysis algorithm to audio information. For example, the filter unit analyzes and filters video information using video analysis technology. The filter unit can also analyze and filter audio information using audio analysis technology. This allows for applying an optimal filtering algorithm depending on the category of information, thereby improving the accuracy of filtering. Some or all of the above-described processing in the filter unit may be performed using, for example, AI, or may be performed without using AI.

[0067] The filter unit improves the accuracy of filtering by referring to the user's past filtering results. For example, the filter unit obtains the user's past filtering results from a database and analyzes them using data mining technology. For example, the filter unit analyzes the results of information previously filtered by the user and filters similar information. The filter unit can also adjust the filtering criteria based on the user's past filtering results. For example, the filter unit changes the filtering criteria based on the user's past filtering results. The filter unit can also optimize the filtering algorithm based on the user's past filtering results. For example, the filter unit adjusts the filtering algorithm based on the past filtering results. In this way, the accuracy of filtering can be improved by referring to the user's past filtering results. Some or all of the above-described processing in the filter unit may be performed using, for example, AI, or may be performed without using AI.

[0068] The warning unit estimates the user's emotion and adjusts the way the warning is expressed based on the estimated user's emotion. For example, the warning unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the warning unit calculates an emotion score based on changes in facial expression. The warning unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the warning unit analyzes the tone and speed of the voice and calculates an emotion score. The warning unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the warning unit calculates an emotion score based on heart rate fluctuations. This allows the user to receive an optimal warning by adjusting the way the warning is expressed based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the warning unit may be performed using AI, for example, or may be performed without using AI.

[0069] The warning unit adjusts the level of detail of the warning based on the importance of the information when issuing a warning. The warning unit evaluates the importance of the information based on, for example, the urgency of the information. For example, the warning unit obtains the urgency of the information from a database and calculates an importance score. The warning unit can also evaluate the importance of the information based on the scope of impact of the information. For example, the warning unit obtains the scope of impact from a database and calculates an importance score. The warning unit also adjusts the level of detail of the warning based on the importance of the information. For example, the warning unit displays a detailed warning for information of high importance and a brief warning for information of low importance. The warning unit can also set importance evaluation criteria and provide a detailed warning only for information that meets the criteria. The warning unit can also display a brief warning for information of low importance so that the user can manually check the details. By adjusting the level of detail of the warning based on the importance of the information, it is possible to provide an optimal warning for the user. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI.

[0070] When issuing a warning, the warning unit applies an appropriate warning algorithm depending on the category of information. For example, the warning unit applies a text analysis algorithm to text information and an image analysis algorithm to image information. For example, the warning unit analyzes the text information using natural language processing technology and issues a warning. The warning unit can also analyze the image information using image recognition technology and issue a warning. The warning unit can also apply a video analysis algorithm to video information and an audio analysis algorithm to audio information. For example, the warning unit analyzes the video information using video analysis technology and issues a warning. The warning unit can also analyze the audio information using audio analysis technology and issue a warning. In this way, by applying the optimal warning algorithm depending on the category of information, the accuracy of the warning can be improved. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI.

[0071] When issuing a warning, the warning unit improves the accuracy of the warning by referring to the user's past warning results. The warning unit, for example, obtains the user's past warning results from a database and analyzes them using data mining technology. For example, the warning unit analyzes the results of warnings the user has received in the past and issues a warning for similar information. The warning unit can also adjust the warning criteria based on the user's past warning results. For example, the warning unit changes the warning criteria based on the user's past warning results. The warning unit can also optimize the warning algorithm based on the user's past warning results. For example, the warning unit adjusts the warning algorithm based on the user's past warning results. In this way, the accuracy of the warning can be improved by referring to the user's past warning results. Some or all of the above-mentioned processing in the warning unit may be performed, for example, using AI or without AI.

