Communication method and device, storage medium and equipment

Abstract

The invention provides a communication method and device, a storage medium and equipment, a first signaling is introduced, after a network element of a core network receives the first signaling from user equipment, a first task intention included in the first signaling can be translated and arranged into one or more sub-tasks, and the one or more sub-tasks are sent to an intelligent agent for processing; according to the embodiment of the invention, the processing result of the sub-task is obtained, the first target processing result matched with the first task intention is generated based on the processing result of one or more sub-tasks, and the first target processing result is sent to the user equipment, so that the calling of the agent service can be realized in the wireless communication network.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a communication method and apparatus, storage medium and device. Background Technology

[0002] An AI agent is a device or program capable of proactive thinking and action, working in a human-like manner, understanding user needs through large models, proactively planning, and using tools to complete tasks. Due to its autonomous decision-making, intelligent interaction, and dynamic adaptability, AI agents have become a key technology in the evolution of wireless communication networks. In this context, how to implement the invocation of AI agent services within wireless communication networks is a technical problem that needs to be solved. Summary of the Invention

[0003] The purpose of this disclosure is to provide a communication method, apparatus, storage medium, and device for invoking intelligent agent services in a wireless communication network.

[0004] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0005] According to a first aspect of this disclosure, a communication method is provided, applied to a core network element. The method includes: receiving a first signaling from a user equipment, the first signaling including a first task intent; translating and orchestrating the first task intent into one or more subtasks; sending the one or more subtasks to an intelligent agent for processing, and receiving the processing results of the one or more subtasks; generating a first target processing result matching the first task intent based on the processing results of the one or more subtasks; and sending the first target processing result to the user equipment.

[0006] In some exemplary embodiments of this disclosure, receiving the first signaling from the user terminal includes: receiving the first signaling forwarded by the Access and Mobility Management Function (AMF) network element.

[0007] In some exemplary embodiments of this disclosure, the first signaling further includes at least one of the following: a protocol identifier, indicating that the first signaling is used to request a service from an agent; a task identifier, used to associate the context of the service; and a message type identifier, used to indicate the message type of the first signaling, the message type including at least one of the following: task creation, task update, and task release.

[0008] In some exemplary embodiments of this disclosure, the method further includes: creating a task context based on the first signaling; and associating the task identifier with the task context if the first signaling includes the task identifier.

[0009] In some exemplary embodiments of this disclosure, the method further includes adding information of the one or more subtasks and / or the processing results of the one or more subtasks to the task context.

[0010] In some exemplary embodiments of this disclosure, the method further includes: receiving a second signaling from the user equipment, the second signaling including update information of the first task intent; updating the first task intent to a second task intent based on the update information of the first task intent; updating the one or more subtasks based on the second task intent to obtain updated subtasks; assigning the updated subtasks to an agent for processing and receiving the processing results of the updated subtasks; updating the updated subtasks and / or the processing results of the updated subtasks to the task context; generating a second target processing result matching the second task intent based on the processing results of the updated subtasks, and sending the second target processing result to the user equipment.

[0011] In some exemplary embodiments of this disclosure, the method further includes: receiving third signaling from the user equipment; and deleting the task context based on the third signaling.

[0012] According to a second aspect of this disclosure, a communication method is provided, applied to a user equipment, the method comprising: sending a first signaling, the first signaling including a first task intent, the first task intent being used to translate and orchestrate into one or more subtasks, the one or more subtasks being executed by an intelligent agent and generating a processing result; and receiving a first target processing result, the first target processing result being generated based on the processing results of the one or more subtasks.

[0013] In some exemplary embodiments of this disclosure, the first signaling further includes at least one of the following: a protocol identifier, indicating that the first signaling is used to request a service from an agent; a task identifier, used to associate the context of the service; and a message type identifier, used to indicate the message type of the first signaling, the message type including at least one of the following: task creation, task update, and task release.

[0014] In some exemplary embodiments of this disclosure, the method further includes: sending a second signaling message, the second signaling message including update information of a first task intent, the update information being used to update the first task intent to a second task intent, the second task intent being used to update the one or more subtasks; and receiving a second target processing result, the second target processing result being generated based on the processing results of the updated one or more subtasks.

[0015] In some exemplary embodiments of this disclosure, the method further includes: sending a third signaling message to instruct the deletion of a task context, the task context being created by the network side based on the first signaling message.

[0016] According to a third aspect of this disclosure, a communication apparatus is provided, comprising: a first receiving module for receiving first signaling from a user equipment, the first signaling including a first task intent; a first processing module for translating and arranging the first task intent into one or more subtasks; a task allocation module for sending the one or more subtasks to an intelligent agent for processing and receiving the processing results of the one or more subtasks; a second processing module for generating a first target processing result matching the first task intent based on the processing results of the one or more subtasks; and a first sending module for sending the first target processing result to the user equipment.

