Communication method and apparatus

Abstract

The present application discloses a communication method and apparatus. The method comprises: a first network apparatus receives first information from a second network apparatus, the first information comprising first parameter information, and the first parameter information being used to describe a requirement of a first service that needs to be used by a first terminal apparatus and / or a requirement of the first terminal apparatus; and on the basis of the first parameter information, the first network apparatus selects a first AI or ML model that matches the requirement of the first service and / or the requirement of the first terminal apparatus. In the present application, a first network apparatus may select, on the basis of a requirement of a first service and / or a requirement of a first terminal apparatus, a first AI or ML model that matches the requirement of the first service and / or the requirement of the first terminal apparatus, so that the first AI or ML model can execute a task corresponding to the first service, thereby ensuring normal running of the service and improving service performance.

Description

A communication method and apparatus

[0001] Cross-references to related applications

[0002] This application claims priority to Chinese Patent Application No. 202411815758.0, filed on December 10, 2024, entitled "A Communication Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of communication technology, and in particular to a communication method and apparatus. Background Technology

[0004] Artificial intelligence (AI) agents (or intelligent agents or smart agents) are intelligent entities capable of perceiving their environment, making decisions, and performing actions. They aim to efficiently execute and process complex tasks through natural language interaction using AI or machine learning (ML) models. For example, an AI agent can input a task description into an AI or ML model, enabling the model to perform that task.

[0005] Currently, AI agents are widely used in the field of mobile communication, capable of handling or assisting in calls. For example, if terminal 1 calls terminal 2, and terminal 2 is using a smart answering service, then terminal 2's AI agent can communicate with terminal 1 on behalf of terminal 2. Similarly, if terminal 1 calls terminal 2, and terminal 1 is using a smart assistance service, then terminal 1's AI agent can provide services to terminal 1 during its call with terminal 2. However, due to differences in capabilities between different AI or ML models, and even differences in capabilities of the same AI or ML model on different hardware, the AI ​​or ML model selected by the terminal's AI agent may not be able to perform the tasks corresponding to the services required by the terminal, affecting normal service operation and resulting in poor service performance. Summary of the Invention

[0006] This application provides a communication method and apparatus for improving service performance.

[0007] In a first aspect, embodiments of this application provide a communication method applicable to a first network device, which is a network-side device. For example, the first network device may be a subscriber artificial intelligence agent function (SAAF) network element, or other devices including SAAF network element functionality, or a chip system (or chip) or other functional module capable of implementing the SAAF network element functionality, and such chip system or functional module may be disposed, for example, within the SAAF network element. The method includes: receiving first information from a second network device, the first information including first parameter information, the first parameter information describing the requirements of a first service to be used by the first terminal device and / or the requirements of the first terminal device; and selecting a first AI or ML model matching the requirements of the first service and / or the requirements of the first terminal device based on the first parameter information.

[0008] In this embodiment of the application, when the first terminal device needs to use the first service, the second network device can indicate the needs of the first terminal and / or the needs of the first terminal device to the first network device, so that the first network device can select a first AI or ML model that matches the needs of the first service and / or the needs of the first terminal device, so that the first AI or ML model can perform the task corresponding to the first service, thereby ensuring the normal operation of the service and improving the service performance.

[0009] In one possible implementation, the first information is sent by the second network device upon receiving the second information, the second information being used to indicate that a media channel has been successfully established between the first terminal device and the media function network element, the media channel being used to transmit media information corresponding to the first service.

[0010] In this embodiment, a method is provided to trigger a second network device to send first information to a first network device. For example, when a media channel between a first terminal device and a media function network element has been successfully established, the second network device can determine that the first terminal device may need to use a first service in a short period of time. Therefore, in order to improve service performance, the second network device can indicate the needs of the first terminal and / or the needs of the first terminal device to the first network device, so that the first network device can select a first AI or ML model that matches the needs of the first service and / or the needs of the first terminal device according to the needs of the first service and / or the needs of the first terminal device.

[0011] In one possible implementation, selecting a first AI or ML model that matches the needs of the first service and / or the needs of the first terminal device based on the first parameter information includes: selecting at least one AI or ML model that matches the needs of the first service and / or the needs of the first terminal device based on the first parameter information; and selecting the first AI or ML model from the at least one AI or ML model.

[0012] In this embodiment, a method is provided for the first network device to select a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device. For example, if the first network device stores parameter information of the AI ​​or ML model, the first network device can directly select at least one AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device, and select the first AI or ML model from at least one AI or ML model according to its own needs, so that the first AI or ML model can perform the task corresponding to the first service, thereby ensuring the normal operation of the service and improving service performance.

[0013] In one possible implementation, selecting a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device based on the first parameter information includes: sending the first parameter information to a third network device, the third network device being used to store parameter information of the AI ​​or ML model; receiving third information from the third network device, the third information being used to indicate at least one AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device; and selecting the first AI or ML model from the at least one AI or ML model.

[0014] In this embodiment, a method is provided for the first network device to select a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device. For example, if the first network device does not store parameter information of the AI ​​or ML model, the first network device can query a third network device that stores the parameter information of the AI ​​or ML model for at least one AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device, and select the first AI or ML model from the at least one AI or ML model according to its own needs. This allows the first AI or ML model to perform the task corresponding to the first service, thereby ensuring the normal operation of the service and improving service performance.

[0015] In one possible implementation, the third information includes the identification information of the at least one AI or ML model and / or the parameter information of the at least one AI or ML model.

[0016] In this embodiment, multiple methods are provided for the third network device to indicate at least one AI or ML model to the first network device. For example, the third network device can indicate the identification information of at least one AI or ML model; this indication method can also be understood as a direct indication method. Another example is that the third network device can indicate the parameter information of at least one AI or ML model; this indication method can also be understood as an indirect indication method. Therefore, the methods by which the third network device indicates at least one AI or ML model to the first network device are quite flexible.

[0017] In one possible implementation, selecting the first AI or ML model from the at least one AI or ML model includes: determining second parameter information, the second parameter information being used to describe the highest priority requirement among the requirements of the first service and / or the requirements of the first terminal device; and selecting the first AI or ML model from the at least one AI or ML model based on the second parameter information.

[0018] In this embodiment, the first network device can select the AI ​​or ML model that best matches the highest priority requirement among the requirements of the first service and / or the first terminal device from at least one AI or ML model that matches the requirements of the first service and / or the first terminal device to execute the task corresponding to the first service. For example, if the requirement of the first service is that parameter 1 is greater than threshold 1, parameter 2 is greater than threshold 2, and parameter 3 is greater than threshold 3, and when parameter 1 being greater than threshold 1 is the highest priority requirement, the first network device can select the AI ​​or ML model with the smallest value of parameter 1 from at least one AI or ML model that matches the requirement of the first service to execute the task corresponding to the first service. This reduces the waste of AI or ML model resources while ensuring the normal operation of the service.

[0019] In one possible implementation, the first information may further include one or more of the following: identification information of the first terminal device; identification information of the first service; and parameter information of the first service.

[0020] In this embodiment, multiple methods are provided for the second network device to indicate to the first network device that the first terminal device needs to use the first service. For example, the second network device can indicate the identification information of the first terminal device and the identification information of the first service; this indication method can also be understood as a direct indication method. As another example, the second network device can indicate the identification information of the first terminal device and the parameter information of the first service; this indication method can also be understood as an indirect indication method. Therefore, the methods by which the second network device indicates to the first network device that the first terminal device needs to use the first service are quite flexible.

[0021] Secondly, embodiments of this application also provide a communication method, which can be applied to a second network device, which is a network-side communication device, such as a data channel application server (DCAS) network element, or other devices including DCAS network element functions, or a chip system (or chip) or other functional module, which can implement the functions of the DCAS network element, and the chip system or functional module is, for example, set in the DCAS network element. The method includes: determining first information, the first information including first parameter information, the first parameter information being used to describe the requirements of a first service to be used by a first terminal device and / or the requirements of the first terminal device; receiving second information, the second information being used to indicate that a media channel between the first terminal device and a media function network element has been successfully established, the media channel being used to transmit media information corresponding to the first service; and sending the first information to the first network device according to the second information, instructing the first network device to select a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device.

[0022] In this embodiment of the application, when the first terminal device needs to use the first service, the second network device can indicate the needs of the first terminal and / or the needs of the first terminal device to the first network device, so that the first network device can select a first AI or ML model that matches the needs of the first service and / or the needs of the first terminal device, so that the first AI or ML model can perform the task corresponding to the first service, thereby ensuring the normal operation of the service and improving the service performance.

[0023] It can be understood that the first information may include the identification information of the first terminal device and the identification information of the first service. The identification information of the first terminal device and the identification information of the first service are used to instruct the first network device to select a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device. This method can also be understood as an indirect instruction method. Alternatively, the first information may include first instruction information, which is used to instruct the first network device to select a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device. This instruction method can also be understood as a direct instruction method. Therefore, the method by which the first information instructs the first network device to select a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device is quite flexible.

[0024] In one possible implementation, before receiving the second information, the method further includes: establishing a media channel between the first terminal device and the media function network element through a voice service processing network element when a first condition is met or a session establishment request is received; wherein the session establishment request is used to request the establishment of a session between the first terminal device and the second terminal device or the first network device.

[0025] In this embodiment, the establishment of a media channel between the first terminal device and the media function network element by the voice service processing network element can be understood as the voice service processing network element establishing media channels with both the first terminal device and the media function network element. The second network device can instruct the voice service processing network element to establish media channels with both the first terminal device and the media function network element when the first condition is met or when a second session establishment request is received. This is so that when it is determined that the media channel between the first terminal device and the media function network element has been successfully established, the second network device can be informed of the first service requirements and / or the requirements of the first terminal device.

[0026] In one possible implementation, the first condition includes the identifier of the first terminal device, the identifier of the first service, and the condition for triggering the first service. Determining the first information includes: if the first condition is met, determining the first information based on the identifier information of the first terminal device and / or the identifier information of the first service.

[0027] In this embodiment, a method is provided for the second network device to determine the requirements of the first service and / or the requirements of the first terminal device that the first terminal device needs to use, based on the identification information of the first terminal device and the identification information of the first service in the first condition. Alternatively, the second network device may determine the requirements of the first service and / or the requirements of the first terminal device through other means, without limitation.

