system

Abstract

The system according to this embodiment aims to prevent the leakage of confidential information contained in emails. [Solution] The system according to the embodiment comprises an analysis unit, an identification unit, a warning unit, and a blocking unit. The analysis unit immediately analyzes the content of the email. The identification unit identifies specific confidential information based on the content of the email analyzed by the analysis unit. The warning unit issues a warning to the user based on the specific confidential information identified by the identification unit. The blocking unit stops sending the email when a warning is issued by the warning unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that measures for preventing leakage of confidential information included in mails are insufficient and the risk of information leakage is high.

[0005] The system according to the embodiment aims to prevent leakage of confidential information included in mails.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, an identification unit, a warning unit, and a blocking unit. The analysis unit immediately analyzes the content of the email. The identification unit identifies specific confidential information based on the content of the email analyzed by the analysis unit. The warning unit issues a warning to the user based on the specific confidential information identified by the identification unit. The blocking unit stops sending the email when a warning is issued by the warning unit. [Effects of the Invention]

[0007] The system according to this embodiment can prevent the leakage of confidential information contained in emails. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An AI agent system according to an embodiment of the present invention is a system that analyzes the content of incoming and outgoing emails in real time, issues a warning if confidential information is found, and blocks the sending of the email as necessary. This AI agent system analyzes the content of emails using natural language processing technology and identifies keywords containing confidential information. Based on the identified confidential information, it issues a warning to the user in real time and blocks the sending of the email as necessary. This allows employees to concentrate on their work with peace of mind without worrying about the risk of information leakage. For example, the AI ​​agent system analyzes the content of emails in real time. Next, the AI ​​agent system identifies keywords containing confidential information. Based on the identified confidential information, the AI ​​agent system issues a warning to the user in real time and blocks the sending of the email as necessary. Through this mechanism, the AI ​​agent system effectively manages the risk of information leakage and realizes an environment in which employees can work with peace of mind. As a result, the AI ​​agent system can analyze the content of incoming and outgoing emails in real time, issue a warning if confidential information is found, and block the sending of the email as necessary.

[0029] The AI ​​agent system according to this embodiment comprises an analysis unit, an identification unit, a warning unit, and a blocking unit. The analysis unit immediately analyzes the content of an email. The analysis unit analyzes the content of an email using, for example, natural language processing technology. Natural language processing technology includes techniques such as morphological analysis, grammatical analysis, and semantic analysis. The identification unit identifies specific confidential information based on the content of the email analyzed by the analysis unit. The identification unit identifies, for example, keywords containing confidential information. Keywords include specific word lists and frequently occurring words. The warning unit issues a warning to the user based on the specific confidential information identified by the identification unit. The warning unit issues a warning by, for example, a pop-up message or an email notification. The blocking unit stops sending the email when a warning is issued by the warning unit. The blocking unit stops sending the email by, for example, disabling the send button or deleting the send queue. As a result, the AI ​​agent system according to this embodiment can reduce the risk of information leakage by analyzing the content of an email in real time, identifying confidential information, issuing a warning, and blocking the sending of the email as necessary.

[0030] The analysis department analyzes email content immediately. Specifically, it uses natural language processing (NLP) techniques to analyze email content in detail. NLP techniques include morphological analysis, grammatical analysis, and semantic analysis. Morphological analysis divides the email text into individual words and identifies the part of speech of each word. Grammatical analysis analyzes the sentence structure and identifies grammatical elements such as subject, predicate, and object. Semantic analysis understands the meaning of the sentence and provides an appropriate interpretation based on the context. This allows the analysis department to accurately understand the content of emails and identify important information and potential risks. Furthermore, the analysis department can use machine learning algorithms to learn from past email data and perform more accurate analyses. For example, it can learn the characteristics of spam and phishing emails and quickly identify them. This allows the analysis department to analyze email content in real time and detect potential risks early.

[0031] The identification unit identifies specific confidential information based on the email content analyzed by the analysis unit. Specifically, it identifies keywords and phrases containing confidential information. The identification unit refers to predefined keyword lists and frequently occurring word lists and checks whether these keywords are included in the email content. For example, if confidential information such as credit card numbers, social security numbers, or passwords is included, it will identify them. The identification unit also uses machine learning models to identify confidential information in context. For example, it can identify highly confidential information that is not included in general keyword lists, such as specific industry jargon or company-specific information. This allows the identification unit to accurately identify confidential information contained in email content and reduce the risk of information leakage. Furthermore, the identification unit also considers the recipient and sender information of the email and can identify confidential information that should not be sent to specific individuals. This allows the identification unit to implement more comprehensive information leakage countermeasures.

[0032] The warning unit issues warnings to users based on specific confidential information identified by the identification unit. Specifically, warnings are issued through methods such as pop-up messages and email notifications. Pop-up messages appear on the screen when a user attempts to send an email, warning that it contains confidential information. Email notifications send a warning message to the user's email address, prompting them to reconfirm sending the confidential information. The warning unit can also customize the content of warning messages, providing specific warnings tailored to the specific confidential information. For example, if a credit card number is included, it will display a specific warning message such as, "This email contains a credit card number. Do you want to send it?" This allows the warning unit to issue appropriate warnings to users and reduce the risk of information leakage. Furthermore, the warning unit can record the warning history for later reference. This allows administrators to review past warning history and evaluate the effectiveness of information leakage prevention measures.

[0033] The blocking unit stops sending emails when a warning is issued by the warning unit. Specifically, it stops sending emails by disabling the send button or deleting them from the send queue. Disabling the send button prevents sending if the user ignores the warning and attempts to send an email. Deleting from the send queue removes the email waiting to be sent from the queue, completely stopping sending. The blocking unit can also automatically block email sending based on specific conditions. For example, it can automatically block sending if the email contains certain confidential information or is being sent to a specific recipient. This allows the blocking unit to proactively prevent the risk of information leakage. Furthermore, the blocking unit can record the blocking history for later reference. This allows administrators to review past blocking history and evaluate the effectiveness of information leakage prevention measures.

[0034] The analysis unit can analyze email content using natural language processing (NLP) techniques. For example, the analysis unit can use morphological analysis to break down email content into individual words, grammatical analysis to analyze sentence structure, and semantic analysis to understand the meaning of sentences. This improves the accuracy of email content analysis by using natural language processing techniques. Natural language processing techniques include, for example, morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input email content into a generative AI, which can then analyze the email content.

[0035] The identification unit can identify keywords containing confidential information. For example, the identification unit can scan email content using a specific word list to identify keywords containing confidential information. The identification unit can also analyze frequently occurring words to identify keywords that may contain confidential information. This improves the accuracy of confidential information detection by identifying keywords containing confidential information. Keywords include, for example, specific word lists and frequently occurring words. Some or all of the above processing in the identification unit may be performed using, for example, a generating AI, or without a generating AI. For example, the identification unit can input email content into a generating AI, which can then identify keywords containing confidential information.