[0017] In some exemplary embodiments of this disclosure, a first receiving module is configured to receive the first signaling forwarded by an Access and Mobility Management Function (AMF) network element.

[0018] In some exemplary embodiments of this disclosure, the first signaling further includes at least one of the following: a protocol identifier, indicating that the first signaling is used to request a service from an agent; a task identifier, used to associate the context of the service; and a message type identifier, used to indicate the message type of the first signaling, the message type including at least one of the following: task creation, task update, and task release.

[0019] In some exemplary embodiments of this disclosure, the communication device may further include a creation module for creating a task context based on the first signaling; and an association module for associating the task identifier and the task context when the first signaling includes the task identifier.

[0020] In some exemplary embodiments of this disclosure, the communication device may further include an adding module for adding information of the one or more subtasks and / or the processing results of the one or more subtasks to the task context.

[0021] In some exemplary embodiments of this disclosure, the communication device may further include a second receiving module for receiving second signaling from the user equipment, the second signaling including update information of the first task intent; an updating module for updating the first task intent to a second task intent based on the update information of the first task intent; and updating the one or more subtasks based on the second task intent to obtain updated subtasks; a task allocation module for allocating the updated subtasks to an agent for processing and receiving the processing result of the updated subtasks; an adding module for adding the updated subtasks and / or the processing result of the updated subtasks to the task context; and a second processing module for generating a second target processing result matching the second task intent based on the processing result of the updated subtasks and sending the second target processing result to the user equipment.

[0022] In some exemplary embodiments of this disclosure, the communication device may further include a third receiving module for receiving third signaling from the user equipment; and a deletion module for deleting the task context based on the third signaling.

[0023] According to a fourth aspect of this disclosure, a communication apparatus is provided, comprising: a first transmitting module for transmitting a first signaling, the first signaling including a first task intent, the first task intent being used to translate and orchestrate into one or more subtasks, the one or more subtasks being executed by an intelligent agent and generating a processing result; and a first receiving module for receiving a first target processing result, the first target processing result being generated based on the processing results of the one or more subtasks.

[0024] In some exemplary embodiments of this disclosure, the first signaling further includes at least one of the following: a protocol identifier, indicating that the first signaling is used to request a service from an agent; a task identifier, used to associate the context of the service; and a message type identifier, used to indicate the message type of the first signaling, the message type including at least one of the following: task creation, task update, and task release.

[0025] In some exemplary embodiments of this disclosure, the communication device may further include: a second sending module, configured to send a second signaling, the second signaling including update information of a first task intent, the update information being used to update the first task intent to a second task intent, the second task intent being used to update the one or more subtasks; and a second receiving module, configured to receive a second target processing result, the second target processing result being generated based on the updated processing results of the one or more subtasks.

[0026] In some exemplary embodiments of this disclosure, the communication device may further include: a third sending module, configured to send a third signaling, the third signaling being configured to instruct the deletion of a task context, the task context being created by the network side based on the first signaling.

[0027] According to a fifth aspect of this disclosure, a network device is provided, including a processor and a memory, the memory being used to store executable instructions of the processor; wherein the processor is configured to perform the method of the first aspect described above by executing the executable instructions.

[0028] According to a sixth aspect of this disclosure, a user equipment is provided, including a processor and a memory, the memory being used to store executable instructions of the processor; wherein the processor is configured to perform the method of the second aspect described above by executing the executable instructions.

[0029] According to a seventh aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method of the first or second aspect described above.

[0030] The communication method, apparatus, storage medium, and device provided in this disclosure introduce a first signaling. After receiving the first signaling from the user equipment, the core network element can translate and arrange the first task intent included in the first signaling into one or more subtasks, and send one or more subtasks to the intelligent agent for processing to obtain the processing results of the subtasks. Based on the processing results of one or more subtasks, a first target processing result matching the first task intent is generated, and the first target processing result is sent to the user equipment, which enables the invocation of intelligent agent services in the wireless communication network.

[0031] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0032] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0033] Figure 1 This is a schematic diagram of a network architecture provided in an embodiment of this disclosure; Figure 2 A flowchart of a communication method according to an embodiment of this disclosure is shown; Figure 3A schematic diagram of a signaling interaction process according to an embodiment of this disclosure is shown; Figure 4 A schematic diagram of another signaling interaction process in an embodiment of this disclosure is shown; Figure 5 A schematic diagram of yet another signaling interaction process in an embodiment of this disclosure is shown; Figure 6 A flowchart of another communication method in an embodiment of this disclosure is shown; Figure 7 This diagram illustrates a communication device according to an embodiment of the present disclosure; Figure 8 A schematic diagram of another communication device according to an embodiment of this disclosure is shown; Figure 9 A structural block diagram of a user equipment according to an embodiment of the present disclosure is shown. Detailed Implementation

[0034] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0035] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0036] To facilitate understanding, some technical terms involved in the embodiments of this disclosure will be explained first.