[0028] In one possible implementation, the session establishment request includes call information, and before determining the first information, the method further includes: upon receiving the session establishment request, determining the first service from the subscribed services of the first terminal device based on the call information.

[0029] In this embodiment, one method is provided for the second network device to determine the first service. For example, upon receiving a session establishment request, the second network device can determine the first service that the first terminal device needs to use from the subscribed services of the first terminal device based on the call information in the session establishment request. For instance, if the calling number is the number of service 1, the called number is the number of the user to whom the first terminal device belongs, and the first terminal device has subscribed to service 1, then the second network device can determine that the first terminal device needs to use service 1. Besides this, the second network device can also determine the first service through other methods, without limitation.

[0030] In one possible implementation, the call information includes one or more of the following: calling number, called number, or call type.

[0031] This implementation provides various possibilities for call information, such as the caller's number, the called number, or the call type. In addition, call information may include other information, without limitation.

[0032] In one possible implementation, the first information may further include one or more of the following: identification information of the first terminal device; identification information of the first service; and parameter information of the first service.

[0033] In this embodiment, multiple methods are provided for the second network device to indicate to the first network device the first service that the first terminal device needs to use. For example, the second network device can indicate the identification information of the first terminal device and the identification information of the first service; this indication method can also be understood as a direct indication method. As another example, the second network device can indicate the identification information of the first terminal device and the parameter information of the first service; this indication method can also be understood as an indirect indication method. Therefore, the methods by which the second network device indicates to the first network device the first service that the first terminal device needs to use are quite flexible.

[0034] Thirdly, embodiments of this application also provide a communication device. The communication device can be the first network device described in the first aspect above. The communication device possesses the functions of the first network device. The communication device is, for example, a SAAF network element, or other equipment including SAAF network element functions, or a chip system (or chip) or other functional module. This chip system or functional module can implement the functions of the SAAF network element, and is, for example, disposed within the SAAF network element. In one optional implementation, the communication device includes a baseband device and a radio frequency device. In another optional implementation, the communication device includes a processing unit (sometimes also called a processing module) and a transceiver unit (sometimes also called a transceiver module). The transceiver unit can implement both transmitting and receiving functions. When the transceiver unit implements the transmitting function, it can be called a transmitting unit (sometimes also called a transmitting module), and when the transceiver unit implements the receiving function, it can be called a receiving unit (sometimes also called a receiving module). The transmitting unit and the receiving unit can be the same functional module, which is called the transceiver unit. This functional module can realize the transmitting and receiving functions; or, the transmitting unit and the receiving unit can be different functional modules, and the transceiver unit is a general term for these functional modules.

[0035] In one embodiment, the transceiver unit is configured to receive first information from a second network device, the first information including first parameter information, the first parameter information being used to describe the requirements of a first service to be used by the first terminal device and / or the requirements of the first terminal device.

[0036] In one embodiment, the processing unit is configured to select a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device based on the first parameter information.

[0037] Fourthly, embodiments of this application also provide a communication device. The communication device can be the second network device described in the second aspect above. The communication device possesses the functions of the aforementioned second network device. This communication device is, for example, a DCAS network element, or other equipment including DCAS network element functions, or a chip system (or chip) or other functional module. This chip system or functional module can implement the functions of the DCAS network element, and is, for example, disposed within the DCAS network element. In one optional implementation, the communication device includes a baseband device and a radio frequency device. In another optional implementation, the communication device includes a processing unit (sometimes also called a processing module) and a transceiver unit (sometimes also called a transceiver module). The transceiver unit can implement both transmitting and receiving functions. When the transceiver unit implements the transmitting function, it can be called a transmitting unit (sometimes also called a transmitting module), and when the transceiver unit implements the receiving function, it can be called a receiving unit (sometimes also called a receiving module). The transmitting unit and the receiving unit can be the same functional module, which is called the transceiver unit. This functional module can realize the transmitting and receiving functions; or, the transmitting unit and the receiving unit can be different functional modules, and the transceiver unit is a general term for these functional modules.

[0038] In one embodiment, the processing unit is configured to determine first information, the first information including first parameter information, the first parameter information being used to describe the requirements of a first service to be used by the first terminal device and / or the requirements of the first terminal device.

[0039] In one embodiment, the transceiver unit is configured to receive second information, the second information indicating that a media channel between the first terminal device and the media function network element has been successfully established, the media channel being used to transmit media information corresponding to the first service;

[0040] In one implementation, the transceiver unit is configured to send the first information to a first network device based on the second information, instructing the first network device to select a first AI or ML model that matches the needs of the first service and / or the needs of the first terminal device.

[0041] Fifthly, a communication device is provided, which can be the first network device described in the first aspect above. The communication device possesses the functions of the first network device. The communication device is, for example, a SAAF network element, or other device including SAAF network element functions, or a system-on-a-chip (or chip) or other functional module capable of implementing the functions of the SAAF network element, and the system-on-a-chip or functional module is, for example, disposed within the SAAF network element. The communication device includes a processor for executing the functions of the first network device described in the first aspect above. Optionally, the communication device further includes a memory. The memory stores a computer program, and the processor is coupled to the memory. When the processor reads the computer program or instructions, it causes the communication device to execute the methods executed by the first network device in the above aspects. Optionally, the memory and the processor are integrated together.

[0042] Sixthly, a communication device is provided, which can be the second network device described in the second aspect above. The communication device possesses the functions of the second network device described above. The communication device is, for example, a DCAS network element, or other device including DCAS network element functions, or a system-on-a-chip (or chip) or other functional module capable of implementing the functions of the DCAS network element, and the system-on-a-chip or functional module is, for example, disposed within the DCAS network element. The communication device includes a processor for executing the functions of the second network device described in the second aspect above. Optionally, the communication device further includes a memory. The memory stores a computer program, and the processor is coupled to the memory. When the processor reads the computer program or instructions, it causes the communication device to execute the methods executed by the second network device in the above aspects. Optionally, the memory and the processor are integrated together.

[0043] A seventh aspect provides a communication system including a first network device and a second network device. The first network device is used to perform the method described in the first aspect. For example, the first network device can be implemented using the communication device described in the third or fifth aspect. The second network device is used to perform the method described in the second aspect. For example, the second network device can be implemented using the communication device described in the fourth or sixth aspect.

[0044] Eighthly, a computer-readable storage medium is provided for storing a computer program or instructions that, when executed, cause the method performed by the first or second network device in the preceding aspects to be implemented.

[0045] Ninthly, a computer program product containing instructions is provided, which, when the computer program or instructions are run on a computer, causes the methods described in the above aspects to be implemented.

[0046] In a tenth aspect, a chip system is provided, including a processor and an interface, the processor being configured to call and execute instructions from the interface to enable the chip system to implement the methods described above.

[0047] The beneficial effects of the second to tenth aspects and their embodiments described above can be referred to the beneficial effects of the first aspect and any of its embodiments, and will not be repeated here. Attached Figure Description

[0048] Figure 1 is a schematic diagram of a communication system provided in an embodiment of this application;

[0049] Figure 2 is a schematic diagram of another communication system provided in an embodiment of this application;

[0050] Figure 3 is a schematic diagram of an artificial intelligence agent provided in an embodiment of this application;

[0051] Figure 4 is a schematic diagram of a service that uses an artificial intelligence agent to process or assist in calls, as provided in this application example;

[0052] Figure 5 is a flowchart illustrating a communication method provided in an embodiment of this application;

[0053] Figure 6a is a flowchart illustrating another communication method provided in an embodiment of this application;

[0054] Figure 6b is a flowchart illustrating another communication method provided in an embodiment of this application;

[0055] Figure 6c is a flowchart illustrating another communication method provided in an embodiment of this application;

[0056] Figure 6d is a flowchart illustrating another communication method provided in an embodiment of this application;

[0057] Figure 6e is a flowchart illustrating another communication method provided in an embodiment of this application;

[0058] Figure 6f is a flowchart illustrating another communication method provided in an embodiment of this application;

[0059] Figure 7 is a schematic diagram of a communication device provided in an embodiment of this application;

[0060] Figure 8 is a schematic diagram of another communication device provided in an embodiment of this application. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0062] The technical solutions provided in the embodiments of this application can be applied to communication systems related to the 3rd Generation Partnership Project (3GPP), such as Long Term Evolution (LTE) communication systems, 5th Generation (5G) mobile communication systems (specifically, New Radio (NR) communication systems, or NR communication systems that introduce Multi-Input Multi-Output (MIMO) technology), or they can also be applied to other next-generation mobile communication systems, other similar communication systems, or communication systems in the future evolution process. Other similar communication systems may include Wireless Fidelity (WiFi), Vehicle-to-Everything (V2X), Internet of Things (IoT) systems, Narrow Band Internet of Things (NB-IoT) systems, or the Industrial Internet, etc.

[0063] Referring to Figure 1, it is a schematic diagram of the structure of a communication system provided in an embodiment of this application. As shown in Figure 1, the communication system may include a radio access network (RAN) 100 and a core network (CN) 200. Optionally, the communication system may also include the Internet 300.

[0064] The wireless access network 100 may include at least one access network device (such as access network devices 110a and 110b in Figure 1, collectively referred to as access network device 110) and at least one terminal device (such as terminal devices 120a-120j in Figure 1, collectively referred to as terminal device 120). The wireless access network 100 may also include other devices, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1). The terminal device 120 is wirelessly connected to the access network device 110. The access network device 110 is wirelessly or wired connected to the core network 200. The core network device 210 in the core network 200 and the access network device 110 in the wireless access network 100 may be different physical devices, or they may be the same physical device integrating core network logical functions and wireless access network logical functions.

[0065] The radio access network 100 can be a 3GPP-related communication system (such as a 5G mobile communication system) or a future mobile communication system. The radio access network 100 can also be an open RAN (O-RAN or ORAN), a cloud radio access network (CRAN), or a WiFi system. The radio access network 100 can also be a communication system that integrates two or more of the above systems.

[0066] Access network equipment 110, also known as RAN node, RAN entity, or access node, is used to help terminal equipment 120 achieve wireless access.