[0036] The warning unit can issue real-time warnings to the user based on identified confidential information. For example, the warning unit can issue a warning to the user by displaying a pop-up message. The warning unit can also issue a warning to the user by sending an email notification. This allows the user to be quickly alerted by issuing a real-time warning based on identified confidential information. Real-time includes, for example, within a few seconds or immediately. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the warning unit can input identified confidential information into a generative AI, and the generative AI can issue a real-time warning.

[0037] The blocking unit can block email transmission based on specific conditions. For example, the blocking unit can block email transmission by disabling the send button. The blocking unit can also block email transmission by deleting the send queue. This reduces the risk of information leakage by blocking email transmission as needed. Specific conditions include, for example, the appearance of specific keywords or the detection of confidential information. Some or all of the above-described processes in the blocking unit may be performed using, for example, a generating AI, or without a generating AI. For example, the blocking unit can input identified confidential information into a generating AI, which can then block email transmission.

[0038] The analysis unit can improve the accuracy of its analysis based on the relationship between the email sender and recipient. For example, if the sender and recipient communicate frequently, the analysis unit can improve the accuracy of its analysis by referring to past email content. Furthermore, if the sender and recipient are communicating for the first time, the analysis unit can perform the analysis based on common patterns of confidential information. In addition, the analysis unit can determine the importance of confidential information by considering the positions and authority of the sender and recipient. This improves the accuracy of the analysis by considering the relationship between the sender and recipient. This relationship includes, for example, positions within the organization and past interactions. Some or all of the above processing in the analysis unit may be performed using, for example, generative AI, or without generative AI. For example, the analysis unit can input sender-recipient relationship data into generative AI, which can then perform the analysis while considering the relationship.

[0039] The analysis department can apply different analysis algorithms depending on the content of the email. For example, in the case of business emails, the analysis department can apply an analysis algorithm that emphasizes industry-specific keywords. In the case of private emails, the analysis department can also apply an analysis algorithm that prevents the leakage of personal information. Furthermore, in the case of emails containing technical content, the analysis department can apply an analysis algorithm that includes technical terms. By applying an analysis algorithm that is appropriate to the content of the email, the accuracy of the analysis is improved. Different analysis algorithms include, for example, keyword matching and contextual analysis. Some or all of the above processing in the analysis department may be performed using, for example, generative AI, or without generative AI. For example, the analysis department can input the email content into a generative AI, and the generative AI can apply an appropriate analysis algorithm.

[0040] The analysis department can perform analysis based on the time and frequency of email transmission. For example, the analysis department will analyze emails sent late at night with special attention because they are outside of normal business hours. The analysis department can also efficiently analyze frequently sent emails by learning patterns. Furthermore, the analysis department can focus its analysis on information related to the meeting content in emails sent before important meetings. This improves the accuracy of the analysis by considering the time and frequency of email transmission. The time and frequency of transmission include, for example, specific time periods and the number of transmissions. Some or all of the above processing in the analysis department may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis department can input email transmission time and frequency data into a generative AI, which can then take this data into consideration and perform the analysis.

[0041] The analysis unit can simultaneously analyze the contents of email attachments. For example, the analysis unit can analyze the contents of documents contained in attachments to detect confidential information. The analysis unit can also apply appropriate analysis methods depending on the type of attachment (PDF, Word, Excel, etc.). Furthermore, the analysis unit can analyze the metadata of attachments to obtain information such as the sender and creation date. This improves the accuracy of confidential information detection by analyzing the contents of email attachments. The contents of attachments include, for example, the file format and the method of content analysis. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the contents of attachments into a generative AI, which can then analyze them.

[0042] The identification unit can improve the accuracy of identifying confidential information based on the context of the email. For example, the identification unit analyzes the context before and after the email to determine the relevance of the confidential information. The identification unit can also evaluate the importance of the confidential information based on the topic or theme of the email. Furthermore, the identification unit can dynamically adjust the criteria for identifying confidential information according to the context of the email. This improves the accuracy of identifying confidential information by considering the context of the email. Context includes, for example, the surrounding sentences and related topics. Some or all of the above processing in the identification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the identification unit can input email context data into a generative AI, which can then identify confidential information while considering the context.

[0043] The identification unit can identify confidential information in multiple languages. For example, it can analyze emails written in multiple languages, such as English, Japanese, and Chinese, and identify confidential information. Furthermore, the identification unit can learn different patterns of confidential information for each language to improve its identification accuracy. In addition, the identification unit can accurately identify confidential information by considering the presence of multiple languages ​​within an email. This improves the accuracy of confidential information identification by supporting multiple languages. These multiple languages ​​include, for example, English, Japanese, and Chinese. Some or all of the above processing in the identification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the identification unit can input emails written in multiple languages ​​into a generative AI, which can then analyze them to identify confidential information.

[0044] The identification unit can identify confidential information based on the sender's job title and authority. For example, if the sender holds a high-ranking position, the identification unit will tighten the criteria for identifying confidential information. The identification unit can also adjust the criteria for identifying confidential information according to the sender's specific authority. Furthermore, the identification unit can evaluate the importance of confidential information based on the sender's job title and authority. This improves the accuracy of confidential information identification by considering the sender's job title and authority. Job titles and authority include, for example, managers and general employees. Some or all of the above processing in the identification unit may be performed using, for example, a generating AI, or without a generating AI. For example, the identification unit can input sender job title and authority data into a generating AI, which can then identify confidential information while considering this data.

[0045] The identification unit can identify confidential information based on past email exchanges. For example, the identification unit analyzes past email exchanges and learns patterns of confidential information. The identification unit can also identify confidential information in current emails based on past exchanges. Furthermore, the identification unit can evaluate the importance of confidential information by referring to the content of past exchanges. This improves the accuracy of confidential information identification by referring to past exchanges. Past exchanges include, for example, past email history and chat logs. Some or all of the above processing in the identification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the identification unit can input past exchange data into a generative AI, which can analyze it to identify confidential information.

[0046] The warning unit can adjust the level of detail of a warning based on the importance of the email when issuing a warning. For example, the warning unit will issue a detailed warning for important emails. It can also issue a concise warning for general emails. Furthermore, it can issue a warning requiring immediate action for urgent emails. This allows for appropriate warnings to be issued by adjusting the level of detail according to the importance of the email. Level of detail includes, for example, the specificity and amount of information in the warning message. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the warning unit can input email importance data into a generative AI, which can then adjust the level of detail of the warning based on that data.