[0037] AI Agent: refers to an intelligent agent that is capable of proactive thinking and action, can work in a human-like manner, "understand" user needs through large models, proactively "plan" to achieve goals, use various "tools" to complete tasks, and ultimately "act" to execute these tasks.

[0038] UE (User Equipment): Various terminal devices with wireless communication capabilities that support users' access to network services.

[0039] AGMF (Agent Management Function): A new core network element added in this embodiment of the disclosure, responsible for the registration management and task management of agent services.

[0040] UDM (Unified Data Management): In the core network, it is responsible for the management of user identifiers, subscription data, authentication data, and user service element registration management.

[0041] AMF (Access and Mobility Management Function): In the core network, it directly manages user access requests through base stations and is responsible for functions such as registration management, connection management, reachability management, and mobility management.

[0042] SUPI (Subscription Permanent Identifier): The terminal's true identity identifier, consisting of the country code, network code, and mobile subscriber identification code.

[0043] NAS (Non-Access Stratum): In mobile communications, it is responsible for authentication, registration, and connection / session management between the UE and the core network.

[0044] NAS-AG (NAS Agent, NAS related to intelligent agent services): This disclosure embodiment adds NAS signaling for calling intelligent agent services set in the core network and receiving service results.

[0045] Figure 1 This is a schematic diagram of a network architecture provided in an embodiment of this disclosure. For example... Figure 1 As shown, the wireless communication network provided in this embodiment may include AGMF (Agent Management Function) network elements and agents set in the core network.

[0046] AGMF is used to manage the registration and status monitoring of agents, and to manage the context of agent services requested by user devices. It identifies the user device's intent through built-in agents, breaks it down into subtasks, distributes them to agents to execute each subtask, and finally aggregates and organizes the processing results of the subtasks and feeds them back to the user device.

[0047] AI Agents: These can be deployed as independent network elements in the core network, or integrated into network elements within the core network. For example, AI agents with network operation and maintenance capabilities can be deployed independently; agents for intent translation and task orchestration can be embedded in the AGMF; agents for traffic prediction and modeling can be embedded in the UPF (User Plane Function); and agents for base station perception and energy-saving control can be embedded in the RAN (Radio Access Network). AI agents embedded in network elements can invoke the functions of the embedded network elements to complete complex tasks. After going online, AI agents need to register their information with the AGMF, including their identifier, function description, service area, and service call interface.

[0048] Of course, the above is merely an illustrative example of the network structure provided in this disclosure, and not a unique limitation. In reality, intelligent agents can be embedded in any core network element, such as AMF (Analog-Based Function), SMF (Session Management Function), or UDM (Unified Device Management) elements. User equipment (UE) can access the network through the RAN and AMF and invoke the services of intelligent agents registered in the core network.

[0049] The communication method provided in this disclosure will be described below with reference to exemplary embodiments.

[0050] Figure 2 A flowchart of a communication method according to an embodiment of this disclosure is shown. This method can be executed by a core network element, which can be understood as any network element with agent service registration capability and agent task management capability, for example... Figure 1 AGMF in, but not limited to AGMF. For example Figure 2 As shown, in some embodiments, the communication method provided by this disclosure may include the following steps.

[0051] In step S201, a first signaling is received from the user equipment, the first signaling including a first task intent.

[0052] In this disclosure, the term "User Equipment" can be understood as any user terminal device capable of wireless communication. For example, in some examples, the User Equipment may also be referred to as a terminal device, communication device, mobile station (MS), or access terminal (AT). The User Equipment may include, but is not limited to, mobile phones, cellular phones, smartphones, tablet computers, wearable terminal devices, personal digital assistants (PDAs), portable computers, desktop computers, such as gaming terminal devices, music storage and playback facilities, in-vehicle wireless terminal devices, wireless endpoints, mobile stations, laptop embedded devices (LEEs), laptop mounted devices (LMEs), Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMDs), vehicles, drones, medical devices, industrial equipment, consumer electronic devices, etc.

[0053] The first signaling can be understood as a new type of signaling added in this embodiment of the disclosure, used to request services from intelligent agents registered in the core network. In this embodiment of the disclosure, the first signaling can be exemplarily understood as the NAS-AG signaling in the foregoing explanation of terminology.

[0054] In some examples, the first task intent may include a description of the task intent, such as "predicting user traffic in area xx during time period to save energy consumption of base stations in area xx", etc.

[0055] In some examples, the first signaling may include a message container, which may include at least the following information: Container identifier, used to identify the starting position of the message container.

[0056] Length, used to identify the length of the message content contained in the message container.

[0057] The message content includes the primary task intent, such as a description of the task intent.

[0058] In some examples, the first signaling may also include at least one of the following: Protocol identifier, representing the first signal used to request services from the agent.

[0059] A task identifier, used to associate the context of the service requested by the user device.

[0060] A message type identifier is used to indicate the message type of the first signaling, which includes at least one of the following: task creation, task update, and task release.

