Communication method and communication device

Abstract

The invention provides a communication method and a communication device, and the method comprises the steps that a first node determines a cooperation node set for executing an intelligent cooperation task, and the cooperation node set comprises a second node; and the first node sends a first message to a second node, the first message being used for configuring the second node to execute the intelligent cooperation task, the first message comprises one or more of information of nodes in the cooperative node set, identification information of the intelligent cooperative task, description information of the intelligent cooperative task or time information of executing the intelligent cooperative task. The communication efficiency can be improved.

Description

Communication method and communication device Technical Field

[0001] The present application relates to the field of communications, and more specifically, to a communication method and a communication device. Background Art

[0002] The application of artificial intelligence (AI) technology in mobile communication systems can meet higher communication performance requirements, realize richer service types and be applicable to more application scenarios, enabling better development and application of mobile communication systems.

[0003] Communication nodes in mobile communication systems can train intelligent models and apply these trained models to improve communication performance. However, research has found that the application of AI technology in mobile communication systems may not achieve the expected results due to insufficient communication node capabilities and / or limited data diversity.

[0004] Summary of the Invention

[0005] The present application provides a communication method and a communication device, which can improve communication efficiency.

[0006] In a first aspect, a communication method is provided. The method can be executed by a communication device or a module (such as a chip) configured in (or used for) a communication device. The following description takes the method executed by the first node in the communication system as an example.

[0007] The method includes: a first node determining a set of collaborative nodes to perform an intelligent collaborative task, the set of collaborative nodes including a second node. The first node sending a first message to the second node, the first message being used to configure the second node to perform the intelligent collaborative task, the first message including one or more of the following information:

[0008] Information about nodes in the collaborative node set;

[0009] Identification information of the intelligent collaboration task;

[0010] Description information of the intelligent collaboration task;

[0011] Time information for executing the intelligent collaboration task.

[0012] According to the above scheme, the first node has the configuration function of intelligent collaborative tasks. The first node can organize and configure multiple nodes to collaboratively perform intelligent collaborative tasks, so that multiple nodes can collaboratively complete intelligent collaborative tasks according to the configuration of the first node, and realize resource sharing between multiple nodes, such as the sharing of processing capabilities and / or sample data for executing AI technology, etc., so that the application of artificial intelligence technology in communication can achieve the expected effect of improving communication efficiency, and can improve the efficiency of executing intelligent tasks and resource utilization.

[0013] In conjunction with the first aspect, in certain implementations of the first aspect, the description information of the intelligent collaboration task is used to indicate one or more of the following:

[0014] The topological structure between the nodes in the collaborative node set;

[0015] The types of interaction parameters between nodes in the collaborative node set;

[0016] The format of the interaction parameter;

[0017] The interaction mode of the interaction parameter;

[0018] Whether the interaction parameters are sent synchronously between the nodes in the collaborative node set;

[0019] The model adopted by this intelligent collaboration task;

[0020] Model training method for this intelligent collaboration task.

[0021] In an optional embodiment, the interaction parameter includes one or more of the following:

[0022] Model parameters, gradients, environment state parameters, execution action parameters, action execution strategy parameters, reward parameters, knowledge extraction representation parameters, or the correlation between node tasks.

[0023] According to the above solution, the first node can configure collaborative nodes to collaborate to complete intelligent collaborative tasks, which can reduce the occurrence of problems such as insufficient data sample diversity in a single node, resulting in the trained model performance not meeting requirements. Furthermore, by defining the descriptive information of the intelligent collaborative task in the first message, the first node and the nodes in the collaborative node set can reach a consensus on the content indicated by the descriptive information, allowing the first node to flexibly configure different types of intelligent collaborative tasks for the nodes based on task requirements, allowing the collaborative node set to collaborate to achieve different types of tasks.

[0024] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: the first node determines the time to execute the intelligent collaborative task based on the load status of the nodes in the collaborative node set, and the time information is used to indicate the time to execute the intelligent collaborative task.

[0025] According to the above scheme, the first node can determine whether each node currently has spare capacity to execute the intelligent collaborative task to be configured, and the impact of each node executing the intelligent collaborative task to be configured on the communication business based on the load status of the nodes in the collaborative node set and the communication traffic and processing overhead of the intelligent collaborative task to be configured by the first node. When the collaborative node set executes the intelligent collaborative task and the impact on the business communication of the nodes is small (such as one or more of the parameters used to determine the load status is lower than the corresponding threshold), the first node determines to configure the collaborative node set to execute the intelligent collaborative task, that is, determines the time for the collaborative node set to execute the intelligent collaborative task. This can reduce the impact of the nodes executing the intelligent collaborative task on the business communication and reduce the occurrence of data congestion caused by the nodes executing the intelligent collaborative task.

[0026] In combination with the first aspect, in some implementations of the first aspect, the method further includes: the first node determining to stop the intelligent collaborative task based on a load status of nodes in the collaborative node set.

[0027] Optionally, the first node sends a second message to the nodes in the collaborative node set, where the second message is used to instruct to stop the intelligent collaborative task.

[0028] Exemplarily, stopping the intelligent collaboration task may be pausing the intelligent collaboration task, terminating the intelligent collaboration task, or stopping the intelligent collaboration task after completing the intelligent collaboration task.

[0029] According to the above scheme, the first node can stop the intelligent collaboration task in time according to the load status of the nodes in the collaborative node set, which can reduce the impact of the node's execution of the intelligent collaboration task on business communications, and reduce the occurrence of data congestion caused by the node's execution of the intelligent collaboration task.

[0030] In one embodiment, the first node receives a third message from the second node, where the third message is used to indicate a load status of the second node.

[0031] In another embodiment, the first node may obtain the load status of nodes in the collaborative node set from a network status management node. For example, the network status management node may obtain the status of nodes in the network, including the load status, and the network status management node may provide the load status of the nodes in the collaborative node set to the first node.

[0032] According to the above solution, the first node can obtain the load status of the nodes in the collaborative node set, so that the first node can monitor the collaborative performance of the collaborative nodes and thus adjust the intelligent collaborative tasks in a timely manner.

[0033] In conjunction with the first aspect, in certain implementations of the first aspect, the load state is determined based on one or more of the following parameters:

[0034] The proportion of input communication traffic of the node's collaborative task in the total input traffic;

[0035] The proportion of the output communication traffic of the node's collaborative task in the total output traffic;

[0036] The proportion of computing power overhead of nodes executing collaborative tasks in the total computing power overhead;

[0037] The ratio of the communication traffic transmission duration of the node's collaborative task in the total session data congestion duration under session data congestion.

[0038] In combination with the first aspect, in some implementations of the first aspect, the method further includes: the first node receiving a fourth message from the third node, where the fourth message is used to request configuration of the intelligent collaborative task.

[0039] Exemplarily, the third node may be an AF node, an NF node, a node in a collaborative node set, or an upper control node of the first node.

[0040] According to the above scheme, the first node can organize and configure a set of collaborative nodes to collaboratively perform intelligent collaborative tasks based on the on-demand requests of nodes in the network, which can improve the efficiency of nodes in performing intelligent tasks and resource utilization, and thus realize the application of artificial intelligence in communication to improve communication efficiency.

[0041] In conjunction with the first aspect, in certain implementations of the first aspect, the set of collaborative nodes includes the first node, and the method further includes: the first node sending a fifth message to a fourth node, the fifth message being used to request authorization for the intelligent collaborative task. In response, the first node receives a sixth message from the fourth node, the sixth message being used to authorize execution of the intelligent collaborative task.

[0042] According to the above scheme, the fourth node can be the control node or management node of the intelligent collaborative task. When the first node needs to organize and configure the intelligent collaborative task, it needs to obtain authorization from the fourth node so that the control node can monitor the intelligent collaborative task and the collaborative performance of the collaborative node, so that the intelligent collaborative task can be carried out in an orderly manner in the network and reduce the impact on business communications.

[0043] In combination with the first aspect, in some implementations of the first aspect, the method further includes: the first node sending a seventh message to the fourth node, where the seventh message is used to request cancellation of the intelligent collaborative task.

[0044] In combination with the first aspect, in certain implementations of the first aspect, the first node determines a set of collaborative nodes that perform intelligent collaborative tasks, including: the first node receives an eighth message from multiple nodes, the eighth message is used to indicate the ability of the node to perform intelligent tasks, the multiple nodes include the second node, and the first node determines the set of collaborative nodes based on the ability of the multiple nodes to perform intelligent tasks, the set of collaborative nodes includes at least one node among the multiple nodes.

[0045] According to the above solution, the first node can obtain the capabilities of multiple nodes to execute the intelligent task. Based on the node capabilities and the task requirements of the intelligent collaborative task, it determines the node whose capabilities can meet the task requirements to execute the intelligent collaborative task. This reduces the situation where the intelligent collaborative task performance cannot meet the requirements due to node capabilities not meeting the task requirements, thus reducing resource waste and improving resource utilization.

[0046] In conjunction with the first aspect, in certain implementations of the first aspect, the eighth message includes one or more of the following information:

[0047] Description of the current intelligent task, description of historical intelligent tasks, local model information, supported model training methods, or information indicating whether model aggregation is supported.

[0048] In combination with the first aspect, in certain implementations of the first aspect, the first node receives an eighth message from multiple nodes, including: the first node sends a ninth message to the second node, the ninth message being used to indicate the second node's ability to report performing intelligent tasks, and the first node receives the eighth message from the second node.

[0049] According to the above scheme, the node can actively report the node capability to the first node, or the first node can actively query the node's ability to perform intelligent collaborative tasks through the ninth message, so that the first node can obtain the node capability, and thus determine the node that meets the task requirements based on the node capability to perform the intelligent collaborative task.

[0050] In a second aspect, a communication method is provided. The method can be executed by a communication device or a module (such as a chip) configured in (or used for) a communication device. The following is an example of the method being executed by a second node in a communication system.

[0051] The method includes: a second node receiving a first message from a first node, the first message being used to configure the second node to perform the intelligent collaboration task, the collaborative node set including the second node, and the second node performing the intelligent collaboration task according to the first message. The first message includes one or more of the following information:

[0052] Information about nodes in the collaborative node set;

[0053] Identification information of the intelligent collaboration task;

[0054] Description information of the intelligent collaboration task;

[0055] Time information for executing the intelligent collaboration task.

[0056] In conjunction with the second aspect, in certain implementations of the second aspect, the description information of the intelligent collaboration task is used to indicate one or more of the following:

[0057] The topological structure between the nodes in the collaborative node set;

[0058] The type of the interaction parameter between the nodes in the collaborative node set;

[0059] The format of the interaction parameter;

[0060] The interaction mode of the interaction parameter;

[0061] Whether the nodes in the collaborative node set send interaction parameters synchronously;

[0062] The model adopted by this intelligent collaboration task;

[0063] Model training method for this intelligent collaboration task.

