# US 2025/0165296 A1 · System for artificial intelligence agent and method of operation of the system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0165296 A1
- Document ID: US20250165296A1
- Status: Published application
- Kind: A1
- Application number: 18/950,323
- Filed: 2024-11-18
- Published: 2025-05-22
- Earliest claimed: 2023-11-16
- Assignees: Piamond Corp.
- Applicants: Piamond Corp.
- Inventors: Doo Geon HWANG
- Web page: https://patentgrep.com/patent/US20250165296A1

## CPC

- G06F 9/5027: {the resource being a machine, e.g. CPUs, Servers, Terminals}
- G06F 9/4843: {by program, e.g. task dispatcher, supervisor, operating system}
- G06F 9/5005: {to service a request}
- G06F 9/5038: {considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration (scheduling strategies G06F9/4881 and subgroups)}
- G06F 9/5044: {considering hardware capabilities}
- G06F 9/5055: {considering software capabilities, i.e. software resources associated or available to the machine}
- G06F 9/542: {Event management; Broadcasting; Multicasting; Notifications}
- G06F 21/53: by executing in a restricted environment, e.g. sandbox or secure virtual machine
- G06F 40/30: Semantic analysis
- H04L 9/32: including means for verifying the identity or authority of a user of the system {or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials}
- G06F 2209/5015: Service provider selection
- G06F 2209/5017: Task decomposition
- G06F 2209/509: Offload
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Disclosed are a system for an artificial intelligence agent and an operating method thereof. An operating method of a mobile-centric agent hub system (MCAHS) may include registering and authenticating AI agents included in an external device, determining a task by analyzing an instruction received from a user, selecting an AI agent for processing the determined task, among the registered AI agents, transmitting the determined task to the selected AI agent, receiving the results of processing of the transferred task from the selected AI agent, and providing a final response generated based on the received results of the processing to the user.

## Claims

### Claim 1

An operating method of a mobile-centric agent hub system (MCAHS) implemented with computer device comprising at least one processor, the operating method comprising:
registering and authenticating, by the at least one processor, AI agents included in an external device;
determining, by the at least one processor, a task by analyzing an instruction received from a user;
selecting, by the at least one processor, an AI agent for processing the determined task, among the registered AI agents;
transmitting, by the at least one processor, the determined task to the selected AI agent;
receiving, by the at least one processor, results of processing of the transferred task from the selected AI agent; and
providing, by the at least one processor, a final response generated based on the received results of the processing to the user.

### Claim 2 (depends on 1)

The operating method of claim 1, wherein:
the determining of the task comprises determining a plurality of tasks for the processing of the instruction,
the selecting of the AI agent comprises selecting a plurality of AI agents for processing the plurality of tasks,
the receiving of the results of the processing comprises receiving a plurality of processing results from the plurality of AI agents, and
the providing of the final response to the user comprises generating the final response based on integrated results of the plurality of processing results and providing the final response to the user.

### Claim 3 (depends on 1)

The operating method of claim 1, wherein:
the selecting of the AI agent comprises selecting a plurality of AI agents for processing the determined task,
the receiving of the results of the processing comprises receiving a plurality of processing results from the plurality of AI agents, and
the providing of the final response to the user comprises selecting one of the plurality of processing results, generating a final response based on the selected processing result, and providing the final response to the user.

### Claim 4 (depends on 1)

The operating method of claim 1, further comprising monitoring, by the at least one processor, a state of the registered AI agent, wherein the selecting of the AI agent comprises selecting an AI agent for processing the determined task based on the monitored state of the AI agent.

### Claim 5 (depends on 1)

The operating method of claim 1, wherein the registering and authenticating of the AI agent comprises:
issuing an authentication token by identifying an identity of the AI agent of the external device that requests a connection through an application programming interface (API) gateway included in the MCAHS;
validating a service that is providable by the AI agent of the external device by receiving service specifications comprising detailed information of the service and the authentication token;
registering the service with a service catalog when the validation of the service is completed and setting access rights and a security policy for the registered service; and
transmitting a registration completion message comprising a unique identifier of the service and an access token to the AI agent of the external device,
wherein the service specifications comprises information on at least one of a name of the service, the unique identifier of the service, a category of the service, a list of functions supported by the service, a description of the functions, a format of an input parameter of the service, a format of a return value of the service, a quality index of the service, rights and an access level required for the service, a version of the service, and an update history of the service.

### Claim 6 (depends on 1)

The operating method of claim 1, wherein the selecting of the AI agent comprises:
generating a list of AI agents corresponding to a service area of the task;
aligning the list of AI agents based on preset priority; and
selecting a preset number of AI agents from a highest priority of the list,
wherein the preset priority comprises static priority and dynamic priority,
the static priority comprises at least one of basic priority that is set based on user preference and priority according to a service quality index, and
the dynamic priority comprises at least one of priority based on results of real-time performance monitoring, priority based on an analysis of a recent use pattern of the user for an AI agent, and adaptive priority that is set based on context.

### Claim 7 (depends on 1)

The operating method of claim 1, wherein:
the computer device comprises a mobile device of the user, and
the operating method of the MCAHS is performed by the at least one processor under a control of an AI agent that is provided by an operating platform supplier of the mobile device.