[0061] User equipment identifier.

[0062] In some implementations, the user equipment can send a first signaling message to the AMF, which identifies the first signaling message as a request for services from the agent based on the protocol identifier in the first signaling message. In this case, the AMF forwards the first signaling message to the corresponding core network element, such as the AGMF. That is, in some examples, the core network element (such as the AGMF) can receive the first signaling message forwarded by the AMF.

[0063] In step S203, the first task intent is translated and arranged into one or more subtasks.

[0064] In some examples, after receiving a first task intent, a core network element (such as AGMF) can translate and orchestrate the first task intent using a built-in agent, converting it into one or more subtasks. The agent translating and orchestrating the first task intent can use a pre-trained model. The model's input is the first task intent, and its output is one or more subtasks derived from it. For example, if the first task intent is "predict user traffic in region xx during time period to save energy consumption of base stations in region xx", then the subtasks output by the agent can include a subtask predicting user traffic in region xx during time period and a subtask controlling energy consumption of base stations in region xx. This is merely an example and not a definitive limitation. It should be noted that the model used for translating and orchestrating the task intent in the above example can be trained using model training methods provided by related technologies. The training data includes task intent samples and subtasks associated with the task intent samples. Specific model training methods can be found in related technologies, and will not be elaborated upon in this embodiment.

[0065] In some implementations, after receiving the first signaling, the core network element (such as AGMF) can create a task context based on the first signaling, and associate the task identifier with the task context if the first signaling includes a task identifier. If the first signaling does not include a task identifier, the task context can be associated with the identifier of the user equipment. In this case, the core network element (such as AGMF) can also add at least one of the following to the aforementioned task context for storage: the received first task intent, information on one or more subtasks translated and orchestrated based on the first task intent (such as the identifier and / or description of the subtasks), and the processing result of the subtasks.

[0066] By adding at least one of the following to the above task context for storage: the first task intent, information of one or more subtasks translated and arranged based on the first task intent, and the processing results of the subtasks, it is beneficial to manage task information.

[0067] In step S205, the one or more subtasks are sent to the intelligent agent for processing, and the processing results of the one or more subtasks are received.

[0068] In some implementations, when an intelligent agent, as described in this disclosure, accesses the core network, it registers its own information, such as identifier and capability information, within the core network. After converting the first task intent into one or more sub-tasks, the core network element (such as AGMF) sends one or more sub-tasks to intelligent agents with corresponding capabilities for processing based on the intelligent agent's registration information, and receives the processing results from the intelligent agents.

[0069] In step S207, based on the processing results of the one or more sub-tasks, a first target processing result that matches the intent of the first task is generated.

[0070] For example, the first task intent is "to predict user traffic in region xx during time period to save energy consumption of base stations in region xx". The subtask derived from this first task intent is the subtask of predicting user traffic in region xx during time period. A core network element (such as AGMF) can predict user traffic in region xx during time period through agent A. In this case, the core network element (such as AGMF) determines the control parameters of the base station based on the processing result of agent A, i.e., the predicted user traffic in region xx during time period. It then adjusts the energy consumption by adjusting these control parameters to save base station energy. The control parameters determined by the core network element (such as AGMF) based on the processing result of agent A can be exemplarily understood as the first target processing result matching the first task intent. Of course, this is merely an example and not the only limitation. For example, in other examples, the operations performed by the core network element (such as AGMF) can also be performed by other intelligent agents, such as agent B. In this case, the core network element (such as AGMF) sends the processing result of agent A to agent B, and agent B determines the control parameters of the base station. Based on the control parameters determined by agent B, the core network element (such as AGMF) generates control signaling, which can be understood as the first target processing result.

[0071] In step S209, the first target processing result is sent to the user equipment.

[0072] according to Figure 2In this embodiment, a first signaling is introduced. After receiving the first signaling from the user equipment, the core network element (such as AGMF) can translate and arrange the first task intent included in the first signaling into one or more subtasks, and send one or more subtasks to the intelligent agent for processing to obtain the processing results of the subtasks. Based on the processing results of one or more subtasks, a first target processing result matching the first task intent is generated, and the first target processing result is sent to the user equipment, which enables the invocation of intelligent agent services in the wireless communication network.

[0073] To better understand Figure 2 The task scheduling process in this embodiment will be described below using an exemplary signaling interaction process.

[0074] Example, Figure 3 A schematic diagram of a signaling interaction process according to an embodiment of this disclosure is shown. Figure 3 As shown, in some embodiments, the signaling interaction process provided by this disclosure may include the following steps.

[0075] In step S301a, the agent registers in AGMF.

[0076] Registration information may include the agent's identifier, capability information (such as network operation and maintenance, base station intelligent control, UPF intelligent processing, etc.), descriptions of one or more available tools (such as sensing data collection, traffic collection, etc.), service area and service call interface, etc.

