system

Abstract

The system according to this embodiment aims to monitor the actions of other agents in real time, detect abnormal behavior, and respond accordingly. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a detection unit, a notification unit, and a response unit. The collection unit intercepts communications of other agents and collects data. The analysis unit analyzes the data collected by the collection unit. The detection unit detects abnormal behavior based on the data analyzed by the analysis unit. The notification unit notifies the user of the abnormal behavior detected by the detection unit. The response unit automatically takes countermeasures in response to the abnormal behavior notified by the notification unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, when using a plurality of agents simultaneously, the internal operations of the agents are opaque, and there is a risk of undesirable behaviors such as leakage of personal information.

[0005] The system according to the embodiment aims to monitor the actions of other agents in real time, detect abnormal actions, and respond to them.

Means for Solving the Problems

[0006] The system according to the embodiment comprises a collection unit, an analysis unit, a detection unit, a notification unit, and a response unit. The collection unit intercepts communications of other agents and collects data. The analysis unit analyzes the data collected by the collection unit. The detection unit detects abnormal behavior based on the data analyzed by the analysis unit. The notification unit notifies the user of the abnormal behavior detected by the detection unit. The response unit automatically takes countermeasures in response to the abnormal behavior notified by the notification unit. [Effects of the Invention]

[0007] The system according to this embodiment can monitor the actions of other agents in real time, detect abnormal behavior, and respond accordingly. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The agent management AI agent system according to an embodiment of the present invention is a system that monitors and controls the behavior of other agents in real time at the context level, in situations where the use of generative AI agents is increasing and users are using multiple agents simultaneously. This agent management AI agent system can analyze the inputs and outputs of agents to detect abnormal behavior, provide notifications to the user, and automatically take corrective actions. For example, the agent management AI agent system intercepts the communications of other agents via a proxy server or middleware and collects data. This includes API calls, messages, and file input / output sent and received by agents. Next, the agent management AI agent system analyzes the collected data using natural language processing (NLP) technology to interpret the content of agent conversations and commands. Furthermore, the agent management AI agent system learns and predicts abnormal behavior patterns using machine learning algorithms. For example, it can detect an unusually large number of data requests or attempts to access the system without authorization. Users can define custom policies to control agent behavior. Role-based access control (RBAC) can be applied to set agent-specific permissions and implement data masking and access restrictions for sensitive information. If abnormal behavior occurs, the user is immediately notified by the real-time notification system. Furthermore, the agent management AI agent system provides a dashboard in the form of a web or mobile application to visualize agent activity. Security and encryption are also enhanced, ensuring the safety of data transfer through TLS / SSL encryption and strengthening authentication procedures with technologies such as two-factor authentication (2FA) and biometric authentication. It also leverages Secure Enclave to enhance the security of sensitive data. This agent management AI agent system is compatible with various agents and uses standard protocols such as RESTful APIs and gRPC. A plugin architecture allows for easy addition of new agents and features, and its cloud-based service enhances scalability and availability.This allows the agent management AI agent system to enable users to safely and efficiently manage multiple agents.

[0029] The agent management AI agent system according to the embodiment comprises a collection unit, an analysis unit, a detection unit, a notification unit, and a response unit. The collection unit intercepts communications of other agents and collects data. The collection unit intercepts agent communications, for example, via a proxy server or middleware, and collects data such as API calls, messages, and file input / output. For example, the collection unit intercepts API calls sent and received by agents and collects their contents. The collection unit can also intercept messages sent and received by agents and collect their contents. Furthermore, the collection unit can intercept file input / output performed by agents and collect their contents. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit uses natural language processing (NLP) technology to analyze the collected data and interpret the agent's conversation content and commands. For example, the analysis unit uses natural language processing technology to analyze the collected data and interpret the agent's conversation content. The analysis unit can also use natural language processing technology to analyze the collected data and interpret the agent's commands. Furthermore, the analysis unit can analyze the collected data using machine learning algorithms to learn and predict abnormal behavior patterns. The detection unit detects abnormal behavior based on the data analyzed by the analysis unit. The detection unit can, for example, learn abnormal behavior patterns using machine learning algorithms and detect abnormal behavior. The detection unit can, for example, detect an unusually large number of data requests. The detection unit can also detect attempts at unauthorized system access. Furthermore, the detection unit can also detect abnormal communication patterns. The notification unit notifies the user of the abnormal behavior detected by the detection unit. The notification unit can, for example, use a real-time notification system to immediately notify the user when abnormal behavior occurs. The notification unit can, for example, send a real-time notification to the user when abnormal behavior occurs. The notification unit can also send a notification to the user via web or mobile application when abnormal behavior occurs. Furthermore, the notification unit can also send a notification to the user via email when abnormal behavior occurs. The response unit automatically takes countermeasures against the abnormal behavior notified by the notification unit.The response unit can, for example, block communication when abnormal behavior is detected. The response unit can, for example, issue a warning when abnormal behavior is detected. The response unit can also change the system's access permissions when abnormal behavior is detected. As a result, the agent management AI agent system according to this embodiment can monitor the communication of other agents in real time, detect abnormal behavior, and respond automatically.

[0030] The data collection unit intercepts communications from other agents and collects data. For example, the data collection unit intercepts agent communications via a proxy server or middleware and collects data such as API calls, messages, and file input / output. Specifically, the proxy server relays communications between agents and captures the content of those communications in the process. This allows for the acquisition of detailed information about API calls sent and received by agents. This includes, for example, API call parameters, request types, and response content. The data collection unit can also intercept messages sent and received by agents and collect their content. These messages include instructions between agents, status information, and error messages. Furthermore, the data collection unit can intercept file input / output performed by agents and collect their content. File input / output includes log files, configuration files, and data files, and analyzing this content allows for the understanding of the agent's operational status and signs of abnormalities. The data collection unit collects this data in real time and sends it to a central database. The database centrally manages the collected data and makes it accessible to the analysis and detection units. This allows the data collection unit to efficiently and effectively monitor agent communications and provide a foundation for understanding the overall system status. Furthermore, the data collection unit can flexibly set the data collection frequency and filtering conditions, enabling data collection tailored to specific situations and conditions. As a result, the data collection unit can reliably collect the necessary data while optimizing system performance.

[0031] The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit utilizes natural language processing (NLP) technology to analyze the collected data and interpret agent conversations and commands. Specifically, it uses NLP technology to analyze message content between agents and extract the intent and instructions of the conversation. For instance, it can identify specific commands or requests from messages sent by agents and interpret their content. Furthermore, the analysis unit can analyze the collected data using machine learning algorithms to learn and predict abnormal behavior patterns. Machine learning algorithms learn normal agent behavior patterns based on past data and build models to detect abnormal behavior. For example, if an agent makes API calls at an unusually high frequency or requests an unusually large amount of data, this can be detected as abnormal behavior. In addition, the analysis unit can analyze the collected data using statistical methods to evaluate agent behavior trends and performance. This allows the analysis unit to comprehensively understand the agent's behavior and perform early detection and prediction of abnormal behavior. Based on these analysis results, the analysis unit can provide appropriate information to the detection and notification units, thereby improving the overall reliability and security of the system.