[0067] In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a base station in a future mobile communication system, or an access node in a WiFi system. A RAN node can be a macro base station (as shown in Figure 1, 110a), a micro base station or indoor station (as shown in Figure 1, 110b), a relay node or donor node, or a radio controller in a CRAN scenario. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, in V2X technology, a RAN node can be a roadside unit (RSU).

[0068] In another possible scenario, multiple RAN nodes can collaborate to assist terminal device 120 in achieving wireless access, with different RAN nodes each implementing a portion of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be configured separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs). The CU can perform the functions of the radio resource control (RRC) protocol and packet data convergence protocol (PDCP) of the base station, and can also perform the functions of the service data adaptation protocol (SDAP). The DU can perform the functions of the radio link control (RLC) layer and medium access control (MAC) layer of the base station, and can also perform some or all of the physical (PHY) layer functions. For specific descriptions of the above protocol layers, please refer to the relevant technical specifications of 3GPP.

[0069] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0070] In this embodiment, the access network device 110 and its components (such as chips, processing units, or processors) can be collectively referred to as network devices. For example, it can be the access network device 110 shown in FIG1, or it can be the chip (system) in the access network device 110 in FIG1.

[0071] The embodiments of this application do not limit the device form of the access network device 110. The apparatus for implementing the functions of the access network device 110 can be the access network device 110 itself; it can also be an apparatus capable of supporting the access network device 110 in implementing the functions, such as a chip system. This apparatus can be installed in the access network device 110 or used in conjunction with the access network device 110. In the embodiments of this application, the chip system can be composed of chips, or it can include chips and other discrete devices. All or part of the functions of the access network device 110 in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform).

[0072] Terminal equipment 120, also known as user equipment (UE), mobile station (MS), mobile terminal (MT), etc., refers to a device that provides voice and / or data connectivity to a user.

[0073] Terminal device 120 can be a handheld device, vehicle-mounted device, or other device with wireless connectivity. For example, terminal device 120 can be a mobile phone, tablet computer, laptop computer, PDA, mobile internet device (MID), wearable device (e.g., smartwatch, smart bracelet, pedometer, smart glasses, etc.), vehicle-mounted device (e.g., car, bicycle, electric vehicle, airplane, ship, train, high-speed rail, etc.), satellite terminal, virtual reality (VR) device, augmented reality (AR) device, point of sale (POS) machine, customer-premises equipment (CPE), light user equipment (light UE), reduced capability user equipment (REDCAP UE), wireless terminal in industrial control, smart home device (e.g., refrigerator, television, air conditioner, electricity meter, etc.), smart robot, robotic arm, workshop equipment, wireless terminal in autonomous driving, wireless terminal in telemedicine, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, or wireless terminal in smart home, flying device (e.g., smart robot, hot air balloon, drone, airplane), etc. Terminal device 120 can also be a vehicle device, such as a complete vehicle device, vehicle module, vehicle chip, on-board unit (OBU), or telematics box (T-BOX). Terminal device 120 can also be other devices with terminal functions; for example, terminal device 120 can also be a device that plays a terminal function in device-to-device (D2D) communication.

[0074] In the embodiments of this application, the terminal device 120 and its components (such as chips, processing units, or processors) can be collectively referred to as a terminal device. For example, it can be the terminal device 120 shown in FIG1, or it can be the chip (system) in the terminal device 120 in FIG1.

[0075] The embodiments of this application do not limit the device form of the terminal device 120. The device used to implement the functions of the terminal device 120 can be the terminal device 120 itself; it can also be a device capable of supporting the terminal device 120 in implementing the functions, such as a chip system. This device can be installed in the terminal device 120 or used in conjunction with the terminal device 120. In the embodiments of this application, the chip system can be composed of chips, or it can include chips and other discrete devices. All or part of the functions of the terminal device 120 in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform).

[0076] The core network device 210 may include different network elements in different communication systems. For example, see Figure 2, which is a schematic diagram of another communication system provided in an embodiment of this application. As shown in Figure 2, in this communication system, the core network equipment may include some or all of the following network elements: Internet Protocol Multimedia Subsystem-Access Media Gateway (IMS-AGW) network element, Proxy-Call Session Control Function (P-CSCF) network element, Serving-Call Session Control Function (S-CSCF) network element, Interrogating-Call Session Control Function (I-CSCF) network element, Media Function (MF) network element, Voice Over Long Term Evolution Application Server (VoLTE AS) network element, Data Channel Signaling Function (DCSF) network element, Data Channel Application Server (DCAS) network element, Artificial Intelligence Agent Management Function (AAMF) (or Intelligent Agent Management Function) network element, and Subscriber Artificial Intelligence Agent (Subscriber Artificial Intelligence Agent) network element. The network elements include: User Agent Function (SAAF) network elements, Subscriber Vector Database Function (SVDF) network elements, Artificial Intelligence (AI) or Machine Learning (ML) model network elements, and Network Repository Function (NRF) network elements. Among these, the MF network element is responsible for providing media functions such as rendering and speech translation. The SAAF network element is responsible for providing AI agent functions to users. The SVDF network element is responsible for storing user information, such as user preference information. The AAMF network element is responsible for allocating SAAF and SVDF network elements to users.The DCAS network element is responsible for storing data channel applications and distributing them to users. The DCSF network element is responsible for managing data channel media capabilities and data channel service capabilities. The NRF network element is responsible for the automated management of all network function services (NFS), including registration, discovery, and status detection. Of course, core network equipment may also include other network elements, which are not listed here.

[0077] In this embodiment, the core network device 210 and its components (such as chips, processing units, or processors) can be collectively referred to as network devices. For example, it can be the core network device 210 shown in FIG1, or it can be the chip (system) in the core network device 210 in FIG1.

[0078] The embodiments of this application do not limit the device form of the core network device 210. The apparatus used to implement the functions of the core network device 210 can be the core network device 210 itself; it can also be an apparatus capable of supporting the core network device 210 in implementing the functions, such as a chip system. This apparatus can be installed in the core network device 210 or used in conjunction with the core network device 210. In the embodiments of this application, the chip system can be composed of chips, or it can include chips and other discrete devices. All or part of the functions of the core network device 210 in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform).

[0079] The communication system applicable to the embodiments of this application has been briefly introduced above. The relevant technical solutions involved in the embodiments of this application are described below.

[0080] Artificial intelligence agents, also known as intelligent agents or intelligent agents, refer to intelligent entities that can perceive the environment, make decisions, and perform actions. They aim to efficiently execute and process complex tasks through AI or ML models using natural language interaction.

[0081] For example, Figure 3 is a schematic diagram of an artificial intelligence agent provided in an embodiment of this application. As shown in Figure 3, the AI ​​or ML model acts as the "brain" of the artificial intelligence agent, responsible for processing and generating text, and performing reasoning and decision-making. Planning, memory, tool use, and action together constitute the core capabilities of the artificial intelligence agent. Among them, planning refers to the ability of the artificial intelligence agent to formulate a series of steps or strategies to achieve the goal based on the current state and the goal. Memory refers to the ability of the artificial intelligence agent to store and retrieve information. Tool use refers to the ability of the artificial intelligence agent to use external tools to perform tasks. Action refers to the ability of the artificial intelligence agent to perform specific operations, including physical operations and virtual operations.

[0082] AI or ML models (such as large language models (LLMs)) have semantic analysis capabilities and can handle various natural language tasks, such as question answering and dialogue. Artificial intelligence agents can input task descriptions into AI or ML models to enable them to perform the task.

[0083] Task description information, also known as task prompts or task guidance information, refers to a piece of descriptive text used to guide AI or ML models in performing tasks. For example, components of task description information may include roles, rules, goals, context, examples, feedback, constraints, workflow prompts, user instructions, short-term memory, and long-term memory.

[0084] Different AI or ML models exhibit varying capabilities, primarily in the following aspects: a) Model size and architecture: Model size and architecture directly impact its ability to process and understand language. Generally, larger models have more parameters and can capture more complex language patterns and relationships. b) Quality and diversity of training data: High-quality, diverse training data helps models learn richer language knowledge and improves their generalization ability. c) Training time and computational resources: Longer training time and more computational resources typically lead to better model performance. d) Optimization strategies and training techniques: Different optimization strategies and training techniques also affect the final performance of the model.

[0085] The same AI or ML model can exhibit performance differences across different hardware, primarily in the following aspects: a) Initial token latency: On high-performance hardware, initial token latency is lower, meaning users receive responses faster and have a better user experience. Conversely, on lower-performance hardware, initial token latency may be higher, leading to a poorer user experience. Tokenization is the smallest unit of meaning that an AI or ML model can understand and generate; it is the fundamental unit of the model. Depending on the specific tokenization scheme used, tokenization can be words, sub-words, or characters. When using AI or ML models, the initial token latency (reflecting response time) and subsequent tokenization latency (affecting inference time) are typically the primary concerns. b) Inference time: On high-performance hardware, AI or ML models can quickly complete the entire inference process. On lower-performance hardware, the inference process may take longer, especially when processing long texts or complex tasks. c) Concurrency processing capability: High-performance hardware can handle multiple requests simultaneously. This means that when multiple users are using AI or ML models at the same time, higher-performance hardware can provide better service, while lower-performance hardware may experience latency or slow response. d) Energy consumption and usage cost: On higher-performance hardware, AI or ML models often consume more energy, resulting in higher usage costs. On lower-performance hardware, although performance is limited, AI or ML models have advantages in energy consumption and usage cost, making them suitable for scenarios where performance requirements are not high but energy saving and low cost are important.

[0086] Currently, artificial intelligence agents are widely used in the field of telephone communication, capable of processing or assisting in calls. For example, Figure 4 is a schematic diagram of a service using an artificial intelligence agent to process or assist in calls according to an embodiment of this application. As shown in Figure 4, the services using artificial intelligence agents to process or assist in calls include intelligent answering (referred to as "chatting on behalf") service, intelligent assistance (referred to as "chatting assistance") service, emotional companionship (referred to as "chatting companion") service, and personal assistant service.

[0087] The intelligent proxy service includes express delivery assistant and food delivery assistant services. For example, if terminal 1 calls terminal 2 and terminal 2 uses the intelligent proxy service, the AI ​​agent of terminal 2 can communicate with terminal 1 on behalf of terminal 2.