[0064] In conjunction with the second aspect, in certain implementations of the second aspect, the interaction parameter includes one or more of the following:

[0065] Model parameters, gradients, environment state parameters, execution action parameters, reward parameters, knowledge extraction representation parameters, or the correlation between node tasks.

[0066] In combination with the second aspect, in some implementations of the second aspect, the method further includes: the second node receiving a second message from the first node, where the second message is used to instruct to stop the intelligent collaborative task.

[0067] In combination with the second aspect, in some implementations of the second aspect, the method further includes: the second node sending a third message to the first node, where the third message is used to indicate a load status of the second node.

[0068] In conjunction with the second aspect, in certain implementations of the second aspect, the load state is determined based on one or more of the following parameters:

[0069] The proportion of input communication traffic of the node's collaborative task in the total input traffic;

[0070] The proportion of the output communication traffic of the node's collaborative task in the total output traffic;

[0071] The proportion of computing power overhead of nodes executing collaborative tasks in the total computing power overhead;

[0072] The ratio of the duration of the node transmitting the communication information of the collaborative task in the total duration of the session data congestion.

[0073] In combination with the second aspect, in certain implementations of the second aspect, the method further includes: the second node sending an eighth message to the first node, the eighth message being used to indicate the ability of the node to perform intelligent tasks, and the multiple nodes including the second node.

[0074] In conjunction with the second aspect, in certain implementations of the second aspect, the eighth message includes one or more of the following information:

[0075] Description of the current intelligent task, description of historical intelligent tasks, local model information, supported model training methods, or information indicating whether model aggregation is supported.

[0076] In conjunction with the second aspect, in certain implementations of the second aspect, the second node sending the eighth message to the first node includes: receiving, at the second node, a ninth message sent from the first node, the ninth message being used to instruct the second node to report its ability to perform intelligent tasks; and sending, at the second node, the eighth message to the first node.

[0077] In conjunction with the second aspect, in certain implementations of the second aspect, the method further includes: the second node communicating with nodes in the collaborative node set using an intelligent model. And / or, the second node transmitting model parameters of the intelligent model. The intelligent model is obtained by executing the intelligent collaborative task.

[0078] It should be noted that, for the above-mentioned multiple messages, such as the first to ninth messages, in the absence of logical conflicts, the functions of the above-mentioned multiple messages may be contained in the same message / same signaling. For example, the eighth message sent by the second node to the first node to indicate the ability of the node to perform intelligent tasks and the third message used to indicate the load status of the node may be different messages, or they may be the same message. For example, a message sent by the second node to the first node is used to indicate both the ability of the second node to perform intelligent tasks and the load status of the second node. The embodiment of the present application does not limit the way of transmitting messages between nodes. The different information contained in a message can be sent by a node to the receiving node at one time, or the different information in the message can be sent by the node to the receiving node multiple times. For example, the first node can first send the identification information of the first intelligent collaborative task in the first message to the second node, and then send the description information of the first intelligent collaborative task to the second node. This application does not limit this.

[0079] According to a third aspect, a communication device is provided. In a design, the communication device has an intelligent collaborative task configuration function and / or an intelligent collaborative task optimization function. The intelligent collaborative task configuration function is used to configure one or more of a set of collaborative nodes for performing intelligent collaborative tasks, a collaborative mode of a set of collaborative nodes, interactive information between collaborative nodes, or a timing for performing intelligent collaborative tasks. The communication device includes a module corresponding to each of the methods / operations / steps / actions described in the first aspect. The module can be a hardware circuit, software, or a combination of a hardware circuit and software.

[0080] Optionally, the communication device has a management function of intelligent collaborative tasks, and the management function of intelligent collaborative tasks is used for one or more of registration, creation, allocation, update or deletion of intelligent collaborative tasks.

[0081] In one design, the apparatus includes: a processing unit configured to determine a set of collaborative nodes to perform an intelligent collaborative task, the set of collaborative nodes including a second node; and a transceiver unit configured to send a first message to the second node, the first message configured to configure the second node to perform the intelligent collaborative task.

[0082] The definitions of messages and information in the third aspect are the same as those of the corresponding messages and information in the first aspect, and can be implemented with reference to the first aspect. For the sake of brevity, they will not be repeated here.

[0083] In combination with the third aspect, in certain implementations of the third aspect, the processing unit is further used to determine the time to execute the intelligent collaborative task based on the load status of the nodes in the collaborative node set, and the time information is used to indicate the time to execute the intelligent collaborative task.

[0084] In conjunction with the third aspect, in certain implementations of the third aspect, the processing unit is further configured to determine, based on a load status of a node in the collaborative node set, whether to terminate the intelligent collaborative task. The transceiver unit is further configured to send a second message to the nodes in the collaborative node set, the second message being configured to instruct the termination of the intelligent collaborative task.

[0085] In combination with the third aspect, in certain implementations of the third aspect, the transceiver unit is further used to receive a third message from the second node, where the third message is used to indicate a load status of the second node.

[0086] In combination with the third aspect, in some implementations of the third aspect, the transceiver unit is further used to receive a fourth message from a third node, where the fourth message is used to request configuration of the intelligent collaborative task.

[0087] In combination with the third aspect, in certain implementations of the third aspect, the collaborative node set includes the communication device, and the transceiver unit is also used to send a fifth message to the fourth node, the fifth message being used to request authorization of the intelligent collaborative task, and to receive a sixth message from the fourth node, the sixth message being used to authorize execution of the intelligent collaborative task.

[0088] In combination with the third aspect, in some implementations of the third aspect, the transceiver unit is further used to send a seventh message to the fourth node, where the seventh message is used to request cancellation of the intelligent collaborative task.

[0089] In conjunction with the third aspect, in certain implementations of the third aspect, the transceiver unit is further configured to receive an eighth message from a plurality of nodes, the eighth message being used to indicate a capability of the nodes to perform the intelligent task, the plurality of nodes including the second node. The processing unit is further configured to determine the set of collaborative nodes based on the capabilities of the plurality of nodes to perform the intelligent task, the set of collaborative nodes including at least one node from the plurality of nodes.

[0090] In combination with the third aspect, in certain implementations of the third aspect, the transceiver unit is further used to send a ninth message to the second node, where the ninth message is used to instruct the second node to report its ability to perform intelligent tasks, and to receive the eighth message from the second node.

[0091] In a fourth aspect, a communication device is provided. In one design, the communication device has the function of performing intelligent collaborative tasks. The device may include a module corresponding to the method, operation, step, or action described in the second aspect. The module may be implemented as hardware circuitry, software, or a combination of hardware circuitry and software.

[0092] In one design, the apparatus includes: a transceiver unit configured to receive a first message from a first node, the first message being configured to configure a second node to perform the intelligent collaborative task, the collaborative node set including the second node; and a processing unit configured to perform the intelligent collaborative task based on the first message.

[0093] The definitions of messages and information in the fourth aspect are the same as those of the corresponding messages and information in the second aspect, and can be implemented with reference to the second aspect. For the sake of brevity, they will not be repeated here.

[0094] In combination with the fourth aspect, in some implementations of the fourth aspect, the transceiver unit is further used to receive a second message from the first node, where the second message is used to instruct to stop the intelligent collaborative task.

[0095] In combination with the fourth aspect, in some implementations of the fourth aspect, the transceiver unit is further used to send a third message to the first node, where the third message is used to indicate a load status of the second node.

[0096] In combination with the fourth aspect, in certain implementations of the fourth aspect, the transceiver unit is further used to send an eighth message to the first node, where the eighth message is used to indicate the node's ability to perform intelligent tasks, and the multiple nodes include the second node.

[0097] In combination with the fourth aspect, in certain implementations of the fourth aspect, the transceiver unit is specifically used to receive a ninth message sent from the first node, where the ninth message is used to instruct the second node to report its ability to perform intelligent tasks, and to send the eighth message to the first node.

[0098] In conjunction with the fourth aspect, in certain implementations of the fourth aspect, the processing unit is further configured to communicate with nodes in the collaborative node set using an intelligent model. And / or, the transceiver unit is further configured to transmit model parameters of the intelligent model. The intelligent model is obtained by executing the intelligent collaborative task.

[0099] In a fifth aspect, a communication device is provided, comprising a processor. The processor can implement the method in any possible implementation of the first aspect or the method in any possible implementation of the second aspect. Optionally, the communication device further includes a memory, and the processor is coupled to the memory and configured to execute instructions in the memory to implement the method in any possible implementation of the first aspect or the method in any possible implementation of the second aspect.

[0100] Optionally, the processor and memory are integrated together.

[0101] Optionally, the communication device further comprises a communication interface, and the processor is coupled to the communication interface. In the embodiment of the present application, the communication interface can be a transceiver, a pin, a circuit, a bus, a module, or other types of communication interfaces, without limitation.

[0102] In one implementation, the communication device is a communication device. When the communication device is a communication device (such as a terminal device or a network device), the communication interface may be a transceiver, or an input / output interface.

[0103] In another implementation, the communication device is a chip configured in a communication device. When the communication device is a chip configured in a communication device, the communication interface may be an input / output interface.

[0104] Optionally, the transceiver may be a transceiver circuit. Optionally, the input / output interface may be an input / output circuit.

[0105] In a sixth aspect, a processor is provided, comprising: an input circuit, an output circuit, and a processing circuit. The processing circuit is configured to receive a signal through the input circuit and transmit a signal through the output circuit, so that the processor executes the method of any possible implementation of the first aspect or the method of any possible implementation of the second aspect.

[0106] In a specific implementation, the processor may be one or more chips, the input circuit may be an input pin, the output circuit may be an output pin, and the processing circuit may be a transistor, a gate circuit, a trigger, or various logic circuits. The input signal received by the input circuit may be, for example, but not limited to, received and input by a receiver, and the signal output by the output circuit may be, for example, but not limited to, output to and transmitted by a transmitter. The input circuit and the output circuit may be the same circuit, which functions as an input circuit and an output circuit at different times. The embodiments of the present application do not limit the specific implementation of the processor and various circuits.

[0107] In the seventh aspect, a computer program product is provided, which includes: a computer program (also referred to as code, or instructions), which, when executed, enables a computer to execute a method in any possible implementation of the first aspect or a method in any possible implementation of the second aspect.

[0108] In an eighth aspect, a computer-readable storage medium is provided, which stores a computer program (also referred to as code, or instructions) which, when run on a computer, enables the computer to execute a method in any possible implementation of the first aspect or a method in any possible implementation of the second aspect.

[0109] In certain embodiments of the eighth aspect, the computer may be the communication device (such as a terminal device or a network device).