[0032] The detection unit detects abnormal behavior based on data analyzed by the analysis unit. The detection unit learns abnormal behavior patterns using, for example, machine learning algorithms. Specifically, it uses a machine learning model to learn the normal operating patterns of agents and detect abnormal behavior in real time. For example, if an agent makes more data requests than usual, or if there is an attempt to gain unauthorized system access, this can be detected as abnormal behavior. The detection unit can also detect abnormal communication patterns. For example, if the communication frequency or content between agents differs from the norm, this can be detected as abnormal. Furthermore, the detection unit transmits the results of the abnormal behavior detection to the notification unit in real time, providing information for immediate countermeasures. This allows the detection unit to quickly and accurately detect abnormal agent behavior and play a crucial role in ensuring the overall system security. To improve the accuracy of abnormal behavior detection, the detection unit can continuously update its machine learning model and learn based on the latest data. This allows the detection unit to always respond to the latest threats and abnormal behaviors, maintaining system reliability.

[0033] The notification unit notifies the user of abnormal behavior detected by the detection unit. The notification unit immediately notifies the user when abnormal behavior occurs, for example, using a real-time notification system. Specifically, when abnormal behavior is detected, it can send a notification to the user via a web or mobile application. For example, it can send a push notification to the user's smartphone, providing detailed information about the abnormal behavior and recommended countermeasures. The notification unit can also send notifications to the user via email. The email includes detailed information such as the time the abnormal behavior occurred, the scope of its impact, and recommended countermeasures. Furthermore, the notification unit can also send notifications to the user via voice call or SMS when abnormal behavior occurs. This allows the notification unit to quickly and reliably inform the user of the occurrence of abnormal behavior and encourage appropriate action. The notification unit can collect user feedback and continuously improve the accuracy and effectiveness of the notification content. For example, based on user feedback, it can review the timing and content of notifications and adopt more effective notification methods. This allows the notification unit to provide users with quick and appropriate information and improve the reliability and security of the entire system.

[0034] The response unit automatically takes countermeasures against abnormal behavior notified by the notification unit. For example, when abnormal behavior is detected, the response unit may block communication. Specifically, it may temporarily suspend communication from the agent exhibiting abnormal behavior to minimize the impact on the entire system. The response unit may also issue a warning when abnormal behavior is detected. For example, it may send a warning message to the system administrator to encourage a prompt response. Furthermore, the response unit may change system access permissions when abnormal behavior is detected. For example, it may restrict the access permissions of the agent that exhibited abnormal behavior to prevent unauthorized operations or data leaks. By automatically executing these countermeasures, the response unit achieves a rapid and effective response to abnormal behavior. In addition, the response unit can record the results of the countermeasures and use them for subsequent analysis and improvement. For example, it can save logs of the countermeasures to analyze the causes of the abnormal behavior and the effectiveness of the countermeasures. This allows the response unit to play a crucial role in improving the overall security and reliability of the system. The response unit can continuously review its countermeasures against abnormal behavior and take optimal measures to address the latest threats and risks. This allows the support unit to maintain system security and provide users with a safe and reliable environment.

[0035] The policy section can define custom policies. The policy section provides, for example, an interface for users to define custom policies. The policy section allows users to set custom policies to control agent behavior. The policy section also allows users to edit custom policies to control agent behavior. Furthermore, the policy section allows users to delete custom policies to control agent behavior. This allows users to control agent behavior by defining custom policies. Some or all of the above processes in the policy section may be performed using AI, or not. For example, the policy section can input user-defined custom policies into the AI, which can then automatically adjust the scope of the policy's application.

[0036] The access control unit can apply role-based access control. For example, the access control unit provides an interface for users to set agent-specific permissions. The access control unit allows users to set agent-specific permissions, edit agent-specific permissions, and delete agent-specific permissions. This allows agent-specific permissions to be set by applying role-based access control. Some or all of the above processes in the access control unit may be performed using AI, or not. For example, the access control unit can input user-defined agent-specific permissions into the AI, which can then automatically adjust the scope of those permissions.

[0037] The masking unit can perform data masking. For example, the masking unit implements data masking for confidential information. For example, the masking unit applies an algorithm for masking confidential information. The masking unit can also set rules for masking confidential information. Furthermore, the masking unit can apply a policy for masking confidential information. This enhances the protection of confidential information through data masking. Some or all of the above processing in the masking unit may be performed using AI, for example, or without AI. For example, the masking unit can input an algorithm for masking confidential information into an AI, which can then automatically adjust the scope of masking.

[0038] The notification system unit can provide a real-time notification system. For example, the notification system unit can immediately send a notification to the user when abnormal behavior occurs. The notification system unit can provide an interface for sending notifications to the user in real time. The notification system unit can also send notifications to the user via a web or mobile application when abnormal behavior occurs. Furthermore, the notification system unit can send notifications to the user via email when abnormal behavior occurs. By providing a real-time notification system, the system can immediately notify the user when abnormal behavior occurs. Some or all of the above processing in the notification system unit may be performed using AI, for example, or without AI. For example, the notification system unit can send notifications using an AI model for sending notifications to the user in real time when abnormal behavior occurs.

[0039] The dashboard unit can provide a dashboard. The dashboard unit can, for example, provide an interface for visualizing agent activity. The dashboard unit can, for example, display data for visualizing agent activity. The dashboard unit can also display graphs and charts for visualizing agent activity. Furthermore, the dashboard unit can generate reports for visualizing agent activity. In this way, agent activity can be visualized by providing a dashboard. Some or all of the above processing in the dashboard unit may be performed using AI, for example, or not using AI. For example, the dashboard unit can input agent activity data into AI, and the AI ​​can automatically visualize the data.

[0040] The encryption unit can perform TLS / SSL encryption. For example, the encryption unit applies TLS / SSL encryption to ensure the security of data transfer. For example, the encryption unit uses a certificate to apply TLS / SSL encryption during data transfer. The encryption unit can also configure a protocol to apply TLS / SSL encryption during data transfer. Furthermore, the encryption unit can apply a security policy to apply TLS / SSL encryption during data transfer. This ensures the security of data transfer by performing TLS / SSL encryption. Some or all of the above processing in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input a certificate to apply TLS / SSL encryption during data transfer into the AI, and the AI ​​can automatically manage the certificate.

[0041] The authentication unit can perform two-factor authentication or biometric authentication. For example, the authentication unit can apply two-factor authentication to strengthen the authentication procedure. For example, the authentication unit can provide an interface for applying two-factor authentication when a user logs in. The authentication unit can also provide an interface for applying biometric authentication when a user logs in. Furthermore, the authentication unit can apply a combination of two-factor authentication and biometric authentication when a user logs in. This strengthens the authentication procedure by performing two-factor authentication or biometric authentication. Some or all of the above processing in the authentication unit may be performed using AI, for example, or without AI. For example, the authentication unit can automatically perform the authentication procedure using an AI model for applying two-factor authentication when a user logs in.

[0042] The security department can utilize secure enclaves. For example, the security department can apply secure enclaves to enhance the security of confidential data. For example, the security department can store confidential data within a secure enclave. The security department can also process confidential data within a secure enclave. Furthermore, the security department can encrypt confidential data within a secure enclave. Thus, the security of confidential data is enhanced by utilizing secure enclaves. Some or all of the above-described processes in the security department may be performed using AI, for example, or not using AI. For example, the security department can automate data management using an AI model for storing confidential data within a secure enclave.