### Claim 8 (depends on 1)

The operating method of claim 1, wherein the determining of the task comprises:
determining an intent of the instruction;
determining a domain of the instruction;
analyzing context associated with the instruction;
generating a feature vector based on the determined intent, the determined domain, and information extracted from the determined context;
predicting a type of the instruction by inputting the generated feature vector to a pre-trained machine learning model; and
determining the task based on synthesized results of the determined intent, the determined domain, the determined context, and the predicted type,
wherein the determining of the task based on the synthesized results comprises:
calculating a confidence score of the synthesized results;
comparing the confidence score with a preset threshold; and
requesting the user to check the determined task when the confidence score is less than the threshold.

### Claim 9

An operating method of a mobile-centric agent hub system (MCAHS) implemented with a computer device comprising at least one processor,
wherein the computer device comprises a trusted AI agent operation environment in an operating system, and
the operating method comprises:
managing, by the at least one processor, information on an application installed in the MCAHS in accordance with an AI agent;
determining, by the at least one processor, a task by analyzing an instruction received from a user and selecting an AI agent for processing the determined task;
generating, by the at least one processor, an execution container for executing the determined task through the trusted AI agent operation environment;
executing, by the at least one processor, an application of the selected AI agent by loading the application onto the generated execution container and executing the determined task through the selected AI agent by allocating the determined task to the generated execution container;
receiving, by the at least one processor, processing results of the executed task from the execution container; and
providing, by the at least one processor, a final response generated based on the received results of the processing to the user.

### Claim 10 (depends on 9)

The operating method of claim 9, wherein the trusted AI agent operation environment comprises:
a resource monitoring module configured to monitor and limit a resource use of an AI agent; and
an execution policy management module configured to manage a policy to control a behavior and access rights of the AI agent,
wherein the execution container in which the AI agent is executed in an isolated environment is generated.

### Claim 11 (depends on 9)

The operating method of claim 9, wherein:
the selecting of the AI agent comprises determining a plurality of tasks for processing the instruction and selecting a plurality of AI agents for processing the plurality of tasks,
the generating of the execution container comprises generating a plurality of execution containers for the plurality of AI agents,
the executing of the determined task comprises processing a corresponding task, among the plurality of tasks, through an application of an AI agent loaded onto the execution container by transmitting the corresponding task to each of the plurality of execution containers,
the receiving of the results of the processing comprises receiving a plurality of processing results from the plurality of execution containers, and
the providing of the final response to the user comprises generating the final response based on integrated results of the plurality of processing results and providing the final response to the user.

### Claim 12 (depends on 9)

The operating method of claim 9, wherein:
the computer device comprises a mobile device of the user, and
the operating method of the MCAHS is performed by the at least one processor under a control of an AI agent that is provided by an operating platform supplier of the mobile device.

### Claim 13 (depends on 9)

The operating method of claim 9, wherein the managing of the information on the application comprises synchronizing the installed application and information of an AI agent corresponding to the installed application with an app store.

### Claim 14 (depends on 9)

The operating method of claim 9, wherein the selecting of the AI agent comprises selecting the AI agent for processing the determined task by considering at least one of a function or service executable by the AI agent, a past use pattern of the user for the AI agent, preference of the user, whether to operate in conjunction with a payment system into which a task that requires payment has been incorporated, information on a location of the user, and an advertising association possibility.

### Claim 15

An AI agent system based on a cloud, comprising:
a user terminal configured to receive an instruction of a user, transmit the instruction to a cloud system, receive results of a processing of the instruction from the cloud system, and provide the results to the user; and
the cloud system configured to determine a task by analyzing the received instruction, select an AI agent for processing the determined task, process the determined task through the selected AI agent, and transmit results of the processing to the user terminal,
wherein the cloud system selects the AI agent for processing the determined task, among AI agents comprising AI agents installed in the user terminal and AI agents included in the cloud system.

### Claim 16 (depends on 15)

The AI agent system of claim 15, wherein:
the user terminal comprises a mobile operating system AI agent that is provided by a mobile operating system platform supplier, and
the mobile operating system AI agent controls the user terminal to receive the instruction of the user, transmit the instruction to the cloud system, receive the results of the processing of the instruction from the cloud system, and provide the results to the user.

### Claim 17 (depends on 15)

The AI agent system of claim 15, wherein:
the user terminal comprises a mobile AI agent manager that manages a list of the AI agents installed in the user terminal, and
the cloud system identifies the AI agents installed in the user terminal by obtaining the list of AI agents from the mobile AI agent manager.

### Claim 18 (depends on 15)

The AI agent system of claim 15, wherein the cloud system comprises:
a cloud AI agent inference service configured to determine the task by analyzing the received instruction and select the AI agent for processing the determined task; and
an AI agent execution engine configured to allocate the determined task to the selected AI agent, process the determined task through the selected AI agent, and transmit the results of the processing to the cloud AI agent inference service,
wherein the AI agent execution engine controls the user terminal so that the AI agent installed in the user terminal processes the determined task in association with the user terminal when the selected AI agent is the AI agent installed in the user terminal.

### Claim 19 (depends on 15)

The AI agent system of claim 15, wherein the selected AI agent comprises at least one AI agent selected among the AI agents installed in the user terminal and at least one AI agent selected among the AI agents included in the cloud system.

### Claim 20 (depends on 15)

The AI agent system of claim 15, wherein the cloud system selects the AI agent installed in the user terminal or the AI agent included in the cloud system by considering a complexity of the determined task.