[0110] In a ninth aspect, a communication system is provided, comprising at least one first node and at least one second node as mentioned above. BRIEF DESCRIPTION OF THE DRAWINGS

[0111] FIG1 is a schematic diagram of a system architecture of a communication system applicable to an embodiment of the present application;

[0112] FIG2 is a schematic flow chart of a communication method provided in an embodiment of the present application;

[0113] FIG3 is another schematic flow chart of a communication method provided in an embodiment of the present application;

[0114] Figures 3a and 3b are schematic diagrams of a node architecture provided in an embodiment of the present application;

[0115] FIG4 is another schematic flow chart of a communication method provided in an embodiment of the present application;

[0116] FIG4a is another schematic diagram of a node architecture provided by an embodiment of the present application;

[0117] FIG5 is another schematic flow chart of a communication method provided in an embodiment of the present application;

[0118] FIG6 is another schematic diagram of the system architecture provided by an embodiment of the present application;

[0119] FIG7 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0120] FIG8 is another schematic structural diagram of a communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0121] In the embodiments of the present application, at least one (item) can also be described as one (item) or multiple (items), and multiple (items) can be two (items), three (items), four (items), or more (items), without limitation. " / " can indicate that the objects associated with each other are in an "or" relationship. For example, A / B can mean A or B. "And / or" can be used to describe that there are three relationships between the associated objects. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. To facilitate the description of the technical solutions of the embodiments of the present application, words such as "first", "second", "A", or "B" can be used to distinguish technical features with the same or similar functions. The words "first", "second", "A", or "B" do not limit the quantity or execution order. Moreover, the words "first", "second", "A", or "B" do not necessarily mean different. The words "exemplary" or "for example" are used to indicate an example, instance, or illustration. Any design solution described as "exemplary" or "for example" should not be interpreted as being preferred or advantageous over other designs. The use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner to facilitate understanding.

[0122] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: long term evolution (LTE) systems (such as LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, etc.), universal mobile telecommunication systems (UMTS), fifth generation (5G) communication systems, and the communication method provided in the present application can also be applied to communication systems in future evolved public land mobile communication networks (PLMNs) (such as sixth generation (6G) communication systems, etc.) or other communication systems. This application is not limited to this.

[0123] The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings.

[0124] Figure 1 is a schematic diagram of a communication system architecture 100 applicable to an embodiment of the present application. System architecture 100 includes user equipment (UE), an access network, and a core network. The access network includes one or more access network devices, such as the radio access network (RAN) device shown in Figure 1.

[0125] The nodes in the core network include the authentication server function (AUSF) node, policy control function (PCF) node, unified data management (UDM), unified data repository (UDR), network repository function (NRF) node, application function (AF) node, access and mobility management function (AMF) node, session management function module (SMF) node, RAN and UPF nodes, etc. as shown in Figure 1.

[0126] The following describes the functions of each core network node. The AUSF node is primarily responsible for user authentication to determine whether a user or device is allowed to access the network. The PCF node is primarily responsible for policy management of billing and QoS policies. The UDM node is primarily responsible for managing subscription data and user access authorization. The UDR node is primarily responsible for accessing subscription data, policy data, application data, and other types of data. The NRF node can be used to provide node discovery, providing node information corresponding to a node type based on requests from other nodes. The NRF node also provides node management services such as node registration, update, and deregistration, as well as node status subscription and push notifications. The AF node primarily communicates application-side requests to the network. The AMF node primarily performs functions such as mobility management and access authentication / authorization. Furthermore, the AMF node is responsible for communicating user policies between the UE and the PCF node. The SMF node is primarily responsible for session management functions such as UE Internet Protocol (IP) address allocation, UPF node selection, and billing and Quality of Service (QoS) policy control. The UPF node serves as the interface UPF with the data network (DN), and is mainly responsible for completing functions such as user plane data forwarding, session / flow-level billing statistics, and bandwidth limitation.

[0127] In addition to the core network nodes shown in Figure 1, the core network may also include network data analytics function (NWDAF) nodes. NWDAF nodes can provide network analysis services based on network service request data. For example, NWDAF nodes can collect and analyze data in the network. The core network may also include network re-function repository (NRF) nodes. NRF nodes can be responsible for network function service registration and status monitoring, etc., to achieve automated management, selection, and scalability of network function services, and allow each network function to discover services provided by other network functions.

[0128] As shown in Figure 1, the functional units can communicate with each other through the next generation network (NG) interface, such as: the UE can transmit control plane messages with the AMF node through the NG interface 1 (referred to as N1), the RAN node can establish a user plane data transmission channel with the UPF through the NG interface 3 (referred to as N3), the RAN node can establish a control plane signaling connection with the AMF node through the NG interface 2 (referred to as N2), the UPF can exchange information with the SMF node through the NG interface 4 (referred to as N4), the UPF can exchange user plane data with the data network DN through the NG interface 6 (referred to as N6), the AMF node can exchange information with the SMF node through the NG interface 11 (referred to as N11), the SMF node can exchange information with the PCF node through the NG interface 7 (referred to as N7), and the AMF node can exchange information with the AUSF through the NG interface 12 (referred to as N12). It should be noted that Figure 1 is only an exemplary architecture diagram. In addition to the functional units shown in Figure 1, the network architecture may also include other functional units.

[0129] The system architecture may also include a server (cloud), which may provide computing or application services for devices requiring integrity transmission services, including control servers, application servers and other devices.

[0130] The access network device may be a base station, a Node B, an evolved Node B (eNodeB or eNB), a transmission reception point (TRP), a next-generation Node B (gNB) in a fifth-generation (5G) mobile communication system, an access network device in an open radio access network (O-RAN or open RAN), a next-generation base station in a sixth-generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a wireless fidelity (WiFi) system. Alternatively, the access network device may be a module or unit that performs some of the functions of a base station, such as a centralized unit (CU), a distributed unit (DU), a centralized unit control plane (CU-CP) module, or a centralized unit user plane (CU-UP) module. The access network device can be a macro base station (such as 110a in Figure 1), a micro base station or an indoor station (such as 110b in Figure 1), or a relay node or a donor node. In the embodiments of the present application, the specific technology and specific device form adopted by the access network device are not limited. Among them, the 5G system can also be referred to as a new radio (NR) system. The access network node in the embodiments of the present application can be an access network device, or can be a module or unit configured in the access network device.

[0131] In the embodiments of the present application, the device for implementing the functions of the access network device may be the access network device; or it may be a device capable of supporting the access network device in implementing the functions, such as a chip system, a hardware circuit, a software module, or a hardware circuit and a software module, which may be installed in the access network device or used in conjunction with the access network device. In the embodiments of the present application, the chip system may be composed of a chip or may include a chip and other discrete components.

[0132] A terminal may also be referred to as a terminal device, user equipment (UE), mobile station, or mobile terminal. A terminal can be widely used in various scenarios for communication. These scenarios include, but are not limited to, at least one of the following: enhanced mobile broadband (eMBB), ultra-reliable low-latency communication (URLLC), massive machine-type communications (mMTC), device-to-device (D2D), vehicle-to-everything (V2X), machine-type communication (MTC), the Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, smart transportation, or smart city. A terminal may be a mobile phone, tablet computer, computer with wireless transceiver capabilities, wearable device, vehicle, drone, helicopter, airplane, ship, robot, robotic arm, or smart home appliance. The embodiments of this application do not limit the specific technology and device form factor used by the terminal.

[0133] In an embodiment of the present application, the device for implementing the function of the terminal can be a terminal; it can also be a device that can support the terminal to implement the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module, which can be installed in the terminal or can be used in combination with the terminal.

[0134] Due to insufficient capabilities of communication nodes and / or limited data diversity, the application of AI technology in wireless communication systems may fail to achieve the expected results. For example, due to the low data processing capabilities of communication nodes and / or insufficient diversity of sample data of communication nodes, the application of intelligent models obtained by executing model training by communication nodes is not effective in actual reasoning. In order to solve the above problems, an embodiment of the present application proposes that a first node with an intelligent collaborative task configuration function can be used to organize and configure multiple nodes to collaboratively perform intelligent collaborative tasks, which can achieve resource sharing between multiple nodes, such as sharing of processing capabilities for executing AI technology and / or sharing of sample data, etc., so that the application of AI technology in communication can achieve the expected effect of improving communication efficiency, and can improve the efficiency of executing intelligent tasks and resource utilization.

[0135] Figure 2 is a schematic flow chart of a communication method 200 provided in an embodiment of the present application. In the embodiment shown in Figure 2, the first node may have but is not limited to an intelligent collaborative task configuration function and / or an intelligent collaborative task optimization function. Among them, the intelligent collaborative task configuration function is used to configure the intelligent collaborative task, including but not limited to determining one or more of the collaborative node set, the collaborative mode of the collaborative node set, and the timing of performing intelligent collaboration, and then configuring each node in the collaborative node set so that the nodes in the collaborative node set perform the intelligent collaborative task. The optimization function of the intelligent collaborative task includes but is not limited to optimizing the intelligent collaborative task configuration according to the network status. The second node may have but is not limited to the function of performing intelligent collaborative tasks, and the second node may be referred to as a collaborative node. The communication method 200 includes but is not limited to the following steps:

[0136] S201: A first node determines a set of collaborative nodes that execute a first intelligent collaborative task, where the set of collaborative nodes includes a second node.

[0137] In one implementation, the collaboration node set further includes a first node, that is, the first node is a collaboration node in the collaboration node set.

[0138] In other words, the first node can be both the organizing node of the intelligent collaboration task and a node that participates in executing the intelligent collaboration task. For example, when the first node needs to collaborate with other nodes to complete the first intelligent collaboration task, the first node can determine the set of collaborative nodes based on the task requirements of the first intelligent collaboration task.

[0139] For example, the first node detects that the inference performance of the currently used intelligent model does not meet the requirements and needs to be jointly trained with other nodes for model training. Then, the first intelligent collaborative task can be a joint model training of multiple nodes. The first node can determine a set of collaborative nodes, which can include the first node and one or more adjacent nodes of the first node. For example, the adjacent nodes of the first node can refer to nodes that are reachable by communication with the first node, that is, nodes that can exchange information with the first node. For example, the adjacent nodes of the first node include nodes that have established a communication interface with the first node and / or nodes that interact with the first node through information forwarding by one or more nodes. This application does not limit this.

[0140] The first node may also organize and participate in the first intelligent collaborative task after receiving a request message from the task requesting node requesting the first intelligent collaborative task. Optionally, the request message may include the task requirements of the first intelligent collaborative task. The task requesting node may be a node in the collaborative node set, such as a node that does not have the ability to organize intelligent collaborative tasks. Alternatively, the task requesting node may be a node outside the collaborative node set, such as an AF node, which requests the first node to configure the first intelligent collaborative task based on application requirements.

[0141] In another implementation, the collaboration node set does not include the first node, and the first node is a control node of the intelligent collaboration task, or is called a management node.

[0142] The first node determines a set of collaborative nodes that execute the first intelligent collaborative task based on the task requirements of the first intelligent collaborative task. For example, after receiving a request message from a task requesting node for requesting the first intelligent collaborative task, the first node can determine a set of collaborative nodes based on the task requirements of the first intelligent collaborative task. Optionally, the request message may include the task requirements of the first intelligent collaborative task. The task requesting node may be a node in the collaborative task set or may not be a node in the collaborative task set, which is not limited in this application.