[0043] The compatibility unit can use RESTful APIs or gRPC. For example, the compatibility unit uses RESTful APIs to ensure compatibility with various agents. For example, the compatibility unit provides an interface for agents to communicate using RESTful APIs. The compatibility unit can also provide an interface for agents to communicate using gRPC. Furthermore, the compatibility unit can provide an interface for agents to communicate using both RESTful APIs and gRPC. This ensures compatibility with various agents by using RESTful APIs and gRPC. Some or all of the above processing in the compatibility unit may be performed using AI, for example, or not using AI. For example, the compatibility unit can automatically manage communication using an AI model for agents to communicate using RESTful APIs.

[0044] The plugin section can provide a plugin architecture. For example, the plugin section can provide a plugin architecture for easily adding new agents or functions. For example, the plugin section can provide an interface for users to add new agents. The plugin section can also provide an interface for users to add new functions. Furthermore, the plugin section can provide an interface for users to extend existing agents or functions. This allows for easy addition of new agents and functions by providing a plugin architecture. Some or all of the above-described processes in the plugin section may be performed using AI, for example, or without AI. For example, the plugin section can automatically add agents using an AI model for users to add new agents.

[0045] The Cloud Division can provide services on a cloud basis. The Cloud Division, for example, provides the infrastructure for providing services on a cloud basis. The Cloud Division, for example, provides services using a cloud platform. The Cloud Division can also ensure scalability for providing services on a cloud basis. Furthermore, the Cloud Division can ensure availability for providing services on a cloud basis. This increases scalability and availability by providing services on a cloud basis. Some or all of the above processes in the Cloud Division may be performed using AI, for example, or not using AI. For example, the Cloud Division can automate service management using an AI model for providing services using a cloud platform.

[0046] The data collection unit can analyze the agent's communication content in real time and quickly identify abnormal communication patterns. For example, if an agent is sending a large amount of data that is different from the usual, the data collection unit can quickly identify that communication content. For example, if an agent is attempting to gain unauthorized system access, the data collection unit can quickly identify that communication content. The data collection unit can also quickly identify the communication content if an agent is communicating during an abnormal time period. In this way, abnormal communication patterns can be quickly identified by analyzing the agent's communication content in real time. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can automatically collect abnormal communication patterns using an AI model for analyzing the agent's communication content in real time.

[0047] The data collection unit can dynamically change the types of data it collects and collect only the necessary data depending on the specific situation. For example, if an agent is handling confidential information, the data collection unit will collect only the content of that communication. For example, if an agent is sending a large amount of data, the data collection unit can collect only the important data. Furthermore, if an agent is exhibiting abnormal behavior, the data collection unit can collect only the data related to that behavior. This enables efficient data collection by collecting only the necessary data depending on the specific situation. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can automatically collect the necessary data using an AI model for analyzing the agent's communication content in real time.

[0048] The data collection unit can consider the geographical location information of the source and destination of communications when collecting the content of agent communications. For example, the data collection unit can collect the content of communications if an agent is communicating from an unusual geographical location. For example, the data collection unit can collect the content of communications if an agent is sending a large amount of data from a specific region. Furthermore, the data collection unit can collect the content of communications if an agent is communicating from multiple geographically dispersed locations. This makes it easier to detect abnormal communications by considering the geographical location information of the source and destination of communications. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, when collecting the content of agent communications, the data collection unit can input geographical location information into AI and have the AI ​​perform the detection of abnormal communications.

[0049] The collection unit can apply different collection methods depending on the type of communication when collecting agent communication content. For example, in the case of an API call, the collection unit can collect the content of the request and response. For example, in the case of message communication, the collection unit can collect the content of the message and its destination. In the case of file input / output, the collection unit can also collect the content of the file and its operation history. This enables efficient data collection by applying different collection methods depending on the type of communication. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, when collecting agent communication content, the collection unit can input the type of communication into the AI ​​and have the AI ​​execute the appropriate collection method.

[0050] The analysis unit can perform more accurate analysis by considering the context of the agent's communication content during the analysis. For example, if the agent is performing a specific task, the analysis unit will consider the context of that task during the analysis. For example, if the agent is making multiple communications, the analysis unit can consider the relationships between those communications during the analysis. Furthermore, if the agent is exhibiting abnormal behavior, the analysis unit can also consider the background of that behavior during the analysis. This makes it possible to perform more accurate analysis by considering the context of the agent's communication content. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the context of the agent's communication content into the AI ​​and have the AI ​​perform a more accurate analysis.

[0051] The analysis unit can apply different analysis algorithms depending on the category of the agent's communication content during analysis. For example, if the agent is making an API call, the analysis unit can apply an algorithm to analyze the content of the request and response. For example, if the agent is communicating messages, the analysis unit can apply an algorithm to analyze the content of those messages. Furthermore, if the agent is performing file input / output, the analysis unit can apply an algorithm to analyze the content of those files. By applying different analysis algorithms depending on the category of the communication content, the accuracy of the analysis is improved. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of the agent's communication content into the AI ​​and have the AI ​​execute an appropriate analysis algorithm.

[0052] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0053] The collection unit can consider the geographical location information of the source and destination of communications when collecting agent communications. For example, if an agent is communicating from an unusual geographical location, the collection unit can collect that communications. Also, if an agent is sending a large amount of data from a specific region, the collection unit can collect that communications. Furthermore, if an agent is communicating from multiple geographically dispersed locations, the collection unit can collect that communications. This makes it easier to detect abnormal communications by considering the geographical location information of the source and destination of communications. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, when collecting agent communications, the collection unit can input geographical location information into the AI ​​and have the AI ​​perform the detection of abnormal communications.

[0054] The analysis unit can perform more accurate analysis by considering the context of the agent's communication content during the analysis. For example, if the agent is performing a specific task, the analysis can consider the context of that task. Also, if the agent is making multiple communications, the analysis can consider the relationships between those communications. Furthermore, if the agent is exhibiting abnormal behavior, the analysis can consider the background of that behavior. In this way, considering the context of the agent's communication content enables more accurate analysis. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the context of the agent's communication content into the AI ​​and have the AI ​​perform a more accurate analysis.

[0055] The collection unit can apply different collection methods depending on the type of communication when collecting agent communication content. For example, in the case of an API call, it can collect the content of the request and response. In the case of message communication, it can collect the content of the message and the recipient. Furthermore, in the case of file input / output, it can collect the content of the file and the operation history. By applying different collection methods depending on the type of communication, efficient data collection becomes possible. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, when collecting agent communication content, the collection unit can input the type of communication into the AI ​​and have the AI ​​execute the appropriate collection method.

[0056] The collection unit can consider the geographical location information of the source and destination of communications when collecting agent communications. For example, if an agent is communicating from an unusual geographical location, the collection unit can collect that communications. Also, if an agent is sending a large amount of data from a specific region, the collection unit can collect that communications. Furthermore, if an agent is communicating from multiple geographically dispersed locations, the collection unit can collect that communications. This makes it easier to detect abnormal communications by considering the geographical location information of the source and destination of communications. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, when collecting agent communications, the collection unit can input geographical location information into the AI ​​and have the AI ​​perform the detection of abnormal communications.