[0072] The access warning unit estimates the user's emotions and adjusts the expression method of the access warning based on the estimated user emotions. For example, the access warning unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, the access warning unit calculates an emotion score based on changes in facial expression. The access warning unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the access warning unit analyzes the tone and speed of the voice and calculates an emotion score. The access warning unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the access warning unit calculates an emotion score based on heart rate fluctuations. This allows the user to receive an optimal warning by adjusting the expression method of the access warning according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the access warning unit may be performed using AI, for example, or may be performed without using AI.

[0073] When issuing an access warning, the access warning unit evaluates the reliability of the phishing site and adjusts the level of detail of the warning based on the reliability. The access warning unit evaluates the reliability based on, for example, the phishing site's past report history. For example, the access warning unit retrieves the report history from a database and calculates a reliability score. The access warning unit can also evaluate the reliability based on ratings from a third-party rating agency. For example, the access warning unit retrieves rating data from the rating agency and calculates a reliability score. The access warning unit adjusts the level of detail of the warning based on the reliability of the phishing site. For example, the access warning unit displays a detailed warning for low-reliability phishing sites and a concise warning for high-reliability sites. The access warning unit can also set reliability evaluation criteria and provide a detailed warning only for sites that meet the criteria. The access warning unit can also display a concise warning for low-reliability sites and allow the user to manually check the details. By adjusting the level of detail of the warning based on the reliability of the phishing site, it is possible to provide an optimal warning for the user. Some or all of the above-described processing in the access warning unit may be performed using, for example, AI, or without AI.

[0074] When issuing an access warning, the access warning unit applies an appropriate warning algorithm depending on the category of the phishing site. For example, the access warning unit applies a text analysis algorithm to text information and an image analysis algorithm to image information. For example, the access warning unit analyzes the text information using natural language processing technology and issues a warning. The access warning unit can also analyze the image information using image recognition technology and issue a warning. The access warning unit can also apply a video analysis algorithm to video information and an audio analysis algorithm to audio information. For example, the access warning unit analyzes the video information using video analysis technology and issues a warning. The access warning unit can also analyze the audio information using audio analysis technology and issue a warning. This allows the application of an optimal warning algorithm depending on the category of the phishing site, thereby improving the accuracy of the warning. Some or all of the above-mentioned processing in the access warning unit may be performed using, for example, AI, or may be performed without using AI.

[0075] When issuing an access warning, the access warning unit improves the accuracy of the warning by referring to the user's past access warning results. The access warning unit, for example, retrieves the user's past access warning results from a database and analyzes them using data mining technology. For example, the access warning unit analyzes the results of access warnings the user has received in the past and issues a warning for similar information. The access warning unit can also adjust the warning criteria based on the user's past access warning results. For example, the access warning unit changes the warning criteria based on the user's past access warning results. The access warning unit can also optimize the warning algorithm based on the user's past access warning results. For example, the access warning unit adjusts the warning algorithm based on the user's past access warning results. This allows the accuracy of the warning to be improved by referring to the user's past access warning results. Some or all of the above-described processing in the access warning unit may be performed using, for example, AI, or may be performed without using AI.

[0076] The information distribution unit estimates the user's emotions and adjusts the timing of information distribution based on the estimated user emotions. For example, the information distribution unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the information distribution unit calculates an emotion score based on changes in facial expressions. The information distribution unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the information distribution unit analyzes the tone and speed of the voice and calculates an emotion score. The information distribution unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the information distribution unit calculates an emotion score based on heart rate fluctuations. This allows the timing of information distribution to be adjusted according to the user's emotions, thereby reducing user stress and optimizing information distribution. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the information distribution unit may be performed using AI, for example, or may be performed without using AI.