[0077] In step S301b, AGMF returns a registration response to the agent.

[0078] In step S303, the UE sends an uplink NAS-AG signaling (i.e., the first signaling) to the AMF, carrying the first mission intent.

[0079] The NAS-AG may also include a protocol identifier, a task identifier, a message type identifier (task creation), and a UE identifier.

[0080] In step S305, the AMF identifies the NAS-AG signaling used to call the agent's service based on the protocol identifier, and the message type identifier indicates that the corresponding message type is task creation.

[0081] In step S307, the AMF sends a task creation request to the AGMF, including the UE's identifier and the task identifier. The request message body includes NAS-AG signaling. The request carries a link to AMF notification feedback, which is used by the AMF to provide feedback on subsequent processing results.

[0082] In step S309, after receiving the task creation request, AGMF queries UDM based on the user identifier to see if the current user has signed up for the network agent's service.

[0083] In step S311, AGMF creates a task context based on the UE's identifier and the task identifier, which is used to record the context information of the services invoked by the UE.

[0084] In step S313, AGMF extracts the first task intent from the NAS-AG message and calls the built-in agent to translate and orchestrate the first task intent, converting the first task intent into subtasks to be dispatched to the agent for execution, and assigning subtask identifiers to each subtask. At the same time, the information of the subtasks, such as the subtask identifiers and the first task intent, is added to the task context.

[0085] In step S315, the AGMF returns a task creation success response, carrying a task creation success message, which is then transmitted to the UE by the AMF via NAS-AG signaling.

[0086] In step S317, AGMF initiates a subtask execution request, carrying the subtask identifier, subtask requirements, and the service call interface of the agent executing the task.

[0087] In step S319, the agent scheduled by the task creates a subtask context, records the subtask identifier and subtask requirements, and the agent completes the task independently or in cooperation with other agents.

[0088] In step S321, the agent scheduled by the task returns the processing result.

[0089] In step S323, AGMF calls the built-in agent to aggregate and organize the processing results of subtasks, generate a first target processing result that matches the first task intent, and add the processing results of each subtask and the first target processing result to the task context.

[0090] In step S325, the AGMF sends a feedback notification to the AMF via the AMF's notification feedback link, carrying the UE's identifier and NAS-AG signaling containing the first target processing result.

[0091] In step S327, the AMF transmits the NAS-AG signaling containing the first target processing result to the UE based on the UE's identifier.

[0092] Figure 3 The implementation method and beneficial effects of the embodiments can be found in [reference]. Figure 2 Examples will not be repeated here.

[0093] For example, in some exemplary embodiments of this disclosure, the user equipment can also update the first task intent to a second task intent via signaling, thereby enabling the network side to re-invoke the agent's service based on the second task intent and provide feedback on the processing result. For instance, in some examples, the user equipment can send a second signaling message carrying update information of the first task intent (such as adding intent, removing intent, or changing parameters / conditions in the first task intent). After receiving the second signaling message, the core network element (such as AGMF) updates the first task intent to a second task intent based on the update information of the first task intent, and updates the orchestrated subtasks (i.e., subtasks translated and orchestrated based on the first task intent) based on the second task intent to obtain the updated subtasks. The updated subtasks are reassigned to agents for execution. The core network element (such as AGMF) aggregates and processes the processing results of the updated subtasks to generate a second target processing result that matches the second task intent, and adds at least one of the second target processing result, the updated subtasks, and the processing results of the updated subtasks to the task context, and feeds back the second target processing result to the user equipment.

[0094] To better understand the above update method, the following explanation will be provided in conjunction with an exemplary signaling interaction process.

[0095] Figure 4 A schematic diagram of another signaling interaction process in an embodiment of this disclosure is shown. For example... Figure 4 As shown, in some embodiments, the signaling interaction process provided by this disclosure may include the following steps.

[0096] In step S401, the UE initiates a task update request to the network side through uplink NAS-AG signaling (i.e., the second signaling). The NAS-AG signaling includes a protocol identifier, a task identifier, a message type identifier, and update information of the first task intent, such as updating the prediction time period and changing the model applicable to prediction over a longer time period.

[0097] In step S403, the AMF identifies the NAS-AG signaling as related to the service calling the agent based on the protocol identifier in the NAS-AG signaling, and identifies the message type of the NAS-AG signaling as a task update request based on the message type identifier.

[0098] In step S405, the AMF initiates a task update request to the AGMF, carrying the UE's identifier (such as SUPI) and the task identifier. The request message body includes the NAS-AG signaling received from the UE.

[0099] In step S407, AGMF finds the corresponding task context based on the UE's identifier and the task identifier.

[0100] In step S409, AGMF extracts the update information of the first task intent from NAS-AG, updates the first task intent recorded in the task context to obtain the second task intent, and calls the built-in intelligent agent to translate and orchestrate the second task intent. Based on the orchestration result, it updates the subtasks and adds the updated subtasks and the second task intent to the task context.