[0047] The warning unit can select the optimal warning method based on the user's past behavior history when issuing a warning. For example, the warning unit can select a more effective warning method by referring to the content of warnings the user has ignored in the past. The warning unit can also select a similar warning method by referring to the content of warnings the user has responded to quickly in the past. Furthermore, the warning unit can select the optimal timing for the warning based on the user's past behavior history. In this way, the optimal warning method can be selected by referring to the user's past behavior history. The optimal warning method may include, for example, past behavior patterns and the user's reactions. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the warning unit can input the user's past behavior history data into a generative AI, and the generative AI can select the optimal warning method based on that data.

[0048] The warning unit can issue warnings based on the number and importance of the email recipients when issuing a warning. For example, if there are many recipients, the warning unit will prioritize warnings to those with high importance. The warning unit can also issue detailed warnings to important recipients if they are included. Furthermore, if the warning unit includes general recipients, it can issue a concise warning. In this way, appropriate warnings can be issued by considering the number and importance of the email recipients. The number and importance of recipients may include, for example, the recipient's job title or the importance of the email. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the warning unit can input email recipient data into a generative AI, and the generative AI can issue warnings based on that data.

[0049] The warning unit can issue a warning based on the content of the email attachment when it sends a warning. For example, if the attachment contains confidential information, the warning unit will issue a detailed warning. The warning unit can also issue an appropriate warning depending on the type of attachment. Furthermore, the warning unit can analyze the content of the attachment and issue a warning according to its importance. This allows for appropriate warnings to be issued to prevent the leakage of confidential information by considering the content of the email attachment. The content of the attachment includes, for example, the file format and the method of analyzing the content. Some or all of the above processing in the warning unit may be performed using, for example, a generating AI, or without a generating AI. For example, the warning unit can input the content data of the attachment into a generating AI, and the generating AI can issue a warning based on that data.

[0050] The blocking unit can adjust its blocking criteria based on the sender's authority and position. For example, if the sender holds a high position, the blocking unit will apply strict criteria and block the email from being sent. The blocking unit can also adjust its blocking criteria according to the sender's specific authority. Furthermore, the blocking unit can evaluate the importance of blocking based on the sender's position and authority. This allows for appropriate management of email sending by adjusting the blocking criteria according to the sender's authority and position. Authority and position include, for example, managers and general employees. Some or all of the above processing in the blocking unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the blocking unit can input sender authority and position data into a generating AI, which can then adjust the blocking criteria based on that data.

[0051] The blocking unit can apply different blocking algorithms depending on the content of the email. For example, in the case of business emails, the blocking unit can apply a blocking algorithm that prioritizes industry-specific confidential information. In the case of private emails, the blocking unit can also apply a blocking algorithm to prevent the leakage of personal information. Furthermore, in the case of emails containing technical content, the blocking unit can apply a blocking algorithm that includes technical terms. This allows for appropriate email sending management by applying a blocking algorithm appropriate to the email content. Examples of different blocking algorithms include keyword matching and contextual analysis. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the blocking unit can input the email content into a generative AI, which can then apply an appropriate blocking algorithm.

[0052] The blocking unit can block emails considering the number and importance of recipients. For example, if there are many recipients, the blocking unit will prioritize blocking those with high importance. The blocking unit can also perform detailed blocking on recipients if they are important. Furthermore, if the recipients are general, the blocking unit can perform simple blocking. This allows for appropriate email sending management by considering the number and importance of recipients. The number and importance of recipients include, for example, the recipient's job title and the importance of the email. Some or all of the above processing in the blocking unit may be performed using, for example, a generation AI, or not. For example, the blocking unit can input email recipient data into a generation AI, which can then perform blocking based on that data.

[0053] The blocking unit can also block the contents of email attachments. For example, if an attachment contains confidential information, the blocking unit will perform detailed blocking. The blocking unit can also perform appropriate blocking depending on the type of attachment. Furthermore, the blocking unit can analyze the contents of attachments and block them according to their importance. This prevents the leakage of confidential information by blocking the contents of email attachments. The contents of attachments include, for example, the file format and the method of analyzing the contents. Some or all of the above processing in the blocking unit may be performed using, for example, a generating AI, or without a generating AI. For example, the blocking unit can input attachment content data into a generating AI, and the generating AI can perform blocking based on that data.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The AI ​​agent system can further adjust the content of warnings based on the relationship between the email sender and recipient. For example, if the sender and recipient communicate frequently, the warning unit can adjust the content of the warning by referring to past email content. Also, if the sender and recipient are communicating for the first time, the warning can be issued based on common patterns of confidential information. Furthermore, the importance of the warning can be determined by considering the positions and authority of the sender and recipient. This makes the content of the warning more appropriate by considering the relationship between the sender and recipient. Relationships include, for example, positions within the organization and past interactions. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the warning unit can input the relationship data between the sender and recipient into a generative AI, and the generative AI can issue a warning while considering the relationship.

[0056] The AI ​​agent system can further apply different warning algorithms depending on the content of the email. For example, for business emails, a warning algorithm that emphasizes industry-specific keywords can be applied. For private emails, a warning algorithm to prevent the leakage of personal information can also be applied. Furthermore, for emails containing technical content, a warning algorithm that includes technical terms can be applied. This improves the accuracy of warnings by applying a warning algorithm tailored to the content of the email. Different warning algorithms include, for example, keyword matching and contextual analysis. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the warning unit can input the email content into a generative AI, which can then apply an appropriate warning algorithm.

[0057] The AI ​​agent system can also issue warnings based on the time and frequency of email transmission. For example, emails sent late at night will receive special attention and warnings because they are outside of normal business hours. Furthermore, frequently sent emails can be efficiently warned about by learning patterns. Additionally, emails sent before important meetings can receive focused warnings on information relevant to the meeting content. This improves the accuracy of warnings by considering the time and frequency of email transmission. This includes, for example, specific time periods and the number of transmissions. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the warning unit can input email transmission time and frequency data into a generative AI, which can then consider this data and issue warnings.

[0058] The AI ​​agent system can further adjust the blocking criteria based on the sender's authority and position. For example, if the sender holds a high position, strict criteria will be applied to block the email. The system can also adjust the blocking criteria according to the sender's specific privileges. Furthermore, it can evaluate the importance of blocking based on the sender's position and authority. This allows for appropriate email sending management by adjusting the blocking criteria according to the sender's authority and position. Authority and position include, for example, management and general employees. Some or all of the above processing in the blocking unit may be performed using, for example, a generating AI, or without a generating AI. For example, the blocking unit can input sender authority and position data into a generating AI, which can then adjust the blocking criteria based on that data.