[0088] Intelligent assistance services include intelligent real-time reminder services. For example, if terminal 1 calls terminal 2 and terminal 1 is using intelligent assistance services, then terminal 1's AI agent can provide services to terminal 1 while terminal 1 is talking to terminal 2.

[0089] The emotional companionship service includes virtual character call services. For example, if terminal 1 uses the emotional companionship service, the AI ​​agent of terminal 1 can communicate with terminal 1. Here, the virtual character can refer to a virtual person with certain human characteristics.

[0090] Personal assistant services include basic life assistant services (knowledge Q&A, weather, search, schedule management), medical assistant services, hotel assistant services, communication assistant services (button-free), food ordering assistant services, travel assistant services, car insurance assistant services, telecommunications service assistant services, and enabling third-party assistant services. For example, if terminal 1 uses the personal assistant service, terminal 1 can call its AI agent, which can then provide services to terminal 1 according to its needs during the call.

[0091] Different terminals and different services have different requirements for the capabilities of AI or ML models. As shown in Table 1 below, the requirements of the food delivery assistant service used by terminal 1, the smart real-time reminder service used by terminal 2, the virtual character caller service used by terminal 3, and the food ordering assistant service used by terminal 4 for the first word segmentation latency, context length, number of dialogue turns, planning ability, tool ability, and reasoning ability of AI or ML models are different.

[0092] Table 1

[0093] Therefore, when a terminal needs to use a service, if the AI ​​or ML model selected by the terminal's artificial intelligence agent does not meet the needs of the terminal or the service, the AI ​​or ML model may not be able to perform the tasks corresponding to the service that the terminal needs to use, thereby affecting the normal operation of the service and resulting in poor service performance.

[0094] Therefore, embodiments of this application provide a communication method for improving service performance.

[0095] In the embodiments of this application, "when," "if," and "if" all refer to the device taking corresponding actions under certain objective circumstances, and are not time-limited, nor do they require the device to perform a judgment action, nor do they imply any other limitations. Unless otherwise specified, "if" and "if" can be substituted, and "when" and "in the case of" can be substituted. "When" and "if" / "if" can be substituted.

[0096] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0097] In this document, "used for indication" can include both direct and indirect indication. For example, when descriptive information I is used to indicate information J, it can mean that information I directly indicates information J or indirectly indicates information J, but it does not necessarily mean that information I carries information J.

[0098] Let information J, indicated by information I, be called the information to be indicated. In practice, there are many ways to indicate the information to be indicated, such as, but not limited to, directly indicating the information to be indicated, such as the information itself or its index. It can also be indirectly indicated by indicating other information, where there is a relationship between the other information and the information to be indicated. It can also indicate only a part of the information to be indicated, while the other parts are known or pre-agreed upon. For example, the indication of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) order of various pieces of information, thereby reducing indication overhead to some extent. Simultaneously, common parts of various pieces of information can be identified and indicated uniformly to reduce the indication overhead caused by individually indicating the same information.

[0099] Furthermore, the specific instruction method can also be any existing instruction method, such as, but not limited to, the above-mentioned instruction methods and their various combinations. As described above, for example, when multiple pieces of information of the same type need to be indicated, the instruction methods for different pieces of information may differ. In specific implementation, the required instruction method can be selected according to specific needs. This application embodiment does not limit the selected instruction method. Therefore, the instruction methods involved in this application embodiment should be understood to cover various methods that enable the party to be instructed to obtain the information to be indicated.

[0100] In the embodiments of this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which may include direct transmission via the air interface or indirect transmission via the air interface by other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which may include direct reception from YY via the air interface or indirect reception from YY via the air interface by other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface.

[0101] Information may undergo necessary processing, such as encoding and modulation, between the source and destination ends, but the destination end can understand the valid information from the source end. Similar statements in the embodiments of this application can be understood in a similar way, and will not be repeated here.

[0102] In this application embodiment, the number of nouns, unless otherwise specified, refers to "singular nouns or plural nouns," that is, "one or more." "At least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " can indicate that the related objects before and after are in an "or" relationship. For example, A / B means: A or B. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c means: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0103] In this application, the ordinal numbers such as "first" and "second" are used to distinguish multiple objects, and are not used to limit the size, content, order, timing, priority, or importance of the multiple objects. For a technical feature, the technical features within that technical feature are distinguished by "A", "B", "C", and "D", and there is no sequential or size order among the technical features described by "A", "B", "C", and "D".

[0104] The solutions provided in the embodiments of this application are described in detail below with reference to the accompanying drawings. In the following description, the communication method provided in the embodiments of this application is used as an example applied to the communication system shown in Figures 1-2. The communication system and application scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. Those skilled in the art will understand that with the evolution of communication systems and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0105] The communication method provided in this application embodiment is described below using a first terminal device, a first network device, a second network device, and a third network device as examples. The first terminal device can be the terminal device shown in Figures 1-2, or a component (such as a chip, processing unit, or processor module) within the terminal device shown in Figures 1-2. The first network device can be the SAAF network element shown in Figure 2, or a component (such as a chip, processing unit, or processor module) within the SAAF network element shown in Figure 2. The second network device can be the DCAS network element shown in Figure 2, or a component (such as a chip, processing unit, or processor module) within the DCAS network element shown in Figure 2. The third network device can be the NRF network element or AAMF network element shown in Figure 2, or a component (such as a chip, processing unit, or processor module) within the NRF network element or AAMF network element shown in Figure 2. When this communication method is implemented by components in the first terminal device, the first network device, the second network device, and the third network device, the receiving and transmitting steps can be understood as the component communicating with other components, for example, communication between a baseband chip and a radio frequency circuit. In the embodiments of this application, the processing performed by a single execution subject can also be divided into multiple execution subjects, which can be logically and / or physically separated.

[0106] Referring to Figure 5, which is a flowchart illustrating a communication method provided in an embodiment of this application, the communication method includes the following steps, as shown in Figure 5.

[0107] S501, the second network device determines the first information. The first information includes first parameter information, which describes the requirements of the first terminal device for the first service and / or the requirements of the first terminal device.

[0108] In this embodiment, the first service may include one or more services required by the first terminal device, such as the intelligent assistance service, the third-party assistant enabling service, and the virtual character caller service shown in Figure 4 above. This embodiment does not limit this.

[0109] It is understood that the requirement of the first service refers to the requirement of the first service for the parameter information of the AI ​​or ML model. The requirement of the first terminal device refers to the requirement of the first terminal device for the parameter information of the AI ​​or ML model. The parameter information of the AI ​​or ML model includes model architecture, model version, initial segmentation latency, subsequent segmentation latency, context length, dialogue rounds, stylization capabilities, etc. This application embodiment does not limit this aspect.

[0110] For example, as shown in Table 2, different businesses have different requirements for AI or ML model capabilities.

[0111] Table 2

[0112] When the primary business is intelligent assistance, it places high demands on the AI ​​or ML model's initial word segmentation latency, subsequent word segmentation latency, number of dialogue rounds, and model parameters. For example, the initial word segmentation latency should be <100 milliseconds, subsequent word segmentation latency <30 milliseconds, the number of dialogue rounds should be >200, and the number of model parameters should be >72 billion. However, the primary business has moderate requirements for the context length of the AI ​​or ML model, such as a context length >10,000 words.

[0113] When the primary business is to enable third-party assistant services, it has high requirements for the initial word segmentation latency, subsequent word segmentation latency, and model parameters of the AI ​​or ML model, such as an initial word segmentation latency of <100 milliseconds and model parameters of >72 billion. However, the primary business has moderate requirements for the context length and dialogue rounds of the AI ​​or ML model, such as a context length of >10,000 words and a dialogue round of >20 rounds.

[0114] When the primary service involves virtual avatars calling, it places high demands on the AI ​​or ML model's context length, number of dialogue turns, and stylization capabilities, such as a context length greater than 50,000 words, a dialogue turn count greater than 200 turns, and support for a humorous style. However, the primary service has moderate requirements for the AI ​​or ML model's initial word segmentation latency, subsequent word segmentation latency, and model parameters, such as an initial word segmentation latency of less than 500 milliseconds, subsequent word segmentation latency of less than 50 milliseconds, and model parameters greater than 7 billion.

[0115] For example, as shown in Table 3 below, different terminal devices have different requirements for AI or ML model capabilities.

[0116] When the first terminal device is Terminal Device 1, it has high requirements for the initial word segmentation latency, subsequent word segmentation latency, number of dialogue rounds, and model parameters of the AI ​​or ML model, such as an initial word segmentation latency of <300 milliseconds, subsequent word segmentation latency of <30 milliseconds, number of dialogue rounds of >200, and model parameters of >72 billion. However, the first business has moderate requirements for the context length of the AI ​​or ML model, such as a context length of >10,000 words.

[0117] When the first terminal device is terminal device 2, the first terminal device has high requirements for the initial word segmentation latency, subsequent word segmentation latency, and context length of the AI ​​or ML model, such as an initial word segmentation latency of <300 milliseconds, a subsequent word segmentation latency of <30 milliseconds, and a context length of >50,000 words. However, the first business has moderate requirements for the number of dialogue rounds and model parameters of the AI ​​or ML model, such as a number of dialogue rounds of >20 rounds and model parameters of >7 billion.

[0118] Table 3

[0119] When the first terminal device is Terminal Device 1, it has high requirements for the initial word segmentation latency, subsequent word segmentation latency, number of dialogue rounds, and model parameters of the AI ​​or ML model, such as an initial word segmentation latency of <300 milliseconds, subsequent word segmentation latency of <30 milliseconds, number of dialogue rounds of >200, and model parameters of >72 billion. However, the first business has moderate requirements for the context length of the AI ​​or ML model, such as a context length of >10,000 words.

[0120] When the first terminal device is terminal device 2, the first terminal device has high requirements for the initial word segmentation latency, subsequent word segmentation latency, and context length of the AI ​​or ML model, such as an initial word segmentation latency of <300 milliseconds, a subsequent word segmentation latency of <30 milliseconds, and a context length of >50,000 words. However, the first business has moderate requirements for the number of dialogue rounds and model parameters of the AI ​​or ML model, such as a number of dialogue rounds of >20 rounds and model parameters of >7 billion.