[0057] The analysis unit can perform more accurate analysis by considering the context of the agent's communication content during the analysis. For example, if the agent is performing a specific task, the analysis can consider the context of that task. Also, if the agent is making multiple communications, the analysis can consider the relationships between those communications. Furthermore, if the agent is exhibiting abnormal behavior, the analysis can consider the background of that behavior. In this way, considering the context of the agent's communication content enables more accurate analysis. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the context of the agent's communication content into the AI ​​and have the AI ​​perform a more accurate analysis.

[0058] The collection unit can apply different collection methods depending on the type of communication when collecting agent communication content. For example, in the case of an API call, it can collect the content of the request and response. In the case of message communication, it can collect the content of the message and the recipient. Furthermore, in the case of file input / output, it can collect the content of the file and the operation history. By applying different collection methods depending on the type of communication, efficient data collection becomes possible. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, when collecting agent communication content, the collection unit can input the type of communication into the AI ​​and have the AI ​​execute the appropriate collection method.

[0059] The following briefly describes the processing flow for example form 1.

[0060] Step 1: The collection unit intercepts communications from other agents and collects data. The collection unit intercepts agent communications via a proxy server or middleware and collects data such as API calls, messages, and file input / output. For example, it intercepts API calls, messages, and file input / output sent and received by agents and collects their contents. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit uses natural language processing (NLP) technology to analyze the collected data and interpret the agent's conversations and commands. It can also learn and predict abnormal behavior patterns using machine learning algorithms. Step 3: The detection unit detects abnormal behavior based on the data analyzed by the analysis unit. The detection unit learns abnormal behavior patterns using machine learning algorithms and detects abnormal behavior. For example, it can detect an unusually large number of data requests, attempts at unauthorized system access, and abnormal communication patterns. Step 4: The notification unit notifies the user of the abnormal behavior detected by the detection unit. The notification unit uses a real-time notification system to immediately notify the user when abnormal behavior occurs. For example, it sends notifications to the user via a web or mobile application or email. Step 5: The response unit automatically takes corrective action in response to abnormal behavior notified by the notification unit. For example, when abnormal behavior is detected, it may block communications, issue warnings, or change system access permissions.

[0061] (Example of form 2) The agent management AI agent system according to an embodiment of the present invention is a system that monitors and controls the behavior of other agents in real time at the context level, in situations where the use of generative AI agents is increasing and users are using multiple agents simultaneously. This agent management AI agent system can analyze the inputs and outputs of agents to detect abnormal behavior, provide notifications to the user, and automatically take corrective actions. For example, the agent management AI agent system intercepts the communications of other agents via a proxy server or middleware and collects data. This includes API calls, messages, and file input / output sent and received by agents. Next, the agent management AI agent system analyzes the collected data using natural language processing (NLP) technology to interpret the content of agent conversations and commands. Furthermore, the agent management AI agent system learns and predicts abnormal behavior patterns using machine learning algorithms. For example, it can detect an unusually large number of data requests or attempts to access the system without authorization. Users can define custom policies to control agent behavior. Role-based access control (RBAC) can be applied to set agent-specific permissions and implement data masking and access restrictions for sensitive information. If abnormal behavior occurs, the user is immediately notified by the real-time notification system. Furthermore, the agent management AI agent system provides a dashboard in the form of a web or mobile application to visualize agent activity. Security and encryption are also enhanced, ensuring the safety of data transfer through TLS / SSL encryption and strengthening authentication procedures with technologies such as two-factor authentication (2FA) and biometric authentication. It also leverages Secure Enclave to enhance the security of sensitive data. This agent management AI agent system is compatible with various agents and uses standard protocols such as RESTful APIs and gRPC. A plugin architecture allows for easy addition of new agents and features, and its cloud-based service enhances scalability and availability.This allows the agent management AI agent system to enable users to safely and efficiently manage multiple agents.

[0062] The agent management AI agent system according to the embodiment comprises a collection unit, an analysis unit, a detection unit, a notification unit, and a response unit. The collection unit intercepts communications of other agents and collects data. The collection unit intercepts agent communications, for example, via a proxy server or middleware, and collects data such as API calls, messages, and file input / output. For example, the collection unit intercepts API calls sent and received by agents and collects their contents. The collection unit can also intercept messages sent and received by agents and collect their contents. Furthermore, the collection unit can intercept file input / output performed by agents and collect their contents. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit uses natural language processing (NLP) technology to analyze the collected data and interpret the agent's conversation content and commands. For example, the analysis unit uses natural language processing technology to analyze the collected data and interpret the agent's conversation content. The analysis unit can also use natural language processing technology to analyze the collected data and interpret the agent's commands. Furthermore, the analysis unit can analyze the collected data using machine learning algorithms to learn and predict abnormal behavior patterns. The detection unit detects abnormal behavior based on the data analyzed by the analysis unit. The detection unit can, for example, learn abnormal behavior patterns using machine learning algorithms and detect abnormal behavior. The detection unit can, for example, detect an unusually large number of data requests. The detection unit can also detect attempts at unauthorized system access. Furthermore, the detection unit can also detect abnormal communication patterns. The notification unit notifies the user of the abnormal behavior detected by the detection unit. The notification unit can, for example, use a real-time notification system to immediately notify the user when abnormal behavior occurs. The notification unit can, for example, send a real-time notification to the user when abnormal behavior occurs. The notification unit can also send a notification to the user via web or mobile application when abnormal behavior occurs. Furthermore, the notification unit can also send a notification to the user via email when abnormal behavior occurs. The response unit automatically takes countermeasures against the abnormal behavior notified by the notification unit.The response unit can, for example, block communication when abnormal behavior is detected. The response unit can, for example, issue a warning when abnormal behavior is detected. The response unit can also change the system's access permissions when abnormal behavior is detected. As a result, the agent management AI agent system according to this embodiment can monitor the communication of other agents in real time, detect abnormal behavior, and respond automatically.

[0063] The data collection unit intercepts communications from other agents and collects data. For example, the data collection unit intercepts agent communications via a proxy server or middleware and collects data such as API calls, messages, and file input / output. Specifically, the proxy server relays communications between agents and captures the content of those communications in the process. This allows for the acquisition of detailed information about API calls sent and received by agents. This includes, for example, API call parameters, request types, and response content. The data collection unit can also intercept messages sent and received by agents and collect their content. These messages include instructions between agents, status information, and error messages. Furthermore, the data collection unit can intercept file input / output performed by agents and collect their content. File input / output includes log files, configuration files, and data files, and analyzing this content allows for the understanding of the agent's operational status and signs of abnormalities. The data collection unit collects this data in real time and sends it to a central database. The database centrally manages the collected data and makes it accessible to the analysis and detection units. This allows the data collection unit to efficiently and effectively monitor agent communications and provide a foundation for understanding the overall system status. Furthermore, the data collection unit can flexibly set the data collection frequency and filtering conditions, enabling data collection tailored to specific situations and conditions. As a result, the data collection unit can reliably collect the necessary data while optimizing system performance.