[0059] The AI ​​agent system can apply different blocking algorithms depending on the content of the email. For example, for business emails, a blocking algorithm that prioritizes industry-specific confidential information can be applied. For private emails, a blocking algorithm to prevent the leakage of personal information can also be applied. Furthermore, for emails containing technical content, a blocking algorithm that includes technical terms can be applied. This allows for appropriate email sending management by applying a blocking algorithm according to the content of the email. Different blocking algorithms include, for example, keyword matching and contextual analysis. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the blocking unit can input the email content into a generative AI, which can then apply an appropriate blocking algorithm.

[0060] The AI ​​agent system can further block emails by considering the number and importance of the recipients. For example, if there are many recipients, it will prioritize blocking those with high importance. It can also perform detailed blocking on recipients that are important. Furthermore, if there are general recipients, it can perform simple blocking. This allows for appropriate email sending management by considering the number and importance of the recipients. The number and importance of recipients include, for example, the recipient's job title and the importance of the email. Some or all of the above processing in the blocking unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the blocking unit can input email recipient data into a generating AI, which can then perform blocking based on that data.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The analysis unit immediately analyzes the email content. The analysis unit analyzes the email content using, for example, natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. Step 2: The identification unit identifies specific confidential information based on the email content analyzed by the analysis unit. The identification unit identifies keywords containing confidential information, for example. Keywords may include specific word lists or frequently occurring words. Step 3: The warning unit issues a warning to the user based on specific confidential information identified by the identification unit. The warning unit issues the warning in a manner such as a pop-up message or email notification. Step 4: The blocking unit stops sending emails if a warning is issued by the warning unit. The blocking unit stops sending emails by methods such as disabling the send button or deleting the email from the send queue.

[0063] (Example of form 2) An AI agent system according to an embodiment of the present invention is a system that analyzes the content of incoming and outgoing emails in real time, issues a warning if confidential information is found, and blocks the sending of the email as necessary. This AI agent system analyzes the content of emails using natural language processing technology and identifies keywords containing confidential information. Based on the identified confidential information, it issues a warning to the user in real time and blocks the sending of the email as necessary. This allows employees to concentrate on their work with peace of mind without worrying about the risk of information leakage. For example, the AI ​​agent system analyzes the content of emails in real time. Next, the AI ​​agent system identifies keywords containing confidential information. Based on the identified confidential information, the AI ​​agent system issues a warning to the user in real time and blocks the sending of the email as necessary. Through this mechanism, the AI ​​agent system effectively manages the risk of information leakage and realizes an environment in which employees can work with peace of mind. As a result, the AI ​​agent system can analyze the content of incoming and outgoing emails in real time, issue a warning if confidential information is found, and block the sending of the email as necessary.

[0064] The AI ​​agent system according to this embodiment comprises an analysis unit, an identification unit, a warning unit, and a blocking unit. The analysis unit immediately analyzes the content of an email. The analysis unit analyzes the content of an email using, for example, natural language processing technology. Natural language processing technology includes techniques such as morphological analysis, grammatical analysis, and semantic analysis. The identification unit identifies specific confidential information based on the content of the email analyzed by the analysis unit. The identification unit identifies, for example, keywords containing confidential information. Keywords include specific word lists and frequently occurring words. The warning unit issues a warning to the user based on the specific confidential information identified by the identification unit. The warning unit issues a warning by, for example, a pop-up message or an email notification. The blocking unit stops sending the email when a warning is issued by the warning unit. The blocking unit stops sending the email by, for example, disabling the send button or deleting the send queue. As a result, the AI ​​agent system according to this embodiment can reduce the risk of information leakage by analyzing the content of an email in real time, identifying confidential information, issuing a warning, and blocking the sending of the email as necessary.

[0065] The analysis department analyzes email content immediately. Specifically, it uses natural language processing (NLP) techniques to analyze email content in detail. NLP techniques include morphological analysis, grammatical analysis, and semantic analysis. Morphological analysis divides the email text into individual words and identifies the part of speech of each word. Grammatical analysis analyzes the sentence structure and identifies grammatical elements such as subject, predicate, and object. Semantic analysis understands the meaning of the sentence and provides an appropriate interpretation based on the context. This allows the analysis department to accurately understand the content of emails and identify important information and potential risks. Furthermore, the analysis department can use machine learning algorithms to learn from past email data and perform more accurate analyses. For example, it can learn the characteristics of spam and phishing emails and quickly identify them. This allows the analysis department to analyze email content in real time and detect potential risks early.

[0066] The identification unit identifies specific confidential information based on the email content analyzed by the analysis unit. Specifically, it identifies keywords and phrases containing confidential information. The identification unit refers to predefined keyword lists and frequently occurring word lists and checks whether these keywords are included in the email content. For example, if confidential information such as credit card numbers, social security numbers, or passwords is included, it will identify them. The identification unit also uses machine learning models to identify confidential information in context. For example, it can identify highly confidential information that is not included in general keyword lists, such as specific industry jargon or company-specific information. This allows the identification unit to accurately identify confidential information contained in email content and reduce the risk of information leakage. Furthermore, the identification unit also considers the recipient and sender information of the email and can identify confidential information that should not be sent to specific individuals. This allows the identification unit to implement more comprehensive information leakage countermeasures.

[0067] The warning unit issues warnings to users based on specific confidential information identified by the identification unit. Specifically, warnings are issued through methods such as pop-up messages and email notifications. Pop-up messages appear on the screen when a user attempts to send an email, warning that it contains confidential information. Email notifications send a warning message to the user's email address, prompting them to reconfirm sending the confidential information. The warning unit can also customize the content of warning messages, providing specific warnings tailored to the specific confidential information. For example, if a credit card number is included, it will display a specific warning message such as, "This email contains a credit card number. Do you want to send it?" This allows the warning unit to issue appropriate warnings to users and reduce the risk of information leakage. Furthermore, the warning unit can record the warning history for later reference. This allows administrators to review past warning history and evaluate the effectiveness of information leakage prevention measures.

[0068] The blocking unit stops sending emails when a warning is issued by the warning unit. Specifically, it stops sending emails by disabling the send button or deleting them from the send queue. Disabling the send button prevents sending if the user ignores the warning and attempts to send an email. Deleting from the send queue removes the email waiting to be sent from the queue, completely stopping sending. The blocking unit can also automatically block email sending based on specific conditions. For example, it can automatically block sending if the email contains certain confidential information or is being sent to a specific recipient. This allows the blocking unit to proactively prevent the risk of information leakage. Furthermore, the blocking unit can record the blocking history for later reference. This allows administrators to review past blocking history and evaluate the effectiveness of information leakage prevention measures.

[0069] The analysis unit can analyze email content using natural language processing (NLP) techniques. For example, the analysis unit can use morphological analysis to break down email content into individual words, grammatical analysis to analyze sentence structure, and semantic analysis to understand the meaning of sentences. This improves the accuracy of email content analysis by using natural language processing techniques. Natural language processing techniques include, for example, morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input email content into a generative AI, which can then analyze the email content.