[0121] The following section describes how the second network device determines the first information segment.

[0122] In scenario A1, upon receiving a session establishment request, the second network device can establish a media channel between the first terminal device and the media function network element through the voice service processing network element.

[0123] The session establishment request can be used to request the establishment of a session between the first terminal device and the second terminal device or the first network device.

[0124] A session establishment request may include call information. Call information may include one or more of the following: calling number, called number, or call type. Call types include consumer-to-consumer (C2C) calls and / or consumer-to-machine (C2M) calls. This application does not limit the scope of the embodiments described herein.

[0125] It is understood that the session establishment request can be initiated by the first terminal device to request the establishment of a session between the first terminal device (i.e., the calling party) and the second terminal device (i.e., the called party); or, the session establishment request can be initiated by the first terminal device to request the establishment of a session between the first terminal device (i.e., the calling party) and the first network device (i.e., the called party); or, the session establishment request can be initiated by the second terminal device to request the establishment of a session between the second terminal device (i.e., the calling party) and the first terminal device (i.e., the called party). This application does not limit this aspect.

[0126] The media channel can be used to transmit media information corresponding to the first service required by the first terminal device. The media information can be one or more of audio, video, images, or text, and this application embodiment does not limit this.

[0127] Media function network elements (such as MF network elements) can be used to process media information, such as encoding and decoding media information, or format conversion of media information. Voice service processing network elements (such as VoLTE AS network elements) can be used to process voice services, such as handling call initiation, reception, and termination. Establishing a media channel between the first terminal device and the media function network element through the voice service processing network element can be understood as the voice service processing network element establishing media channels with both the first terminal device and the media function network element.

[0128] The second network device can also, upon receiving a session establishment request, determine the first service from the subscribed services of the first terminal device based on the call information, and then determine the first information.

[0129] For example, when a first terminal device calls a second terminal device, if the first terminal device needs to use a smart assistance service as shown in Figure 4 above (e.g., a smart real-time reminder service), then the first network device needs to provide services to the first terminal device during the call between the first and second terminal devices. Therefore, the first terminal device can send a session establishment request to the second network device. This request requests the establishment of a session between the first and second terminal devices. After receiving this session establishment request from the first terminal device, the second network device can determine that the first terminal device needs to use a smart assistance service during the call with the second terminal device, and send information describing the need for the smart assistance service and / or the needs of the first terminal device to the first network device. This allows the first network device to select an appropriate AI or ML model to provide services to the first terminal device during the call.

[0130] As shown in Figure 6a, taking the first service required by the first terminal device as intelligent assisted service, the first terminal device as UE1, the second terminal device as UE2, the first network device as SAAF network element, the second network device as DCAS network element, the media function network element as MF network element, and the voice service processing network element as VoLTE AS network element as an example, this application can perform the following steps.

[0131] Steps A0-A4 are the intelligent auxiliary service setup stage, and steps A5-A16 are the C2C call establishment stage.

[0132] Step A0: The SAAF network element is pre-configured to support intelligent auxiliary services.

[0133] Step A1: UE1 sends a Smart Assisted Service Subscription Request to the DCAS network element, and the DCAS network element receives the Smart Assisted Service Subscription Request from UE1. The Smart Assisted Service Subscription Request includes parameter information for the Smart Assisted Service.

[0134] Step A2: The DCAS network element sends a call event subscription request to the DCSF network element, and the DCSF network element receives the call event subscription request from the DCAS network element. The call event subscription request is used to subscribe to call events related to the intelligent assistance service. When a call event related to the intelligent assistance service occurs, the DCSF network element immediately notifies the DCAS network element.

[0135] Step A3: The DCSF network element sends a call event subscription response to the DCAS network element, and the DCAS network element receives the call event subscription response from the DCSF network element.

[0136] Step A4: The DCAS network element sends a smart assisted service subscription response to UE1, and UE1 receives the smart assisted service subscription response from the DCAS network element.

[0137] Step A5: When a user belonging to UE1 dials the phone number of a user belonging to UE2, UE1 sends an INVITE message to the VoLTE AS network element. Correspondingly, the VoLTE AS network element receives an invitation (INVITE) message from UE1. The INVITE message is used to request the establishment of a session, such as a voice call, video call, or other types of multimedia session.

[0138] Step A6: The VoLTE AS network element sends a BEGIN message to the DCSF network element, and the DCSF network element receives the BEGIN message from the VoLTE AS network element. The BEGIN message indicates that a new session has begun.

[0139] Step A7: The DCSF network element sends a BEGIN message to the DCAS network element, and the DCAS network element receives the BEGIN message from the DCSF network element.

[0140] Step A8: The DCAS network element sends a CONTINUE message to the DCSF network element. Correspondingly, the DCSF network element receives the CONTINUE message from the DCAS network element. The CONTINUE message indicates that the DCAS network element has completed the relevant processing logic and allows the DCSF network element to continue processing the current session.

[0141] Step A9: The VoLTE AS network element sends a media resource creation request to the MF network element, and the MF network element receives the media resource creation request from the VoLTE AS network element.

[0142] Step A10: The VoLTE AS network element sends a 183 response message, a 180 ringing message, and a 200 response message 1 to UE1. Correspondingly, UE1 receives the 183 response message, the 180 ringing message, and the 200 response message 1 from the VoLTE AS network element. The 183 response message is a temporary response message indicating that the session is in progress but not yet complete. The 180 ringing message notifies the initiator (e.g., UE1) that the called party (e.g., the VoLTE AS network element) has received the call request and is attempting to connect. The 200 response message 1 confirms receipt of the 180 ringing message.

[0143] Step A11: UE1 sends an acknowledgment (ACK) message to the VoLTE AS network element, and UE1 receives the ACK message from the VoLTE AS network element accordingly.

[0144] Step A12: The VoLTE AS network element sends a re-INVITE message to UE1. Correspondingly, UE1 receives the re-INVITE message from the VoLTE AS network element. The re-INVITE message is used to request a session update.

[0145] Step A13: UE1 sends a 200 response message 2 to the VoLTE AS network element, and correspondingly, UE1 receives a 200 response message 2 from the VoLTE AS network element. The 200 response message 2 is used to confirm receipt of the re-INVITE message.

[0146] Step A14: The VoLTE AS network element sends an update media resource request to the MF network element, and the MF network element receives the update media resource request from the VoLTE AS network element.

[0147] Step A15: The VoLTE AS network element sends an ANSWER message to the DCSF network element, and correspondingly, the DCSF network element receives the ANSWER message from the VoLTE AS network element. The ANSWER message indicates that the session has been established.

[0148] Step A16: The DCSF network element sends an ANSWER message to the DCAS network element, and the DCAS network element receives the ANSWER message from the DCSF network element.

[0149] It is understandable that in step A7 above, after the DCAS network element receives the BEGIN message from the DCAS network element, the DCAS network element can determine that UE1 needs to use the intelligent assistance service based on the fact that the calling number is the phone number of the user to which UE1 belongs, the called number is the phone number of the user to which UE2 belongs, the call type is a C2C call, and UE1 has subscribed to the intelligent assistance service. In this way, the DCAS network element can determine the information used to describe the demand for the intelligent assistance service and / or the demand for UE1.

[0150] In step A5 above, UE1 requests to establish a media channel with the VoLTE AS network element by sending an INVITE message to the VoLTE AS network element; in step A9 above, the VoLTE AS network element requests to establish a media channel with the MF network element by sending a media resource creation request to the MF network element.

[0151] For example, if the first terminal device needs to use a personal assistant service as shown in Figure 4 above (such as a food ordering assistant service, enabling third-party assistant services, etc.), then the first terminal device needs to call the first network device. The first network device needs to provide services to the first terminal device according to its needs during the call. Therefore, the first terminal device can send a session establishment request to the second network device. This session establishment request is used to request the establishment of a session between the first terminal device and the first network device. After receiving the session establishment request from the first terminal device, the second network device can determine that the first terminal device needs to use the personal assistant service during the call with the second terminal device, and send information describing the needs of the personal assistant service and / or the needs of the first terminal device to the first network device, so that the first network device can select an appropriate AI or ML model to provide services to the first terminal device according to its needs during the call.

[0152] As shown in Figure 6b, taking the first service required by the first terminal device as enabling the third-party assistant service, the first terminal device as UE1, the first network device as SAAF network element, the second network device as DCAS network element, the media function network element as MF network element, and the voice service processing network element as VoLTE AS network element as an example, this application can perform the following steps.

[0153] Steps B0-B7 are the enable third-party assistant setup stage, and steps B8-B19 are the C2M call establishment stage.

[0154] Step B0: The third-party application sends a registration request to the DCAS network element, and the DCAS network element receives the registration request from the third-party application. The registration request is used to request the third-party application to register with the DCAS network element.

[0155] Step B1: The DCAS network element sends a registration enable third-party tool request to the SAAF network element. Correspondingly, the SAAF network element receives the registration enable third-party tool request from the DCAS network element. This registration enable third-party tool request is used to request the registration of third-party applications with the SAAF network element.

[0156] Step B2: The SAAF network element sends a registration enable third-party tool response to the DCAS network element, and the DCAS network element receives the registration enable third-party tool response from the SAAF network element.

[0157] Step B3: The DCAS network element sends a registration response to the third-party application, and the third-party application receives the registration response from the DCAS network element.

[0158] Step B4: UE1 sends an enable third-party assistant service subscription request to the DCAS network element. Correspondingly, the DCAS network element receives the enable third-party assistant service subscription request from UE1. The enable third-party assistant service subscription request includes parameter information for enabling the third-party assistant service, such as the third-party application access number information configured by UE1, and the third-party application authorized login information.

[0159] Step B5: The DCAS network element sends a call event subscription request to the DCSF network element, and the DCSF network element receives the call event subscription request from the DCAS network element. The call event subscription request is used to subscribe to call events related to enabling the third-party assistant service. When a call event related to enabling the third-party assistant service occurs, the DCSF network element will immediately notify the DCAS network element.

[0160] Step B6: The DCSF network element sends a call event subscription response to the DCAS network element, and the DCAS network element receives the call event subscription response from the DCSF network element.

[0161] Step B7: The DCAS network element sends an enable third-party assistant service subscription response to UE1. Correspondingly, UE1 receives the enable third-party assistant service subscription response from the DCAS network element.