[0064] The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit utilizes natural language processing (NLP) technology to analyze the collected data and interpret agent conversations and commands. Specifically, it uses NLP technology to analyze message content between agents and extract the intent and instructions of the conversation. For instance, it can identify specific commands or requests from messages sent by agents and interpret their content. Furthermore, the analysis unit can analyze the collected data using machine learning algorithms to learn and predict abnormal behavior patterns. Machine learning algorithms learn normal agent behavior patterns based on past data and build models to detect abnormal behavior. For example, if an agent makes API calls at an unusually high frequency or requests an unusually large amount of data, this can be detected as abnormal behavior. In addition, the analysis unit can analyze the collected data using statistical methods to evaluate agent behavior trends and performance. This allows the analysis unit to comprehensively understand the agent's behavior and perform early detection and prediction of abnormal behavior. Based on these analysis results, the analysis unit can provide appropriate information to the detection and notification units, thereby improving the overall reliability and security of the system.

[0065] The detection unit detects abnormal behavior based on data analyzed by the analysis unit. The detection unit learns abnormal behavior patterns using, for example, machine learning algorithms. Specifically, it uses a machine learning model to learn the normal operating patterns of agents and detect abnormal behavior in real time. For example, if an agent makes more data requests than usual, or if there is an attempt to gain unauthorized system access, this can be detected as abnormal behavior. The detection unit can also detect abnormal communication patterns. For example, if the communication frequency or content between agents differs from the norm, this can be detected as abnormal. Furthermore, the detection unit transmits the results of the abnormal behavior detection to the notification unit in real time, providing information for immediate countermeasures. This allows the detection unit to quickly and accurately detect abnormal agent behavior and play a crucial role in ensuring the overall system security. To improve the accuracy of abnormal behavior detection, the detection unit can continuously update its machine learning model and learn based on the latest data. This allows the detection unit to always respond to the latest threats and abnormal behaviors, maintaining system reliability.

[0066] The notification unit notifies the user of abnormal behavior detected by the detection unit. The notification unit immediately notifies the user when abnormal behavior occurs, for example, using a real-time notification system. Specifically, when abnormal behavior is detected, it can send a notification to the user via a web or mobile application. For example, it can send a push notification to the user's smartphone, providing detailed information about the abnormal behavior and recommended countermeasures. The notification unit can also send notifications to the user via email. The email includes detailed information such as the time the abnormal behavior occurred, the scope of its impact, and recommended countermeasures. Furthermore, the notification unit can also send notifications to the user via voice call or SMS when abnormal behavior occurs. This allows the notification unit to quickly and reliably inform the user of the occurrence of abnormal behavior and encourage appropriate action. The notification unit can collect user feedback and continuously improve the accuracy and effectiveness of the notification content. For example, based on user feedback, it can review the timing and content of notifications and adopt more effective notification methods. This allows the notification unit to provide users with quick and appropriate information and improve the reliability and security of the entire system.

[0067] The response unit automatically takes countermeasures against abnormal behavior notified by the notification unit. For example, when abnormal behavior is detected, the response unit may block communication. Specifically, it may temporarily suspend communication from the agent exhibiting abnormal behavior to minimize the impact on the entire system. The response unit may also issue a warning when abnormal behavior is detected. For example, it may send a warning message to the system administrator to encourage a prompt response. Furthermore, the response unit may change system access permissions when abnormal behavior is detected. For example, it may restrict the access permissions of the agent that exhibited abnormal behavior to prevent unauthorized operations or data leaks. By automatically executing these countermeasures, the response unit achieves a rapid and effective response to abnormal behavior. In addition, the response unit can record the results of the countermeasures and use them for subsequent analysis and improvement. For example, it can save logs of the countermeasures to analyze the causes of the abnormal behavior and the effectiveness of the countermeasures. This allows the response unit to play a crucial role in improving the overall security and reliability of the system. The response unit can continuously review its countermeasures against abnormal behavior and take optimal measures to address the latest threats and risks. This allows the support unit to maintain system security and provide users with a safe and reliable environment.

[0068] The policy section can define custom policies. The policy section provides, for example, an interface for users to define custom policies. The policy section allows users to set custom policies to control agent behavior. The policy section also allows users to edit custom policies to control agent behavior. Furthermore, the policy section allows users to delete custom policies to control agent behavior. This allows users to control agent behavior by defining custom policies. Some or all of the above processes in the policy section may be performed using AI, or not. For example, the policy section can input user-defined custom policies into the AI, which can then automatically adjust the scope of the policy's application.

[0069] The access control unit can apply role-based access control. For example, the access control unit provides an interface for users to set agent-specific permissions. The access control unit allows users to set agent-specific permissions, edit agent-specific permissions, and delete agent-specific permissions. This allows agent-specific permissions to be set by applying role-based access control. Some or all of the above processes in the access control unit may be performed using AI, or not. For example, the access control unit can input user-defined agent-specific permissions into the AI, which can then automatically adjust the scope of those permissions.

[0070] The masking unit can perform data masking. For example, the masking unit implements data masking for confidential information. For example, the masking unit applies an algorithm for masking confidential information. The masking unit can also set rules for masking confidential information. Furthermore, the masking unit can apply a policy for masking confidential information. This enhances the protection of confidential information through data masking. Some or all of the above processing in the masking unit may be performed using AI, for example, or without AI. For example, the masking unit can input an algorithm for masking confidential information into an AI, which can then automatically adjust the scope of masking.

[0071] The notification system unit can provide a real-time notification system. For example, the notification system unit can immediately send a notification to the user when abnormal behavior occurs. The notification system unit can provide an interface for sending notifications to the user in real time. The notification system unit can also send notifications to the user via a web or mobile application when abnormal behavior occurs. Furthermore, the notification system unit can send notifications to the user via email when abnormal behavior occurs. By providing a real-time notification system, the system can immediately notify the user when abnormal behavior occurs. Some or all of the above processing in the notification system unit may be performed using AI, for example, or without AI. For example, the notification system unit can send notifications using an AI model for sending notifications to the user in real time when abnormal behavior occurs.

[0072] The dashboard unit can provide a dashboard. The dashboard unit can, for example, provide an interface for visualizing agent activity. The dashboard unit can, for example, display data for visualizing agent activity. The dashboard unit can also display graphs and charts for visualizing agent activity. Furthermore, the dashboard unit can generate reports for visualizing agent activity. In this way, agent activity can be visualized by providing a dashboard. Some or all of the above processing in the dashboard unit may be performed using AI, for example, or not using AI. For example, the dashboard unit can input agent activity data into AI, and the AI ​​can automatically visualize the data.

[0073] The encryption unit can perform TLS / SSL encryption. For example, the encryption unit applies TLS / SSL encryption to ensure the security of data transfer. For example, the encryption unit uses a certificate to apply TLS / SSL encryption during data transfer. The encryption unit can also configure a protocol to apply TLS / SSL encryption during data transfer. Furthermore, the encryption unit can apply a security policy to apply TLS / SSL encryption during data transfer. This ensures the security of data transfer by performing TLS / SSL encryption. Some or all of the above processing in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input a certificate to apply TLS / SSL encryption during data transfer into the AI, and the AI ​​can automatically manage the certificate.

[0074] The authentication unit can perform two-factor authentication or biometric authentication. For example, the authentication unit can apply two-factor authentication to strengthen the authentication procedure. For example, the authentication unit can provide an interface for applying two-factor authentication when a user logs in. The authentication unit can also provide an interface for applying biometric authentication when a user logs in. Furthermore, the authentication unit can apply a combination of two-factor authentication and biometric authentication when a user logs in. This strengthens the authentication procedure by performing two-factor authentication or biometric authentication. Some or all of the above processing in the authentication unit may be performed using AI, for example, or without AI. For example, the authentication unit can automatically perform the authentication procedure using an AI model for applying two-factor authentication when a user logs in.