[0070] The identification unit can identify keywords containing confidential information. For example, the identification unit can scan email content using a specific word list to identify keywords containing confidential information. The identification unit can also analyze frequently occurring words to identify keywords that may contain confidential information. This improves the accuracy of confidential information detection by identifying keywords containing confidential information. Keywords include, for example, specific word lists and frequently occurring words. Some or all of the above processing in the identification unit may be performed using, for example, a generating AI, or without a generating AI. For example, the identification unit can input email content into a generating AI, which can then identify keywords containing confidential information.

[0071] The warning unit can issue real-time warnings to the user based on identified confidential information. For example, the warning unit can issue a warning to the user by displaying a pop-up message. The warning unit can also issue a warning to the user by sending an email notification. This allows the user to be quickly alerted by issuing a real-time warning based on identified confidential information. Real-time includes, for example, within a few seconds or immediately. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the warning unit can input identified confidential information into a generative AI, and the generative AI can issue a real-time warning.

[0072] The blocking unit can block email transmission based on specific conditions. For example, the blocking unit can block email transmission by disabling the send button. The blocking unit can also block email transmission by deleting the send queue. This reduces the risk of information leakage by blocking email transmission as needed. Specific conditions include, for example, the appearance of specific keywords or the detection of confidential information. Some or all of the above-described processes in the blocking unit may be performed using, for example, a generating AI, or without a generating AI. For example, the blocking unit can input identified confidential information into a generating AI, which can then block email transmission.

[0073] The analysis unit can estimate the user's emotions and adjust the email content analysis method based on the estimated emotions. For example, if the user is stressed, the analysis unit can apply a simplified analysis method and provide results quickly. If the user is relaxed, the analysis unit can also perform a detailed analysis and provide comprehensive results. Furthermore, if the user is in a hurry, the analysis unit can perform an analysis that focuses on key points. This allows for more appropriate analysis results by adjusting the analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using or without a generative AI. For example, the analysis unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the analysis method.

[0074] The analysis unit can improve the accuracy of its analysis based on the relationship between the email sender and recipient. For example, if the sender and recipient communicate frequently, the analysis unit can improve the accuracy of its analysis by referring to past email content. Furthermore, if the sender and recipient are communicating for the first time, the analysis unit can perform the analysis based on common patterns of confidential information. In addition, the analysis unit can determine the importance of confidential information by considering the positions and authority of the sender and recipient. This improves the accuracy of the analysis by considering the relationship between the sender and recipient. This relationship includes, for example, positions within the organization and past interactions. Some or all of the above processing in the analysis unit may be performed using, for example, generative AI, or without generative AI. For example, the analysis unit can input sender-recipient relationship data into generative AI, which can then perform the analysis while considering the relationship.

[0075] The analysis department can apply different analysis algorithms depending on the content of the email. For example, in the case of business emails, the analysis department can apply an analysis algorithm that emphasizes industry-specific keywords. In the case of private emails, the analysis department can also apply an analysis algorithm that prevents the leakage of personal information. Furthermore, in the case of emails containing technical content, the analysis department can apply an analysis algorithm that includes technical terms. By applying an analysis algorithm that is appropriate to the content of the email, the accuracy of the analysis is improved. Different analysis algorithms include, for example, keyword matching and contextual analysis. Some or all of the above processing in the analysis department may be performed using, for example, generative AI, or without generative AI. For example, the analysis department can input the email content into a generative AI, and the generative AI can apply an appropriate analysis algorithm.

[0076] The analysis unit can estimate the user's emotions and prioritize the analysis results based on the estimated emotions. For example, if the user is stressed, the analysis unit will prioritize displaying important analysis results. If the user is relaxed, the analysis unit can also sequentially display detailed analysis results. Furthermore, if the user is in a hurry, the analysis unit can display the most important analysis results first. This allows for the rapid delivery of important information by prioritizing analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or not. For example, the analysis unit can input user emotion data into a generative AI, which can estimate emotions and determine the priority of analysis results.

[0077] The analysis department can perform analysis based on the time and frequency of email transmission. For example, the analysis department will analyze emails sent late at night with special attention because they are outside of normal business hours. The analysis department can also efficiently analyze frequently sent emails by learning patterns. Furthermore, the analysis department can focus its analysis on information related to the meeting content in emails sent before important meetings. This improves the accuracy of the analysis by considering the time and frequency of email transmission. The time and frequency of transmission include, for example, specific time periods and the number of transmissions. Some or all of the above processing in the analysis department may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis department can input email transmission time and frequency data into a generative AI, which can then take this data into consideration and perform the analysis.

[0078] The analysis unit can simultaneously analyze the contents of email attachments. For example, the analysis unit can analyze the contents of documents contained in attachments to detect confidential information. The analysis unit can also apply appropriate analysis methods depending on the type of attachment (PDF, Word, Excel, etc.). Furthermore, the analysis unit can analyze the metadata of attachments to obtain information such as the sender and creation date. This improves the accuracy of confidential information detection by analyzing the contents of email attachments. The contents of attachments include, for example, the file format and the method of content analysis. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the contents of attachments into a generative AI, which can then analyze them.

[0079] The identification unit can estimate the user's emotions and adjust the criteria for identifying confidential information based on the estimated emotions. For example, if the user is stressed, the identification unit can apply strict criteria to strictly identify confidential information. If the user is relaxed, the identification unit can also apply flexible criteria to identify confidential information. Furthermore, if the user is in a hurry, the identification unit can apply criteria that allow for quick identification. This improves the accuracy of identifying confidential information by adjusting the criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the identification unit may be performed using, for example, a generative AI, or not. For example, the identification unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the criteria.

[0080] The identification unit can improve the accuracy of identifying confidential information based on the context of the email. For example, the identification unit analyzes the context before and after the email to determine the relevance of the confidential information. The identification unit can also evaluate the importance of the confidential information based on the topic or theme of the email. Furthermore, the identification unit can dynamically adjust the criteria for identifying confidential information according to the context of the email. This improves the accuracy of identifying confidential information by considering the context of the email. Context includes, for example, the surrounding sentences and related topics. Some or all of the above processing in the identification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the identification unit can input email context data into a generative AI, which can then identify confidential information while considering the context.

[0081] The identification unit can identify confidential information in multiple languages. For example, it can analyze emails written in multiple languages, such as English, Japanese, and Chinese, and identify confidential information. Furthermore, the identification unit can learn different patterns of confidential information for each language to improve its identification accuracy. In addition, the identification unit can accurately identify confidential information by considering the presence of multiple languages ​​within an email. This improves the accuracy of confidential information identification by supporting multiple languages. These multiple languages ​​include, for example, English, Japanese, and Chinese. Some or all of the above processing in the identification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the identification unit can input emails written in multiple languages ​​into a generative AI, which can then analyze them to identify confidential information.

