Artificial intelligence agent system for mobile operating system and operating method of the artificial intelligence agent system

A non-transitory computer-readable storage medium having recorded thereon a computer program for executing an operating method of an artificial intelligence system on a computer device,

• wherein the artificial intelligence agent system comprises an agent runtime environment, an agent communication layer, and an agent security manager, and
• wherein the operating method comprises:
• receiving a processing request for an identified task from an application that receives a user request and identifies a task requiring agent operation, at the agent communication layer, the processing request being received from the application via an agent development tool, and the agent development tool normalizing the processing request into a standardized format, attaching a security token and authentication information required for the processing request to the processing request, collecting context information required for execution of the task, and packaging the normalized processing request, the security token, the authentication information, and the context information into a message format to pass to the agent communication layer;
• verifying permission for the processing request via the agent security manager, at the agent runtime environment;
• processing the task by invoking at least one agent based on a mobile operating system for the processing request for which the permission has been verified, at the agent runtime environment, the at least one agent being invoked as a process executing within the mobile operating system by executing a system call to a kernel module of the mobile operating system;
• and
• transmitting a result of the task processing to the application via the agent communication layer, at the agent runtime environment,
• wherein the processing the task comprises:
• dynamically setting a resource allocation limit comprising CPU and memory usage for the invoked at least one agent based on a real-time system load and a battery state of the mobile operating system;
• monitoring an execution status of the invoked at least one agent against the resource allocation limit;
• and
• detecting and cleaning up the invoked at least one agent as an abnormal agent process in response to the invoked at least one agent exceeding the resource allocation limit.

An artificial intelligence agent system, comprising:

• at least one processor;
• and
• a memory coupled to the at least one processor, the memory storing instructions that, when executed by the at least one processor, cause the artificial intelligence agent system to implement:
• an agent communication layer for receiving a processing request for an identified task from an application that receives a user request and identifies a task requiring agent operation, the processing request being received from the application via an agent development tool, and the agent development tool normalizing the processing request into a standardized format, attaching a security token and authentication information required for the processing request to the processing request, collecting context information required for execution of the task, and packaging the normalized processing request, the security token, the authentication information, and the context information into a message format to pass to the agent communication layer;
• an agent runtime environment for verifying permission for the processing request via an agent security manager, processing the task by invoking at least one agent based on a mobile operating system for the processing request for which the permission has been verified, the at least one agent being invoked as a process executing within the mobile operating system by executing a system call to a kernel module of the mobile operating system, and transmitting a result of the task processing to the application via the agent communication layer, and
• the agent security manager for managing permission of the task and permission of the at least one agent,
• wherein the processing the task by the agent runtime environment comprises:
• dynamically setting a resource allocation limit comprising CPU and memory usage for the invoked at least one agent based on a real-time system load and a battery state of the mobile operating system;
• monitoring an execution status of the invoked at least one agent against the resource allocation limit;
• and
• detecting and cleaning up the invoked at least one agent as an abnormal agent process in response to the invoked at least one agent exceeding the resource allocation limit.