[0143] In one embodiment, the first node can determine a set of collaborative nodes that execute the first intelligent collaborative task based on the task requirements of the first intelligent collaborative task and the ability of the nodes to execute the intelligent task. The ability of the nodes in the collaborative node set to execute the intelligent task can meet the task requirements of the first intelligent collaborative task.

[0144] The first node can receive an eighth message from multiple nodes, where the eighth message is used to indicate the node's ability to perform intelligent tasks. The first node determines a set of collaborative nodes based on the ability of the multiple nodes to perform intelligent tasks, where the set of collaborative nodes includes at least one node from the multiple nodes.

[0145] The multiple nodes are nodes that have the ability to perform intelligent tasks and can be called candidate collaborative nodes. For example, a node that has the ability to perform intelligent tasks can send an eighth message to the first node to inform the first node of its ability to perform intelligent tasks. The first node will obtain the node with the ability to perform intelligent tasks as a candidate collaborative node. When it is necessary to assign a collaborative node to perform the first intelligent collaborative task for the first intelligent collaborative task, the first node can determine multiple collaborative nodes that perform the first intelligent collaborative task among the candidate collaborative nodes, that is, a collaborative node set. For example, after receiving a request message from the task request node, the first node determines, based on the ability of the candidate collaborative node to perform intelligent tasks, a node whose ability meets the task requirements of the first intelligent collaborative task as a collaborative node.

[0146] Each node can autonomously send an eighth message to the first node to inform the node of its ability to perform intelligent tasks. Alternatively, the first node can send a ninth message to multiple nodes, which is used to instruct the second node to report its ability to perform intelligent tasks. Upon receiving the ninth message, the multiple nodes send the eighth message to the first node. In other words, the first node can proactively query the node's ability to perform intelligent tasks through the ninth message, so that after receiving the ninth message, the node sends the eighth message to the first node, allowing the first node to obtain the node's ability to perform intelligent tasks.

[0147] Exemplarily, the eighth message may be referred to as a capability reporting message, and the ninth message may be referred to as a capability query message or a capability request message.

[0148] The eighth message may include but is not limited to one or more of the following information of the node:

[0149] Description of the current intelligent task, description of historical intelligent tasks, local model information, supported model training methods, or information indicating whether model aggregation is supported.

[0150] Among them, the description information of the above-mentioned intelligent task (such as the description information of the current intelligent task and / or the description information of the historical intelligent task) can be used to indicate the type of intelligent task of the node. For example, the type of intelligent task can be a training task or an inference task of an intelligent model. When the type of intelligent task is a training task of an intelligent model, the description information of the intelligent task can also include one or more of the loss function, model optimization algorithm or initialization model adopted by the training task. When the type of intelligent task is an inference task, the description information of the intelligent task can also indicate one or more of the intelligent model, input parameter type or output parameter type adopted for inference. The first node can determine the first intelligent collaborative task that the node can support based on the description information of the current intelligent task and / or the description information of the historical intelligent task reported by the node. It should be noted that the current intelligent task or the historical intelligent task can be an intelligent task completed independently by the node, or it can be an intelligent collaborative task completed in collaboration with other nodes.

[0151] The eighth message may include the node's local model information, which is used to indicate the node's existing local model, so that the first node can determine whether the node's existing intelligent model meets the requirements for executing the first intelligent collaboration task, and then determine whether the node supports executing the first intelligent collaboration task. The local model information may include an identifier of the node's existing intelligent model. Alternatively, it may include model parameters of the local existing model, and the first node may determine the node's intelligent model based on the model parameters. This application does not limit this.

[0152] The eighth message may include information about supported model training methods, which may indicate whether the node supports one or more model training methods such as supervised learning, unsupervised learning, or reinforcement learning. The first node may determine whether the model training method required by the first intelligent collaboration task is met based on the model training methods supported by the node, thereby determining whether the node supports executing the first intelligent collaboration task. Exemplarily, identifiers of multiple model training methods may be predefined, and the eighth message may include identifiers of the model training methods supported by the node.

[0153] The eighth message may include information indicating whether the node supports model aggregation. The first node may determine the node to execute the first intelligent collaboration task based on whether the node supports model aggregation and whether the first intelligent collaboration task requires the node to support model aggregation. If the first intelligent collaboration task requires the node to support model aggregation, the first node selects a node that supports model aggregation to execute the first intelligent collaboration task. If the first intelligent collaboration task does not require the node to support model aggregation, the first node does not need to consider whether the node supports model aggregation when determining the set of collaborative nodes.

[0154] S202: The first node sends a first message to the second node, where the first message is used to configure the second node to perform an intelligent collaboration task.

[0155] After determining the set of collaborative nodes to execute the intelligent collaborative task, the first node may send a configuration message to the nodes in the collaborative node set, configuring the nodes to execute the intelligent collaborative task, so that the nodes in the collaborative node set can execute the intelligent collaborative task based on the configuration message. If the configuration message sent by the first node to the second node is a first message, the second node will receive the first message from the first node accordingly. The configuration messages sent by the first node to other nodes in the collaborative node set can be implemented with reference to the first message and will not be further described here.

[0156] The first message may include but is not limited to one or more of the following information:

[0157] Information of nodes in the collaborative node set, identification information of the first intelligent collaborative task, description information of the first intelligent collaborative task, or time information of executing the first intelligent collaborative task.

[0158] Among them, the information of the nodes in the collaborative node set may include the identifier of at least one node in the collaborative node set. In one example, the information of the node may include the identifier of the collaborative node in the collaborative node set that needs to interact with the second node for information when executing the first intelligent collaborative task, and the second node can determine the collaborative node with which to interact with the information based on the node information. Optionally, the information of the node also includes the identifier of the collaborative node in the collaborative node set that does not interact with the second node, that is, the information of the node includes the identifier of each node in the collaborative node set, and the second node can determine each collaborative node that participates in executing the first intelligent collaborative task. This application is not limited to this.

[0159] The first message may include description information of the first intelligent collaboration task, and the description information of the first intelligent collaboration task may be used to indicate one or more configuration parameters of the following 1 to 7.

[0160] 1. Topological structure between nodes in the collaborative node set

[0161] Exemplarily, the descriptive information may indicate the type of the topological structure of the first intelligent collaborative task, such as the type of the topological structure may be point to point (P2P), centralized or decentralized, etc., and the identifier of each type of topological structure may be predefined, and the descriptive information includes the identifier of the topological structure type.

[0162] Among them, the centralized topology type refers to a collaborative node set including a central node and multiple distributed nodes. The distributed nodes send the results (intermediate results or final results) obtained by executing the intelligent collaborative task to the central node, and the central node collects the results obtained from the distributed nodes and performs the tasks undertaken by the central node in the intelligent collaborative task. For example, the intelligent collaborative task can be federated learning. After each distributed node performs at least one iteration of model training based on local data, the obtained gradient and / or model parameters are sent to the central node. The central node integrates the training results of multiple distributed nodes to obtain the updated model parameters of this training, and notifies each distributed node. The distributed node then performs the next iteration of model training based on the updated model parameters. However, the present application is not limited to this. The centralized intelligent collaborative task can also be an intelligent reasoning task or other model training task with a central node.

[0163] The decentralized topology type means that there is no central node in the collaborative node set, and the nodes can perform information exchange in the intelligent collaborative task based on the connection relationship. For example, the intelligent collaborative task can be segmentation learning, where the neural network model is divided into multiple sub-models, and each collaborative node in the collaborative node set is responsible for the training of a sub-model. During forward reasoning, a collaborative node inputs local data into the sub-model to complete the reasoning, and then outputs the reasoning result to one or more collaborative nodes where the lower-level sub-model is located. And so on, to complete an iteration of model training, and then perform the reverse transfer of gradients after the reasoning is completed. However, the present application is not limited to this, and the decentralized intelligent collaborative task can also be an intelligent reasoning task or other model training task without a central node.

[0164] The description information may also include connection relationships between topological structures.

[0165] In one example, the topology is a point-to-point topology or a decentralized topology type, and the description information may include the identifier of the upstream node and / or the identifier of the downstream node of the second node. The upstream node is the node that sends interaction information to the second node when collaboratively executing the first intelligent collaborative task, and the downstream node is the node that receives interaction information from the second node when executing the first intelligent collaborative task. The second node can determine the connection relationship between the second node and other nodes in the topology structure based on the identifier of the upstream node and the identifier of the downstream node indicated by the description information. The upstream node and the downstream node of the second node can be one or more.

[0166] In another example, the topology is a centralized topology type, and the description information may include an identifier of the central node. The second node determines the central node according to the identifier and interacts with the central node when executing the first intelligent collaborative task.

[0167] 2. The type of interaction parameters between nodes in the collaborative node set;

[0168] Exemplarily, the interaction parameters may include one or more of the following types of interaction parameters:

[0169] Model parameters, gradients, environment state parameters, action parameters, policy parameters, reward parameters, knowledge extraction representation parameters, or correlation between node tasks.

[0170] For example, the first intelligent collaborative task is a model training task, and the model training task uses a loss function and a gradient descent algorithm to solve the model parameters. Then, the first node can indicate the interaction parameters including gradients and / or model parameters through the description information of the first intelligent collaborative task. For example, the model training task can be implemented by using federated learning or transfer learning.

[0171] For another example, the first intelligent collaborative task is a model training task using reinforcement learning, and the interaction parameters indicated by the description information can be one or more of the environment state parameters, execution action parameters, execution action strategy parameters or reward parameters in reinforcement learning.

[0172] The interaction parameter indicated by the descriptive information may be the correlation between the tasks undertaken by the nodes in the first intelligent collaborative task. For example, the correlation may be used as a constraint term of the loss function. That is, the tasks undertaken by the nodes may have a certain degree of correlation to achieve mutual learning between differentiated tasks.

[0173] The interaction parameters indicated by the description information can be knowledge extraction representation parameters, that is, abstract representation parameters obtained by extracting the parameters obtained in the model training task (such as the above-mentioned model parameters, gradients, etc.). Compared with the original parameters, the amount of information is small, which can reduce the overhead of interactive information and improve communication efficiency.

[0174] 3. Format of interaction parameters

[0175] The format of the interaction parameter may include, but is not limited to, the precision of the interaction parameter and / or the number of bits occupied by the interaction parameter in the interaction information.

[0176] 4. Interaction method of interaction parameters

[0177] The interaction mode may be that the interaction parameters adopt single-frequency interaction or periodic interaction. For example, the description information indicates that the interaction mode of the interaction parameters is single-frequency interaction, and the second node is single-frequency interaction according to the interaction mode indicated by the description information. Then, the second node outputs interaction information once after executing the task undertaken by the second node, and the interaction information includes the interaction parameters. Or the description information may indicate that the interaction mode of the interaction parameters may be periodic. Optionally, the description information may also include the length of the interaction cycle. The cycle length may be expressed in terms of the number of times. For example, the second node undertakes the model training task in the first intelligent collaboration task. The description information may indicate the number of iterations N. The second node may determine to send interaction information once after every N iterations in the execution of the model training process. The interaction information includes the interaction parameters. Or the cycle length may be expressed in terms of time length. The description information may indicate that the cycle length is duration T, and the second node sends interaction information once after each duration T. However, the present application is not limited thereto.