[0082] The identification unit can estimate the user's emotions and determine the importance of the identified confidential information based on the estimated user emotions. For example, if the user is stressed, the identification unit will set the importance of the identified confidential information to a high level. The identification unit can also set the importance of the identified confidential information appropriately if the user is relaxed. Furthermore, if the user is in a hurry, the identification unit can set the importance of confidential information requiring a quick response to a high level. This allows for a quick response to important information by determining the importance of confidential information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the identification unit may be performed using a generative AI, or not using a generative AI. For example, the identification unit can input user emotion data into a generative AI, which can estimate the emotions and determine the importance of the confidential information.

[0083] The identification unit can identify confidential information based on the sender's job title and authority. For example, if the sender holds a high-ranking position, the identification unit will tighten the criteria for identifying confidential information. The identification unit can also adjust the criteria for identifying confidential information according to the sender's specific authority. Furthermore, the identification unit can evaluate the importance of confidential information based on the sender's job title and authority. This improves the accuracy of confidential information identification by considering the sender's job title and authority. Job titles and authority include, for example, managers and general employees. Some or all of the above processing in the identification unit may be performed using, for example, a generating AI, or without a generating AI. For example, the identification unit can input sender job title and authority data into a generating AI, which can then identify confidential information while considering this data.

[0084] The identification unit can identify confidential information based on past email exchanges. For example, the identification unit analyzes past email exchanges and learns patterns of confidential information. The identification unit can also identify confidential information in current emails based on past exchanges. Furthermore, the identification unit can evaluate the importance of confidential information by referring to the content of past exchanges. This improves the accuracy of confidential information identification by referring to past exchanges. Past exchanges include, for example, past email history and chat logs. Some or all of the above processing in the identification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the identification unit can input past exchange data into a generative AI, which can analyze it to identify confidential information.

[0085] The warning unit can estimate the user's emotions and adjust the way the warning is expressed based on the estimated emotions. For example, if the user is tense, the warning unit will issue a warning in a calm tone. If the user is relaxed, the warning unit can also issue a warning in a friendly tone. Furthermore, if the user is in a hurry, the warning unit can issue a quick and concise warning. This allows for more effective warnings by adjusting the way the warning is expressed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the warning unit may be performed using a generative AI, or not using a generative AI. For example, the warning unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the way the warning is expressed.

[0086] The warning unit can adjust the level of detail of a warning based on the importance of the email when issuing a warning. For example, the warning unit will issue a detailed warning for important emails. It can also issue a concise warning for general emails. Furthermore, it can issue a warning requiring immediate action for urgent emails. This allows for appropriate warnings to be issued by adjusting the level of detail according to the importance of the email. Level of detail includes, for example, the specificity and amount of information in the warning message. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the warning unit can input email importance data into a generative AI, which can then adjust the level of detail of the warning based on that data.

[0087] The warning unit can select the optimal warning method based on the user's past behavior history when issuing a warning. For example, the warning unit can select a more effective warning method by referring to the content of warnings the user has ignored in the past. The warning unit can also select a similar warning method by referring to the content of warnings the user has responded to quickly in the past. Furthermore, the warning unit can select the optimal timing for the warning based on the user's past behavior history. In this way, the optimal warning method can be selected by referring to the user's past behavior history. The optimal warning method may include, for example, past behavior patterns and the user's reactions. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the warning unit can input the user's past behavior history data into a generative AI, and the generative AI can select the optimal warning method based on that data.

[0088] The alert unit can estimate the user's emotions and determine the priority of alerts based on the estimated emotions. For example, if the user is stressed, the alert unit will prioritize displaying important alerts. It can also sequentially display detailed alerts if the user is relaxed. Furthermore, if the user is in a hurry, the alert unit can display the most important alerts first. This allows for the rapid display of important alerts by prioritizing them according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the alert unit may be performed using or without a generative AI. For example, the alert unit can input user emotion data into a generative AI, which can estimate the emotions and determine the priority of alerts.

[0089] The warning unit can issue warnings based on the number and importance of the email recipients when issuing a warning. For example, if there are many recipients, the warning unit will prioritize warnings to those with high importance. The warning unit can also issue detailed warnings to important recipients if they are included. Furthermore, if the warning unit includes general recipients, it can issue a concise warning. In this way, appropriate warnings can be issued by considering the number and importance of the email recipients. The number and importance of recipients may include, for example, the recipient's job title or the importance of the email. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the warning unit can input email recipient data into a generative AI, and the generative AI can issue warnings based on that data.

[0090] The warning unit can issue a warning based on the content of the email attachment when it sends a warning. For example, if the attachment contains confidential information, the warning unit will issue a detailed warning. The warning unit can also issue an appropriate warning depending on the type of attachment. Furthermore, the warning unit can analyze the content of the attachment and issue a warning according to its importance. This allows for appropriate warnings to be issued to prevent the leakage of confidential information by considering the content of the email attachment. The content of the attachment includes, for example, the file format and the method of analyzing the content. Some or all of the above processing in the warning unit may be performed using, for example, a generating AI, or without a generating AI. For example, the warning unit can input the content data of the attachment into a generating AI, and the generating AI can issue a warning based on that data.

[0091] The blocking unit can estimate the user's emotions and adjust the criteria for blocking email delivery based on the estimated emotions. For example, if the user is stressed, the blocking unit can apply strict criteria to block email delivery. Conversely, if the user is relaxed, the blocking unit can apply flexible criteria to block email delivery. Furthermore, if the user is in a hurry, the blocking unit can apply criteria requiring a quick response. This allows for appropriate email delivery management by adjusting the delivery blocking criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the blocking unit may be performed using or without a generative AI. For example, the blocking unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the delivery blocking criteria.

[0092] The blocking unit can adjust its blocking criteria based on the sender's authority and position. For example, if the sender holds a high position, the blocking unit will apply strict criteria and block the email from being sent. The blocking unit can also adjust its blocking criteria according to the sender's specific authority. Furthermore, the blocking unit can evaluate the importance of blocking based on the sender's position and authority. This allows for appropriate management of email sending by adjusting the blocking criteria according to the sender's authority and position. Authority and position include, for example, managers and general employees. Some or all of the above processing in the blocking unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the blocking unit can input sender authority and position data into a generating AI, which can then adjust the blocking criteria based on that data.

[0093] The blocking unit can apply different blocking algorithms depending on the content of the email. For example, in the case of business emails, the blocking unit can apply a blocking algorithm that prioritizes industry-specific confidential information. In the case of private emails, the blocking unit can also apply a blocking algorithm to prevent the leakage of personal information. Furthermore, in the case of emails containing technical content, the blocking unit can apply a blocking algorithm that includes technical terms. This allows for appropriate email sending management by applying a blocking algorithm appropriate to the email content. Examples of different blocking algorithms include keyword matching and contextual analysis. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the blocking unit can input the email content into a generative AI, which can then apply an appropriate blocking algorithm.