[0162] Step B8: When a user belonging to UE1 dials a third-party application number, UE1 sends an INVITE message to the VoLTE AS network element, and the VoLTE AS network element receives the INVITE message from UE1.

[0163] Step B9: The VoLTE AS network element sends a BEGIN message to the DCSF network element, and correspondingly, the DCSF network element receives the BEGIN message from the VoLTE AS network element.

[0164] Step B10: The DCSF network element sends a BEGIN message to the DCAS network element, and the DCAS network element receives the BEGIN message from the DCSF network element.

[0165] Step B11: The DCAS network element sends a CONTINUE message to the DCSF network element, and correspondingly, the DCSF network element receives the CONTINUE message from the DCAS network element.

[0166] Step B12: The VoLTE AS network element sends a media resource creation request to the MF network element, and the MF network element receives the media resource creation request from the VoLTE AS network element.

[0167] Step B13: The VoLTE AS network element sends a 183 response message, a 180 ringing message, and a 200 response message 1 to UE1. Correspondingly, UE1 receives the 183 response message, the 180 ringing message, and the 200 response message 1 from the VoLTE AS network element.

[0168] Step B14: UE1 sends an ACK message to the VoLTE AS network element, and correspondingly, UE1 receives an ACK message from the VoLTE AS network element.

[0169] Step B15: The VoLTE AS network element sends a re-INVITE message to UE1, and UE1 receives the re-INVITE message from the VoLTE AS network element.

[0170] Step B16: UE1 sends a 200 response message 2 to the VoLTE AS network element, and correspondingly, UE1 receives a 200 response message 2 from the VoLTE AS network element.

[0171] Step B17: The VoLTE AS network element sends an update media resource request to the MF network element, and the MF network element receives the update media resource request from the VoLTE AS network element.

[0172] Step B18: The VoLTE AS network element sends an ANSWER message to the DCSF network element, and correspondingly, the DCSF network element receives the ANSWER message from the VoLTE AS network element.

[0173] Step B19: The DCSF network element sends an ANSWER message to the DCAS network element, and correspondingly, the DCAS network element receives the ANSWER message from the DCSF network element.

[0174] It is understood that steps B8-B19 can be referred to as steps A5-A16 above, and will not be repeated here.

[0175] It is understandable that in step B10 above, after the DCAS network element receives the BEGIN message from the DCAS network element, the DCAS network element can determine that UE1 needs to use the enabled third-party assistant service and has been matched with a third-party application based on the fact that the calling number is the phone number of the user to which UE1 belongs, the called number is the third-party application number, the call type is C2M call, and UE1 has subscribed to enable the third-party assistant service and has been matched with a third-party application. In this way, the DCAS network element can determine the information used to describe the needs of enabling the third-party assistant service and / or the needs of UE1.

[0176] In step B8 above, UE1 requests to establish a media channel with the VoLTE AS network element by sending an INVITE message to the VoLTE AS network element; in step B12 above, the VoLTE AS network element requests to establish a media channel with the MF network element by sending a media resource creation request to the MF network element.

[0177] For example, when a second terminal device calls a first terminal device, if the first terminal device needs to use a smart answering service as shown in Figure 4 above (such as a courier assistant service, a food delivery assistant service, etc.), then the first network device needs to communicate with the second terminal device on behalf of the first terminal device. Therefore, the second terminal device can send a session establishment request to the second network device. This session establishment request is used to request the establishment of a session between the second terminal device and the first terminal device. After receiving this session establishment request from the second terminal device, the second network device can determine that the first terminal device needs to use the smart answering service when communicating with the second terminal device, and send information describing the need for the smart answering service and / or the needs of the first terminal device to the first network device, so that the first network device can select a suitable AI or ML model to communicate with the second terminal device on behalf of the first terminal device.

[0178] In scenario A2, the second network device can establish a media channel between the first terminal device and the media function network element through the voice service processing network element, provided that the first condition is met.

[0179] The first condition can be pre-configured, standard-defined, or negotiated between the second network device and the first terminal device, such as being configured by the first terminal device to the second network device. This embodiment of the application does not limit this. The first condition may include the identification information of the first terminal device, the identification information of the first service, and the condition for triggering the first service. The condition for triggering the first service may include, for example, reaching a pre-configured time or receiving pre-configured user input information. This embodiment of the application does not limit this.

[0180] The second network device can also determine the first information based on the identification information of the first terminal device and the identification information of the first service, provided that the first condition is met.

[0181] For example, if the first terminal device needs to use the emotional companionship service (e.g., virtual character caller service) as shown in Figure 4 above, then the first network device needs to communicate with the first terminal device. Therefore, after the first condition is met, the second network device can determine that the first terminal device needs to use the emotional companionship service, and send information describing the need for the emotional companionship service and / or the needs of the first terminal device to the first network device, so that the first network device can select an appropriate AI or ML model to communicate with the first terminal device.

[0182] For example, as shown in Figure 6c, taking the first service required by the first terminal device as the virtual character caller service, the first terminal device as UE1, the first network device as the SAAF network element, the second network device as the DCAS network element, the media function network element as the MF network element, and the voice service processing network element as the VoLTE AS network element as an example, this application can perform the following steps.

[0183] Steps C0-C4 are the virtual character caller service setup stage, and steps A5-A21 are the machine-to-consumer (M2C) call establishment stage.

[0184] Step C0: The SAAF network element is pre-configured to support virtual character caller service.

[0185] Step C1: UE1 sends a virtual character caller ID service subscription request to the DCAS network element. Correspondingly, the DCAS network element receives the virtual character caller ID service subscription request from UE1. The virtual character caller ID service subscription request includes parameter information for the virtual character caller ID service, such as the virtual character caller ID information, virtual character identifier information, and opening remarks configured by UE1.

[0186] Step C2: The DCAS network element sends a call event subscription request to the DCSF network element, and the DCSF network element receives the call event subscription request from the DCAS network element. The call event subscription request is used to subscribe to call events related to the virtual character call service. When a call event related to the virtual character call service occurs, the DCSF network element immediately notifies the DCAS network element.

[0187] Step C3: The DCSF network element sends a call event subscription response to the DCAS network element, and the DCAS network element receives the call event subscription response from the DCSF network element.

[0188] Step C4: The DCAS network element sends a virtual person caller service subscription response to UE1, and UE1 receives the virtual person caller service subscription response from the DCAS network element.

[0189] Step C5: Upon reaching the virtual character's incoming call time configured for UE1, the DCAS network element sends an outbound call request to the DCSF network element. Correspondingly, the DCSF network element receives the outbound call request from the DCAS network element. This outbound call request is used to request triggering the virtual character's incoming call, configure call information (e.g., caller ID, called number, or displayed number), and create media resources (e.g., audio and video).

[0190] Step C6: The DCSF network element sends an outbound call request to the VoLTE AS network element, and the VoLTE AS network element receives the outbound call request from the DCSF network element.

[0191] Step C7: The VoLTE AS network element sends an INVITE message to UE1, and UE1 receives the INVITE message from the VoLTE AS network element. The INVITE message is used to request the establishment of a session, such as a voice call, video call, or other types of multimedia session.

[0192] Step C8: The VoLTE AS network element sends a media resource creation request to the MF network element, and the MF network element receives the media resource creation request from the VoLTE AS network element.

[0193] In step C9, UE1 sends a 183 response message to the VoLTE AS network element, and the VoLTE AS network element receives the 183 response message from UE1. The 183 response message is a temporary response message used to indicate that the session is in progress but has not yet been completed.

[0194] Step C10: The VoLTE AS network element sends a provisional response acknowledgment (PRACK) message to UE1. Correspondingly, UE1 receives the PRACK message from the VoLTE AS network element. It can be understood that after receiving the PRACK message from the VoLTE AS network element, UE1 can send a 200 response message 1 to the VoLTE AS network element, and the VoLTE AS network element can receive the 200 response message 1 from UE1. The PRACK message is used to confirm receipt of the 183 response message. The 200 response message 1 is used to confirm receipt of the PRACK message.

[0195] In step C11, UE1 sends an update message to the VoLTE AS network element, and the VoLTE AS network element receives the update message from UE1. It can be understood that after receiving the update message from UE1, the VoLTE AS network element can send a 200 response message 2 to UE1, and UE1 can receive a 200 response message 2 from the VoLTE AS network element. The update message is used to confirm the resource reservation status. The 200 response message 2 is used to confirm receipt of the update message.

[0196] In step C12, UE1 sends a 180 ringing message to the VoLTE AS network element, and the VoLTE AS network element receives the 180 ringing message from UE1. The 180 ringing message is used to notify the initiating party (such as the VoLTE AS network element) that the called party (such as UE1) has received the call request and is attempting to connect.

[0197] In step C13, UE1 sends a 200 response message 3 to the VoLTE AS network element, and the VoLTE AS network element receives the 200 response message 3 from UE1. The 200 response message 3 is used to confirm receipt of the 180 ringing message.

[0198] Step C14: The VoLTE AS network element sends an acknowledgment (ACK) message 1 to UE1. Correspondingly, UE1 receives the ACK message 1 from the VoLTE AS network element.

[0199] In step C15, UE1 sends a re-INVITE message to the VoLTE AS network element, and correspondingly, UE1 receives a re-INVITE message from the VoLTE AS network element. The re-INVITE message is used to request a session update and includes SDP information (used to negotiate session media parameters, such as audio and video).

[0200] Step C16: The VoLTE AS network element sends a 200 Response Message 4 to UE1. Correspondingly, UE1 receives the 200 Response Message 4 from the VoLTE AS network element. The 200 Response Message 4 is used to acknowledge receipt of the re-INVITE message. The 200 Response Message 4 includes SDP information (used to negotiate media parameters for the session, such as audio and video).

[0201] Step C17: The VoLTE AS network element sends an update media resource request to the MF network element, and correspondingly, the MF network element receives the update media resource request from the VoLTE AS network element.

[0202] Step C18: VoLTE AS network element UE1 sends ACK message 2, and correspondingly, UE1 receives ACK message 2 from VoLTE AS network element.