[0077] The information distribution unit evaluates the trustworthiness of a company when distributing information and determines the priority of information distribution based on the trustworthiness. The information distribution unit evaluates the trustworthiness based on, for example, the company's past transaction history. For example, the information distribution unit retrieves the company's transaction history from a database and calculates a trustworthiness score. The information distribution unit can also evaluate the trustworthiness based on ratings from a third-party rating agency. For example, the information distribution unit retrieves rating data from the rating agency and calculates a trustworthiness score. The information distribution unit also determines the priority of information distribution based on the trustworthiness of the company. For example, the information distribution unit prioritizes information from highly trustworthy companies and postpones information from less trustworthy companies. The information distribution unit can also set trustworthiness evaluation criteria and distribute only information from companies that meet the criteria. The information distribution unit can also save information from less trustworthy companies in a separate folder so that the user can manually check it. In this way, by determining the priority of information distribution based on the trustworthiness of the company, highly reliable information can be preferentially distributed. Some or all of the above-described processing in the information distribution unit may be performed using, for example, AI, or may be performed without using AI.

[0078] When distributing information, the information distribution unit selects an appropriate distribution means depending on the type of information. For example, the information distribution unit distributes text information via email and images and videos via a dedicated app. For example, the information distribution unit may obtain text information from an email server and display it on the user's email client. The information distribution unit may also distribute images and videos via a dedicated app and display them on the user's device. The information distribution unit may also store large videos in cloud storage and distribute links to them. For example, the information distribution unit may upload videos to cloud storage and send the links to the user. The information distribution unit may also distribute important text information via push notifications so that the information can be viewed immediately. For example, the information distribution unit may obtain important text information from a push notification server and notify the user's device. This allows for efficient information distribution by selecting the optimal distribution means depending on the type of information. Some or all of the above-described processing in the information distribution unit may be performed using AI, for example, or without AI.

[0079] When distributing information, the information distribution unit analyzes the user's past information distribution history and selects the optimal distribution method. For example, the information distribution unit retrieves the user's past information distribution history from a database and analyzes it using data mining technology. For example, the information distribution unit analyzes the format of information the user frequently received in the past and distributes the information in a similar format. The information distribution unit can also prioritize the type of information the user has previously preferred. For example, the information distribution unit prioritizes the distribution of specific types of information based on the user's past information distribution history. The information distribution unit can also optimize the information to be distributed during specific time periods based on the user's past information distribution history. For example, the information distribution unit distributes information during specific time periods based on the user's past information distribution history. By analyzing the user's past information distribution history, the optimal distribution method can be selected, improving user convenience. Some or all of the above-described processing in the information distribution unit may be performed using, for example, AI, or may be performed without AI.

[0080] The takedown unit estimates the user's emotions and adjusts the takedown method based on the estimated user emotions. For example, the takedown unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the takedown unit calculates an emotion score based on changes in facial expressions. The takedown unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the takedown unit analyzes the tone and speed of the voice and calculates an emotion score. The takedown unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the takedown unit calculates an emotion score based on heart rate fluctuations. This allows the takedown method to be adjusted according to the user's emotions, thereby reducing the burden on the user and enabling quick takedown. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the takedown section may be performed using AI, for example, or may be performed without using AI.

[0081] The takedown unit evaluates the reliability of a phishing site during takedown and determines the priority of takedown based on the reliability. The takedown unit evaluates the reliability based on, for example, the phishing site's past reporting history. For example, the takedown unit obtains the reporting history from a database and calculates a reliability score. The takedown unit can also evaluate the reliability based on ratings from a third-party rating agency. For example, the takedown unit obtains rating data from the rating agency and calculates a reliability score. The takedown unit also determines the priority of takedown based on the reliability of the phishing site. For example, the takedown unit prioritizes takedown of phishing sites with low reliability and postpones takedown of sites with high reliability. The takedown unit can also set reliability evaluation criteria and prioritize takedown of only sites that meet the criteria. The takedown unit can also quickly take down low-reliability sites to ensure user safety. Thus, by determining the priority of takedown based on the reliability of phishing sites, user safety can be ensured. Some or all of the above-described processing in the takedown section may be performed using AI, for example, or may be performed without using AI.