[0178] 5. Whether the nodes in the collaborative node set send interaction parameters synchronously

[0179] The descriptive information may indicate the synchronization mechanism for transmitting interaction parameters by the collaborative nodes in the collaborative node set in the first intelligent collaborative task, such as synchronous, asynchronous, or hybrid. For example, if the first intelligent collaborative task is centralized federated learning, the descriptive information may indicate that the interaction parameters are transmitted synchronously, and multiple participating nodes need to synchronously transmit the interaction parameters to the central node. The descriptive information may indicate the timing for the participating nodes to transmit the interaction parameters, so that the multiple participating nodes transmit the interaction parameters synchronously. Alternatively, when the multiple participating nodes determine, through the descriptive information, that the interaction parameter transmission method is synchronous, the multiple participating nodes may negotiate the synchronization timing through information exchange. This is not limited in this application. For another example, the descriptive information may indicate the use of an asynchronous or hybrid method, and the descriptive information may also indicate the duration of a timer, which is used by the central node to determine the duration for receiving the interaction parameters. This can reduce the possibility of the first intelligent collaborative task stalling due to prolonged non-receipt of interaction parameters. Alternatively, the descriptive information may not indicate the duration of the timer, which may be predefined.

[0180] 6. Model used in the first intelligent collaboration task

[0181] For example, the description information may indicate the model type used in the first intelligent collaboration task, such as a nearest neighbor model, a decision tree model, a Bayesian model, a linear model, or a multi-layer neural network model. Optionally, the description information may also include model parameters of the model, and the second node may determine the model used to execute the first intelligent collaboration task based on the description information. For example, if the first intelligent collaboration task is a model training task, the model may be the initial model for model training. For another example, if the first intelligent collaboration task is a reasoning task, the model may be the model used to execute the reasoning task.

[0182] For another example, multiple models and corresponding identifiers of each model may be predefined, and the description information may include the identifiers of the one or more models. After receiving the description information, the second node uses the model corresponding to the identifier to execute the first intelligent collaboration task.

[0183] 7. Model training method for the first intelligent collaboration task.

[0184] For example, if the first intelligent collaboration task is a model training task, the description information may indicate a model training method used by the first intelligent collaboration task, such as supervised learning, unsupervised learning, or reinforcement learning. The second node executes the model training task using the model training method indicated by the description information.

[0185] In one embodiment, multiple intelligent collaborative tasks and corresponding identifiers can be predefined, and the description information of the first intelligent collaborative task can indicate one or more configuration parameters 1 to 7 of the first intelligent collaborative task by indicating the predefined identifier of the first intelligent collaborative task.

[0186] Exemplarily, N types of intelligent collaborative tasks as shown in Table 1 can be predefined, and the identifiers of the N types of intelligent collaborative tasks are 1 to N, respectively, and the topological structure, type of interaction parameters, format, synchronization mechanism and interaction method, and model training method of each intelligent collaborative task are defined respectively. The description information of the first intelligent collaborative task in the first message may include the identifier of the first intelligent collaborative task, and the second node may determine to execute the first intelligent collaborative task corresponding to the identifier in Table 1 based on the identifier in the description information. It should be noted that Table 1 is an example provided to better understand the solution of the present application, and the present application is not limited thereto. In a specific implementation, the intelligent collaborative tasks may be predefined according to specific implementation requirements. In addition, each of the above-mentioned configuration parameters 1 to 7 of the intelligent collaborative task is defined in the example of Table 1. In a specific implementation, a part of the above-mentioned configuration parameters 1 to 7 of the intelligent collaborative task may also be defined in a predefined manner. In one embodiment, a part of the above-mentioned configuration parameters 1 to 7 of the intelligent collaborative task may be predefined, and the other parts may be indicated by the description information of the intelligent collaborative task. This application is not limited to this.

[0187] Table 1

[0188]

[0189]

[0190] According to the above solution, the description information of the first intelligent collaborative task can be used to configure collaborative nodes to collaborate and complete the first intelligent collaborative task. This can reduce the possibility that the performance of the trained model does not meet the requirements due to insufficient data sample diversity of a single node. Furthermore, by defining the description information of the intelligent collaborative task, the first node and the nodes in the collaborative node set can reach a consensus on the content indicated by the description information, allowing the first node to flexibly configure different types of intelligent collaborative tasks for the nodes based on the task requirements.

[0191] The first message sent by the first node to the second node may also include information about the time when the second node will execute the first intelligent collaborative task. For example, the first node may determine the time when the collaborative node set will execute the first intelligent collaborative task based on the network load status and the necessity and urgency of the first intelligent collaborative task, and notify the second node via the first message.

[0192] A node in the collaborative node set can send a message indicating the node's load status to the first node, allowing the first node to learn the load status of the collaborative node set. For example, a second node can send a third message indicating the second node's load status to the first node. The first node can determine the time for the collaborative node set to execute the first intelligent collaborative task based on the load status reported by the node.

[0193] The load status may be determined based on one or more of the following parameters:

[0194] The proportion of input communication traffic of the node's collaborative task in the total input traffic is P1;

[0195] The proportion of the output communication traffic of the node's collaborative task in the total output traffic is P2;

[0196] The proportion of computing power overhead of nodes executing collaborative tasks in the total computing power overhead is P3;

[0197] In the case of session data congestion, the communication traffic transmission duration of the node's collaborative task accounts for P4 of the total session data congestion duration.

[0198] The third message may include one or more of the above parameters, so that the first node can determine the load status of the second node. If the third message may include P1, the second node can determine P1 based on the input communication traffic of the collaborative type task currently being executed at the communication entrance and the total input communication traffic of the communication entrance (including but not limited to the input communication traffic of the collaborative type task, the input communication traffic of the non-collaborative type task and the input communication traffic of the business communication, etc.), and notify the first node through the third message. The first node is able to measure the traffic of the collaborative task obtained by the node based on the input traffic proportion P1 of the collaborative task of the node. If the collaborative input traffic is excessive, it may cause a node processing bottleneck. If the third message may include P2, the second node determines the output communication traffic proportion of the collaborative type task at the communication exit and notifies the first node through the third message. The first node is able to measure the traffic of the collaborative task output by the node based on the output traffic proportion P2 of the collaborative task of the node. If the collaborative output traffic is excessive, it may cause a collaborative traffic storm in the network.

[0199] For example, the input traffic of the communication inlet may be the interface traffic of a node's receiver, the interface traffic of a processor's input interface, or the input traffic of other interfaces. The input traffic of the communication outlet may be the interface traffic of a node's transmitter, the interface traffic of a processor's output interface, or the output traffic of other interfaces, which is not limited in this application.

[0200] Furthermore, the third message may include P3 and / or P4, which are determined by the second node and notified to the first node via the third message. Based on the collaborative computing power percentage (P3), the first node can measure the overhead of collaborative information on node computing power, which can be used as a metric for evaluating collaborative gain. Furthermore, based on the communication traffic transmission duration percentage (P4) of collaborative tasks under session congestion, the first node can measure the impact of collaborative traffic on congestion during a congested session.

[0201] The first node can determine whether each node currently has spare capacity to execute the intelligent collaborative task to be configured, and the impact of each node executing the first intelligent collaborative task on the communication service based on the load status of the nodes in the collaborative node set and the communication traffic and processing overhead of the first intelligent collaborative task to be configured. When the collaborative node set executes the first intelligent collaborative task and the impact on the business communication of the nodes is small (such as one or more of the parameters used to determine the load status is lower than the corresponding threshold), the first node determines to configure the collaborative node set to execute the first intelligent collaborative task, that is, determines the time for the collaborative node set to execute the first intelligent collaborative task. This can reduce the impact of the nodes executing the intelligent collaborative task on the business communication and reduce the occurrence of data congestion caused by the nodes executing the intelligent collaborative task.

[0202] Through the above description, the first node can determine one or more of the collaborative node set for the first intelligent collaborative task, the collaborative mode of the collaborative node set, the interaction information between the collaborative nodes, and the time to execute the first intelligent collaborative task, and the first node can configure the first intelligent collaborative task for the collaborative node set through a configuration message, and the nodes in the collaborative node set can execute the first intelligent collaborative task based on the configuration message after obtaining the configuration message, such as the second node executing S203.

[0203] S203: The second node executes the first intelligent collaboration task according to the first message.

[0204] After receiving the first message in S202 , the second node collaborates with the nodes in the collaborative node set to perform the first intelligent collaborative task.

[0205] In one embodiment, the first node determines to stop the first intelligent collaborative task based on the load status of the nodes in the collaborative node set. Optionally, the first node may send a second message to the nodes in the collaborative node set, the second message being used to instruct the nodes in the collaborative node set to stop the first intelligent collaborative task.

[0206] In one example, after the collaborative node set starts to execute the first intelligent collaborative task, the first node can determine whether the node's execution of the first intelligent collaborative task has an impact on business communications based on the load status of the collaborative node set. When the collaborative node set executes the first intelligent collaborative task and the impact on the node's business communications is large (such as one or more of the parameters used to determine the load status is higher than the corresponding threshold), the first node can notify the nodes in the collaborative node set to stop the first intelligent collaborative task through a second message. The stop can be to suspend the first intelligent collaborative task. When the first node determines that the impact on business communications is small, it can instruct the collaborative node set to continue to execute the first intelligent collaborative task. Or the stop can be termination (i.e., end). For example, if the first node determines that the first intelligent collaborative task seriously affects business communications based on the load status, it notifies the collaborative node set to terminate the first intelligent collaborative task, so that the intelligent collaborative node can release the resources occupied by the first intelligent collaborative task so that the node's communication business can meet business needs.

[0207] The nodes in the collaborative node set can periodically send the node load status to the first node, or the first node can request the nodes in the collaborative node set to send the node load status through messages, so that the first node can monitor the network status and evaluate the impact of intelligent collaborative tasks on business communications, so that the first node can optimize the network status and reduce the situation where intelligent collaborative tasks cause network congestion and affect communication services.

[0208] In another example, the nodes in the collaborative node set can feedback the collaborative status of the first intelligent collaborative task to the first node, such as the parameters obtained in the first intelligent collaborative task (such as model parameters, gradients, etc.). The first node determines the degree of completion of the first intelligent collaborative task based on the collaborative status. When the degree of completion meets the requirements, the second message notifies the second node that the intelligent collaborative task has been completed and stops the first intelligent collaborative task. Alternatively, the collaborative node can determine whether the collaboration is completed based on the parameters obtained in the execution of the first intelligent collaborative task. In this case, the first node may not send the second message to the collaborative node, and the collaborative node determines that the first intelligent collaborative task is completed and stops the first intelligent collaborative task.

[0209] In one implementation, after completing the first intelligent collaboration task, the second node may communicate using the intelligent model obtained by the first intelligent collaboration task.