[0075] The security department can utilize secure enclaves. For example, the security department can apply secure enclaves to enhance the security of confidential data. For example, the security department can store confidential data within a secure enclave. The security department can also process confidential data within a secure enclave. Furthermore, the security department can encrypt confidential data within a secure enclave. Thus, the security of confidential data is enhanced by utilizing secure enclaves. Some or all of the above-described processes in the security department may be performed using AI, for example, or not using AI. For example, the security department can automate data management using an AI model for storing confidential data within a secure enclave.

[0076] The compatibility unit can use RESTful APIs or gRPC. For example, the compatibility unit uses RESTful APIs to ensure compatibility with various agents. For example, the compatibility unit provides an interface for agents to communicate using RESTful APIs. The compatibility unit can also provide an interface for agents to communicate using gRPC. Furthermore, the compatibility unit can provide an interface for agents to communicate using both RESTful APIs and gRPC. This ensures compatibility with various agents by using RESTful APIs and gRPC. Some or all of the above processing in the compatibility unit may be performed using AI, for example, or not using AI. For example, the compatibility unit can automatically manage communication using an AI model for agents to communicate using RESTful APIs.

[0077] The plugin section can provide a plugin architecture. For example, the plugin section can provide a plugin architecture for easily adding new agents or functions. For example, the plugin section can provide an interface for users to add new agents. The plugin section can also provide an interface for users to add new functions. Furthermore, the plugin section can provide an interface for users to extend existing agents or functions. This allows for easy addition of new agents and functions by providing a plugin architecture. Some or all of the above-described processes in the plugin section may be performed using AI, for example, or without AI. For example, the plugin section can automatically add agents using an AI model for users to add new agents.

[0078] The Cloud Division can provide services on a cloud basis. The Cloud Division, for example, provides the infrastructure for providing services on a cloud basis. The Cloud Division, for example, provides services using a cloud platform. The Cloud Division can also ensure scalability for providing services on a cloud basis. Furthermore, the Cloud Division can ensure availability for providing services on a cloud basis. This increases scalability and availability by providing services on a cloud basis. Some or all of the above processes in the Cloud Division may be performed using AI, for example, or not using AI. For example, the Cloud Division can automate service management using an AI model for providing services using a cloud platform.

[0079] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. For example, if the user is stressed, the data collection unit can reduce the frequency of data collection to alleviate the burden. For example, if the user is relaxed, the data collection unit can increase the frequency of data collection to collect more detailed information. The data collection unit can also prioritize the collection of only important data if the user is in a hurry. This reduces the burden on the user by adjusting the timing of data collection according to their 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 data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI adjust the timing of data collection.

[0080] The data collection unit can analyze the agent's communication content in real time and quickly identify abnormal communication patterns. For example, if an agent is sending a large amount of data that is different from the usual, the data collection unit can quickly identify that communication content. For example, if an agent is attempting to gain unauthorized system access, the data collection unit can quickly identify that communication content. The data collection unit can also quickly identify the communication content if an agent is communicating during an abnormal time period. In this way, abnormal communication patterns can be quickly identified by analyzing the agent's communication content in real time. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can automatically collect abnormal communication patterns using an AI model for analyzing the agent's communication content in real time.

[0081] The data collection unit can dynamically change the types of data it collects and collect only the necessary data depending on the specific situation. For example, if an agent is handling confidential information, the data collection unit will collect only the content of that communication. For example, if an agent is sending a large amount of data, the data collection unit can collect only the important data. Furthermore, if an agent is exhibiting abnormal behavior, the data collection unit can collect only the data related to that behavior. This enables efficient data collection by collecting only the necessary data depending on the specific situation. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can automatically collect the necessary data using an AI model for analyzing the agent's communication content in real time.

[0082] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated emotions. For example, if the user is stressed, the data collection unit can prioritize collecting only important data. If the user is relaxed, the data collection unit can prioritize collecting detailed data. If the user is in a hurry, the data collection unit can also prioritize collecting data that can be collected quickly. In this way, important data can be prioritized by determining the priority of data to collect according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI determine the priority of the data.

[0083] The data collection unit can consider the geographical location information of the source and destination of communications when collecting the content of agent communications. For example, the data collection unit can collect the content of communications if an agent is communicating from an unusual geographical location. For example, the data collection unit can collect the content of communications if an agent is sending a large amount of data from a specific region. Furthermore, the data collection unit can collect the content of communications if an agent is communicating from multiple geographically dispersed locations. This makes it easier to detect abnormal communications by considering the geographical location information of the source and destination of communications. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, when collecting the content of agent communications, the data collection unit can input geographical location information into AI and have the AI ​​perform the detection of abnormal communications.

[0084] The collection unit can apply different collection methods depending on the type of communication when collecting agent communication content. For example, in the case of an API call, the collection unit can collect the content of the request and response. For example, in the case of message communication, the collection unit can collect the content of the message and its destination. In the case of file input / output, the collection unit can also collect the content of the file and its operation history. This enables efficient data collection by applying different collection methods depending on the type of communication. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, when collecting agent communication content, the collection unit can input the type of communication into the AI ​​and have the AI ​​execute the appropriate collection method.

[0085] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is nervous, the analysis unit can provide a simple and highly visible display method. For example, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that gets straight to the point. By adjusting the display method of the analysis results according to the user's emotions, it becomes possible to provide a display that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's emotion data into the generative AI and have the generative AI adjust the display method of the analysis results.

[0086] The analysis unit can perform more accurate analysis by considering the context of the agent's communication content during the analysis. For example, if the agent is performing a specific task, the analysis unit will consider the context of that task during the analysis. For example, if the agent is making multiple communications, the analysis unit can consider the relationships between those communications during the analysis. Furthermore, if the agent is exhibiting abnormal behavior, the analysis unit can also consider the background of that behavior during the analysis. This makes it possible to perform more accurate analysis by considering the context of the agent's communication content. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the context of the agent's communication content into the AI ​​and have the AI ​​perform a more accurate analysis.

[0087] The analysis unit can apply different analysis algorithms depending on the category of the agent's communication content during analysis. For example, if the agent is making an API call, the analysis unit can apply an algorithm to analyze the content of the request and response. For example, if the agent is communicating messages, the analysis unit can apply an algorithm to analyze the content of those messages. Furthermore, if the agent is performing file input / output, the analysis unit can apply an algorithm to analyze the content of those files. By applying different analysis algorithms depending on the category of the communication content, the accuracy of the analysis is improved. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of the agent's communication content into the AI ​​and have the AI ​​execute an appropriate analysis algorithm.

[0088] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0089] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, a simple and highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that gets straight to the point can be provided. In this way, by adjusting the display method of the analysis results according to the user's emotions, a display that is easy for the user to understand can be made. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the display method of the analysis results.

[0090] The collection unit can consider the geographical location information of the source and destination of communications when collecting agent communications. For example, if an agent is communicating from an unusual geographical location, the collection unit can collect that communications. Also, if an agent is sending a large amount of data from a specific region, the collection unit can collect that communications. Furthermore, if an agent is communicating from multiple geographically dispersed locations, the collection unit can collect that communications. This makes it easier to detect abnormal communications by considering the geographical location information of the source and destination of communications. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, when collecting agent communications, the collection unit can input geographical location information into the AI ​​and have the AI ​​perform the detection of abnormal communications.