[0082] During takedown, the takedown unit applies an appropriate takedown method depending on the category of the phishing site. For example, the takedown unit applies a text analysis algorithm to text information and an image analysis algorithm to image information. For example, the takedown unit analyzes the text information using natural language processing technology and performs takedown. The takedown unit can also analyze the image information using image recognition technology and perform takedown. The takedown unit can also apply a video analysis algorithm to video information and an audio analysis algorithm to audio information. For example, the takedown unit analyzes the video information using video analysis technology and performs takedown. The takedown unit can also analyze the audio information using audio analysis technology and perform takedown. This allows the application of an optimal takedown method depending on the category of the phishing site, thereby improving the accuracy of the takedown. Some or all of the above-mentioned processing in the takedown unit may be performed using, for example, AI, or may be performed without using AI.

[0083] During takedown, the takedown unit improves the accuracy of the takedown by referring to the user's past takedown results. The takedown unit, for example, obtains the user's past takedown results from a database and analyzes them using data mining technology. For example, the takedown unit analyzes the results of takedowns previously performed by the user and performs takedowns on similar information. The takedown unit can also adjust the takedown criteria based on the user's past takedown results. For example, the takedown unit changes the takedown criteria based on the user's past takedown results. The takedown unit can also optimize the takedown algorithm based on the user's past takedown results. For example, the takedown unit adjusts the takedown algorithm based on the past takedown results. This allows the accuracy of the takedown to be improved by referring to the user's past takedown results. Some or all of the above-described processing in the takedown unit may be performed using, for example, AI, or may be performed without using AI. === Hard Collateral 1-1 === Each of the multiple elements, including the receiving unit, filtering unit, warning unit, access warning unit, information distribution unit, and takedown unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the receiving unit receives legitimate information and official website information from companies via the communication I / F 44 of the smart device 14. The filtering unit, realized by the specific processing unit 290 of the data processing device 12, filters the received information to determine whether it is legitimate. The warning unit, realized by the control unit 46A of the smart device 14, issues a warning if the information is not legitimate and displays the legitimate customer service contact point. The access warning unit, realized by the control unit 46A of the smart device 14, issues a warning if a phishing site is accessed. The information distribution unit, realized by the specific processing unit 290 of the data processing device 12, automatically transmits information to the company when a warning is issued. The takedown unit, realized by the specific processing unit 290 of the data processing device 12, performs takedown based on the transmitted information. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned receiving unit, filtering unit, warning unit, access warning unit, information distribution unit, and takedown unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the receiving unit receives legitimate information and official website information from companies via the communication I / F 44 of the smart glasses 214. The filtering unit is realized by the specific processing unit 290 of the data processing device 12 and filters the received information to determine whether it is legitimate. The warning unit is realized by the control unit 46A of the smart glasses 214 and issues a warning if the information is not legitimate and displays the legitimate customer service contact point. The access warning unit is realized by the control unit 46A of the smart glasses 214 and issues a warning if a phishing site is accessed. The information distribution unit is realized by the specific processing unit 290 of the data processing device 12 and automatically transmits information to the company when a warning is issued. The takedown unit is realized by the specific processing unit 290 of the data processing device 12 and performs takedown based on the transmitted information. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned receiving unit, filtering unit, warning unit, access warning unit, information distribution unit, and takedown unit, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the receiving unit receives legitimate information and official website information from companies via the communication I / F 44 of the headset terminal 314. The filtering unit is realized by the specific processing unit 290 of the data processing device 12 and filters the received information to determine whether it is legitimate. The warning unit is realized by the control unit 46A of the headset terminal 314 and issues a warning if the information is not legitimate and displays the legitimate CS office. The access warning unit is realized by the control unit 46A of the headset terminal 314 and issues a warning if a phishing site is accessed. The information distribution unit is realized by the specific processing unit 290 of the data processing device 12 and automatically transmits information to the company when a warning is issued. The takedown unit is realized by the specific processing unit 290 of the data processing device 12 and performs takedown based on the transmitted information. === Hard Collateral 1-4 === Each of the multiple elements, including the receiving unit, filtering unit, warning unit, access warning unit, information distribution unit, and takedown unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the receiving unit receives legitimate information and official website information from companies via the communication I / F 44 of the robot 414. The filtering unit is realized by the specific processing unit 290 of the data processing device 12 and filters the received information to determine whether it is legitimate. The warning unit is realized by the control unit 46A of the robot 414 and issues a warning if the information is not legitimate and displays the legitimate customer service contact point. The access warning unit is realized by the control unit 46A of the robot 414 and issues a warning if a phishing site is accessed. The information distribution unit is realized by the specific processing unit 290 of the data processing device 12 and automatically transmits information to the company when a warning is issued. The takedown unit is realized by the specific processing unit 290 of the data processing device 12 and performs takedown based on the transmitted information.