[0101] In step S411, the AGMF returns a task update success response, carrying a task update success message, which is then passed through to the UE by the AMF.

[0102] In step S413, AGMF initiates a subtask update request, carrying the identifier of the updated subtask and the requirement information of the updated subtask.

[0103] In step S415, the agent scheduled by the task updates the subtask context, adds the identifier and requirement information of the newly assigned subtask, and executes the subtask to obtain the processing result of the subtask.

[0104] In step S417, the agent provides feedback on the processing results of the subtask.

[0105] In step S419, AGMF calls the built-in agent to aggregate the processing results of subtasks and generates a second target processing result that matches the second task intent. At the same time, the second target processing result and the processing results of subtasks are added to the task context.

[0106] In step S421, the AGMF sends a feedback notification to the AMF via the AMF notification feedback link, carrying the UE's identifier and a NAS-AG instruction containing the second target processing result.

[0107] In step S423, the AMF transmits the NAS-AG instruction carrying the second target processing result to the UE based on the UE's identifier.

[0108] according to Figure 4 In this embodiment of the present disclosure, the user equipment can update the task intent sent to the network side through signaling, which helps to improve the flexibility of intelligent agent task scheduling and improve user experience.

[0109] For example, in some exemplary embodiments of this disclosure, the user terminal may also send a third signaling to the network side. After receiving the third signaling from the user equipment, the core network element (such as AGMF) on the network side may delete the task context established for the user equipment, thereby releasing the intelligent agent service established by the network side for the user equipment.

[0110] Example, Figure 5A schematic diagram of yet another signaling interaction process according to an embodiment of this disclosure is shown. For example... Figure 5 As shown, in some embodiments, the signaling interaction process provided by this disclosure may include the following steps.

[0111] In step S501, the UE initiates a task release request to the network side through uplink NAS-AG signaling (i.e., third signaling). The NAS-AG signaling includes a protocol identifier, a task identifier, a message type identifier (task release), and the UE's identifier.

[0112] In step S503, the AMF identifies the signaling as being related to agent services based on the protocol identifier in the NAS-AG signaling, and identifies the message type as a task release request based on the message type identifier.

[0113] In step S505, the AMF sends a task release request to the AGMF. The request carries the UE's identifier and the task identifier, and the message body of the request carries the NAS-AG signaling received from the UE.

[0114] In step S507, AGMF searches for the corresponding task context based on the UE's identifier and the task identifier.

[0115] In step S509, AGMF initiates a subtask release request to the agent executing each subtask based on the task context, carrying the subtask identifier.

[0116] In step S511, the agent executing the subtask deletes the subtask's context and reclaims resources.

[0117] In step S513, the agent executing the subtask returns a result indicating that the subtask was successfully deleted.

[0118] In step S515, AGMF deletes the task context associated with the user equipment.

[0119] In step S517, the AGMF sends a task release success response, carrying the information that the task release was successful in the message body, which is then passed through to the UE by the AMF.

[0120] according to Figure 5 In this embodiment of the present disclosure, the user equipment can instruct the network side to release the established intelligent agent service through signaling, which helps to improve the controllability of the intelligent agent service and improve the user experience.

[0121] Figure 6 A flowchart of another communication method according to an embodiment of this disclosure is shown. This method can be performed by a user device as exemplarily described in the above embodiments. Figure 6 As shown, the method may include the following steps.

[0122] In step S601, a first signaling is sent, which includes a first task intent.

[0123] The first task is intended to translate and arrange into one or more sub-tasks, which are executed by an agent to generate processing results.

[0124] In step S603, a first target processing result is received, which is generated based on the processing results of one or more subtasks.

[0125] In some implementations, the first signaling further includes at least one of the following: Protocol identifier, representing the first signal used to request services from the agent.

[0126] A task identifier, used to associate the context of the service requested by the user device.

[0127] The message type identifier is used to indicate the message type of the first signaling, and the message type includes at least one of the following: task creation, task update, and task release.

[0128] In some implementations, the user equipment is further configured to send a second signaling message, the second signaling message including update information of a first task intent, the update information of the first task intent being used to update the first task intent into a second task intent, the second task intent being used to update one or more subtasks; and to receive a second target processing result, the second target processing result being generated based on the processing results of the updated one or more subtasks.

[0129] In some implementations, the user equipment is also used to send a third signaling message, which is used to instruct the deletion of the context of the service requested by the first signaling message.

[0130] Figure 6 The implementation method and beneficial effects of the embodiments can be found in the foregoing. Figures 2-5 The parts related to user equipment will not be elaborated here.

[0131] Figure 7 A schematic diagram of a communication device according to an embodiment of this disclosure is shown. Figure 7 As shown, in some embodiments, the communication device 700 may include: The first receiving module 701 is configured to receive a first signaling from a user equipment, wherein the first signaling includes a first task intent.