[0091] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated emotions. For example, if the user is stressed, only important data can be prioritized for collection. If the user is relaxed, detailed data can be prioritized for collection. Furthermore, if the user is in a hurry, data that can be collected quickly can be prioritized for collection. In this way, important data can be prioritized by determining the priority of data to collect according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, or not using AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI determine the priority of the data.

[0092] The analysis unit can perform more accurate analysis by considering the context of the agent's communication content during the analysis. For example, if the agent is performing a specific task, the analysis can consider the context of that task. Also, if the agent is making multiple communications, the analysis can consider the relationships between those communications. Furthermore, if the agent is exhibiting abnormal behavior, the analysis can consider the background of that behavior. In this way, considering the context of the agent's communication content enables more accurate analysis. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the context of the agent's communication content into the AI ​​and have the AI ​​perform a more accurate analysis.

[0093] The collection unit can apply different collection methods depending on the type of communication when collecting agent communication content. For example, in the case of an API call, it can collect the content of the request and response. In the case of message communication, it can collect the content of the message and the recipient. Furthermore, in the case of file input / output, it can collect the content of the file and the operation history. By applying different collection methods depending on the type of communication, efficient data collection becomes possible. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, when collecting agent communication content, the collection unit can input the type of communication into the AI ​​and have the AI ​​execute the appropriate collection method.

[0094] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, a simple and highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that gets straight to the point can be provided. In this way, by adjusting the display method of the analysis results according to the user's emotions, a display that is easy for the user to understand can be made. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the display method of the analysis results.

[0095] The collection unit can consider the geographical location information of the source and destination of communications when collecting agent communications. For example, if an agent is communicating from an unusual geographical location, the collection unit can collect that communications. Also, if an agent is sending a large amount of data from a specific region, the collection unit can collect that communications. Furthermore, if an agent is communicating from multiple geographically dispersed locations, the collection unit can collect that communications. This makes it easier to detect abnormal communications by considering the geographical location information of the source and destination of communications. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, when collecting agent communications, the collection unit can input geographical location information into the AI ​​and have the AI ​​perform the detection of abnormal communications.

[0096] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated emotions. For example, if the user is stressed, only important data can be prioritized for collection. If the user is relaxed, detailed data can be prioritized for collection. Furthermore, if the user is in a hurry, data that can be collected quickly can be prioritized for collection. In this way, important data can be prioritized by determining the priority of data to collect according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, or not using AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI determine the priority of the data.

[0097] The analysis unit can perform more accurate analysis by considering the context of the agent's communication content during the analysis. For example, if the agent is performing a specific task, the analysis can consider the context of that task. Also, if the agent is making multiple communications, the analysis can consider the relationships between those communications. Furthermore, if the agent is exhibiting abnormal behavior, the analysis can consider the background of that behavior. In this way, considering the context of the agent's communication content enables more accurate analysis. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the context of the agent's communication content into the AI ​​and have the AI ​​perform a more accurate analysis.

[0098] The collection unit can apply different collection methods depending on the type of communication when collecting agent communication content. For example, in the case of an API call, it can collect the content of the request and response. In the case of message communication, it can collect the content of the message and the recipient. Furthermore, in the case of file input / output, it can collect the content of the file and the operation history. By applying different collection methods depending on the type of communication, efficient data collection becomes possible. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, when collecting agent communication content, the collection unit can input the type of communication into the AI ​​and have the AI ​​execute the appropriate collection method.

[0099] The following briefly describes the processing flow for example form 2.

[0100] Step 1: The collection unit intercepts communications from other agents and collects data. The collection unit intercepts agent communications via a proxy server or middleware and collects data such as API calls, messages, and file input / output. For example, it intercepts API calls, messages, and file input / output sent and received by agents and collects their contents. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit uses natural language processing (NLP) technology to analyze the collected data and interpret the agent's conversations and commands. It can also learn and predict abnormal behavior patterns using machine learning algorithms. Step 3: The detection unit detects abnormal behavior based on the data analyzed by the analysis unit. The detection unit learns abnormal behavior patterns using machine learning algorithms and detects abnormal behavior. For example, it can detect an unusually large number of data requests, attempts at unauthorized system access, and abnormal communication patterns. Step 4: The notification unit notifies the user of the abnormal behavior detected by the detection unit. The notification unit uses a real-time notification system to immediately notify the user when abnormal behavior occurs. For example, it sends notifications to the user via a web or mobile application or email. Step 5: The response unit automatically takes corrective action in response to abnormal behavior notified by the notification unit. For example, when abnormal behavior is detected, it may block communications, issue warnings, or change system access permissions.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] Each of the multiple elements described above, including the collection unit, analysis unit, detection unit, notification unit, response unit, policy unit, access control unit, masking unit, notification system unit, dashboard unit, encryption unit, authentication unit, security unit, compatibility unit, plug-in unit, and cloud unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the processor 46 of the smart device 14 and collects data by intercepting agent communications. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The detection unit is implemented by the specific processing unit 290 of the data processing unit 12 and detects abnormal behavior. The notification unit is implemented by the control unit 46A of the smart device 14 and notifies the user of abnormal behavior. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically takes countermeasures against abnormal behavior. The policy unit is implemented by the control unit 46A of the smart device 14 and defines custom policies. The access control unit is implemented by the specific processing unit 290 of the data processing device 12 and applies role-based access control. The masking unit is implemented by the specific processing unit 290 of the data processing device 12 and performs data masking. The notification system unit is implemented by the control unit 46A of the smart device 14 and provides a real-time notification system. The dashboard unit is implemented by the control unit 46A of the smart device 14 and provides a dashboard. The encryption unit is implemented by the specific processing unit 290 of the data processing device 12 and performs TLS / SSL encryption. The authentication unit is implemented by the control unit 46A of the smart device 14 and performs two-factor authentication or biometric authentication. The security unit is implemented by the specific processing unit 290 of the data processing device 12 and utilizes a secure enclave. The compatibility unit is implemented by the control unit 46A of the smart device 14 and uses RESTful APIs and gRPC. The plug-in unit is implemented by the control unit 46A of the smart device 14 and provides a plug-in architecture. The cloud unit is implemented by the specific processing unit 290 of the data processing device 12 and provides services on a cloud basis. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0105] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] Each of the multiple elements described above, including the collection unit, analysis unit, detection unit, notification unit, response unit, policy unit, access control unit, masking unit, notification system unit, dashboard unit, encryption unit, authentication unit, security unit, compatibility unit, plug-in unit, and cloud unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the processor 46 of the smart glasses 214 and collects data by intercepting agent communications. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The detection unit is implemented by the specific processing unit 290 of the data processing unit 12 and detects abnormal behavior. The notification unit is implemented by the control unit 46A of the smart glasses 214 and notifies the user of abnormal behavior. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically takes countermeasures against abnormal behavior. The policy unit is implemented by the control unit 46A of the smart glasses 214 and defines custom policies. The access control unit is implemented by the specific processing unit 290 of the data processing device 12 and applies role-based access control. The masking unit is implemented by the specific processing unit 290 of the data processing device 12 and performs data masking. The notification system unit is implemented by the control unit 46A of the smart glasses 214 and provides a real-time notification system. The dashboard unit is implemented by the control unit 46A of the smart glasses 214 and provides a dashboard. The encryption unit is implemented by the specific processing unit 290 of the data processing device 12 and performs TLS / SSL encryption. The authentication unit is implemented by the control unit 46A of the smart glasses 214 and performs two-factor authentication or biometric authentication. The security unit is implemented by the specific processing unit 290 of the data processing device 12 and utilizes a secure enclave. The compatibility unit is implemented by the control unit 46A of the smart glasses 214 and uses RESTful APIs and gRPC. The plug-in unit is implemented by the control unit 46A of the smart glasses 214 and provides a plug-in architecture. The cloud section is implemented by the specific processing unit 290 of the data processing device 12 and provides services on a cloud-based basis. The correspondence between each section and the device or control unit is not limited to the example described above and can be modified in various ways.