[0094] The block unit can estimate the user's emotions and determine the priority of blocks based on the estimated emotions. For example, if the user is stressed, the block unit will prioritize executing important blocks. If the user is relaxed, the block unit can also execute detailed blocks sequentially. Furthermore, if the user is in a hurry, the block unit can execute the most important blocks first. This allows for the rapid execution of important blocks by prioritizing them according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the block unit may be performed using a generative AI, or not. For example, the block unit can input user emotion data into a generative AI, which can estimate the emotions and determine the priority of blocks.

[0095] The blocking unit can block emails considering the number and importance of recipients. For example, if there are many recipients, the blocking unit will prioritize blocking those with high importance. The blocking unit can also perform detailed blocking on recipients if they are important. Furthermore, if the recipients are general, the blocking unit can perform simple blocking. This allows for appropriate email sending management by considering the number and importance of recipients. The number and importance of recipients include, for example, the recipient's job title and the importance of the email. Some or all of the above processing in the blocking unit may be performed using, for example, a generation AI, or not. For example, the blocking unit can input email recipient data into a generation AI, which can then perform blocking based on that data.

[0096] The blocking unit can also block the contents of email attachments. For example, if an attachment contains confidential information, the blocking unit will perform detailed blocking. The blocking unit can also perform appropriate blocking depending on the type of attachment. Furthermore, the blocking unit can analyze the contents of attachments and block them according to their importance. This prevents the leakage of confidential information by blocking the contents of email attachments. The contents of attachments include, for example, the file format and the method of analyzing the contents. Some or all of the above processing in the blocking unit may be performed using, for example, a generating AI, or without a generating AI. For example, the blocking unit can input attachment content data into a generating AI, and the generating AI can perform blocking based on that data.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] The AI ​​agent system can further estimate the user's emotions and adjust the content of warnings based on the estimated emotions. For example, if the user is stressed, the warning unit can issue a warning with a more detailed explanation. If the user is relaxed, it can issue a concise warning. Furthermore, if the user is in a hurry, it can issue a warning that requires immediate attention. This allows for more effective warnings by adjusting the content of warnings according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the warning unit may be performed using a generative AI, or not using a generative AI. For example, the warning unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the content of the warning.

[0099] The AI ​​agent system can further adjust the content of warnings based on the relationship between the email sender and recipient. For example, if the sender and recipient communicate frequently, the warning unit can adjust the content of the warning by referring to past email content. Also, if the sender and recipient are communicating for the first time, the warning can be issued based on common patterns of confidential information. Furthermore, the importance of the warning can be determined by considering the positions and authority of the sender and recipient. This makes the content of the warning more appropriate by considering the relationship between the sender and recipient. Relationships include, for example, positions within the organization and past interactions. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the warning unit can input the relationship data between the sender and recipient into a generative AI, and the generative AI can issue a warning while considering the relationship.

[0100] The AI ​​agent system can further apply different warning algorithms depending on the content of the email. For example, for business emails, a warning algorithm that emphasizes industry-specific keywords can be applied. For private emails, a warning algorithm to prevent the leakage of personal information can also be applied. Furthermore, for emails containing technical content, a warning algorithm that includes technical terms can be applied. This improves the accuracy of warnings by applying a warning algorithm tailored to the content of the email. Different warning algorithms include, for example, keyword matching and contextual analysis. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the warning unit can input the email content into a generative AI, which can then apply an appropriate warning algorithm.

[0101] The AI ​​agent system can further estimate the user's emotions and determine the priority of warnings based on the estimated emotions. For example, if the user is stressed, important warnings can be displayed first. If the user is relaxed, detailed warnings can be displayed sequentially. Furthermore, if the user is in a hurry, the most important warnings can be displayed first. This allows important warnings to be displayed quickly by determining the priority of warnings according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the warning unit may be performed using a generative AI, or not using a generative AI. For example, the warning unit can input user emotion data into a generative AI, which can estimate the emotions and determine the priority of warnings.

[0102] The AI ​​agent system can also issue warnings based on the time and frequency of email transmission. For example, emails sent late at night will receive special attention and warnings because they are outside of normal business hours. Furthermore, frequently sent emails can be efficiently warned about by learning patterns. Additionally, emails sent before important meetings can receive focused warnings on information relevant to the meeting content. This improves the accuracy of warnings by considering the time and frequency of email transmission. This includes, for example, specific time periods and the number of transmissions. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the warning unit can input email transmission time and frequency data into a generative AI, which can then consider this data and issue warnings.

[0103] The AI ​​agent system can further estimate the user's emotions and adjust the blocking criteria based on the estimated emotions. For example, if the user is stressed, strict criteria can be applied to block email transmission. Conversely, if the user is relaxed, flexible criteria can be applied to block email transmission. Furthermore, if the user is in a hurry, criteria requiring a quick response can be applied. This allows for appropriate email transmission management by adjusting the transmission blocking criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the blocking unit may be performed using a generative AI, or not. For example, the blocking unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the transmission blocking criteria.

[0104] The AI ​​agent system can further adjust the blocking criteria based on the sender's authority and position. For example, if the sender holds a high position, strict criteria will be applied to block the email. The system can also adjust the blocking criteria according to the sender's specific privileges. Furthermore, it can evaluate the importance of blocking based on the sender's position and authority. This allows for appropriate email sending management by adjusting the blocking criteria according to the sender's authority and position. Authority and position include, for example, management and general employees. Some or all of the above processing in the blocking unit may be performed using, for example, a generating AI, or without a generating AI. For example, the blocking unit can input sender authority and position data into a generating AI, which can then adjust the blocking criteria based on that data.

[0105] The AI ​​agent system can apply different blocking algorithms depending on the content of the email. For example, for business emails, a blocking algorithm that prioritizes industry-specific confidential information can be applied. For private emails, a blocking algorithm to prevent the leakage of personal information can also be applied. Furthermore, for emails containing technical content, a blocking algorithm that includes technical terms can be applied. This allows for appropriate email sending management by applying a blocking algorithm according to the content of the email. Different blocking algorithms include, for example, keyword matching and contextual analysis. Some or all of the above processing in the blocking unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the blocking unit can input the email content into a generative AI, which can then apply an appropriate blocking algorithm.

[0106] The AI ​​agent system can further estimate the user's emotions and determine the priority of blocks based on the estimated emotions. For example, if the user is stressed, important blocks can be executed first. If the user is relaxed, detailed blocks can be executed sequentially. Furthermore, if the user is in a hurry, the most important blocks can be executed first. This allows for the rapid execution of important blocks by determining the priority of blocks according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the block section may be performed using a generative AI, or not using a generative AI. For example, the block section can input user emotion data into a generative AI, which can estimate the emotions and determine the priority of blocks.