[0210] The second node can use the intelligent model to communicate with other nodes in the collaborative node set. Exemplarily, the first intelligent collaborative task is for the second node to collaborate with other collaborative nodes in the collaborative node set to complete a model training task for an autoencoder model. The collaborative node set collaborates to complete model training for encoding and decoding models. After the training task is completed, the resulting model is used for encoding and decoding signals between the collaborative node sets. However, the present application is not limited thereto.

[0211] In another embodiment, after completing the first intelligent collaboration task, the second node sends model parameters of the intelligent model, where the intelligent model is an intelligent model obtained by executing the first intelligent collaboration task.

[0212] The second node can assist other nodes in completing model training. After the model training, the second node sends the model parameters of the intelligent model obtained after training to other collaborative nodes, so that the collaborative nodes can apply the model in communication.

[0213] In another embodiment, after completing the first intelligent collaboration task, the second node not only uses the intelligent model obtained by executing the first intelligent collaboration task to communicate, but also sends model parameters of the intelligent model to other nodes.

[0214] The second node can apply the intelligent model obtained by executing the first intelligent collaboration task to communication, thereby improving the reliability and efficiency of communication. The second node also sends the model parameters of the intelligent model to other nodes, allowing other nodes to apply the intelligent model to communication. Alternatively, the second node can use the intelligent model and local samples to obtain an intelligent model suitable for the node and apply it to communication, thus achieving model sharing and improving resource utilization.

[0215] Exemplarily, the set of collaborative nodes may include, but is not limited to, one or more nodes selected from terminals, access network nodes, or core network nodes. The above-described solution enables intelligent collaboration (HIC) among multi-level nodes. The above-described first node may be an access network node or a core network node, or in other words, the access network node or the core network node may have the functionality of the first node. The present application is not limited thereto; the first node may also be a network node other than an access network node or a core network node.

[0216] According to the above solution provided by this application, a first node can configure multiple nodes in the network to collaborate and perform different types of intelligent collaborative tasks on demand. The collaborative completion of intelligent collaborative tasks between nodes can reduce the occurrence of problems such as insufficient data sample diversity in a single node, resulting in the trained model performance not meeting the requirements. It can also improve the efficiency of nodes in executing intelligent tasks and resource utilization, thereby realizing the application of artificial intelligence in communications to improve communication efficiency.

[0217] As described above, the first node may not participate in the execution of the first intelligent collaborative task, but configure the first intelligent collaborative task as the organization and management node of the first intelligent collaborative task. The first node may have one or more of the above-mentioned intelligent collaborative task configuration function, the above-mentioned intelligent collaborative task optimization function, or the intelligent collaborative task management function, wherein the intelligent collaborative task management function is used for one or more of the registration, creation, allocation, update, or deletion of the intelligent collaborative task. The first node may be called a control node or a management node. Figure 3 is a schematic flow chart of a communication method 300 provided in an embodiment of the present application. The collaborative nodes shown in Figure 3 (such as collaborative node 1, collaborative node 2, and collaborative node 3) are collaborative nodes in the collaborative node set that executes the first intelligent collaborative task, and have the function of the second node described above. For example, collaborative node 1, collaborative node 2, and collaborative node 3 are terminals, access network nodes, and core network nodes, respectively, but the present application is not limited thereto, and at least two or all of the three collaborative nodes may also be nodes of the same type.

[0218] The collaborative mode of the intelligent collaborative task shown in FIG3 can be called a hierarchical organization mode. The architecture of the hierarchical organization mode can be shown in FIG3a, where the first node organizes, configures, and manages nodes with intelligent collaborative capabilities (such as collaborative node 1, collaborative node 2, and collaborative node 3) to collaboratively perform intelligent collaborative tasks. It should be noted that the parts of the embodiment shown in FIG3 that are the same as those in the embodiment shown in FIG2 can be referred to the description of the embodiment shown in FIG2, and will not be repeated here. The method 300 includes but is not limited to the following steps:

[0219] S301: The coordination node sends an eighth message to the first node, where the eighth message is used to indicate the capability of the node to execute an intelligent task.

[0220] In one embodiment, a node capable of performing intelligent tasks can register with the first node, that is, send an eighth message to the first node, and notify the first node of the node's ability to perform intelligent tasks through the eighth message, so that the first node can configure intelligent tasks for the node based on the node's capabilities.

[0221] In another embodiment, before S301, the first node may send a query message (i.e., an example of the ninth message) to the node, where the query message is used to query the node's ability to perform intelligent tasks. After receiving the query message, the node sends the eighth message to the first node.

[0222] Optionally, in S302, the first node receives a request message, where the request message is used to request configuration of a first intelligent collaboration task.

[0223] For example, the AF node or the network function (NF) node shown in FIG3 may send the request message to the first node according to demand, requesting the first node to configure the first intelligent collaborative task.

[0224] In another example, the upper control node of the first node may send a request message to the first node, requesting the first node to configure a first intelligent collaborative task. If the control nodes are deployed in a multi-layer manner, the first node shown in FIG3 may serve as a lower control node to manage collaborative tasks for a set of nodes within its range. The upper control node of the first node may manage collaborative tasks between multiple sets of nodes by controlling the lower control nodes. The first node may be referred to as a local control node, and the upper control node of the first node may be referred to as a global control node. For example, a multi-layer deployment may be as shown in FIG3b . After receiving a collaborative task request message from the global control node, the local control node determines a collaborative node set based on the task request message. For example, the collaborative node set includes terminals managed by the local control node, access network node 1, and access network node 2. The local collaborative node configures collaborative nodes to perform the first intelligent collaborative task through collaborative control. The nodes in the collaborative node set perform the first intelligent collaborative task and exchange collaborative data during the execution of the task. For example, the local control node may be an access network node, and the global control node may be a core network node. Alternatively, the local control node may be a micro base station, and the global control node may be a macro base station. Alternatively, the local control node and the global control node may be different core network nodes, which is not limited in this application.

[0225] In the above two examples, the request message may include the description information of the first intelligent collaborative task described above. After receiving the request message, the first node may determine the set of collaborative nodes in S303 based on the description information of the first intelligent collaborative task, and forward the description information of the first intelligent collaborative task through the first message in S304. Alternatively, the request message may include the task requirements of the first intelligent collaborative task, and the first node determines the first intelligent collaborative task based on the task requirements and includes the description information of the first intelligent collaborative task in the first message in S304.

[0226] For another example, the collaboration node shown in Figure 3 can send a request message to the first node based on the node's communication requirements. The request message may include the node's communication requirements and / or the task requirements of the first intelligent collaboration task. Based on the request message, the first node configures the collaboration node set and the first intelligent collaboration task for the collaboration node.

[0227] For another example, the first node may also initiate and configure the first intelligent collaboration task based on the network status, which is not limited in this application.

[0228] S303: The first node determines a set of collaborative nodes.

[0229] For example, the collaboration node set includes collaboration node 1, collaboration node 2, and collaboration node 3.

[0230] S304: The first node sends a first message to the set of collaborative nodes, where the first message is used to configure execution of a first intelligent collaborative task.

[0231] Accordingly, the nodes in the set of cooperating nodes receive the first message from the first node.

[0232] S305: The collaboration node executes the first intelligent collaboration task according to the first message.

[0233] In one embodiment, the first message includes descriptive information of the first intelligent collaborative task. After the collaborative node configures the execution of the first intelligent collaborative task according to the descriptive information of the first intelligent collaborative task, it sends a response message to the first node. The response message is used to notify the first node that the relevant configuration for executing the first intelligent collaborative task has been completed. After receiving the response message, the first node determines the time for the collaborative node set to execute the first intelligent collaborative task based on the network status (such as the load status of the collaborative node, etc.). The first node sends a trigger message to the collaborative node set to trigger the collaborative node set to execute the first intelligent collaborative task. The trigger message includes the identifier of the first intelligent collaborative task configured by the first message. The collaborative node can determine the start of execution of the first intelligent collaborative task corresponding to the identifier based on the identifier.

[0234] In another embodiment, the first message includes description information of the first intelligent collaborative task and time information of the collaborative node set executing the first intelligent collaborative task. After the collaborative node is configured to execute the first intelligent collaborative task according to the description information of the first intelligent collaborative task, it starts executing the first intelligent collaborative task at the time indicated by the time information.

[0235] S306: The coordinating node sends a third message to the first node, where the third message is used to indicate the load status of the node.

[0236] The collaborative nodes in the collaborative node set may send a third message to the first node when executing the first intelligent collaborative task, so that the first node may monitor the collaborative performance of the collaborative nodes according to the third message, so as to adjust the first intelligent collaborative task in a timely manner.

[0237] Optionally, in S307 , the first node sends a second message to the collaboration node, where the second message is used to instruct to stop the first intelligent collaboration task.

[0238] As described above, the second message may notify the cooperating node to suspend or terminate the first intelligent collaborative task. Alternatively, the second message may notify the cooperating node that the first intelligent collaborative task has been completed and terminate the first intelligent collaborative task. Alternatively, the first node may not send the second message to the cooperating node, and the cooperating node may determine that the first intelligent collaborative task has been completed and terminate the first intelligent collaborative task.

[0239] The hierarchical organization of intelligent collaborative tasks, as shown in Figure 3, in which the first node organizes, configures, and manages the collaboration, can reduce the complexity of negotiation between collaborative nodes and improve the efficiency of collaboration. It is suitable for scenarios with a large number of collaborative nodes participating in intelligent collaborative tasks.

[0240] The collaborative nodes participating in the intelligent collaborative task may also have the ability to organize intelligent collaboration, and can perform intelligent collaborative tasks through negotiation on a small scale. The collaborative mode of the intelligent collaborative task can be called a self-organizing mode. Figure 4 is a schematic flow chart of a communication method 400 provided in an embodiment of the present application. The collaborative node shown in Figure 4 is a collaborative node in the collaborative node set that performs the first intelligent collaborative task, and has the function of the second node described above. Among them, the collaborative node 1 may also have the intelligent collaborative task configuration function and / or the intelligent collaborative task optimization function of the above-mentioned first node. Figure 4a is a schematic architecture diagram of a self-organizing mode, and the collaborative node 1 organizes the collaborative node 2 and the collaborative node 3 to collaborate with the collaborative node 1 to perform the first intelligent task by configuring the first message of the first collaborative task. The method 400 includes but is not limited to the following steps:

[0241] S401: The cooperation node 1 receives an eighth message from multiple nodes, where the eighth message is used to indicate the capability of the node to execute an intelligent task.

[0242] The multiple nodes are nodes with the ability to perform intelligent tasks. For example, the nodes with the ability to perform intelligent tasks can interact with each other to determine their respective abilities to perform intelligent tasks. Alternatively, a node with a configuration function for intelligent collaborative tasks (such as collaborative node 1) can send a query message to multiple nodes. If the multiple nodes are adjacent nodes of the first node, the first node queries the adjacent nodes for their ability to perform intelligent collaborative tasks through the query message. After receiving the query message, the multiple nodes send an eighth message to the collaborative node 1 to inform the node of its ability to perform intelligent collaborative tasks.