[0121] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] Each of the multiple elements described above, including the collection unit, analysis unit, detection unit, notification unit, response unit, policy unit, access control unit, masking unit, notification system unit, dashboard unit, encryption unit, authentication unit, security unit, compatibility unit, plug-in unit, and cloud unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the processor 46 of the headset terminal 314 and collects data by intercepting agent communications. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The detection unit is implemented by the specific processing unit 290 of the data processing unit 12 and detects abnormal behavior. The notification unit is implemented by the control unit 46A of the headset terminal 314 and notifies the user of abnormal behavior. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically takes countermeasures against abnormal behavior. The policy unit is implemented by the control unit 46A of the headset terminal 314 and defines custom policies. The access control unit is implemented by the specific processing unit 290 of the data processing device 12 and applies role-based access control. The masking unit is implemented by the specific processing unit 290 of the data processing device 12 and performs data masking. The notification system unit is implemented by the control unit 46A of the headset terminal 314 and provides a real-time notification system. The dashboard unit is implemented by the control unit 46A of the headset terminal 314 and provides a dashboard. The encryption unit is implemented by the specific processing unit 290 of the data processing device 12 and performs TLS / SSL encryption. The authentication unit is implemented by the control unit 46A of the headset terminal 314 and performs two-factor authentication or biometric authentication. The security unit is implemented by the specific processing unit 290 of the data processing device 12 and utilizes a secure enclave. The compatibility unit is implemented by the control unit 46A of the headset terminal 314 and uses RESTful APIs and gRPC. The plug-in unit is implemented by the control unit 46A of the headset terminal 314 and provides a plug-in architecture. The cloud section is implemented by the specific processing unit 290 of the data processing device 12 and provides services on a cloud-based basis.The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0137] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0138] 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.

[0139] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0140] The 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.

[0141] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS 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).

[0143] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] Each of the multiple elements described above, including the collection unit, analysis unit, detection unit, notification unit, response unit, policy unit, access control unit, masking unit, notification system unit, dashboard unit, encryption unit, authentication unit, security unit, compatibility unit, plug-in unit, and cloud unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the processor 46 of the robot 414 and collects data by intercepting agent communications. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The detection unit is implemented by the specific processing unit 290 of the data processing unit 12 and detects abnormal behavior. The notification unit is implemented by the control unit 46A of the robot 414 and notifies the user of abnormal behavior. The response unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically takes countermeasures against abnormal behavior. The policy unit is implemented by the control unit 46A of the robot 414 and defines custom policies. The access control unit is implemented by the specific processing unit 290 of the data processing device 12 and applies role-based access control. The masking unit is implemented by the specific processing unit 290 of the data processing device 12 and performs data masking. The notification system unit is implemented by the control unit 46A of the robot 414 and provides a real-time notification system. The dashboard unit is implemented by the control unit 46A of the robot 414 and provides a dashboard. The encryption unit is implemented by the specific processing unit 290 of the data processing device 12 and performs TLS / SSL encryption. The authentication unit is implemented by the control unit 46A of the robot 414 and performs two-factor authentication or biometric authentication. The security unit is implemented by the specific processing unit 290 of the data processing device 12 and utilizes a secure enclave. The compatibility unit is implemented by the control unit 46A of the robot 414 and uses RESTful APIs and gRPC. The plug-in unit is implemented by the control unit 46A of the robot 414 and provides a plug-in architecture. The cloud unit is implemented by the specific processing unit 290 of the data processing device 12 and provides services on a cloud basis. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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."

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] (Note 1) A collection unit that intercepts communications from other agents and collects data, An analysis unit analyzes the data collected by the aforementioned collection unit, A detection unit detects abnormal behavior based on the data analyzed by the aforementioned analysis unit, A notification unit that notifies the user of abnormal behavior detected by the detection unit, The system includes a response unit that automatically takes countermeasures in response to abnormal behavior notified by the notification unit. A system characterized by the following features. (Note 2) It includes a policy section for defining custom policies. The system described in Appendix 1, characterized by the features described herein. (Note 3) The system includes an access control unit that applies role-based access control. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a masking section for performing data masking. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes a notification system unit that provides a real-time notification system. The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes a dashboard section that provides the dashboard. The system described in Appendix 1, characterized by the features described herein. (Note 7) It is equipped with an encryption unit that performs TLS / SSL encryption. The system described in Appendix 1, characterized by the features described herein. (Note 8) It is equipped with an authentication unit that performs two-factor authentication and biometric authentication. The system described in Appendix 1, characterized by the features described herein. (Note 9) The security department utilizes a secure enclave. The system described in Appendix 1, characterized by the features described herein. (Note 10) It includes a compatibility section that uses RESTful APIs and gRPC. The system described in Appendix 1, characterized by the features described herein. (Note 11) It includes a plugin section that provides a plugin architecture. The system described in Appendix 1, characterized by the features described herein. (Note 12) It has a cloud division that provides cloud-based services. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned collection unit is The system analyzes agent communications in real time and promptly detects abnormal communication patterns. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned collection unit is Dynamically change the types of data collected, and collect only the data necessary depending on the specific situation. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned collection unit is When collecting agent communications, consider the geographical location information of the source and destination of the communications. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned collection unit is When collecting agent communications, different collection methods are applied depending on the type of communication. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, During analysis, the context of the agent's communication content is taken into consideration to perform a more accurate analysis. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the agent's communication content. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0173] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A collection unit that intercepts communications from other agents and collects data, An analysis unit analyzes the data collected by the aforementioned collection unit, A detection unit detects abnormal behavior based on the data analyzed by the aforementioned analysis unit, A notification unit that notifies the user of abnormal behavior detected by the detection unit, The system includes a response unit that automatically takes countermeasures in response to abnormal behavior notified by the notification unit. A system characterized by the following features.

2. It includes a policy section for defining custom policies. The system according to feature 1.

3. The system includes an access control unit that applies role-based access control. The system according to feature 1.

4. It includes a masking section for performing data masking. The system according to feature 1.

5. It includes a notification system unit that provides a real-time notification system. The system according to feature 1.

6. It includes a dashboard section that provides the dashboard. The system according to feature 1.

7. It is equipped with an encryption unit that performs TLS / SSL encryption. The system according to feature 1.

8. It is equipped with an authentication unit that performs two-factor authentication and biometric authentication. The system according to feature 1.

Images