[0203] Step C19: The VoLTE AS network element sends an outbound call response to the DCAS network element, and correspondingly, the DCAS network element receives the outbound call response from the VoLTE AS network element. The outbound call response includes the UE1's audio stream address (Uniform Resource Locator, URL) 1 and video stream address (URL 2).

[0204] Step C20: The DCAS network element sends an outbound party response to the DCSF network element, and correspondingly, the DCSF network element receives the outbound party response from the DCAS network element.

[0205] Step C21: The DCSF network element sends a 200 response message 5 to the DCAS network element. Correspondingly, the DCAS network element receives the 200 response message from the DCSF network element. The 200 response message 5 is used to confirm receipt of a response from the outgoing party.

[0206] It is understandable that in step C5 above, after the virtual person's call time configured for UE1 is reached, the DCAS network element can determine that UE1 needs to use the virtual person for the call. The DCAS network element can then send an outbound call request to the VoLTE AS network element, instructing the VoLTE AS network element to establish media channels with both UE1 and the MF network element. For example, in step C7 above, the VoLTE AS network element requests to establish a media channel with UE1 by sending an INVITE message to UE1; in step C8 above, the VoLTE AS network element requests to establish a media channel with the MF network element by sending a media resource creation request to the MF network element.

[0207] In one possible implementation, the first information may further include one or more of the following: identification information of the first terminal device; identification information of the first service; and parameter information of the first service. This application does not limit this aspect.

[0208] For example, the first piece of information can be shown in Table 4 below.

[0209] Table 4

[0210] S502, the second network device receives the second information. The second information indicates that a media channel has been successfully established between the first terminal device and the media function network element, and the media channel is used to transmit media information corresponding to the first service.

[0211] In this embodiment of the application, the second information may be encapsulated or carried in a Hypertext Transfer Protocol (HTTP) message, or it may be encapsulated or carried in other messages. This embodiment of the application does not limit this.

[0212] The media channel between the first terminal device and the media function network element has been successfully established. This can be understood as the first terminal device being successfully called as the called terminal device or as the calling terminal device in an M2C call, C2M call, or C2C call, and the media channel between the first terminal device and the MF network element has been successfully established.

[0213] For example, as shown in Figure 6a, in step A19 above, after the DCAS network element receives the outgoing party's response from the VoLTE AS network element, the DCAS network element can determine that UE1 has been successfully called as the called terminal in the M2C call, and that the media channel between UE1 and the MF network element has been successfully established.

[0214] For example, as shown in Figure 6b, in step B16 above, after the DCAS network element receives the ANSWER message from the DCSF network element, the DCAS network element can determine that UE1 has successfully made a call as the calling terminal in the C2M call, and that the media channel between UE1 and the MF network element has been successfully established.

[0215] For example, as shown in Figure 6c, in step C19 above, after the DCAS network element receives the ANSWER message from the DCSF network element, the DCAS network element can determine that UE1 has successfully made a call as the calling terminal in the C2M call, and that the media channel between UE1 and the MF network element has been successfully established.

[0216] S503, the second network device sends the first information, and correspondingly, the first network device receives the first information.

[0217] In the embodiments of this application, the first information may be encapsulated or carried in an HTTP message, or it may be encapsulated or carried in other messages. The embodiments of this application do not limit this.

[0218] It is understood that the first information may also include the identification information of the first terminal device and the identification information of the first service. The identification information of the first terminal device and the identification information of the first service are used to instruct the first network device and the first terminal device to select a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device. This instruction method can be understood as an indirect instruction method. Alternatively, the first information may also include first instruction information, which is used to instruct the first network device to select a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device. This instruction method can also be understood as a direct instruction method. The embodiments of this application do not limit this.

[0219] For example, as shown in Figure 6d, taking the first service required by the first terminal device as intelligent assisted service, the first terminal device as UE1, the first network device as SAAF network element, the second network device as DCAS network element, the media function network element as MF network element, and the voice service processing network element as VoLTE AS network element as an example, after executing step A16 shown in Figure 6a above, this application can also execute the following steps.

[0220] Step A17: The DCAS network element sends a service initiation request to the SAAF network element through the DCSF network element. Correspondingly, the SAAF network element receives the service initiation request from the DCAS network element through the DCSF network element. The service initiation request includes information indicating the requirements of the intelligent assisted services that UE1 needs to use and / or the requirements of UE1 itself.

[0221] Step A18: The SAAF network element sends a service initiation response to the DCAS network element through the DCSF network element. Correspondingly, the DCAS network element receives the service initiation response from the SAAF network element through the DCSF network element.

[0222] Step A19: The DCSF network element sends a media stream copy request to the MF network element, and the MF network element receives the media stream copy request from the DCSF network element.

[0223] Step A20: The MF network element sends a push media replication request to the SAAF network element, and correspondingly, the SAAF network element receives the push media replication request from the MF network element.

[0224] Step A21: The SAAF network element sends a push media replication response to the MF network element, and the MF network element receives the push media replication response from the SAAF network element.

[0225] Step A22: The MF network element sends a media stream replication response to the DCSF network element, and the corresponding DCSF network element receives the media stream replication response from the MF network element.

[0226] It can be understood that steps A19-A22 are used to copy the media channel between UE1 and the MF network element to the media channel between UE1 and the SAAF network element, that is, to establish a media channel between UE1 and the SAAF network element. The media channel between UE1 and the SAAF network element can be used to transmit media information corresponding to the intelligent auxiliary services that UE1 needs to use.

[0227] S504. The first network device selects a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device based on the first parameter information.

[0228] In this embodiment of the application, after receiving the first information, the first network device can determine that the first terminal device needs to use the first service. In order to improve the performance of the first service, the first network device can implement the first service by selecting a first AI or ML model that matches the needs of the first service and / or the needs of the first terminal device.

[0229] The following sections will describe different scenarios based on whether the first network device stores parameter information for AI or ML models.

[0230] In scenario B1, the first network device stores parameter information for an AI or ML model. As shown in Figure 6e, the first network device can perform the following steps a1-a2 to select a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device.

[0231] Step a1: Based on the first parameter information, select at least one AI or ML model that matches the needs of the first service and / or the needs of the first terminal device.

[0232] For example, taking the selection of at least one AI or ML model that matches the needs of the first service and the first terminal device as an example, the first network device may store the parameter information of the AI ​​or ML model as shown in Table 5 below. As shown in Table 5 below, the parameter information of different AI or ML models is different.

[0233] Table 5

[0234] When the requirements of the first service are: initial word segmentation latency < 300 milliseconds, subsequent word segmentation latency < 30 milliseconds, context length > 10,000 words, and number of dialogue rounds > 20, and the requirements of the first terminal device are: initial word segmentation latency < 300 milliseconds, subsequent word segmentation latency < 30 milliseconds, context length > 30,000 words, and number of dialogue rounds > 200, that is, when the requirements of the first service and the first terminal device are: initial word segmentation latency < 300 milliseconds, subsequent word segmentation latency < 30 milliseconds, context length > 30,000 words, and number of dialogue rounds > 200, the first network device can determine that AI or ML model 1 and AI or ML model 2 match the requirements of the first service and the first terminal device, while AI or ML model 3 does not match the requirements of the first service and the first terminal device.

[0235] Step a2: Select a first AI or ML model from at least one AI or ML model that matches the needs of the first service and / or the needs of the first terminal device.

[0236] Specifically, the first network device can determine the second parameter information and, based on the second parameter information, select a first AI or ML model from at least one AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device. The second parameter information describes the highest priority requirement among the requirements of the first service and / or the requirements of the first terminal device.

[0237] For example, the requirements for the first service are: initial word segmentation latency <300 milliseconds, subsequent word segmentation latency <30 milliseconds, context length >3000 words, and number of dialogue rounds >20. When the number of dialogue rounds >20 is the highest priority requirement, the first network device can select the AI ​​or ML model 3 with the smallest number of dialogue rounds from AI or ML model 1 and AI or ML model 3 that match the requirements of the first service to implement the first service. Alternatively, the first network device can select the AI ​​or ML model 1 with the highest number of dialogue rounds from AI or ML model 1 and AI or ML model 3 that match the requirements of the first service to implement the first service.

[0238] In other words, the first network device can select the AI ​​or ML model that best matches the highest priority requirement among the requirements of the first service and / or the requirements of the first terminal device from at least one AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device to implement the first service, thereby reducing the waste of AI or ML model resources while ensuring the normal operation of the service.

[0239] In scenario B2, the first network device does not store parameter information for the AI ​​or ML model. As shown in Figure 6f, the first network device can select a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device by performing the following steps b1-b3.

[0240] Step b1: The first network device sends first parameter information to the third network device, and correspondingly, the third network device receives the first parameter information from the first network device.

[0241] The first parameter information can be encapsulated or carried in an HTTP message, or it can be encapsulated or carried in other messages. This application embodiment does not limit this.

[0242] The third network device stores parameter information of the AI ​​or ML model. The method by which the third network device selects at least one AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device can be referred to the method by which the first network device selects at least one AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device in step a1 above, and will not be repeated here.

[0243] Step b2: The third network device sends third information to the first network device, and correspondingly, the first network device receives the third information from the third network device.

[0244] The third information may be encapsulated or carried in an HTTP message, or it may be encapsulated or carried in other messages. This application does not limit this.

[0245] The third information can be used to indicate at least one AI or ML model that matches the needs of the first business and / or the needs of the first terminal device.

[0246] The third information may include one or more of the following: identification information of at least one AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device; parameter information of at least one AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device. This application does not limit this information.

[0247] Step b3: Select a first AI or ML model from at least one AI or ML model that matches the needs of the first service and / or the needs of the first terminal device.

[0248] For details on step b3, please refer to step a2 above; it will not be repeated here.

[0249] According to the above scheme, when the first terminal device needs to use the first service, the second network device can indicate the needs of the first terminal and / or the needs of the first terminal device to the first network device, so that the first network device can select a first AI or ML model that matches the needs of the first service and / or the needs of the first terminal device, so that the first AI or ML model can perform the task corresponding to the first service, thereby ensuring the normal operation of the service and improving the service performance.