[0132] The first processing module 702 is used to translate and arrange the first task intent into one or more sub-tasks.

[0133] The task allocation module 703 is used to send one or more subtasks to the intelligent agent for processing and to receive the processing results of the one or more subtasks.

[0134] The second processing module 704 is used to generate a first target processing result that matches the intent of the first task based on the processing results of the one or more sub-tasks.

[0135] The first sending module 705 is used to send the first target processing result to the user equipment.

[0136] In some exemplary embodiments of this disclosure, the first receiving module 701 is used to receive the first signaling forwarded by the Access and Mobility Management Function (AMF) network element.

[0137] In some exemplary embodiments of this disclosure, the first signaling further includes at least one of the following: a protocol identifier, indicating that the first signaling is used to request a service from an agent; a task identifier, used to associate the context of the service; and a message type identifier, used to indicate the message type of the first signaling, the message type including at least one of the following: task creation, task update, and task release.

[0138] In some exemplary embodiments of this disclosure, the communication device 700 may further include a creation module for creating a task context based on the first signaling; and an association module for associating the task identifier and the task context when the first signaling includes the task identifier.

[0139] In some exemplary embodiments of this disclosure, the communication device 700 may further include an adding module for adding information of the one or more subtasks and / or the processing results of the one or more subtasks to the task context.

[0140] In some exemplary embodiments of this disclosure, the communication device 700 may further include a second receiving module for receiving second signaling from the user equipment, the second signaling including update information of the first task intent; an updating module for updating the first task intent to a second task intent based on the update information of the first task intent; and updating the one or more subtasks based on the second task intent to obtain updated subtasks; a task allocation module for allocating the updated subtasks to an agent for processing and receiving the processing results of the updated subtasks; an adding module for adding the updated subtasks and / or the processing results of the updated subtasks to the task context; and a second processing module for generating a second target processing result matching the second task intent based on the processing results of the updated subtasks and sending the second target processing result to the user equipment.

[0141] In some exemplary embodiments of this disclosure, the communication device 700 may further include a third receiving module for receiving third signaling from the user equipment; and a deletion module for deleting the task context based on the third signaling.

[0142] Figure 7 The implementation method and beneficial effects of the communication device provided in the embodiments can be found in [reference needed]. Figures 2-5 Any of the embodiments described herein will not be repeated here.

[0143] Figure 8 A schematic diagram of another communication device according to an embodiment of this disclosure is shown. For example... Figure 8 As shown, in some embodiments, the communication device 800 may include: The first sending module 801 is used to send a first signaling, the first signaling including a first task intent, the first task intent being used to translate and orchestrate into one or more sub-tasks, the one or more sub-tasks being executed by an intelligent agent to generate processing results.

[0144] The first receiving module 802 is used to receive the first target processing result, which is generated based on the processing results of the one or more sub-tasks.

[0145] In some exemplary embodiments of this disclosure, the first signaling further includes at least one of the following: a protocol identifier, indicating that the first signaling is used to request a service from an agent; a task identifier, used to associate the context of the service; and a message type identifier, used to indicate the message type of the first signaling, the message type including at least one of the following: task creation, task update, and task release.

[0146] In some exemplary embodiments of this disclosure, the communication device 800 may further include: a second sending module, configured to send a second signaling, the second signaling including update information of a first task intent, the update information being used to update the first task intent to a second task intent, the second task intent being used to update the one or more subtasks; and a second receiving module, configured to receive a second target processing result, the second target processing result being generated based on the updated processing results of the one or more subtasks.

[0147] In some exemplary embodiments of this disclosure, the communication device 800 may further include: a third sending module for sending a third signaling, the third signaling being used to instruct the deletion of a task context, the task context being created by the network side based on the first signaling.

[0148] Figure 8 The communication device provided in the embodiments, its execution method and beneficial effects can be found in [reference needed]. Figure 6 Examples will not be repeated here.

[0149] In some embodiments, this disclosure also provides a user equipment including a processor and a memory, the memory being used to store executable instructions of the processor; wherein the processor is configured to execute the method performed by the user equipment in any of the above method embodiments by executing the executable instructions.

[0150] Figure 9 A structural block diagram of a user equipment according to an embodiment of this disclosure is shown. Referring below... Figure 9 To describe a user equipment 900 according to this embodiment of the invention. Figure 9 The user equipment 900 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0151] like Figure 9 As shown, the user equipment 900 is presented in the form of a general-purpose computing device. The components of the user equipment 900 may include, but are not limited to: at least one processing unit 910 (included in one or more processors), at least one storage unit 920 (included in one or more memories), and a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910).

[0152] The storage unit stores program code that can be executed by the processing unit 910, causing the processing unit 910 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of the present invention.

[0153] Storage unit 920 may include readable media in the form of volatile storage units, such as random access memory (RAM) 921 and / or cache memory 922, and may further include read-only memory (ROM) 923.