[0107] The AI ​​agent system can further block emails by considering the number and importance of the recipients. For example, if there are many recipients, it will prioritize blocking those with high importance. It can also perform detailed blocking on recipients that are important. Furthermore, if there are general recipients, it can perform simple blocking. This allows for appropriate email sending management by considering the number and importance of the recipients. The number and importance of recipients include, for example, the recipient's job title and the importance of the email. Some or all of the above processing in the blocking unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the blocking unit can input email recipient data into a generating AI, which can then perform blocking based on that data.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The analysis unit immediately analyzes the email content. The analysis unit analyzes the email content using, for example, natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. Step 2: The identification unit identifies specific confidential information based on the email content analyzed by the analysis unit. The identification unit identifies keywords containing confidential information, for example. Keywords may include specific word lists or frequently occurring words. Step 3: The warning unit issues a warning to the user based on specific confidential information identified by the identification unit. The warning unit issues the warning in a manner such as a pop-up message or email notification. Step 4: The blocking unit stops sending emails if a warning is issued by the warning unit. The blocking unit stops sending emails by methods such as disabling the send button or deleting the email from the send queue.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0111] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0112] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0113] Each of the multiple elements described above, including the analysis unit, identification unit, warning unit, and blocking unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and immediately analyzes the email content. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and identifies specific confidential information based on the analyzed email content. The warning unit is implemented by the control unit 46A of the smart device 14 and issues a warning to the user based on the identified specific confidential information. The blocking unit is implemented by the identification processing unit 290 of the data processing unit 12 and stops sending the email when a warning is issued. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0114] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0115] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0120] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0121] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0122] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0123] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0124] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0125] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0127] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0128] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements described above, including the analysis unit, identification unit, warning unit, and blocking unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and immediately analyzes the email content. The identification unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and identifies specific confidential information based on the analyzed email content. The warning unit is implemented, for example, by the control unit 46A of the smart glasses 214 and issues a warning to the user based on the identified specific confidential information. The blocking unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and stops sending the email when a warning is issued. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0133] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0134] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0136] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0137] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0138] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0139] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0140] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0141] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0144] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements described above, including the analysis unit, identification unit, warning unit, and blocking unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and immediately analyzes the email content. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and identifies specific confidential information based on the analyzed email content. The warning unit is implemented by the control unit 46A of the headset terminal 314 and issues a warning to the user based on the identified specific confidential information. The blocking unit is implemented by the identification processing unit 290 of the data processing unit 12 and stops sending the email when a warning is issued. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0146] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0147] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0148] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0150] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0152] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0153] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0154] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0155] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0156] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0157] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the analysis unit, identification unit, warning unit, and blocking unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and immediately analyzes the email content. The identification unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and identifies specific confidential information based on the analyzed email content. The warning unit is implemented, for example, by the control unit 46A of the robot 414 and issues a warning to the user based on the identified specific confidential information. The blocking unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and stops sending the email when a warning is issued. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0163] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0164] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0165] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0166] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0167] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0168] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0171] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0172] 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.

[0173] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0174] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0175] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0176] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0177] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0178] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0179] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0180] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0181] (Note 1) The analysis department analyzes the email content immediately, An identification unit that identifies specific confidential information based on the email content analyzed by the aforementioned analysis unit, A warning unit that issues a warning to the user based on specific confidential information identified by the aforementioned identification unit, The system includes a blocking unit that stops sending emails when a warning is issued by the warning unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit is Analyze email content using natural language processing technology The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned identification unit is Identify keywords containing confidential information The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned warning unit is It issues real-time alerts to users based on identified sensitive information. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned block section is Block email sending based on specific conditions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit is We estimate the user's emotions and adjust the email content analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit is Improve the accuracy of analysis based on the relationship between email senders and recipients. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit is Apply different analysis algorithms depending on the content of the email. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit is It estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit is The analysis is based on the time and frequency of email sending. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit is The contents of email attachments are also analyzed simultaneously. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned identification unit is We estimate user sentiment and adjust the criteria for identifying sensitive information based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned identification unit is Improving the accuracy of identifying sensitive information based on the context of emails. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned identification unit is Identify confidential information using multiple languages. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned identification unit is It estimates the user's emotions and determines the importance of the identified sensitive information based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned identification unit is Identify confidential information based on the sender's job title and authority. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned identification unit is Identify confidential information based on past email exchanges. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned warning unit is The system estimates the user's emotions and adjusts the way warnings are presented based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned warning unit is When issuing a warning, adjust the level of detail of the warning based on the importance of the email. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned warning unit is When issuing a warning, the system selects the most appropriate warning method based on the user's past behavior history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned warning unit is The system estimates the user's emotions and prioritizes warnings based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned warning unit is When issuing a warning, the system will send warnings based on the number of recipients and the importance of the warning. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned warning unit is When issuing a warning, the warning will be based on the content of the email attachment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned block section is The system estimates the user's sentiment and adjusts the criteria for blocking email delivery based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned block section is Adjust blocking criteria based on the sender's permissions and job title. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned block section is Apply different blocking algorithms depending on the content of the email. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned block section is It estimates the user's emotions and determines the priority of blocking based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned block section is Blocking is performed considering the number of recipients and the importance of the email. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned block section is Block the contents of email attachments at the same time. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analysis department analyzes the email content immediately, An identification unit that identifies specific confidential information based on the email content analyzed by the aforementioned analysis unit, A warning unit that issues a warning to the user based on specific confidential information identified by the aforementioned identification unit, The system includes a blocking unit that stops sending emails when a warning is issued by the warning unit. A system characterized by the following features.

2. The aforementioned analysis unit is Analyze email content using natural language processing technology The system according to feature 1.

3. The aforementioned identification unit is Identify keywords containing confidential information The system according to feature 1.

4. The aforementioned warning unit is It issues real-time alerts to users based on identified sensitive information. The system according to feature 1.

5. The aforementioned block section is Block email sending based on specific conditions. The system according to feature 1.

6. The aforementioned analysis unit is We estimate the user's emotions and adjust the email content analysis method based on the estimated user emotions. The system according to feature 1.

7. The aforementioned analysis unit is Improve the accuracy of analysis based on the relationship between email senders and recipients. The system according to feature 1.

8. The aforementioned analysis unit is Apply different analysis algorithms depending on the content of the email. The system according to feature 1.

9. The aforementioned analysis unit is It estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. The system according to feature 1.

10. The aforementioned analysis unit is The analysis is based on the time and frequency of email sending. The system according to feature 1.

Images