[0250] In the embodiments provided above, the methods provided by the embodiments of this application are described using the execution of a first network device and a second network device as examples. In this application, each embodiment can be implemented independently or in combination based on certain inherent connections; in each embodiment, different implementation methods can be implemented in combination or independently. To achieve the functions in the methods provided by the embodiments of this application above, the steps executed by the terminal device can be implemented by different functional entities constituting the terminal device. The steps executed by the network device can be implemented by different functional entities constituting the network device. To achieve the functions in the methods provided by the embodiments of this application above, the first network device and the second network device may include hardware structures and / or software modules, implementing the above functions in the form of hardware structures, software modules, or hardware structures plus software modules. Whether a certain function is executed in the form of hardware structures, software modules, or hardware structures plus software modules depends on the specific application and design constraints of the technical solution.

[0251] The methods provided by the embodiments of this application have been described above with reference to the accompanying drawings. The apparatus provided by the embodiments of this application will be described below with reference to the accompanying drawings.

[0252] Based on the same technical concept, embodiments of this application provide a communication device, which includes a module / unit / means for executing the method performed by the device in the above-described method embodiments. This module / unit / means can be implemented in software, or in hardware, or implemented by hardware executing corresponding software.

[0253] For example, referring to Figure 7, which is a schematic diagram of a communication device 700, the device 700 includes a transceiver module 701 and a processing module 702. This device can be the first network device or the second network device described above.

[0254] When the device 700 is a first network device, the functions of each module of the device 700 are as follows:

[0255] The transceiver module 701 is used to receive first information from the second network device. The first information includes first parameter information, which describes the requirements of the first terminal device for the first service and / or the requirements of the first terminal device.

[0256] The processing module 702 is configured to select a first AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device based on the first parameter information.

[0257] In one possible implementation, the first information is sent by the second network device upon receiving the second information, the second information being used to indicate that a media channel has been successfully established between the first terminal device and the media function network element, the media channel being used to transmit media information corresponding to the first service.

[0258] In one possible implementation, the processing module 702 is configured to select at least one AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device based on the first parameter information; and select the first AI or ML model from the at least one AI or ML model.

[0259] In one possible implementation, the transceiver module 701 is configured to send the first parameter information to a third network device, the third network device being configured to store parameter information of an AI or ML model; receive third information from the third network device, the third information being configured to indicate at least one AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device; and the processing module 702 is configured to determine the first AI or ML model from the at least one AI or ML model.

[0260] In one possible implementation, the third information includes the identification information of the at least one AI or ML model and / or the parameter information of the at least one AI or ML model.

[0261] In one possible implementation, the processing module 702 is configured to determine second parameter information, the second parameter information being used to describe the highest priority requirement among the requirements of the first service and / or the requirements of the first terminal device; and to select the first AI or ML model from the at least one AI or ML model based on the second parameter information.

[0262] In one possible implementation, the first information may further include one or more of the following: identification information of the first terminal device; identification information of the first service; and parameter information of the first service.

[0263] Alternatively, when the device 700 is a second network device, the functions of each module of the device 700 are as follows:

[0264] Processing module 702 is used to determine first information, the first information including first parameter information, the first parameter information being used to describe the requirements of the first service to be used by the first terminal device and / or the requirements of the first terminal device;

[0265] The transceiver module 701 receives second information, which indicates that a media channel has been successfully established between the first terminal device and the media function network element, and the media channel is used to transmit media information corresponding to the first service.

[0266] The transceiver module 701 sends the first information to the first network device according to the second information, and instructs the first network device to select a first AI or ML model that matches the needs of the first service and / or the needs of the first terminal device.

[0267] In one possible implementation, before receiving the second information, the processing module 702 is configured to establish the media channel between the first terminal device and the media function network element through the voice service processing network element when the first condition is met or a session establishment request is received; wherein, the session establishment request is used to request the establishment of a session between the first terminal device and the second terminal device or the first network device.

[0268] In one possible implementation, the first condition includes the identifier of the first terminal device, the identifier of the first service, and the condition for triggering the first service. The processing module 702 is specifically used to determine the first information based on the identifier information of the first terminal device and / or the identifier information of the first service when the first condition is met.

[0269] In one possible implementation, the session establishment request includes call information. Before determining the first information, the processing module 702 is further configured to, upon receiving the session establishment request, determine the first service from the subscribed services of the first terminal device based on the call information.

[0270] In one possible implementation, the call information includes one or more of the following: calling number, called number, or call type.

[0271] In one possible implementation, the first information includes one or more of the following: identification information of the first terminal device; identification information of the first service; and parameter information of the first service.

[0272] In practical implementation, the above-mentioned device 700 can have various product forms. Several possible product forms are introduced below.

[0273] Referring to Figure 8, which is a schematic diagram of another communication device, the communication device 800 includes a processor 801, which uses logic circuits or execution instructions to implement the methods executed by the communication device or terminal device in the above method embodiments.

[0274] Optionally, the communication device 800 may further include an interface circuit 802, which is used to receive signals from other communication devices outside the communication device and transmit them to the processor 801, or to send signals from the processor 801 to other communication devices outside the communication device. The processor 801 and the interface circuit 802 are coupled to each other. It is understood that the interface circuit 802 can be a transceiver or an input / output interface.

[0275] Optionally, the communication device 800 may also include a memory 803 for storing instructions executed by the processor 801, or storing input data required by the processor 801 to execute instructions, or storing data generated after the processor 801 executes instructions.

[0276] It should be understood that the processor mentioned in the embodiments of this application can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor, implemented by reading software code stored in memory.

[0277] For example, the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), microprocessor units (MPUs), microcontroller units (MCUs), graphics processing units (GPUs), field-programmable gate arrays (FPGAs), artificial intelligence processors (AI processors) or neural processing units (NPUs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0278] It should be understood that the memory mentioned in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be cache or random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0279] It is understandable that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor.

[0280] It should be noted that the memories described herein are intended to include, but are not limited to, these and any other suitable types of memories.

[0281] Based on the same technical concept, embodiments of this application also provide a computer-readable storage medium storing a computer program or instructions, which, when executed by a processor, causes the methods executed by the first network device and the second network device in the above method embodiments to be implemented.

[0282] Based on the same technical concept, this application also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, cause the methods executed by the first network device and the second network device in the above method embodiments to be implemented.

[0283] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0284] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0285] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0286] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

Claims

1. A communication method, characterized in that, Applied to a first network device, the method includes: Receive first information from a second network device, the first information including first parameter information, the first parameter information being used to describe the requirements of a first service that the first terminal device needs to use and / or the requirements of the first terminal device; Based on the first parameter information, select a first AI or ML model that matches the needs of the first service and / or the needs of the first terminal device.

2. The method according to claim 1, characterized in that, The first information is sent by the second network device upon receiving the second information. The second information is used to indicate that a media channel has been successfully established between the first terminal device and the media function network element. The media channel is used to transmit media information corresponding to the first service.

3. The method according to claim 1 or 2, characterized in that, Based on the first parameter information, selecting a first AI or ML model that matches the needs of the first service and / or the needs of the first terminal device includes: Based on the first parameter information, select at least one AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device; The first AI or ML model is selected from the at least one AI or ML model.

4. The method according to claim 1 or 2, characterized in that, Based on the first parameter information, selecting a first AI or ML model that matches the needs of the first service and / or the needs of the first terminal device includes: The first parameter information is sent to a third network device, which is used to store the parameter information of the AI ​​or ML model; Receive third information from the third network device, the third information being used to indicate at least one AI or ML model that matches the requirements of the first service and / or the requirements of the first terminal device; The first AI or ML model is selected from the at least one AI or ML model.

5. The method according to claim 4, characterized in that, The third information includes the identification information of the at least one AI or ML model and / or the parameter information of the at least one AI or ML model.

6. The method according to any one of claims 3-5, characterized in that, Selecting the first AI or ML model from the at least one AI or ML model includes: Determine the second parameter information, which is used to describe the highest priority requirement among the requirements of the first service and / or the requirements of the first terminal device; Based on the second parameter information, the first AI or ML model is selected from the at least one AI or ML model.

7. The method according to any one of claims 1-6, characterized in that, The first information also includes one or more of the following: The identification information of the first terminal device; The identification information of the first service; The parameter information of the first service.

8. A communication method, characterized in that, The method, using a second network device, includes: Determine first information, which includes first parameter information, and the first parameter information is used to describe the requirements of the first service that the first terminal device needs to use and / or the requirements of the first terminal device. Receive second information, the second information being used to indicate that a media channel between the first terminal device and the media function network element has been successfully established, the media channel being used to transmit media information corresponding to the first service; The first information is sent to the first network device according to the second information, instructing the first network device to select a first AI or ML model that matches the needs of the first service and / or the needs of the first terminal device.

9. The method according to claim 8, characterized in that, Before receiving the second information, the method further includes: If the first condition is met or a session establishment request is received, the media channel is established between the first terminal device and the media function network element through the voice service processing network element. The session establishment request is used to request the establishment of a session between the first terminal device and the second terminal device or the first network device.

10. The method according to claim 9, characterized in that, The first condition includes the identifier of the first terminal device, the identifier of the first service, and the condition for triggering the first service. Determining the first information includes: If the first condition is met, the first information is determined based on the identification information of the first terminal device and / or the identification information of the first service.

11. The method according to claim 9, characterized in that, The session establishment request includes call information, and before determining the first information, the method further includes: Upon receiving the session establishment request, the first service is determined from the subscribed services of the first terminal device based on the call information.

12. The method according to claim 11, characterized in that, The call information includes one or more of the following: the calling number, the called number, or the call type.

13. The method according to any one of claims 8-12, characterized in that, The first information also includes one or more of the following: The identification information of the first terminal device; The identification information of the first service; The parameter information of the first service.

14. A communication device, characterized in that, The communication device includes a module for performing the method as described in any one of claims 1 to 7, or a module for performing the method as described in any one of claims 8 to 13.

15. A communication device, characterized in that, The communication device includes a processor for performing the method as described in any one of claims 1 to 7, or the method as described in any one of claims 8 to 13.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program that, when run on a computer, causes the method as described in any one of claims 1 to 7 to be performed, or causes the method as described in any one of claims 8 to 13 to be performed.

17. A computer program product, characterized in that, The computer program product includes a computer program that, when run on a computer, causes the method as described in any one of claims 1 to 7 to be performed, or causes the method as described in any one of claims 8 to 13 to be performed.

Images