[0084] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0085] The receiving unit can also acquire location information of the user and adjust the timing of receiving information based on the location information. For example, when the user is on the move, the receiving unit can delay the reception of important information. Furthermore, when the user is in a specific location, the receiving unit can prioritize receiving information related to that location. Furthermore, when the user is at home, the receiving unit can prioritize receiving private information. In this way, by adjusting the timing of receiving information based on the user's location information, it is possible to improve convenience for the user.

[0086] The receiving unit can also estimate the user's emotions and customize the received information content based on the estimated user's emotions. For example, if the user is feeling stressed, the receiving unit can prioritize receiving information that helps the user relax. Also, if the user is excited, the receiving unit can receive information to help the user stay calm. Furthermore, if the user is sad, the receiving unit can receive an encouraging message. In this way, the received information content can be customized according to the user's emotions, thereby supporting the user's emotions.

[0087] The receiving unit can also take into account social media ratings when evaluating a company's trustworthiness. For example, the receiving unit can collect ratings and comments on a company's social media and reflect them in the trustworthiness score. The receiving unit can also evaluate trustworthiness based on the number of followers and engagement rate of the company. Furthermore, the receiving unit can dynamically update the company's trustworthiness based on trend information on social media. In this way, by taking social media ratings into consideration, a more accurate trustworthiness evaluation can be performed.

[0088] The receiving unit can also take into consideration the state of the user's device when selecting an appropriate receiving means depending on the type of information. For example, when the user's device is low on battery, the receiving unit can prioritize receiving light text information. Also, when the user's device is connected to Wi-Fi, the receiving unit can receive large images and videos. Furthermore, when the user's device is in silent mode, the receiving unit can refrain from sending notifications. This allows for efficient information reception by selecting the optimal receiving means depending on the state of the user's device.

[0089] The receiving unit can also take the user's behavioral patterns into consideration when analyzing the user's past reception history. For example, if the user tends to preferentially receive specific information during a specific time period, the receiving unit can prioritize receiving similar information during that time period. Also, if the user tends to receive specific information on a specific day of the week, the receiving unit can prioritize receiving similar information on that day. Furthermore, if the user tends to receive specific information at a specific location, the receiving unit can prioritize receiving similar information at that location. This allows the optimal reception method to be selected based on the user's behavioral patterns, thereby improving user convenience.

[0090] The filter unit may estimate the user's emotion and adjust the display method of the filtering results based on the estimated user's emotion. For example, the filter unit may display the filtering results simply when the user is feeling stressed. The filter unit may also display the filtering results in detail when the user is relaxed. Furthermore, the filter unit may visually emphasize the filtering results when the user is excited. In this way, adjusting the display method of the filtering results according to the user's emotion can help the user understand.

[0091] The filter unit can also take into account the geographic location of the source of the information when evaluating the reliability of the information. For example, the filter unit can prioritize evaluation of information from a specific region. The filter unit can also reflect information from a specific region in the reliability score. Furthermore, the filter unit can dynamically update the reliability of the information based on the geographic location. This allows for a more accurate reliability evaluation by taking into account the geographic location of the source of the information.

[0092] The filter unit can also take into account the importance of the information when applying an appropriate filtering algorithm depending on the category of information. For example, the filter unit can apply a strict filtering algorithm to information with high importance. The filter unit can also apply a simple filtering algorithm to information with low importance. Furthermore, the filter unit can dynamically adjust the filtering algorithm based on the importance of the information. This allows for improved filtering accuracy by taking the importance of the information into account.