[0154] Storage unit 920 may also include a program / utility 924 having a set (at least one) program module 925, such program module 925 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0155] Bus 930 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0156] User equipment 900 can also communicate with one or more external devices 940 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with user equipment 900, and / or with any device that enables user equipment 900 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 950. Furthermore, user equipment 900 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 960. As shown, network adapter 960 communicates with other modules of user equipment 900 via bus 930. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with user equipment 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0157] In some exemplary embodiments of this disclosure, a network device is also provided, including a processor and a memory, the memory being used to store executable instructions of the processor; wherein the processor is configured to perform the above-mentioned tasks by executing the executable instructions. Figures 2-5 The method shown in any of the embodiments.

[0158] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0159] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the invention may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the invention described in the "Exemplary Methods" section of this specification.

[0160] A program product for implementing the above-described method according to embodiments of the present invention is described. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0161] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0162] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0163] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0164] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0165] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0166] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0167] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. A communication method, characterized in that, Applied to a core network element, the method includes: Receive a first signaling from a user equipment, the first signaling including a first task intent; Translate and organize the first task intent into one or more sub-tasks; Send the one or more subtasks to the agent for processing, and receive the processing results of the one or more subtasks; Based on the processing results of the one or more sub-tasks, a first target processing result that matches the intent of the first task is generated; The first target processing result is sent to the user equipment.

2. The method according to claim 1, characterized in that, The receiving of the first signaling from the user terminal includes: The first signaling is received from the Access and Mobility Management Function (AMF) network element.

3. The method according to claim 1, characterized in that, The first signaling also includes at least one of the following: The protocol identifier indicates that the first signaling is used to request the agent's service; A task identifier, used to associate the context of the service; A message type identifier is used to indicate the message type of the first signaling, and the message type includes at least one of the following: task creation, task update, and task release.

4. The method according to claim 3, characterized in that, The method further includes: Based on the first signaling, a task context is created; If the first signaling includes the task identifier, the task identifier and the task context are associated.

5. The method according to claim 4, characterized in that, The method further includes: Add the information of the one or more subtasks and / or the processing results of the one or more subtasks to the task context.

6. The method according to claim 5, characterized in that, The method further includes: Receive a second signaling from the user equipment, the second signaling including update information of the first task intent; Based on the update information of the first task intent, the first task intent is updated to the second task intent; The one or more subtasks are updated based on the second task intent to obtain the updated subtasks; The updated subtasks are assigned to agents for processing, and the processing results of the updated subtasks are received. Add the updated subtask and / or the processing result of the updated subtask to the task context; Based on the processing results of the updated subtasks, a second target processing result matching the second task intent is generated, and the second target processing result is sent to the user equipment.

7. The method according to claim 4, characterized in that, The method further includes: Receive third signaling from the user equipment; Based on the third signaling, the task context is deleted.

8. A communication method, characterized in that, Applied to user equipment, the method includes: Send a first signaling message, the first signaling message including a first task intent, the first task intent being used to translate and orchestrate into one or more subtasks, the one or more subtasks being executed by an intelligent agent and generating processing results; Receive the first target processing result, which is generated based on the processing results of the one or more sub-tasks.

9. The method according to claim 8, characterized in that, The first signaling also includes at least one of the following: The protocol identifier indicates that the first signaling is used to request the agent's service; A task identifier, used to associate the context of the service; A message type identifier is used to indicate the message type of the first signaling, and the message type includes at least one of the following: task creation, task update, and task release.

10. The method according to claim 8, characterized in that, The method further includes: Send a second signaling message, the second signaling message including update information of the first task intent, the update information being used to update the first task intent to a second task intent, the second task intent being used to update the one or more subtasks; Receive the second target processing result, which is generated based on the updated processing results of one or more subtasks.

11. The method according to claim 8, characterized in that, The method further includes: A third signaling message is sent to instruct the deletion of the task context, which was created by the network side based on the first signaling message.

12. A communication device, characterized in that, include: The first receiving module is configured to receive first signaling from the user equipment, wherein the first signaling includes a first task intent; The first processing module is used to translate and arrange the first task intent into one or more sub-tasks; The task allocation module is used to send one or more subtasks to the intelligent agent for processing and to receive the processing results of one or more subtasks. The second processing module is used to generate a first target processing result that matches the intent of the first task based on the processing results of the one or more sub-tasks. The first sending module is used to send the first target processing result to the user equipment.

13. A communication device, characterized in that, include: A first sending module is used to send a first signaling, the first signaling including a first task intent, the first task intent being used to translate and orchestrate into one or more sub-tasks, the one or more sub-tasks being executed by an intelligent agent and generating processing results; The first receiving module is used to receive the first target processing result, which is generated based on the processing results of the one or more sub-tasks.

14. A network device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

15. A user equipment, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to perform the method of any one of claims 8-11 by executing the executable instructions.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method according to any one of claims 1 to 11.

Images