[0243] S402: The coordinating node 1 determines a coordinating node set according to the eighth message.

[0244] The collaboration node set includes collaboration node 1, collaboration node 2, and collaboration node 3. After collaboration node 1 determines a first intelligent collaboration task that needs to be completed by the collaboration node set, S403 is executed.

[0245] In one example, the collaboration node 1 may determine one or more of the following configuration parameters of the first intelligent collaboration task mentioned above based on requirements and algorithms:

[0246] The topological structure between the nodes in the collaborative node set, the type of interaction parameters between the nodes in the collaborative node set, the format of the interaction parameters, the interaction method of the interaction parameters, whether the interaction parameters are sent synchronously between the nodes in the collaborative node set, the model adopted by the first intelligent collaborative task or the model training method of the first intelligent collaborative task.

[0247] In another example, the collaboration node 1 may determine a first intelligent collaboration task from a plurality of predefined intelligent collaboration tasks.

[0248] S403: The collaboration node 1 sends a fifth message to the control node, where the fifth message is used to request authorization for the first intelligent collaboration task.

[0249] The fifth message may include one or more of the following information:

[0250] Information of nodes in the collaborative node set, description information of the first intelligent collaborative task, or time information of executing the first intelligent collaborative task.

[0251] S404: The control node sends a sixth message to the collaboration node 1, where the sixth message is used to authorize execution of the first intelligent collaboration task.

[0252] If the control node receives the fifth message and determines based on the network status that the first intelligent collaborative task requested by the collaborative node 1 through the fifth message can be authorized, the control node can assign an identifier to the first intelligent collaborative task and notify the collaborative node 1 through the sixth message that the first intelligent collaborative task requested by it is authorized and the identifier of the first intelligent collaborative task.

[0253] S405 , the collaboration node 1 sends a first message, where the first message is used to configure a first intelligent collaboration task.

[0254] S406: The collaborative node set executes the first intelligent collaborative task.

[0255] In an optional embodiment, the collaborative node 1 has an optimization function for intelligent collaborative tasks, and the collaborative node 2 and the collaborative node 3 can send a third message to the collaborative node 1 to inform the collaborative node 1 of the node load status when executing the first intelligent collaborative task. The collaborative node 1 can optimize the configuration of the first intelligent collaborative task or instruct to stop executing the first intelligent collaborative task based on the node load status.

[0256] In another optional implementation, the collaborative nodes in the collaborative node set can send a third message to the control node during the execution of the first intelligent collaborative task, so that the control node can monitor the first intelligent collaborative task and the collaborative performance of the collaborative nodes so as to be able to adjust the first intelligent collaborative task in a timely manner.

[0257] S407: The collaboration node 1 sends a seventh message to the control node, where the seventh message is used to cancel the first intelligent collaboration task.

[0258] After the collaborative node set completes the first intelligent collaborative task, it sends a seventh message to the control node to cancel the first intelligent collaborative task. The seventh message includes an identifier of the first intelligent collaborative task. After receiving the seventh message, the control node can cancel the management of the first intelligent collaborative task.

[0259] It should be noted that some of the nodes participating in the execution of the intelligent collaborative task may have the configuration function and / or optimization function of the intelligent collaborative task, while some of the nodes participating in the execution of the intelligent collaborative task may not have the configuration function and optimization function of the intelligent collaborative task. In the embodiment shown in Figure 4, the collaborative node 2 and the collaborative node 3 do not have the configuration function and optimization function of the intelligent collaborative task, and can only participate in the execution of the intelligent collaborative task based on the configuration. Or each node that can participate in the intelligent collaborative task can have the configuration function and / or optimization function of the intelligent collaborative task of the collaborative node 1 in the method 400. In the embodiment shown in Figure 4, the collaborative node 2 and the collaborative node 3 may also have the configuration function and optimization function of the intelligent collaborative task and can organize the intelligent collaborative task. This application does not limit this.

[0260] Figure 5 is a schematic flow chart of a communication method 500 provided in an embodiment of the present application. In this method 500, both collaboration node 1 and collaboration node 2 have the function of configuring intelligent collaborative tasks. For the parts of method 500 that are identical to those in the previous embodiments, reference can be made to the previous description and will not be repeated here for the sake of brevity.

[0261] Collaboration node 1 can determine the set of collaboration nodes (including collaboration node 1 and collaboration node 2) and the need to collaborate to complete intelligent collaboration task 1, send a message A1 to the control node in S501 to request authorization of intelligent collaboration task 1, and determine in S502 that intelligent collaboration task 1 has been authorized through the message B1 received from the control node. In S503, collaboration node 1 sends a message C1 (i.e., an example of the first message) to collaboration node 2 to configure collaboration node 2 to perform intelligent collaboration task 1. Collaboration node 2 performs intelligent collaboration task 1 with collaboration node 1 according to message C1. After intelligent collaboration task 1 is completed, collaboration node 1 executes S505 and sends a message D1 to the control node to cancel intelligent collaboration task 1.

[0262] After completing intelligent collaborative task 1 with the collaborative node, collaborative node 2 can initiate intelligent collaborative task 2 based on the results of intelligent collaborative task 1. If intelligent collaborative task 1 is a model training task, collaborative node 2 can execute intelligent collaborative task 2 with collaborative node 3 based on the intelligent model trained in intelligent collaborative task 1. This approach eliminates the need for collaborative node 2 and collaborative node 3 to start model training from an initial model. Instead, they only need to perform adaptive training adjustments based on the existing model and sample data from collaborative node 3, which can improve node resource utilization and thus communication efficiency. After collaborative node 2 and the control node authorize the intelligent collaborative task through message A2 in S506 and message B2 in S507, collaborative node 2 sends message C2 to collaborative node 3 in S508 to configure intelligent collaborative task 2. After collaborative node 2 and collaborative node 3 execute intelligent collaborative task 2, they can obtain an intelligent model suitable for communication between collaborative node 2 and collaborative node 3. Collaborative node 2 sends message D2 to the control node in S510 to cancel intelligent collaborative task 2.

[0263] The above solution enables multiple nodes in an on-demand network to collaborate and execute different types of intelligent collaborative tasks. This collaborative execution of intelligent collaborative tasks by nodes can reduce the likelihood of insufficient training model performance due to insufficient data sample diversity at a single node. It can also improve the efficiency of intelligent task execution and resource utilization at the node level, thereby enabling the application of artificial intelligence in communications to enhance communication efficiency.

[0264] As described above, the collaborative node set may include, but is not limited to, one or more nodes selected from terminals, access network nodes, or core network nodes. This enables intelligent collaboration (HIC) between multiple levels of nodes. A node that has the configuration, optimization, and management functions of the intelligent collaboration tasks of the first node can be referred to as an HIC controller node, denoted as HIC C. A node that has the execution function of the intelligent collaboration tasks of the second node can be referred to as an HIC agent node, denoted as HIC A. Some or all of the HIC As may also have the configuration and / or optimization functions of the intelligent collaboration tasks of the first node.

[0265] Nodes in a communication system can collaborate to complete intelligent collaborative tasks through the organization and configuration of a first node (i.e., HIC C) in a hierarchical organization as shown in Figures 3, 3a, and 3b, or can collaborate to complete intelligent collaborative tasks through the organization and configuration of a HIC A with intelligent collaborative task configuration capabilities in a self-organizing manner as shown in Figures 4 and 4a. This is more suitable for collaboration with a small number of nodes, and through self-negotiation, collaboration is more efficient. Alternatively, nodes in a communication system can collaborate to complete intelligent collaborative tasks through both a hierarchical organization and a self-organizing manner. This is more suitable for collaboration with a large number of nodes, reducing negotiation complexity and enabling more efficient collaboration among multiple nodes through planning and coordination performed by the same node. As shown in Figure 6, a HIC A in a collaborative node set A has the function of configuring intelligent collaborative tasks. This HIC A can negotiate with other HIC A's to determine a collaborative node set A and an intelligent collaborative task A to be executed. After obtaining authorization from the HIC C to execute the intelligent collaborative task, it configures other HIC A's in the collaborative node set and participates in the collaborative execution of the intelligent collaborative task A. The specific process can be referred to the description of the embodiment shown in Figure 4 and will not be repeated here. HIC C can determine the collaborative node set B that executes the intelligent collaborative task B, and configure the intelligent collaborative task B to the nodes in the collaborative node set B so that HIC A in the collaborative node set B can collaboratively execute the intelligent collaborative task B. The specific process can be referred to the description of the embodiment shown in FIG3 and will not be repeated here.

[0266] It should be noted that for the multiple messages defined in the embodiments of the present application, such as the first to ninth messages mentioned above, in the absence of logical conflicts, the same message may have the functions of the above multiple messages. For example, the eighth message sent by the second node to the first node for indicating the ability of the node to perform intelligent tasks and the third message for indicating the load status of the node may be different messages, or they may be the same message. For example, a message sent by the second node to the first node is used to indicate both the ability of the second node to perform intelligent tasks and the load status of the second node. The embodiments of the present application do not limit the way of transmitting messages between nodes. The different information contained in a message can be sent by a node to the receiving node at one time, or the different information in the message can be sent by the node to the receiving node multiple times. For example, the first node can first send the identification information of the first intelligent collaborative task in the first message to the second node, and then send the description information of the first intelligent collaborative task to the second node. This application does not limit this.

[0267] It is understood that, in order to implement the functions in the above embodiments, the base station and the terminal include hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily appreciate that, in conjunction with the units and method steps of the various examples described in the embodiments disclosed in this application, this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in hardware or in a computer software-driven hardware manner depends on the specific application scenario and design constraints of the technical solution.

[0268] Figures 7 and 8 are schematic diagrams of the structures of possible communication devices provided in embodiments of the present application. These communication devices can be used to implement the functions of the first node or the second node in the above-mentioned method embodiments, thereby also achieving the beneficial effects of the above-mentioned method embodiments. In the embodiments of the present application, the communication device can be one of the UE, RAN node, or core network node as shown in Figure 1, or a module (such as a chip or chip system) applied to a communication device.

[0269] The communication device 700 includes a transceiver unit 720, which can be used to receive or send information. The communication device 700 can also include a processing unit 710, which can be used to process instructions or data to implement corresponding operations.

[0270] It should be understood that when the communication device 700 is a chip configured in (or used in) a communication device, the transceiver unit 720 in the communication device 700 can be the input / output interface or circuit of the chip, and the processing unit 710 in the communication device 700 can be the processor in the chip.

[0271] Optionally, the communication device 700 may further include a storage unit 730, which may be used to store instructions or data. The processing unit 710 may execute the instructions or data stored in the storage unit to enable the communication device to perform corresponding operations.