[0093] The filter unit may also take user feedback into consideration when improving filtering accuracy by referring to the user's past filtering results. For example, the filter unit may adjust filtering criteria based on feedback provided by the user in the past. The filter unit may also collect user feedback in real time and reflect it in the filtering algorithm. Furthermore, the filter unit may dynamically update the filtering results based on the user's feedback. In this way, the accuracy of filtering can be improved by taking user feedback into consideration.

[0094] The warning unit can also estimate the user's emotions and adjust the timing of the warning based on the estimated user's emotions. For example, the warning unit can delay the timing of the warning when the user is feeling stressed. The warning unit can also issue a warning immediately when the user is relaxed. Furthermore, the warning unit can adjust the timing of the warning when the user is excited to give the user time to calm down. In this way, the burden on the user can be reduced by adjusting the timing of the warning according to the user's emotions.

[0095] The processing flow of the second embodiment will be briefly explained below.

[0096] Step 1: The receiving unit receives legitimate information and official website information from the company. For example, the receiving unit can receive information from the company's official website or information from an authenticated third-party site. Step 2: The filter unit filters the information received by the receiver to determine whether it is legitimate. For example, the filter unit analyzes the information using keyword filtering or blacklist filtering to determine whether it is legitimate. Step 3: The warning unit issues a warning if the filter unit determines that the request is not legitimate and displays the legitimate customer support contact point. For example, the warning unit issues a warning using a pop-up message or email notification and displays the company's official customer support contact point. Step 4: The access warning unit issues a warning when a phishing site is accessed. For example, the access warning unit detects phishing sites using URL pattern matching or blacklist reference, and issues a warning. Step 5: When a warning is issued by the warning unit and the access warning unit, the information distribution unit automatically transmits information to the company. For example, the information distribution unit automatically transmits information to the company using an API. Step 6: The takedown unit performs takedown based on the information sent by the information distribution unit. For example, the takedown unit removes the phishing site through legal procedures.

[0097] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0098] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0099] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0100] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0101] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0102] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0103] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0104] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0108] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0110] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0111] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0112] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0113] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0116] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0117] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0118] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0119] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0124] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0133] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0134] 7, a 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.

[0135] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0140] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0141] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0142] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0143] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0144] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0145] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0146] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0147] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0148] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0149] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0150] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0151] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0152] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0153] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0154] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0155] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0156] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0157] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0158] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0159] 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.

[0160] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0161] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0162] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0163] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0164] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0165] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0166] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0167] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0168] [Explanation of symbols]

[0169] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A receiving unit that receives official information from companies and official website information; a filter unit that filters the information received by the receiver unit to determine whether it is authentic; a warning unit that issues a warning when the filter unit determines that the call is not legitimate and displays a legitimate customer service contact point; an access warning unit that issues a warning when a phishing site is accessed; an information distribution unit that automatically transmits information to a company when a warning is issued by the warning unit and the access warning unit; a takedown unit that performs takedown based on the information transmitted by the information distribution unit. A system characterized by:

2. The receiving unit The system estimates the user's emotions and adjusts the timing of receiving information based on the estimated user emotions.

2. The system of claim 1.

3. The receiving unit Evaluate the trustworthiness of companies and prioritize receiving information based on that trustworthiness.

2. The system of claim 1.

4. The receiving unit When receiving, select the appropriate receiving method depending on the type of information 2. The system of claim 1.

5. The receiving unit When receiving, analyze the user's past reception history and select the appropriate reception method.

2. The system of claim 1.

6. The filter section is Estimate the user's emotions and adjust the filtering criteria based on the estimated user emotions.

2. The system of claim 1.

7. The filter section is When filtering, the reliability of information is evaluated and filtering accuracy is improved based on the reliability.

2. The system of claim 1.

8. The filter section is When filtering, apply appropriate filtering algorithms depending on the category of information 2. The system of claim 1.

Images