[0272] The communication device 700 can be used to implement the functions of the first node in the method embodiments shown in Figures 2 and 3, or the collaboration node 1 shown in Figures 4 and 5. The communication device 700 has the above-mentioned intelligent collaboration task configuration function and / or the above-mentioned intelligent collaboration task optimization function. When the communication device 700 is used to implement the functions of the first node in the method embodiments shown in Figures 2 and 3, the communication device 700 may also have the intelligent collaboration task management function.

[0273] When communication device 700 is used to implement the functions of the first node in the method embodiments shown in Figures 2 and 3, or the collaboration node 1 shown in Figures 4 and 5: processing unit 710 is configured to determine a set of collaboration nodes to perform an intelligent collaboration task, where the set of collaboration nodes includes the second node. Transceiver unit 720 sends a first message to the second node, where the first message is used to configure the second node to perform the intelligent collaboration task.

[0274] The communication device 700 can be used to implement the function of the first node in the method embodiment shown in Figure 2, or the cooperation node shown in Figures 3 and 4. The communication device 700 has the function of executing intelligent cooperation tasks.

[0275] When the communication device 700 can be used to implement the functions of the second node in the method embodiment shown in FIG. 2 or the collaboration node shown in FIG. 3 to FIG. 5 , the transceiver unit 720 is configured to receive a first message from the first node, the first message being used to configure the second node to perform the intelligent collaboration task. The processing unit 710 is configured to perform the intelligent collaboration task based on the first message.

[0276] For a more detailed description of the processing unit 710 and the transceiver unit 720 , reference may be made to the relevant descriptions in the method embodiments shown in FIG. 2 to FIG. 5 .

[0277] It should be understood that the transceiver unit 720 in the communication device 700 can be implemented through a communication interface (such as a transceiver, a transceiver circuit, an input / output interface, or a pin, etc.). When the communication interface is a transceiver, the transceiver can be composed of a receiver and / or a transmitter. The processing unit 710 in the communication device 700 can be implemented by at least one processor. The processing unit 710 in the communication device 700 can also be implemented by at least one logic circuit. Optionally, the communication device 700 also includes a storage unit, which can be implemented by a memory.

[0278] As shown in Figure 8, communication device 800 includes a processor 810 and an interface circuit 820. Processor 810 and interface circuit 820 are coupled to each other. It will be appreciated that interface circuit 820 may be a transceiver or an input / output interface. Optionally, communication device 800 may further include a memory 830 for storing instructions executed by processor 810, input data required by processor 810 to execute instructions, or data generated after processor 810 executes instructions.

[0279] When the communication device 800 is used to implement the method shown in FIG. 8 , the processor 810 is used to implement the functions of the processing unit 810 , and the interface circuit 820 is used to implement the functions of the transceiver unit 820 .

[0280] When the communication device is a chip used in a terminal device, the terminal device chip can implement the functions of the first node or the second node in the above method embodiment. The terminal device chip receives information from other modules in the terminal device (such as a radio frequency module or antenna), and the information is sent by the network device to the terminal device; or the terminal device chip sends information to other modules in the terminal device (such as a radio frequency module or antenna), and the information is sent by the terminal device to the network device.

[0281] When the communication device is a module applied to a network device (such as an access network device or a core network device), the network device module can implement the functions of the first node or the second node in the above method embodiment. The network device module receives information from other modules in the network device (such as a radio frequency module or an antenna), and the information is sent by the terminal device to the network device; or the network device module sends information to other modules in the network device (such as a radio frequency module or an antenna), and the information is sent by the network device to the terminal device.

[0282] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0283] The method steps in the embodiments of the present application can be implemented in hardware or in software instructions that can be executed by a processor. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disk, mobile hard disk, CD-ROM or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. The storage medium can also be an integral part of the processor. The processor and storage medium can be located in an ASIC. In addition, the ASIC can be located in an access network device or a terminal device. The processor and storage medium can also exist in the access network device or the terminal device as discrete components.

[0284] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are performed in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, or other programmable device. The computer program or instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions may be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; an optical medium, such as a digital video disk; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or nonvolatile storage medium, or may include both volatile and nonvolatile types of storage media.

[0285] In the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0286] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A communication method, characterized in that: include: The first node determines a set of collaborative nodes that perform an intelligent collaborative task, where the set of collaborative nodes includes the second node; The first node sends a first message to the second node, where the first message is used to configure the second node to perform the intelligent collaboration task, and the first message includes one or more of the following information: Information about nodes in the collaborative node set; identification information of the intelligent collaboration task; Description information of the intelligent collaboration task; Time information for executing the intelligent collaboration task.

2. The method according to claim 1, characterized in that The description information of the intelligent collaboration task is used to indicate one or more of the following: A topological structure between nodes in the collaborative node set; Types of interaction parameters between nodes in the collaborative node set; the format of the interaction parameters; an interaction mode of the interaction parameter; whether the interaction parameters are sent synchronously between the nodes in the collaborative node set; The model adopted by the intelligent collaboration task; The model training method of the intelligent collaboration task.

3. The method according to claim 2, characterized in that The interaction parameters include one or more of the following: Model parameters, gradients, environment state parameters, execution action parameters, action execution strategy parameters, reward parameters, knowledge extraction representation parameters, or the correlation between node tasks.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: The first node determines the time to execute the intelligent collaborative task according to the load status of the nodes in the collaborative node set, and the time information is used to indicate the time to execute the intelligent collaborative task.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: The first node determines to stop the intelligent collaborative task according to the load status of the nodes in the collaborative node set; The first node sends a second message to the nodes in the collaboration node set, where the second message is used to instruct to stop the intelligent collaboration task.

6. The method according to claim 4 or 5, characterized in that The method further comprises: The first node receives a third message from the second node, where the third message is used to indicate a load status of the second node.

7. The method according to any one of claims 4 to 6, characterized in that The load status is determined based on one or more of the following parameters: The proportion of input communication traffic of the node's collaborative task in the total input traffic; The proportion of the output communication traffic of the node's collaborative task in the total output traffic; The proportion of computing power overhead of nodes executing collaborative tasks in the total computing power overhead; The ratio of the communication traffic transmission duration of the node's collaborative task in the total session data congestion duration under session data congestion.

8. The method according to any one of claims 1 to 7, characterized in that The method further comprises: The first node receives a fourth message from the third node, where the fourth message is used to request configuration of the intelligent collaborative task.

9. The method according to any one of claims 1 to 7, characterized in that The set of cooperating nodes includes the first node, and the method further includes: The first node sends a fifth message to the fourth node, where the fifth message is used to request authorization of the intelligent collaboration task; The first node receives a sixth message from the fourth node, where the sixth message is used to authorize execution of the intelligent collaborative task.

10. The method according to claim 9, characterized in that The method further comprises: The first node sends a seventh message to the fourth node, where the seventh message is used to request cancellation of the intelligent collaboration task.

11. The method according to any one of claims 1 to 10, characterized in that The first node determines a set of collaborative nodes that perform the intelligent collaborative task, including: The first node receives an eighth message from a plurality of nodes, the eighth message being used to indicate an ability of the node to perform an intelligent task, the plurality of nodes including the second node; The first node determines the collaborative node set according to capabilities of the multiple nodes in executing intelligent tasks, where the collaborative node set includes at least one node from the multiple nodes.

12. The method according to claim 11, characterized in that The eighth message includes one or more of the following information: Description of the current intelligent task, description of historical intelligent tasks, local model information, supported model training methods, or information indicating whether model aggregation is supported.

13. The method according to claim 11 or 12, characterized in that The first node receives an eighth message from the plurality of nodes, including: The first node sends a ninth message to the second node, where the ninth message is used to instruct the second node to report a capability of performing the intelligent task; The first node receives the eighth message from the second node.

14. A communication method, characterized in that: include: A second node receives a first message from a first node, where the first message is used to configure the second node to perform an intelligent collaborative task, and the collaborative node set includes the second node; The second node executes the intelligent collaboration task according to the first message, The first message includes one or more of the following information: Information about nodes in the collaborative node set; identification information of the intelligent collaboration task; Description information of the intelligent collaboration task; Time information for executing the intelligent collaboration task.

15. The method according to claim 14, characterized in that The description information of the intelligent collaboration task is used to indicate one or more of the following: A topological structure between nodes in the collaborative node set; Types of interaction parameters between nodes in the collaborative node set; the format of the interaction parameters; an interaction mode of the interaction parameter; whether the interaction parameters are sent synchronously between the nodes of the collaborative node set; The model adopted by the intelligent collaboration task; The model training method of the intelligent collaboration task.

16. The method according to claim 15, characterized in that The interaction parameters include one or more of the following: Model parameters, gradients, environment state parameters, execution action parameters, reward parameters, knowledge extraction representation parameters, or the correlation between node tasks.

17. The method according to any one of claims 14 to 16, characterized in that The method further comprises: The second node receives a second message from the first node, where the second message is used to instruct to stop the intelligent collaborative task.

18. The method according to any one of claims 14 to 17, characterized in that The method further comprises: The second node sends a third message to the first node, where the third message is used to indicate a load status of the second node.

19. The method according to claim 18, characterized in that The load status is determined based on one or more of the following parameters: The proportion of input communication traffic of the node's collaborative task in the total input traffic; The proportion of the output communication traffic of the node's collaborative task in the total output traffic; The proportion of computing power overhead of nodes executing collaborative tasks in the total computing power overhead; The ratio of the duration of the node transmitting the communication information of the collaborative task in the total duration of the session data congestion.

20. The method according to any one of claims 14 to 19, characterized in that The method further comprises: The second node sends an eighth message to the first node, where the eighth message is used to indicate the node's ability to perform intelligent tasks.

21. The method according to claim 20, characterized in that The eighth message includes one or more of the following information: Description of the current intelligent task, description of historical intelligent tasks, local model information, supported model training methods, or information indicating whether model aggregation is supported.

22. The method according to claim 20 or 21, characterized in that The second node sends an eighth message to the first node, including: The second node receives a ninth message sent from the first node, where the ninth message is used to instruct the second node to report a capability of performing the intelligent task; The second node sends the eighth message to the first node.

23. The method according to any one of claims 14 to 22, characterized in that The method further comprises: The second node communicates with nodes in the collaborative node set using an intelligent model; and / or, The second node sends model parameters of the intelligent model; The intelligent model is obtained by executing the intelligent collaboration task.

24. A communication device, characterized in that: The communication device includes units or modules for implementing the method according to any one of claims 1 to 13.

25. A communication device, characterized in that: The communication device comprises a unit or module for implementing the method according to any one of claims 14 to 23.

26. A communication device, characterized in that: comprising at least one processor coupled to a memory; The memory is used to store programs or instructions; The at least one processor is configured to execute the program or instruction to enable the apparatus to implement the method according to any one of claims 1 to 13, or to implement the method according to any one of claims 14 to 23.

27. A computer-readable storage medium comprising a computer program, which, when executed by one or more processors, causes an apparatus comprising the processor to perform the method according to any one of claims 1 to 13, or implement the method according to any one of claims 14 to 23.

28. A communication system, characterized in that: Comprising the communication device according to claim 24 and the communication device according to claim 25.

Images